Recent Publications

2015

  • D. Valeriani and A. Matran-Fernandez, “Towards a Wearable Device for Controlling a Smartphone with Eye Winks,” in 7th computer science and electronic engineering conference (ceec15), 2015.
    [BibTeX] [Abstract]

    The development of mobile technology over the last years and the consequent boom of available apps has enabled users to migrate a wide range of activities that were traditionally performed on computers to their smartphones. Despite this new freedom to work ubiquitously, there are circumstances in which operating the device becomes difficult, e.g., when the hands are not free due to driving or other activities. Even though there are voice-control alternatives for operating smartphones, these do not perform well in crowded or noisy environments. In this paper we present EyeWink: an innovative hands- and voice-free wearable device that allows users to operate the smartphones with eye winks. The system records the Electrooculography (EOG) signals on the forehead by means of two facial electrodes. Eye winks are detected by comparing the potentials recorded from the electrodes, which also helps avoid false actuations due to (unavoidable) eye blinks. The user can associate the action to perform with each eye by means of an app installed on the smartphone. The proposed device can be widely used, with customers ranging from runners to people with severe disabilities.

    @inproceedings{Valeriani2015a,
    abstract = {The development of mobile technology over the last years and the consequent boom of available apps has enabled users to migrate a wide range of activities that were traditionally performed on computers to their smartphones. Despite this new freedom to work ubiquitously, there are circumstances in which operating the device becomes difficult, e.g., when the hands are not free due to driving or other activities. Even though there are voice-control alternatives for operating smartphones, these do not perform well in crowded or noisy environments. In this paper we present EyeWink: an innovative hands- and voice-free wearable device that allows users to operate the smartphones with eye winks. The system records the Electrooculography (EOG) signals on the forehead by means of two facial electrodes. Eye winks are detected by comparing the potentials recorded from the electrodes, which also helps avoid false actuations due to (unavoidable) eye blinks. The user can associate the action to perform with each eye by means of an app installed on the smartphone. The proposed device can be widely used, with customers ranging from runners to people with severe disabilities.},
    author = {Valeriani, Davide and Matran-Fernandez, Ana},
    booktitle = {7th Computer Science and Electronic Engineering Conference (CEEC15)},
    file = {:Users/davide/Documents/Mendeley/Valeriani, Matran-Fernandez/2015/Valeriani, Matran-Fernandez - 2015 - Towards a Wearable Device for Controlling a Smartphone with Eye Winks.pdf:pdf},
    title = {{Towards a Wearable Device for Controlling a Smartphone with Eye Winks}},
    year = {2015}
    }

  • D. Valeriani, A. Matran-Fernandez, D. Perez-Liebana, J. Asensio-Cubero, C. O’Connell, and A. Iacob, “A Comparison of Ensemble Methods for Motor Imagery Brain-Computer Interfaces,” in European conference on data analysis 2015, 2015.
    [BibTeX] [Abstract]

    A Brain-Computer Interface (BCI) provides an alternative means of communication for people who are locked-in. For a BCI to work, the user will perform a specific mental task whilst wearing an Electroencephalography (EEG) cap that contains several electrodes. In particular, in a Motor Imagery (MI) BCI, users imagine themselves performing specific movements, e.g., ro- tating the right hand or moving his/her feet. The signals recorded by these electrodes are then preprocessed and fed to a classifier that will decide which of the possible actions is being performed. The output of the classifier is then sent to a device (e.g., a computer or wheelchair) for its execution. In this paper, we will compare the performance of different systems (several ensembles us- ing various voting algorithms and multiclass classifiers) on a 4-class MI task (left/right hand and feet MI, plus an “idle" state). These methods will be ranked using a combination of different evaluation metrics. The best system will be applied to a real-time BCI used in an international competition.

    @inproceedings{Valeriani2015c,
    abstract = {A Brain-Computer Interface (BCI) provides an alternative means of communication for people who are locked-in. For a BCI to work, the user will perform a specific mental task whilst wearing an Electroencephalography (EEG) cap that contains several electrodes. In particular, in a Motor Imagery (MI) BCI, users imagine themselves performing specific movements, e.g., ro- tating the right hand or moving his/her feet. The signals recorded by these electrodes are then preprocessed and fed to a classifier that will decide which of the possible actions is being performed. The output of the classifier is then sent to a device (e.g., a computer or wheelchair) for its execution. In this paper, we will compare the performance of different systems (several ensembles us- ing various voting algorithms and multiclass classifiers) on a 4-class MI task (left/right hand and feet MI, plus an “idle" state). These methods will be ranked using a combination of different evaluation metrics. The best system will be applied to a real-time BCI used in an international competition.},
    author = {Valeriani, Davide and Matran-Fernandez, Ana and Perez-Liebana, Diego and Asensio-Cubero, Javier and O'Connell, Christian and Iacob, Andrei},
    booktitle = {European Conference on Data Analysis 2015},
    file = {:Users/davide/Documents/Mendeley/Valeriani et al/2015/Valeriani et al. - 2015 - A Comparison of Ensemble Methods for Motor Imagery Brain-Computer Interfaces.pdf:pdf},
    title = {{A Comparison of Ensemble Methods for Motor Imagery Brain-Computer Interfaces}},
    year = {2015}
    }

  • D. Valeriani, R. Poli, and C. Cinel, “A Collaborative Brain-Computer Interface for Improving Group Detection of Visual Targets in Complex Natural Environments,” in 7th international ieee embs neural engineering conference, 2015.
    [BibTeX] [Abstract]

    Detecting a target in a complex environment can be a difficult task, both for a single individual and a group, especially if the scene is very rich of structure and there are strict time constraints. In recent research, we have demon- strated that collaborative Brain-Computer Interfaces (cBCIs) can use neural signals and response times to estimate the decision confidence of participants and use this to improve group decisions. We successfully tested this approach with visual-matching and visual-search tasks with artificial stimuli (e.g., squares, rectangles, etc.). This paper extends that work in two ways. Firstly, we use a much harder target detection task where observers are presented with complex natural scenes where targets are very difficult to identify. Secondly, we complement the neural and behavioural information used in our previous cBCIs with physiological features representing eye movements and eye blinks of participants in the period preceding their decisions. Results obtained with 10 participants indicate that the proposed cBCI improves decision errors by up to 3.4{\%} (depending on group size) over group decisions made by a majority vote. Further- more, results show that providing the system with information about eye movements and blinks further significantly improves performance over our best previously reported method. This suggests that cBCIs may soon be ready for deployment in real- world decision tasks.

    @inproceedings{Valeriani2015b,
    abstract = {Detecting a target in a complex environment can be a difficult task, both for a single individual and a group, especially if the scene is very rich of structure and there are strict time constraints. In recent research, we have demon- strated that collaborative Brain-Computer Interfaces (cBCIs) can use neural signals and response times to estimate the decision confidence of participants and use this to improve group decisions. We successfully tested this approach with visual-matching and visual-search tasks with artificial stimuli (e.g., squares, rectangles, etc.). This paper extends that work in two ways. Firstly, we use a much harder target detection task where observers are presented with complex natural scenes where targets are very difficult to identify. Secondly, we complement the neural and behavioural information used in our previous cBCIs with physiological features representing eye movements and eye blinks of participants in the period preceding their decisions. Results obtained with 10 participants indicate that the proposed cBCI improves decision errors by up to 3.4{\%} (depending on group size) over group decisions made by a majority vote. Further- more, results show that providing the system with information about eye movements and blinks further significantly improves performance over our best previously reported method. This suggests that cBCIs may soon be ready for deployment in real- world decision tasks.},
    author = {Valeriani, Davide and Poli, Riccardo and Cinel, Caterina},
    booktitle = {7th International IEEE EMBS Neural Engineering Conference},
    file = {:Users/davide/Documents/Mendeley/Valeriani, Poli, Cinel/2015/Valeriani, Poli, Cinel - 2015 - A Collaborative Brain-Computer Interface for Improving Group Detection of Visual Targets in Complex Natu.pdf:pdf},
    title = {{A Collaborative Brain-Computer Interface for Improving Group Detection of Visual Targets in Complex Natural Environments}},
    year = {2015}
    }

  • D. Valeriani, R. Poli, and C. Cinel, “A Collaborative Brain-Computer Interface to Improve Human Performance in a Visual Search Task,” in 7th international ieee embs neural engineering conference, 2015.
    [BibTeX] [Abstract]

    In this paper we use a collaborative brain- computer interface to integrate the decision confidence of multiple non-communicating observers as a mechanism to improve group decisions. In recent research we tested the idea with the decisions associated with a simple visual matching task and found that a collaborative BCI can significantly outperform group decisions made by a majority vote. Here we considerably extend these initial findings by: (a) looking at a more traditional (and more difficult) visual search task involving deciding whether a red vertical bar is present in a random set of 40 red and green, horizontal and vertical bars shown for a very short time, (b) using spatio-temporal CSP filters instead of the spatio-temporal PCA we previously used to extract features from the neural signals, while also reducing the number of features and free parameters used in the system. Results obtained with 10 participants indicate that for almost all group sizes our new CSP-based collaborative BCI yields group decisions that are statistically significantly better than both traditional (majority-based) group decisions and group decisions made by a PCA-based collaborative BCI.

    @inproceedings{Valeriani2015,
    abstract = {In this paper we use a collaborative brain- computer interface to integrate the decision confidence of multiple non-communicating observers as a mechanism to improve group decisions. In recent research we tested the idea with the decisions associated with a simple visual matching task and found that a collaborative BCI can significantly outperform group decisions made by a majority vote. Here we considerably extend these initial findings by: (a) looking at a more traditional (and more difficult) visual search task involving deciding whether a red vertical bar is present in a random set of 40 red and green, horizontal and vertical bars shown for a very short time, (b) using spatio-temporal CSP filters instead of the spatio-temporal PCA we previously used to extract features from the neural signals, while also reducing the number of features and free parameters used in the system. Results obtained with 10 participants indicate that for almost all group sizes our new CSP-based collaborative BCI yields group decisions that are statistically significantly better than both traditional (majority-based) group decisions and group decisions made by a PCA-based collaborative BCI.},
    author = {Valeriani, Davide and Poli, Riccardo and Cinel, Caterina},
    booktitle = {7th International IEEE EMBS Neural Engineering Conference},
    file = {:Users/davide/Documents/Mendeley/Valeriani, Poli, Cinel/2015/Valeriani, Poli, Cinel - 2015 - A Collaborative Brain-Computer Interface to Improve Human Performance in a Visual Search Task.pdf:pdf},
    title = {{A Collaborative Brain-Computer Interface to Improve Human Performance in a Visual Search Task}},
    year = {2015}
    }

  • M. Dyson, T. Balli, J. Q. Gan, F. Sepulveda, and R. Palaniappan, Approximate Entropy for EEG-based Movement Detection Approximate Entropy for EEG-based Movement Detection, Verlag der Technischen Universit{\{}ä{\}}t Graz, 2015.
    [BibTeX]
    @book{dyson2008approximate,
    author = {Dyson, M and Balli, T and Gan, J Q and Sepulveda, F and Palaniappan, R},
    pages = {1--7},
    publisher = {Verlag der Technischen Universit{\{}{\"{a}}{\}}t Graz},
    title = {{Approximate Entropy for EEG-based Movement Detection Approximate Entropy for EEG-based Movement Detection}},
    year = {2015}
    }

  • J. Ortega, J. Asensio-Cubero, J. Q. Gan, and A. Ortiz, “Evolutionary multiobjective feature selection in multiresolution analysis for BCI,” in Bioinformatics and biomedical engineering, Springer, 2015, pp. 347-359.
    [BibTeX]
    @incollection{ortega2015evolutionary,
    author = {Ortega, Julio and Asensio-Cubero, Javier and Gan, John Q and Ortiz, Andr{\'{e}}s},
    booktitle = {Bioinformatics and Biomedical Engineering},
    pages = {347--359},
    publisher = {Springer},
    title = {{Evolutionary multiobjective feature selection in multiresolution analysis for BCI}},
    year = {2015}
    }

  • J. Asensio-Cubero, J. Q. Gan, and R. Palaniappan, “Multiresolution Analysis over Graphs for a Motor Imagery Based Online BCI Game,” Computers in biology and medicine, vol. 68, pp. 21-26, 2015. doi:10.1016/j.compbiomed.2015.10.016
    [BibTeX] [Abstract] [Download PDF]

    Multiresolution analysis (MRA) over graph representation of EEG data has proved to be a promising method for offline brain–computer interfacing (BCI) data analysis. For the first time we aim to prove the feasibility of the graph lifting transform in an online BCI system. Instead of developing a pointer device or a wheel-chair controller as test bed for human–machine interaction, we have designed and developed an engaging game which can be controlled by means of imaginary limb movements. Some modifications to the existing MRA analysis over graphs for BCI have also been proposed, such as the use of common spatial patterns for feature extraction at the different levels of decomposition, and sequential floating forward search as a best basis selection technique. In the online game experiment we obtained for three classes an average classification rate of 63.0{\%} for fourteen naive subjects. The application of a best basis selection method helps significantly decrease the computing resources needed. The present study allows us to further understand and assess the benefits of the use of tailored wavelet analysis for processing motor imagery data and contributes to the further development of BCI for gaming purposes.

    @article{asensio2016multiresolution,
    abstract = {Multiresolution analysis (MRA) over graph representation of EEG data has proved to be a promising method for offline brain–computer interfacing (BCI) data analysis. For the first time we aim to prove the feasibility of the graph lifting transform in an online BCI system. Instead of developing a pointer device or a wheel-chair controller as test bed for human–machine interaction, we have designed and developed an engaging game which can be controlled by means of imaginary limb movements. Some modifications to the existing MRA analysis over graphs for BCI have also been proposed, such as the use of common spatial patterns for feature extraction at the different levels of decomposition, and sequential floating forward search as a best basis selection technique. In the online game experiment we obtained for three classes an average classification rate of 63.0{\%} for fourteen naive subjects. The application of a best basis selection method helps significantly decrease the computing resources needed. The present study allows us to further understand and assess the benefits of the use of tailored wavelet analysis for processing motor imagery data and contributes to the further development of BCI for gaming purposes.},
    author = {Asensio-Cubero, Javier and Gan, John Q. and Palaniappan, Ramaswamy},
    doi = {10.1016/j.compbiomed.2015.10.016},
    issn = {00104825},
    journal = {Computers in Biology and Medicine},
    keywords = {BCI game,EEG graph representation,Motor imagery,Wavelet lifting},
    pages = {21--26},
    pmid = {26599827},
    publisher = {Elsevier},
    title = {{Multiresolution Analysis over Graphs for a Motor Imagery Based Online BCI Game}},
    url = {http://www.sciencedirect.com/science/article/pii/S0010482515003583},
    volume = {68},
    year = {2015}
    }

  • L. Zhang, J. Q. Gan, and H. Wang, “Localization of neural efficiency of the mathematically gifted brain through a feature subset selection method,” Cognitive neurodynamics, vol. 9, iss. 5, pp. 495-508, 2015. doi:10.1007/s11571-015-9345-1
    [BibTeX]
    @article{zhang2015localization,
    author = {Zhang, Li and Gan, John Q. and Wang, Haixian},
    doi = {10.1007/s11571-015-9345-1},
    isbn = {1157101593},
    issn = {18714099},
    journal = {Cognitive Neurodynamics},
    keywords = {EEG Gamma-band response,Feature subset selection,Math-gifted adolescents,Neural efficiency,Numerical inductive reasoning},
    number = {5},
    pages = {495--508},
    publisher = {Springer},
    title = {{Localization of neural efficiency of the mathematically gifted brain through a feature subset selection method}},
    volume = {9},
    year = {2015}
    }

  • S. Mouli, R. Palaniappan, I. P. Sillitoe, and J. Q. Gan, “Quantification of SSVEP responses using multi-chromatic LED stimuli: Analysis on colour, orientation and frequency,” in Computer science and electronic engineering conference (ceec), 2015 7th, 2015, pp. 93-98.
    [BibTeX]
    @inproceedings{mouli2015quantification,
    author = {Mouli, Surej and Palaniappan, Ramaswamy and Sillitoe, Ian P and Gan, John Q},
    booktitle = {Computer Science and Electronic Engineering Conference (CEEC), 2015 7th},
    organization = {IEEE},
    pages = {93--98},
    title = {{Quantification of SSVEP responses using multi-chromatic LED stimuli: Analysis on colour, orientation and frequency}},
    year = {2015}
    }

  • S. Plansangket and J. Q. Gan, “A New Term Weighting Scheme Based on Class Specific Document Frequency for Document Representation and Classification,” in Computer science and electronic engineering conference (ceec), 2015 7th, 2015, pp. 7-10.
    [BibTeX]
    @inproceedings{plansangket2015new,
    author = {Plansangket, Suthira and Gan, John Q},
    booktitle = {Computer Science and Electronic Engineering Conference (CEEC), 2015 7th},
    isbn = {9781467394819},
    organization = {IEEE},
    pages = {7--10},
    title = {{A New Term Weighting Scheme Based on Class Specific Document Frequency for Document Representation and Classification}},
    year = {2015}
    }

  • M. I. Abdulhussain and J. Q. Gan, “An experimental investigation on PCA based on cosine similarity and correlation for text feature dimensionality reduction,” in Computer science and electronic engineering conference (ceec), 2015 7th, 2015, pp. 1-4.
    [BibTeX]
    @inproceedings{abdulhussain2015experimental,
    author = {Abdulhussain, Maysa I and Gan, John Q},
    booktitle = {Computer Science and Electronic Engineering Conference (CEEC), 2015 7th},
    organization = {IEEE},
    pages = {1--4},
    title = {{An experimental investigation on PCA based on cosine similarity and correlation for text feature dimensionality reduction}},
    year = {2015}
    }

  • S. Plansangket and J. Q. Gan, “A query suggestion method combining TF-IDF and Jaccard Coefficient for interactive web search,” Artificial intelligence research, vol. 4, iss. 2, pp. 119-125, 2015. doi:10.5430/air.v4n2p119
    [BibTeX] [Abstract] [Download PDF]

    This paper proposes a query suggestion method combining two ranked retrieval methods: TF-IDF and Jaccard coefficient. Four performance criteria plus user evaluation have been adopted to evaluate this combined method in terms of ranking and relevance from different perspectives. Two experiments have been conducted using carefully designed eighty test queries which are related to eight topics. One experiment aims to evaluate the quality of the query suggestions generated by the proposed method, and the other aims to evaluate the improvement of the relevance of retuned documents in interactive web search by using the query suggestions so as to evaluate the effectiveness of the developed method. The experimental results show that the method developed in this paper is the best method for query suggestion among the methods evaluated, significantly outperforming the most popularly used TF-IDF method. In addition, the query suggestions generated by the proposed method significantly improve the relevance of returned documents in interactive web search in terms of increasing the precision or the number of highly relevant documents.

    @article{plansangket2015query,
    abstract = {This paper proposes a query suggestion method combining two ranked retrieval methods: TF-IDF and Jaccard coefficient. Four performance criteria plus user evaluation have been adopted to evaluate this combined method in terms of ranking and relevance from different perspectives. Two experiments have been conducted using carefully designed eighty test queries which are related to eight topics. One experiment aims to evaluate the quality of the query suggestions generated by the proposed method, and the other aims to evaluate the improvement of the relevance of retuned documents in interactive web search by using the query suggestions so as to evaluate the effectiveness of the developed method. The experimental results show that the method developed in this paper is the best method for query suggestion among the methods evaluated, significantly outperforming the most popularly used TF-IDF method. In addition, the query suggestions generated by the proposed method significantly improve the relevance of returned documents in interactive web search in terms of increasing the precision or the number of highly relevant documents.},
    author = {Plansangket, Suthira and Gan, John Q},
    doi = {10.5430/air.v4n2p119},
    issn = {1927-6982},
    journal = {Artificial Intelligence Research},
    keywords = {4,a cold-start problem,analysed three types of,and found that,are often used when,in find- query suggestions,information retrieval,internet search engines play,kato et al,logs in the microsoft,performance evaluation,query expansion,query suggestion,s search engine bing,search engine,the most important role,the original query},
    number = {2},
    pages = {119--125},
    title = {{A query suggestion method combining TF-IDF and Jaccard Coefficient for interactive web search}},
    url = {http://www.sciedupress.com/journal/index.php/air/article/view/6978},
    volume = {4},
    year = {2015}
    }

  • P. Martin-Smith, J. Ortega, J. Asensio-Cubero, J. Q. Gan, and A. Ortiz, “A Label-Aided Filter Method for Multi-objective Feature Selection in EEG Classification for BCI,” in Advances in computational intelligence, pt i, Springer, 2015, vol. 9094, pp. 133-144. doi:10.1007/978-3-319-19258-1{_}12
    [BibTeX] [Download PDF]
    @incollection{martin2015label,
    author = {Martin-Smith, Pedro and Ortega, Julio and Asensio-Cubero, Javier and Gan, John Q and Ortiz, Andres},
    booktitle = {Advances in Computational Intelligence, Pt I},
    doi = {10.1007/978-3-319-19258-1{\_}12},
    isbn = {978-3-319-19258-1; 978-3-319-19257-4},
    pages = {133--144},
    publisher = {Springer},
    title = {{A Label-Aided Filter Method for Multi-objective Feature Selection in EEG Classification for BCI}},
    url = {<Go to ISI>://WOS:000363763800012},
    volume = {9094},
    year = {2015}
    }

  • L. Zhang, J. Q. Gan, and H. Wang, “Mathematically gifted adolescents mobilize enhanced workspace configuration of theta cortical network during deductive reasoning,” Neuroscience, vol. 289, pp. 334-348, 2015. doi:10.1016/j.neuroscience.2014.12.072
    [BibTeX] [Abstract]

    Previous studies have established the importance of the fronto-parietal brain network in the information processing of reasoning. At the level of cortical source analysis, this eletroencepalogram (EEG) study investigates the functional reorganization of the theta-band (4-8. Hz) neurocognitive network of mathematically gifted adolescents during deductive reasoning. Depending on the dense increase of long-range phase synchronizations in the reasoning process, math-gifted adolescents show more significant adaptive reorganization and enhanced "workspace" configuration in the theta network as compared with average-ability control subjects. The salient areas are mainly located in the anterior cortical vertices of the fronto-parietal network. Further correlation analyses have shown that the enhanced workspace configuration with respect to the global topological metrics of the theta network in math-gifted subjects is correlated with the intensive frontal midline theta (fm theta) response that is related to strong neural effort for cognitive events. These results suggest that by investing more cognitive resources math-gifted adolescents temporally mobilize an enhanced task-related global neuronal workspace, which is manifested as a highly integrated fronto-parietal information processing network during the reasoning process.

    @article{zhang2015mathematically,
    abstract = {Previous studies have established the importance of the fronto-parietal brain network in the information processing of reasoning. At the level of cortical source analysis, this eletroencepalogram (EEG) study investigates the functional reorganization of the theta-band (4-8. Hz) neurocognitive network of mathematically gifted adolescents during deductive reasoning. Depending on the dense increase of long-range phase synchronizations in the reasoning process, math-gifted adolescents show more significant adaptive reorganization and enhanced "workspace" configuration in the theta network as compared with average-ability control subjects. The salient areas are mainly located in the anterior cortical vertices of the fronto-parietal network. Further correlation analyses have shown that the enhanced workspace configuration with respect to the global topological metrics of the theta network in math-gifted subjects is correlated with the intensive frontal midline theta (fm theta) response that is related to strong neural effort for cognitive events. These results suggest that by investing more cognitive resources math-gifted adolescents temporally mobilize an enhanced task-related global neuronal workspace, which is manifested as a highly integrated fronto-parietal information processing network during the reasoning process.},
    author = {Zhang, L. and Gan, J. Q. and Wang, H.},
    doi = {10.1016/j.neuroscience.2014.12.072},
    issn = {18737544},
    journal = {Neuroscience},
    keywords = {Cortical source analysis,Frontal midline theta response,Functional network reorganization,Graph theory,Math-gifted adolescents,Workspace configuration},
    pages = {334--348},
    pmid = {25595993},
    publisher = {Elsevier},
    title = {{Mathematically gifted adolescents mobilize enhanced workspace configuration of theta cortical network during deductive reasoning}},
    volume = {289},
    year = {2015}
    }

  • X. Tan, M. Chen, and J. Q. Gan, “A co-training algorithm based on modified Fisher’s linear discriminant analysis,” Intelligent data analysis, vol. 19, iss. 2, pp. 279-292, 2015. doi:10.3233/IDA-150717
    [BibTeX]
    @article{tan2015co,
    author = {Tan, Xue-Min and Chen, Min-You and Gan, John Q.},
    doi = {10.3233/IDA-150717},
    journal = {Intelligent Data Analysis},
    number = {2},
    pages = {279--292},
    publisher = {IOS Press},
    title = {{A co-training algorithm based on modified Fisher's linear discriminant analysis}},
    volume = {19},
    year = {2015}
    }

2014

  • A. Matran-Fernandez and R. Poli, “Collaborative brain-computer interfaces for target detection and localisation in rapid serial visual presentation,” School of Computer Science and Electronic Engineering, University of Essex., CES-531, 2014.
    [BibTeX] [Download PDF]
    @TechReport{matran-fernandez14:_collab_brain_comput_inter_target,
    author = {Ana Matran-Fernandez and Riccardo Poli},
    title = {Collaborative Brain-Computer Interfaces for Target Detection and Localisation in Rapid Serial Visual Presentation},
    institution = {School of Computer Science and Electronic Engineering, University of Essex.},
    url = {http://cswww.essex.ac.uk/staff/poli/technical-reports/tr-ces-531.pdf},
    year = 2014,
    number = {CES-531},
    month = july
    }

  • R. Poli, D. Valeriani, and C. Cinel, “Collaborative Brain-Computer Interface for Aiding Decision-Making,” Plos one, vol. 9, iss. 7, 2014. doi:10.1371/journal.pone.0102693
    [BibTeX] [Abstract] [Download PDF]

    We look at the possibility of integrating the percepts from multiple non-communicating observers as a means of achieving better joint perception and better group decisions. Our approach involves the combination of a brain-computer interface with human behavioural responses. To test ideas in controlled conditions, we asked observers to perform a simple matching task involving the rapid sequential presentation of pairs of visual patterns and the subsequent decision as whether the two patterns in a pair were the same or different. We recorded the response times of observers as well as a neural feature which predicts incorrect decisions and, thus, indirectly indicates the confidence of the decisions made by the observers. We then built a composite neuro-behavioural feature which optimally combines the two measures. For group decisions, we uses a majority rule and three rules which weigh the decisions of each observer based on response times and our neural and neuro-behavioural features. Results indicate that the integration of behavioural responses and neural features can significantly improve accuracy when compared with the majority rule. An analysis of event-related potentials indicates that substantial differences are present in the proximity of the response for correct and incorrect trials, further corroborating the idea of using hybrids of brain-computer interfaces and traditional strategies for improving decision making.

    @article{Poli2014,
    abstract = {We look at the possibility of integrating the percepts from multiple non-communicating observers as a means of achieving better joint perception and better group decisions. Our approach involves the combination of a brain-computer interface with human behavioural responses. To test ideas in controlled conditions, we asked observers to perform a simple matching task involving the rapid sequential presentation of pairs of visual patterns and the subsequent decision as whether the two patterns in a pair were the same or different. We recorded the response times of observers as well as a neural feature which predicts incorrect decisions and, thus, indirectly indicates the confidence of the decisions made by the observers. We then built a composite neuro-behavioural feature which optimally combines the two measures. For group decisions, we uses a majority rule and three rules which weigh the decisions of each observer based on response times and our neural and neuro-behavioural features. Results indicate that the integration of behavioural responses and neural features can significantly improve accuracy when compared with the majority rule. An analysis of event-related potentials indicates that substantial differences are present in the proximity of the response for correct and incorrect trials, further corroborating the idea of using hybrids of brain-computer interfaces and traditional strategies for improving decision making.},
    author = {Poli, Riccardo and Valeriani, Davide and Cinel, Caterina},
    doi = {10.1371/journal.pone.0102693},
    editor = {Chacron, Maurice J.},
    issn = {1932-6203},
    journal = {PLoS ONE},
    month = jul,
    number = {7},
    title = {{Collaborative Brain-Computer Interface for Aiding Decision-Making}},
    url = {http://dx.plos.org/10.1371/journal.pone.0102693},
    volume = {9},
    year = {2014}
    }

  • J. Q. Gan, B. {Awwad Shiekh Hasan}, and C. S. L. Tsui, “A filter-dominating hybrid sequential forward floating search method for feature subset selection in high-dimensional space,” International journal of machine learning and cybernetics, vol. 5, iss. 3, pp. 413-423, 2014. doi:10.1007/s13042-012-0139-z
    [BibTeX] [Abstract]

    Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on five feature data sets, with different combinations of classifier and separability index as alternative criteria for evaluating the performance of potential feature subsets. The classifiers under consideration include linear discriminate analysis classifier, support vector machine, and K-nearest neighbors classifier, and the separability indexes include the Davies-Bouldin index and a mutual information based index. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection.

    @article{gan2014filter,
    abstract = {Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on five feature data sets, with different combinations of classifier and separability index as alternative criteria for evaluating the performance of potential feature subsets. The classifiers under consideration include linear discriminate analysis classifier, support vector machine, and K-nearest neighbors classifier, and the separability indexes include the Davies-Bouldin index and a mutual information based index. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection.},
    author = {Gan, John Q. and {Awwad Shiekh Hasan}, Bashar and Tsui, Chun Sing Louis},
    doi = {10.1007/s13042-012-0139-z},
    isbn = {1304201201},
    issn = {1868808X},
    journal = {International Journal of Machine Learning and Cybernetics},
    keywords = {Data mining,Feature selection,High-dimensional data analysis,Performance evaluation,Search algorithm},
    number = {3},
    pages = {413--423},
    publisher = {Springer},
    title = {{A filter-dominating hybrid sequential forward floating search method for feature subset selection in high-dimensional space}},
    volume = {5},
    year = {2014}
    }

  • L. Zhang, J. Q. Gan, and H. Wang, “Optimized Gamma Synchronization Enhances Functional Binding of Fronto-Parietal Cortices in Mathematically Gifted Adolescents during Deductive Reasoning,” Frontiers in human neuroscience, vol. 8, iss. June, pp. 1-13, 2014. doi:10.3389/fnhum.2014.00430
    [BibTeX] [Abstract] [Download PDF]

    As enhanced fronto-parietal network has been suggested to support reasoning ability of math-gifted adolescents, the main goal of this EEG source analysis is to investigate the temporal binding of the gamma-band (30-60 Hz) synchronization between frontal and parietal cortices in adolescents with exceptional mathematical ability, including the functional connectivity of gamma neurocognitive network, the temporal dynamics of fronto-parietal network (phase-locking durations and network lability in time domain), and the self-organized criticality of synchronizing oscillation. Compared with the average-ability subjects, the math-gifted adolescents show a highly integrated fronto-parietal network due to distant gamma phase-locking oscillations, which is indicated by lower modularity of the global network topology, more "connector bridges" between the frontal and parietal cortices and less "connector hubs" in the sensorimotor cortex. The time domain analysis finds that, while maintaining more stable phase dynamics of the fronto-parietal coupling, the math-gifted adolescents are characterized by more extensive fronto-parietal connection reconfiguration. The results from sample fitting in the power-law model further find that the phase-locking durations in the math-gifted brain abides by a wider interval of the power-law distribution. This phase-lock distribution mechanism could represent a relatively optimized pattern for the functional binding of frontal-parietal network, which underlies stable fronto-parietal connectivity and increases flexibility of timely network reconfiguration.

    @article{zhang2014optimized,
    abstract = {As enhanced fronto-parietal network has been suggested to support reasoning ability of math-gifted adolescents, the main goal of this EEG source analysis is to investigate the temporal binding of the gamma-band (30-60 Hz) synchronization between frontal and parietal cortices in adolescents with exceptional mathematical ability, including the functional connectivity of gamma neurocognitive network, the temporal dynamics of fronto-parietal network (phase-locking durations and network lability in time domain), and the self-organized criticality of synchronizing oscillation. Compared with the average-ability subjects, the math-gifted adolescents show a highly integrated fronto-parietal network due to distant gamma phase-locking oscillations, which is indicated by lower modularity of the global network topology, more "connector bridges" between the frontal and parietal cortices and less "connector hubs" in the sensorimotor cortex. The time domain analysis finds that, while maintaining more stable phase dynamics of the fronto-parietal coupling, the math-gifted adolescents are characterized by more extensive fronto-parietal connection reconfiguration. The results from sample fitting in the power-law model further find that the phase-locking durations in the math-gifted brain abides by a wider interval of the power-law distribution. This phase-lock distribution mechanism could represent a relatively optimized pattern for the functional binding of frontal-parietal network, which underlies stable fronto-parietal connectivity and increases flexibility of timely network reconfiguration.},
    author = {Zhang, Li and Gan, John Q. and Wang, Haixian},
    doi = {10.3389/fnhum.2014.00430},
    issn = {1662-5161},
    journal = {Frontiers in Human Neuroscience},
    keywords = {eeg cortical network,fronto-parietal functional binding,gamma,mathematically gifted adolescents,mathematically gifted adolescents, fronto-parietal,phase-locking duration,power-law model},
    number = {June},
    pages = {1--13},
    pmid = {24966829},
    publisher = {Frontiers Media SA},
    title = {{Optimized Gamma Synchronization Enhances Functional Binding of Fronto-Parietal Cortices in Mathematically Gifted Adolescents during Deductive Reasoning}},
    url = {http://journal.frontiersin.org/article/10.3389/fnhum.2014.00430/abstract},
    volume = {8},
    year = {2014}
    }

  • J. Asensio-Cubero, J. Q. Gan, and R. Palaniappan, “Wavelet Lifting over Information-Based EEG Graphs for Motor Imagery Data Classification,” in Physiological computing systems, phycs 2014, Springer, 2014, vol. 8908, pp. 3-19. doi:10.1007/978-3-662-45686-6{_}1
    [BibTeX] [Download PDF]
    @incollection{asensio2014wavelet,
    author = {Asensio-Cubero, Javier and Gan, John Q and Palaniappan, Ramaswamy},
    booktitle = {Physiological Computing Systems, Phycs 2014},
    doi = {10.1007/978-3-662-45686-6{\_}1},
    isbn = {978-3-662-45686-6; 978-3-662-45685-9},
    pages = {3--19},
    publisher = {Springer},
    title = {{Wavelet Lifting over Information-Based EEG Graphs for Motor Imagery Data Classification}},
    url = {<Go to ISI>://WOS:000354701700001},
    volume = {8908},
    year = {2014}
    }

  • L. Wang, J. Q. Gan, and H. Wang, “CSP-Based EEG Analysis on Dissociated Brain Organization for Single-Digit Addition and Multiplication,” in Advances in neural networks – isnn 2014, Springer, 2014, vol. 8866, pp. 131-139. doi:10.1007/978-3-319-12436-0{_}15
    [BibTeX] [Download PDF]
    @incollection{wang2014csp,
    author = {Wang, Lihan and Gan, John Q and Wang, Haixian},
    booktitle = {Advances in Neural Networks - Isnn 2014},
    doi = {10.1007/978-3-319-12436-0{\_}15},
    isbn = {978-3-319-12436-0; 978-3-319-12435-3},
    pages = {131--139},
    publisher = {Springer},
    title = {{CSP-Based EEG Analysis on Dissociated Brain Organization for Single-Digit Addition and Multiplication}},
    url = {<Go to ISI>://WOS:000354869400015},
    volume = {8866},
    year = {2014}
    }

  • J. Q. Gan and S. Plansangket, “Performance Evaluation of State-of-the-Art Ranked Retrieval Methods and Their Combinations for Query Suggestion,” , 2014.
    [BibTeX]
    @article{gan2014performance,
    author = {Gan, John Q and Plansangket, Suthira},
    title = {{Performance Evaluation of State-of-the-Art Ranked Retrieval Methods and Their Combinations for Query Suggestion}},
    year = {2014}
    }

  • M. Chen, X. Tan, and J. Q. Gan, “A Batch-mode Active Learning Method Based on the Nearest Average-class Distance ( NACD ) for Multiclass Brain-Computer Interfaces,” Journal of fiber bioengineering and informatics, vol. 4, iss. Cd, pp. 627-636, 2014. doi:10.3993/jfbi12201415
    [BibTeX] [Abstract]

    In this paper, a novel batch-mode active learning method based on the nearest average-class distance (ALNACD) is proposed to solvemulti-class problems with Linear Discriminate Analysis (LDA) classifiers. Using the Nearest Average-class Distance (NACD) query function, the ALNACD algorithm selects a batch of most uncertain samples from unlabeled data to improve gradually pre-trained classifiers’ performance. As our method only needs a small set of labeled samples to train initial classifiers, it is very useful in applications like Brain-computer Interface (BCI) design. To verify the effectiveness of the proposed ALNACD method, we test the ALNACD algorithm on the Dataset 2a of BCI Competition IV. The test results show that the ALNACD algorithm offers similar classification results using less sample labeling effort than Random Sampling (RS) method. It also provides competitive results compared with active Support Vector Machine (active SVM), but uses less time than the active SVM in terms of the training.

    @article{chen2014batch,
    abstract = {In this paper, a novel batch-mode active learning method based on the nearest average-class distance (ALNACD) is proposed to solvemulti-class problems with Linear Discriminate Analysis (LDA) classifiers. Using the Nearest Average-class Distance (NACD) query function, the ALNACD algorithm selects a batch of most uncertain samples from unlabeled data to improve gradually pre-trained classifiers’ performance. As our method only needs a small set of labeled samples to train initial classifiers, it is very useful in applications like Brain-computer Interface (BCI) design. To verify the effectiveness of the proposed ALNACD method, we test the ALNACD algorithm on the Dataset 2a of BCI Competition IV. The test results show that the ALNACD algorithm offers similar classification results using less sample labeling effort than Random Sampling (RS) method. It also provides competitive results compared with active Support Vector Machine (active SVM), but uses less time than the active SVM in terms of the training.},
    author = {Chen, Minyou and Tan, Xuemin and Gan, John Q},
    doi = {10.3993/jfbi12201415},
    issn = {19408676},
    journal = {Journal of Fiber Bioengineering and Informatics},
    keywords = {active learning,bci,brain-computer interface,lda,linear discriminant analysis,nacd,nearest average-class distance},
    number = {Cd},
    pages = {627--636},
    publisher = {Binary Information Press {\&} Textile Bioengineering and Informatics Society},
    title = {{A Batch-mode Active Learning Method Based on the Nearest Average-class Distance ( NACD ) for Multiclass Brain-Computer Interfaces}},
    volume = {4},
    year = {2014}
    }

  • H. F. G. Nia, H. Hu, and J. Q. Gan, “A novel fuzzy logic approach to online exposure time calculation of line scan cameras in industrial inspection,” International journal of modelling, identification and control, vol. 21, iss. 1, pp. 8-16, 2014.
    [BibTeX]
    @article{nia2014novel,
    author = {Nia, Hossein Farid Ghassem and Hu, Huosheng and Gan, John Q},
    journal = {International Journal of Modelling, Identification and Control},
    number = {1},
    pages = {8--16},
    publisher = {Inderscience Publishers Ltd},
    title = {{A novel fuzzy logic approach to online exposure time calculation of line scan cameras in industrial inspection}},
    volume = {21},
    year = {2014}
    }

2013

  • R. Poli, C. Cinel, A. Matran-Fernandez, F. Sepulveda, and A. Stoica, “Towards cooperative brain-computer interfaces for space navigation,” in Proceedings of the international conference on intelligent user interfaces (iui), Santa Monica, CA USA, 2013, pp. 149-160.
    [BibTeX]
    @InProceedings{poli13:_towar_cooper_brain_comput_inter_space_navig,
    author = {Riccardo Poli and Caterina Cinel and Ana Matran-Fernandez and Francisco Sepulveda and Adrian Stoica},
    title =  {Towards cooperative brain-computer interfaces for space navigation},
    booktitle = {Proceedings of the International Conference on Intelligent User Interfaces (IUI)},
    pages = {149--160},
    year = 2013,
    address = {Santa Monica, CA USA},
    month =  {19--22 March},
    organization = {ACM}
    }

  • J. Asensio-Cubero, J. Q. Gan, and R. Palaniappan, “Multiresolution analysis over simple graphs for brain computer interfaces.,” Journal of neural engineering, vol. 10, iss. June 2015, p. 46014, 2013. doi:10.1088/1741-2560/10/4/046014
    [BibTeX] [Abstract] [Download PDF]

    OBJECTIVE: Multiresolution analysis (MRA) offers a useful framework for signal analysis in the temporal and spectral domains, although commonly employed MRA methods may not be the best approach for brain computer interface (BCI) applications. This study aims to develop a new MRA system for extracting tempo-spatial-spectral features for BCI applications based on wavelet lifting over graphs.$\backslash$n$\backslash$nAPPROACH: This paper proposes a new graph-based transform for wavelet lifting and a tailored simple graph representation for electroencephalography (EEG) data, which results in an MRA system where temporal, spectral and spatial characteristics are used to extract motor imagery features from EEG data. The transformed data is processed within a simple experimental framework to test the classification performance of the new method.$\backslash$n$\backslash$nMAIN RESULTS: The proposed method can significantly improve the classification results obtained by various wavelet families using the same methodology. Preliminary results using common spatial patterns as feature extraction method show that we can achieve comparable classification accuracy to more sophisticated methodologies. From the analysis of the results we can obtain insights into the pattern development in the EEG data, which provide useful information for feature basis selection and thus for improving classification performance.$\backslash$n$\backslash$nSIGNIFICANCE: Applying wavelet lifting over graphs is a new approach for handling BCI data. The inherent flexibility of the lifting scheme could lead to new approaches based on the hereby proposed method for further classification performance improvement.

    @article{asensio2013multiresolution,
    abstract = {OBJECTIVE: Multiresolution analysis (MRA) offers a useful framework for signal analysis in the temporal and spectral domains, although commonly employed MRA methods may not be the best approach for brain computer interface (BCI) applications. This study aims to develop a new MRA system for extracting tempo-spatial-spectral features for BCI applications based on wavelet lifting over graphs.$\backslash$n$\backslash$nAPPROACH: This paper proposes a new graph-based transform for wavelet lifting and a tailored simple graph representation for electroencephalography (EEG) data, which results in an MRA system where temporal, spectral and spatial characteristics are used to extract motor imagery features from EEG data. The transformed data is processed within a simple experimental framework to test the classification performance of the new method.$\backslash$n$\backslash$nMAIN RESULTS: The proposed method can significantly improve the classification results obtained by various wavelet families using the same methodology. Preliminary results using common spatial patterns as feature extraction method show that we can achieve comparable classification accuracy to more sophisticated methodologies. From the analysis of the results we can obtain insights into the pattern development in the EEG data, which provide useful information for feature basis selection and thus for improving classification performance.$\backslash$n$\backslash$nSIGNIFICANCE: Applying wavelet lifting over graphs is a new approach for handling BCI data. The inherent flexibility of the lifting scheme could lead to new approaches based on the hereby proposed method for further classification performance improvement.},
    author = {Asensio-Cubero, J and Gan, J Q and Palaniappan, R},
    doi = {10.1088/1741-2560/10/4/046014},
    isbn = {1741-2560},
    issn = {1741-2552},
    journal = {Journal of neural engineering},
    number = {June 2015},
    pages = {046014},
    pmid = {23843600},
    publisher = {IOP Publishing},
    title = {{Multiresolution analysis over simple graphs for brain computer interfaces.}},
    url = {http://www.ncbi.nlm.nih.gov/pubmed/23843600},
    volume = {10},
    year = {2013}
    }

  • S. Mouli, R. Palaniappan, I. P. Sillitoe, and J. Q. Gan, “Performance analysis of multi-frequency SSVEP-BCI using clear and frosted colour LED stimuli,” in 13th ieee international conference on bioinformatics and bioengineering, ieee bibe 2013, 2013, pp. 1-4. doi:10.1109/BIBE.2013.6701552
    [BibTeX] [Abstract]

    Among the many paradigms used in brain-computer interface (BCI), steady state visual evoked potential (SSVEP) offers the quickest response; however it is disadvantageous from the point of view of visual fatigue, which prevents subjects from prolonged usage of visual stimuli especially when LEDs are used. In this paper, we propose a visual stimulator using readily available RGB LEDs with clear and frosted glass, with the latter being tested for performance and qualitative user comfort using electroencephalogram (EEG) data from four subjects. Furthermore, we also compare frosted and clear stimuli for three colours Red, Green and Blue with frequency values of 7, 8, 9 and 10 Hz. The results using band-pass filtering and Fast Fourier Transform showed that 7 Hz Green clear LED stimuli gave the highest response in general, although all the subjects indicated that they were more comfortable with frosted LED stimuli. © 2013 IEEE.

    @inproceedings{mouli2013performance,
    abstract = {Among the many paradigms used in brain-computer interface (BCI), steady state visual evoked potential (SSVEP) offers the quickest response; however it is disadvantageous from the point of view of visual fatigue, which prevents subjects from prolonged usage of visual stimuli especially when LEDs are used. In this paper, we propose a visual stimulator using readily available RGB LEDs with clear and frosted glass, with the latter being tested for performance and qualitative user comfort using electroencephalogram (EEG) data from four subjects. Furthermore, we also compare frosted and clear stimuli for three colours Red, Green and Blue with frequency values of 7, 8, 9 and 10 Hz. The results using band-pass filtering and Fast Fourier Transform showed that 7 Hz Green clear LED stimuli gave the highest response in general, although all the subjects indicated that they were more comfortable with frosted LED stimuli. © 2013 IEEE.},
    author = {Mouli, Surej and Palaniappan, Ramaswamy and Sillitoe, Ian P. and Gan, John Q.},
    booktitle = {13th IEEE International Conference on BioInformatics and BioEngineering, IEEE BIBE 2013},
    doi = {10.1109/BIBE.2013.6701552},
    isbn = {9781479931637},
    organization = {IEEE},
    pages = {1--4},
    title = {{Performance analysis of multi-frequency SSVEP-BCI using clear and frosted colour LED stimuli}},
    year = {2013}
    }

  • J. Asensio-Cubero, J. Q. Gan, and R. Palaniappan, “Extracting optimal tempo-spatial features using local discriminantbases and common spatial patterns for brain computer interfacing.pdf,” Biomedical signal processing and control, vol. 8, iss. 6, pp. 772-778, 2013.
    [BibTeX]
    @article{asensio2013extracting,
    author = {Asensio-Cubero, Javier and Gan, John Q and Palaniappan, Ramaswamy},
    journal = {Biomedical Signal Processing and Control},
    number = {6},
    pages = {772--778},
    publisher = {Elsevier},
    title = {{Extracting optimal tempo-spatial features using local discriminantbases and common spatial patterns for brain computer interfacing.pdf}},
    volume = {8},
    year = {2013}
    }

  • Q. Gan, J. M. P. M. P. Langlois, and Y. Savaria, “Parallel array histogram architecture for embedded implementations,” Electronics letters, vol. 49, iss. 2, pp. 99-101, 2013. doi:10.1049/el.2012.2701
    [BibTeX] [Download PDF]
    @article{gan2013parallel,
    author = {Gan, Q. and Langlois, J.M.P. M P and Savaria, Y.},
    doi = {10.1049/el.2012.2701},
    issn = {0013-5194},
    journal = {Electronics Letters},
    number = {2},
    pages = {99--101},
    publisher = {IET},
    title = {{Parallel array histogram architecture for embedded implementations}},
    url = {http://digital-library.theiet.org/content/journals/10.1049/el.2012.2701},
    volume = {49},
    year = {2013}
    }

  • H. Hu and J. Q. Gan, “Feature-channel subset selection for optimising myoelectric human-machine interface design Mohammadreza Asghari Oskoei *,” International journal of biomechatronics and biomedical robotics, vol. 2, iss. 2-4, pp. 195-208, 2013.
    [BibTeX]
    @article{oskoei2013feature,
    author = {Hu, Huosheng and Gan, John Q},
    journal = {International Journal of Biomechatronics and Biomedical Robotics},
    keywords = {2013,a,and gan,davies-bouldin index,dbi,design,feature subset selection,feature-channel subset selection for,follows,h,hu,j,m,multi-objective genetic algorithm,myoelectric hmi,optimising myoelectric human-machine interface,oskoei,q,reference to this paper,should be made as},
    number = {2-4},
    pages = {195--208},
    publisher = {Inderscience Publishers Ltd},
    title = {{Feature-channel subset selection for optimising myoelectric human-machine interface design Mohammadreza Asghari Oskoei *}},
    volume = {2},
    year = {2013}
    }

  • L. Zhang, H. Wang, and J. Q. Gan, “EEG-based cortical localization of neural efficiency related to mathematical giftedness,” in Neural information processing, 2013, pp. 25-32.
    [BibTeX]
    @inproceedings{zhang2013eeg,
    author = {Zhang, Li and Wang, Haixian and Gan, John Q},
    booktitle = {Neural Information Processing},
    organization = {Springer},
    pages = {25--32},
    title = {{EEG-based cortical localization of neural efficiency related to mathematical giftedness}},
    year = {2013}
    }

2012

  • R. Poli, C. Cinel, A. Matran-Fernandez, F. Sepulveda, and A. Stoica, “Some steps towards realtime control of a space-craft simulator via a brain-computer interface,” School of Computer Science and Electronic Engineering, University of Essex, CES-525, 2012.
    [BibTeX] [Download PDF]
    @TechReport{poli12:_some_steps_realt_contr_space,
    author = {Riccardo Poli and Caterina Cinel and Ana Matran-Fernandez and Francisco Sepulveda and Adrian Stoica},
    title = {Some Steps towards Realtime Control of a Space-craft Simulator via a Brain-computer Interface},
    institution = {School of Computer Science and Electronic Engineering, University of Essex},
    url = {http://cswww.essex.ac.uk/staff/poli/technical-reports/tr-ces-525.pdf},
    year = 2012,
    number = {CES-525},
    month = {October}
    }

  • B. A. S. Hasan and J. Q. Gan, “Hangman BCI: An unsupervised adaptive self-paced Brain-Computer Interface for playing games,” Computers in biology and medicine, vol. 42, iss. 5, pp. 598-606, 2012. doi:10.1016/j.compbiomed.2012.02.004
    [BibTeX] [Abstract]

    This paper presents a novel user interface suitable for adaptive Brain Computer Interface (BCI) system. A customized self-paced BCI architecture is introduced where the system combines onset detection system along with an adaptive classifier working in parallel. An unsupervised adaptive method based on sequential expectation maximization for Gaussian mixture model is employed with new timing scheme and an additional averaging step to avoid over-fitting. Sigmoid function based post-processing approach is proposed to enhance the classifiers’ output. The adaptive system is compared to a non-adaptive one and tested on five subjects who used the BCI to play the hangman game. The results show significant improvement of the True-False difference for all the classes and a reduction in the number of steps required to solve the problem. ?? 2012 Elsevier Ltd.

    @article{hasan2012hangman,
    abstract = {This paper presents a novel user interface suitable for adaptive Brain Computer Interface (BCI) system. A customized self-paced BCI architecture is introduced where the system combines onset detection system along with an adaptive classifier working in parallel. An unsupervised adaptive method based on sequential expectation maximization for Gaussian mixture model is employed with new timing scheme and an additional averaging step to avoid over-fitting. Sigmoid function based post-processing approach is proposed to enhance the classifiers' output. The adaptive system is compared to a non-adaptive one and tested on five subjects who used the BCI to play the hangman game. The results show significant improvement of the True-False difference for all the classes and a reduction in the number of steps required to solve the problem. ?? 2012 Elsevier Ltd.},
    author = {Hasan, Bashar Awwad Shiekh and Gan, John Q.},
    doi = {10.1016/j.compbiomed.2012.02.004},
    isbn = {0010-4825},
    issn = {00104825},
    journal = {Computers in Biology and Medicine},
    keywords = {Adaptive BCI,Discrete control,Gaussian mixture models,Human-machine interaction,Post-processing,Self-paced Brain-Computer Interfaces},
    number = {5},
    pages = {598--606},
    pmid = {22406226},
    publisher = {Elsevier},
    title = {{Hangman BCI: An unsupervised adaptive self-paced Brain-Computer Interface for playing games}},
    volume = {42},
    year = {2012}
    }

  • Q. Gan, R. Xu, and X. Kang, “Synchronization of unknown chaotic delayed competitive neural networks with different time scales based on adaptive control and parameter identification,” Control theory & applications, iet, vol. 6, iss. 10, pp. 1893-1902, 2012. doi:10.1007/s11071-011-0116-1
    [BibTeX]
    @article{gan2012synchronisation,
    author = {Gan, Qintao and Xu, Rui and Kang, Xibing},
    doi = {10.1007/s11071-011-0116-1},
    journal = {Control Theory {\&} Applications, IET},
    keywords = {competitive neural,networks,parameter identification,synchronization,time scale},
    number = {10},
    pages = {1893--1902},
    publisher = {IET},
    title = {{Synchronization of unknown chaotic delayed competitive neural networks with different time scales based on adaptive control and parameter identification}},
    volume = {6},
    year = {2012}
    }

  • J. Asensio-Cubero, J. Q. Gan, and R. Palaniappan, “Extracting common spatial patterns based on wavelet lifting for brain computer interface design,” in 2012 4th computer science and electronic engineering conference (ceec), 2012, pp. 160-163. doi:10.1109/CEEC.2012.6375397
    [BibTeX] [Download PDF]
    @inproceedings{asensio2012extracting,
    author = {Asensio-Cubero, Javier and Gan, John Q. and Palaniappan, Ramaswamy},
    booktitle = {2012 4th Computer Science and Electronic Engineering Conference (CEEC)},
    doi = {10.1109/CEEC.2012.6375397},
    isbn = {978-1-4673-2666-7},
    organization = {IEEE},
    pages = {160--163},
    title = {{Extracting common spatial patterns based on wavelet lifting for brain computer interface design}},
    url = {http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=6375397},
    year = {2012}
    }

  • N. {Al Moubayed}, B. A. S. Hasan, J. Q. Gan, A. Petrovski, and J. McCall, “Continuous presentation for multi-objective channel selection in brain-computer interfaces,” in 2012 ieee congress on evolutionary computation, cec 2012, 2012, pp. 1-7. doi:10.1109/CEC.2012.6252991
    [BibTeX] [Abstract]

    A novel presentation for channel selection problem in Brain-Computer Interfaces (BCI) is introduced here. Continuous presentation in a projected two-dimensional space of the Electroencephalograph (EEG) cap is proposed. A multi-objective particle swarm optimization method (D-2 MOPSO) is employed where particles move in the EEG cap space to locate the optimum set of solutions that minimize the number of selected channels and the classification error rate. This representation focuses on the local relationships among EEG channels as the physical location of the channels is explicitly represented in the search space avoiding picking up channels that are known to be uncorrelated with the mental task. In addition continuous presentation is a more natural way for problem solving in PSO framework. The method is validated on 10 subjects performing right-vs-left motor imagery BCI. The results are compared to these obtained using Sequential Floating Forward Search (SFFS) and shows significant enhancement in classification accuracy but most importantly in the distribution of the selected channels.

    @inproceedings{al2012continuous,
    abstract = {A novel presentation for channel selection problem in Brain-Computer Interfaces (BCI) is introduced here. Continuous presentation in a projected two-dimensional space of the Electroencephalograph (EEG) cap is proposed. A multi-objective particle swarm optimization method (D-2 MOPSO) is employed where particles move in the EEG cap space to locate the optimum set of solutions that minimize the number of selected channels and the classification error rate. This representation focuses on the local relationships among EEG channels as the physical location of the channels is explicitly represented in the search space avoiding picking up channels that are known to be uncorrelated with the mental task. In addition continuous presentation is a more natural way for problem solving in PSO framework. The method is validated on 10 subjects performing right-vs-left motor imagery BCI. The results are compared to these obtained using Sequential Floating Forward Search (SFFS) and shows significant enhancement in classification accuracy but most importantly in the distribution of the selected channels.},
    author = {{Al Moubayed}, Noura and Hasan, Bashar Awwad Shiekh and Gan, John Q. and Petrovski, Andrei and McCall, John},
    booktitle = {2012 IEEE Congress on Evolutionary Computation, CEC 2012},
    doi = {10.1109/CEC.2012.6252991},
    isbn = {9781467315098},
    keywords = {Brain Computer Interfaces,Channel Selection,Continuous Presentation,D2MOPSO,Decomposition,Dominance,EEG,Multi-Objective Particle Swarm Optimization,Multi-Objective Problem},
    organization = {IEEE},
    pages = {1--7},
    title = {{Continuous presentation for multi-objective channel selection in brain-computer interfaces}},
    year = {2012}
    }

  • R. Amorim, B. Mirkin, and J. Q. Gan, “Anomalous pattern based clustering of mental tasks with subject independent learning – some preliminary results,” Artificial intelligence research, vol. 1, iss. 1, pp. 1-8, 2012. doi:10.5430/air.v1n1p55
    [BibTeX]
    @article{cordeiro2012anomalous,
    author = {Amorim, Renato and Mirkin, Boris and Gan, John Q.},
    doi = {10.5430/air.v1n1p55},
    issn = {1927-6974},
    journal = {Artificial Intelligence Research},
    keywords = {clustering,eeg,feature extraction,intelligent k-means},
    number = {1},
    pages = {1--8},
    publisher = {Sciedu Press},
    title = {{Anomalous pattern based clustering of mental tasks with subject independent learning – some preliminary results}},
    volume = {1},
    year = {2012}
    }

  • R. Amorim, B. Mirkin, and J. Q. Gan, “Anomalous pattern based clustering of mental tasks with subject independent learning – some preliminary results,” Artificial intelligence research, vol. 1, iss. 1, pp. 1-8, 2012. doi:10.5430/air.v1n1p55
    [BibTeX]
    @article{cordeiro2012anomalous,
    author = {Amorim, Renato and Mirkin, Boris and Gan, John Q.},
    doi = {10.5430/air.v1n1p55},
    issn = {1927-6974},
    journal = {Artificial Intelligence Research},
    keywords = {clustering,eeg,feature extraction,intelligent k-means},
    number = {1},
    pages = {1--8},
    publisher = {Sciedu Press},
    title = {{Anomalous pattern based clustering of mental tasks with subject independent learning – some preliminary results}},
    volume = {1},
    year = {2012}
    }

  • L-C. Zhang, Y-T. Zheng, J-P. Xiong, J-Q. Gan, B. Jia, and J-X. Xiao, “A Study on the Effect of Prescribed Burning on Microorganism in Soil,” Acta agriculturae universitatis jiangxiensis, vol. 34, iss. 5, pp. 988-992, 2012.
    [BibTeX]
    @article{zhang2012study,
    author = {Zhang, L-C and Zheng, Y-T and Xiong, J-P and Gan, J-Q and Jia, B and Xiao, J-X},
    journal = {Acta Agriculturae Universitatis Jiangxiensis},
    number = {5},
    pages = {988--992},
    title = {{A Study on the Effect of Prescribed Burning on Microorganism in Soil}},
    volume = {34},
    year = {2012}
    }

2011

  • C. S. L. Tsui, J. Q. Gan, and H. Hu, “A Self-Paced Motor Imagery Based Brain-Computer Interface for Robotic Wheelchair Control,” Clinical eeg and neuroscience, vol. 42, iss. 4, pp. 225-229, 2011. doi:10.1177/155005941104200407
    [BibTeX] [Abstract]

    This paper presents a simple self-paced motor imagery based brain-computer interface (BCI) to control a robotic wheelchair. An innovative control protocol is proposed to enable a 2-class self-paced BCI for wheelchair control, in which the user makes path planning and fully controls the wheelchair except for the automatic obstacle avoidance based on a laser range finder when necessary. In order for the users to train their motor imagery control online safely and easily, simulated robot navigation in a specially designed environment was developed. This allowed the users to practice motor imagery control with the core self-paced BCI system in a simulated scenario before controlling the wheelchair. The self-paced BCI can then be applied to control a real robotic wheelchair using a protocol similar to that controlling the simulated robot. Our emphasis is on allowing more potential users to use the BCI controlled wheelchair with minimal training; a simple 2-class self paced system is adequate with the novel control protocol, resulting in a better transition from offline training to online control. Experimental results have demonstrated the usefulness of the online practice under the simulated scenario, and the effectiveness of the proposed self-paced BCI for robotic wheelchair control.

    @article{tsui2011self,
    abstract = {This paper presents a simple self-paced motor imagery based brain-computer interface (BCI) to control a robotic wheelchair. An innovative control protocol is proposed to enable a 2-class self-paced BCI for wheelchair control, in which the user makes path planning and fully controls the wheelchair except for the automatic obstacle avoidance based on a laser range finder when necessary. In order for the users to train their motor imagery control online safely and easily, simulated robot navigation in a specially designed environment was developed. This allowed the users to practice motor imagery control with the core self-paced BCI system in a simulated scenario before controlling the wheelchair. The self-paced BCI can then be applied to control a real robotic wheelchair using a protocol similar to that controlling the simulated robot. Our emphasis is on allowing more potential users to use the BCI controlled wheelchair with minimal training; a simple 2-class self paced system is adequate with the novel control protocol, resulting in a better transition from offline training to online control. Experimental results have demonstrated the usefulness of the online practice under the simulated scenario, and the effectiveness of the proposed self-paced BCI for robotic wheelchair control.},
    author = {Tsui, C. S. L. and Gan, J. Q. and Hu, H.},
    doi = {10.1177/155005941104200407},
    isbn = {1550-0594},
    issn = {1550-0594},
    journal = {Clinical EEG and Neuroscience},
    keywords = {brain-computer interface,electroencephalography,signals},
    number = {4},
    pages = {225--229},
    pmid = {22208119},
    publisher = {SAGE Publications},
    title = {{A Self-Paced Motor Imagery Based Brain-Computer Interface for Robotic Wheelchair Control}},
    volume = {42},
    year = {2011}
    }

  • B. A. S. Hasan and J. Q. Gan, “Temporal modeling of EEG during self-paced hand movement and its application in onset detection,” Journal of neural engineering, vol. 8, iss. 5, p. 56015, 2011. doi:10.1088/1741-2560/8/5/056015
    [BibTeX] [Abstract]

    The temporal behavior of electroencephalography (EEG) recorded during self-paced hand movement is investigated for the purpose of improving EEG classification in general and onset detection in particular. Four temporal models based on conditional random fields are developed and applied to classify EEG data into the movement or idle class. They are further used for building an onset detection system and tested on self-paced EEG signals recorded from five subjects. True-false rates ranging from 74{\%} to 98{\%} have been achieved on different subjects, with significant improvement over non-temporal methods. The effectiveness of the proposed methods suggests their potential use in self-paced brain-computer interfaces.

    @article{hasan2011temporal,
    abstract = {The temporal behavior of electroencephalography (EEG) recorded during self-paced hand movement is investigated for the purpose of improving EEG classification in general and onset detection in particular. Four temporal models based on conditional random fields are developed and applied to classify EEG data into the movement or idle class. They are further used for building an onset detection system and tested on self-paced EEG signals recorded from five subjects. True-false rates ranging from 74{\%} to 98{\%} have been achieved on different subjects, with significant improvement over non-temporal methods. The effectiveness of the proposed methods suggests their potential use in self-paced brain-computer interfaces.},
    author = {Hasan, Bashar Awwad Shiekh and Gan, John Q},
    doi = {10.1088/1741-2560/8/5/056015},
    isbn = {1741-2560},
    issn = {1741-2560},
    journal = {Journal of Neural Engineering},
    number = {5},
    pages = {056015},
    pmid = {21926453},
    publisher = {IOP Publishing},
    title = {{Temporal modeling of EEG during self-paced hand movement and its application in onset detection}},
    volume = {8},
    year = {2011}
    }

  • J. W. Yoon, S. J. Roberts, M. Dyson, and J. Q. Gan, “Bayesian inference for an adaptive Ordered Probit model: An application to Brain Computer Interfacing,” Neural networks, vol. 24, iss. 7, pp. 726-734, 2011. doi:10.1016/j.neunet.2011.03.019
    [BibTeX] [Abstract]

    This paper proposes an algorithm for adaptive, sequential classification in systems with unknown labeling errors, focusing on the biomedical application of Brain Computer Interfacing (BCI). The method is shown to be robust in the presence of label and sensor noise. We focus on the inference and prediction of target labels under a nonlinear and non-Gaussian model. In order to handle missing or erroneous labeling, we model observed labels as a noisy observation of a latent label set with multiple classes (???2). Whilst this paper focuses on the method’s application to BCI systems, the algorithm has the potential to be applied to many application domains in which sequential missing labels are to be imputed in the presence of uncertainty. This dynamic classification algorithm combines an Ordered Probit model and an Extended Kalman Filter (EKF). The EKF estimates the parameters of the Ordered Probit model sequentially with time. We test the performance of the classification approach by processing synthetic datasets and real experimental EEG signals with multiple classes (2, 3 and 4 labels) for a Brain Computer Interfacing (BCI) experiment. ?? 2011 Elsevier Ltd.

    @article{yoon2011bayesian,
    abstract = {This paper proposes an algorithm for adaptive, sequential classification in systems with unknown labeling errors, focusing on the biomedical application of Brain Computer Interfacing (BCI). The method is shown to be robust in the presence of label and sensor noise. We focus on the inference and prediction of target labels under a nonlinear and non-Gaussian model. In order to handle missing or erroneous labeling, we model observed labels as a noisy observation of a latent label set with multiple classes (???2). Whilst this paper focuses on the method's application to BCI systems, the algorithm has the potential to be applied to many application domains in which sequential missing labels are to be imputed in the presence of uncertainty. This dynamic classification algorithm combines an Ordered Probit model and an Extended Kalman Filter (EKF). The EKF estimates the parameters of the Ordered Probit model sequentially with time. We test the performance of the classification approach by processing synthetic datasets and real experimental EEG signals with multiple classes (2, 3 and 4 labels) for a Brain Computer Interfacing (BCI) experiment. ?? 2011 Elsevier Ltd.},
    author = {Yoon, Ji Won and Roberts, Stephen J. and Dyson, Mathew and Gan, John Q.},
    doi = {10.1016/j.neunet.2011.03.019},
    isbn = {0893-6080},
    issn = {08936080},
    journal = {Neural Networks},
    keywords = {Brain Computer Interfacing,Extended Kalman Filter,Multi-class classifier,Ordered Probit model,Sequential decisions},
    number = {7},
    pages = {726--734},
    pmid = {21493037},
    publisher = {Elsevier},
    title = {{Bayesian inference for an adaptive Ordered Probit model: An application to Brain Computer Interfacing}},
    volume = {24},
    year = {2011}
    }

  • B. A. S. Hasan and J. Q. Gan, “Conditional random fields as classifiers for three-class motor-imagery brain-computer interfaces.,” Journal of neural engineering, vol. 8, iss. 2, p. 25013, 2011. doi:10.1088/1741-2560/8/2/025013
    [BibTeX] [Abstract]

    Conditional random fields (CRFs) are demonstrated to be a discriminative model able to exploit the temporal properties of EEG data obtained during synchronous three-class motor-imagery-based brain-computer interface experiments. The advantages of CRFs over the hidden Markov model (HMM) are both theoretical and practical. Theoretically, CRFs focus on modeling latent variables (labels) rather than both observation and latent variables. Furthermore, CRFs’ loss function is convex, guaranteeing convergence to the global optimum. Practically, CRFs are much less prone to singularity problems. This property allows for the use of both time- and frequency-based features, such as band power. The HMM, on the other hand, requires temporal features such as autoregressive coefficients. A CRF-based classifier is tested on 13 subjects. Significant improvement is found when applying CRFs over HMM- and LDA-based classifiers.

    @article{hasan2011conditional,
    abstract = {Conditional random fields (CRFs) are demonstrated to be a discriminative model able to exploit the temporal properties of EEG data obtained during synchronous three-class motor-imagery-based brain-computer interface experiments. The advantages of CRFs over the hidden Markov model (HMM) are both theoretical and practical. Theoretically, CRFs focus on modeling latent variables (labels) rather than both observation and latent variables. Furthermore, CRFs' loss function is convex, guaranteeing convergence to the global optimum. Practically, CRFs are much less prone to singularity problems. This property allows for the use of both time- and frequency-based features, such as band power. The HMM, on the other hand, requires temporal features such as autoregressive coefficients. A CRF-based classifier is tested on 13 subjects. Significant improvement is found when applying CRFs over HMM- and LDA-based classifiers.},
    author = {Hasan, Bashar Awwad Shiekh and Gan, John Q},
    doi = {10.1088/1741-2560/8/2/025013},
    isbn = {1741-2560},
    issn = {1741-2560},
    journal = {Journal of neural engineering},
    number = {2},
    pages = {025013},
    pmid = {21436518},
    publisher = {IOP Publishing},
    title = {{Conditional random fields as classifiers for three-class motor-imagery brain-computer interfaces.}},
    volume = {8},
    year = {2011}
    }

  • J. Q. Gan, B. A. S. Hasan, and C. S. L. Tsui, “A Hybrid Approach to Feature Subset Selection for Brain-Computer Interface Design,” in Intelligent data engineering and automated learning – ideal 2011, Springer, 2011, vol. 6936, pp. 279-286.
    [BibTeX] [Abstract]

    In brain-computer interface (BCI) development, temporal/spectral/spatial/statistical features can be extracted from multiple electro-encephalography (EEG) signals and the number of features available could be up to thousands. Therefore, feature subset selection is an important and challenging problem in BC! design. Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on BCI feature data, in which both linear and nonlinear classifiers as wrappers and Davies-Bouldin index and mutual information based index as filters are alternatively used to evaluate potential feature subsets. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection for BCI design.

    @incollection{gan2011hybrid,
    abstract = {In brain-computer interface (BCI) development, temporal/spectral/spatial/statistical features can be extracted from multiple electro-encephalography (EEG) signals and the number of features available could be up to thousands. Therefore, feature subset selection is an important and challenging problem in BC! design. Sequential forward floating search (SFFS) has been well recognized as one of the best feature selection methods. This paper proposes a filter-dominating hybrid SFFS method, aiming at high efficiency and insignificant accuracy sacrifice for high-dimensional feature subset selection. Experiments with this new hybrid approach have been conducted on BCI feature data, in which both linear and nonlinear classifiers as wrappers and Davies-Bouldin index and mutual information based index as filters are alternatively used to evaluate potential feature subsets. Experimental results have demonstrated the advantages and usefulness of the proposed method in high-dimensional feature subset selection for BCI design.},
    author = {Gan, John Q and Hasan, Bashar Awwad Shiekh and Tsui, Chun Sing Louis},
    booktitle = {Intelligent Data Engineering and Automated Learning - Ideal 2011},
    isbn = {0302-9743; 978-3-642-23877-2},
    pages = {279--286},
    publisher = {Springer},
    title = {{A Hybrid Approach to Feature Subset Selection for Brain-Computer Interface Design}},
    volume = {6936},
    year = {2011}
    }

  • J. Asensio-Cubero, R. Palaniappan, and J. Q. Gan, “A study on temporal segmentation strategies for extracting common spatial patterns for brain computer interfacing,” , 2011.
    [BibTeX]
    @article{asensio2011study,
    author = {Asensio-Cubero, Javier and Palaniappan, Ramaswamy and Gan, John Q},
    publisher = {University of Manchester, School of Computer Science},
    title = {{A study on temporal segmentation strategies for extracting common spatial patterns for brain computer interfacing}},
    year = {2011}
    }

  • J. Asensio, E. Galvan, R. Palaniappan, and J. Q. Gan, “Wavelet Design by Means of Multi-Objective GAs for Motor Imagery EEG Analysis,” , pp. 1-4, 2011.
    [BibTeX]
    @article{asensio2011wavelet,
    author = {Asensio, Javier and Galvan, Edgar and Palaniappan, Ramaswamy and Gan, John Q},
    pages = {1--4},
    publisher = {Verlag der Technischen Universitat Graz},
    title = {{Wavelet Design by Means of Multi-Objective GAs for Motor Imagery EEG Analysis}},
    year = {2011}
    }

2010

  • B. {Awwad Shiekh Hasan} and J. Q. Gan, “Unsupervised movement onset detection from EEG recorded during self-paced real hand movement,” Medical and biological engineering and computing, vol. 48, iss. 3, pp. 245-253, 2010. doi:10.1007/s11517-009-0550-0
    [BibTeX] [Abstract]

    This article presents an unsupervised method for movement onset detection from electroencephalography (EEG) signals recorded during self-paced real hand movement. A Gaussian Mixture Model (GMM) is used to model the movement and idle-related EEG data. The GMM built along with appropriate classification and post processing methods are used to detect movement onsets using self-paced EEG signals recorded from five subjects, achieving True-False rate difference between 63 and 98{\%}. The results show significant performance enhancement using the proposed unsupervised method, both in the sample-by-sample classification accuracy and the event-by-event performance, in comparison with the state-of-the-art supervised methods. The effectiveness of the proposed method suggests its potential application in self-paced Brain-Computer Interfaces (BCI).

    @article{hasan2010unsupervised,
    abstract = {This article presents an unsupervised method for movement onset detection from electroencephalography (EEG) signals recorded during self-paced real hand movement. A Gaussian Mixture Model (GMM) is used to model the movement and idle-related EEG data. The GMM built along with appropriate classification and post processing methods are used to detect movement onsets using self-paced EEG signals recorded from five subjects, achieving True-False rate difference between 63 and 98{\%}. The results show significant performance enhancement using the proposed unsupervised method, both in the sample-by-sample classification accuracy and the event-by-event performance, in comparison with the state-of-the-art supervised methods. The effectiveness of the proposed method suggests its potential application in self-paced Brain-Computer Interfaces (BCI).},
    author = {{Awwad Shiekh Hasan}, Bashar and Gan, John Q.},
    doi = {10.1007/s11517-009-0550-0},
    isbn = {0140-0118},
    issn = {01400118},
    journal = {Medical and Biological Engineering and Computing},
    keywords = {Electroencephalography,Gaussian Mixture Models,Movement onset detection,Post processing,Self-paced BCI,Unsupervised learning},
    number = {3},
    pages = {245--253},
    pmid = {19888613},
    publisher = {Springer},
    title = {{Unsupervised movement onset detection from EEG recorded during self-paced real hand movement}},
    volume = {48},
    year = {2010}
    }

  • T. Geng, J. Q. Gan, and H. Hu, “A self-paced online BCI for mobile robot control,” International journal of advanced mechatronic systems, vol. 2, iss. 1-2, pp. 28-35, 2010.
    [BibTeX]
    @article{geng2010self,
    author = {Geng, Tao and Gan, John Q and Hu, Huosheng},
    journal = {International Journal of Advanced Mechatronic Systems},
    number = {1-2},
    pages = {28--35},
    publisher = {Inderscience Publishers},
    title = {{A self-paced online BCI for mobile robot control}},
    volume = {2},
    year = {2010}
    }

  • N. {Al Moubayed}, B. {Awwad Shiekh Hasan}, J. Q. Gan, A. Petrovski, and J. McCall, “Binary-SDMOPSO and its application in channel selection for brain-computer interfaces,” in 2010 uk workshop on computational intelligence, ukci 2010, 2010, pp. 1-6. doi:10.1109/UKCI.2010.5625570
    [BibTeX] [Abstract]

    In, we introduced Smart Multi-Objective Particle Swarm Optimisation using Decomposition (SDMOPSO). The method uses the decomposition approach proposed in Multi-Objective Evolutionary Algorithms based on Decomposition (MOEA/D), whereby a multi-objective problem (MOP) is represented as several scalar aggregation problems. The scalar aggregation problems are viewed as particles in a swarm; each particle assigns weights to every optimisation objective. The problem is solved then as a Multi-Objective Particle Swarm Optimisation (MOPSO), in which every particle uses information from a set of defined neighbours. This work customize SDMOSPO to cover binary problems and applies the proposed binary method on the channel selection problem for Brain-Computer Interfaces (BCI).

    @inproceedings{moubayed2010binary,
    abstract = {In, we introduced Smart Multi-Objective Particle Swarm Optimisation using Decomposition (SDMOPSO). The method uses the decomposition approach proposed in Multi-Objective Evolutionary Algorithms based on Decomposition (MOEA/D), whereby a multi-objective problem (MOP) is represented as several scalar aggregation problems. The scalar aggregation problems are viewed as particles in a swarm; each particle assigns weights to every optimisation objective. The problem is solved then as a Multi-Objective Particle Swarm Optimisation (MOPSO), in which every particle uses information from a set of defined neighbours. This work customize SDMOSPO to cover binary problems and applies the proposed binary method on the channel selection problem for Brain-Computer Interfaces (BCI).},
    author = {{Al Moubayed}, Noura and {Awwad Shiekh Hasan}, Bashar and Gan, John Q. and Petrovski, Andrei and McCall, John},
    booktitle = {2010 UK Workshop on Computational Intelligence, UKCI 2010},
    doi = {10.1109/UKCI.2010.5625570},
    isbn = {9781424487752},
    organization = {IEEE},
    pages = {1--6},
    title = {{Binary-SDMOPSO and its application in channel selection for brain-computer interfaces}},
    year = {2010}
    }

  • M. Dyson, F. Sepulveda, and J. Q. Gan, “Localisation of cognitive tasks used in EEG-based BCIs,” Clinical neurophysiology, vol. 121, iss. 9, pp. 1481-1493, 2010. doi:10.1016/j.clinph.2010.03.011
    [BibTeX] [Abstract]

    Objective: To provide candidate electrode sites and neurophysiological reference information for cognitive tasks used in brain-computer interfacing research. Methods: Six cognitive tasks were tested against the idle state. Data representing the idle state were collected with active cognitive task data during each recording session. Cross subject candidate electrode sites were obtained via a wrapper method based upon a sequential forward floating search algorithm. Source localisation results were obtained using sLORETA software. Results: Spatial feature distributions and localisation results are presented. Primary centres of activity for motor imagery tasks are localised to the pre- and postcentral gyrus. Auditory-based tasks show activity in the middle temporal gyrus. Calculation activity was localised to the left inferior frontal gyrus and right supramarginal gyrus. Navigation imagery produced activity in the precuneus and anterior cingulate cortex. Conclusions: Spatial areas of activation suggest that arithmetic and auditory tasks show promise for pairwise discrimination based on single recording sites. sLORETA significance levels suggest that motor imagery tasks will show greatest discrimination from baseline EEG activity. Significance: This is the first study to provide candidate electrode sites for multiple tasks used in brain-computer interfacing. ?? 2010 International Federation of Clinical Neurophysiology.

    @article{dyson2010localisation,
    abstract = {Objective: To provide candidate electrode sites and neurophysiological reference information for cognitive tasks used in brain-computer interfacing research. Methods: Six cognitive tasks were tested against the idle state. Data representing the idle state were collected with active cognitive task data during each recording session. Cross subject candidate electrode sites were obtained via a wrapper method based upon a sequential forward floating search algorithm. Source localisation results were obtained using sLORETA software. Results: Spatial feature distributions and localisation results are presented. Primary centres of activity for motor imagery tasks are localised to the pre- and postcentral gyrus. Auditory-based tasks show activity in the middle temporal gyrus. Calculation activity was localised to the left inferior frontal gyrus and right supramarginal gyrus. Navigation imagery produced activity in the precuneus and anterior cingulate cortex. Conclusions: Spatial areas of activation suggest that arithmetic and auditory tasks show promise for pairwise discrimination based on single recording sites. sLORETA significance levels suggest that motor imagery tasks will show greatest discrimination from baseline EEG activity. Significance: This is the first study to provide candidate electrode sites for multiple tasks used in brain-computer interfacing. ?? 2010 International Federation of Clinical Neurophysiology.},
    author = {Dyson, M. and Sepulveda, F. and Gan, J. Q.},
    doi = {10.1016/j.clinph.2010.03.011},
    isbn = {1388-2457},
    issn = {13882457},
    journal = {Clinical Neurophysiology},
    keywords = {Brain-computer interface (BCI),Cognitive task,SLORETA,Source localisation},
    number = {9},
    pages = {1481--1493},
    pmid = {20435514},
    publisher = {Elsevier},
    title = {{Localisation of cognitive tasks used in EEG-based BCIs}},
    volume = {121},
    year = {2010}
    }

  • T. Geng and J. Q. Gan, “Planar biped walking with an equilibrium point controller and state machines,” Ieee/asme transactions on mechatronics, vol. 15, iss. 2, pp. 253-260, 2010. doi:10.1109/TMECH.2009.2024742
    [BibTeX] [Abstract]

    In this paper, we present both simulation analysis and experimental study of a planar dynamic biped walking robot. The proposed control structure involves an equilibrium point controller at the local joint level and state machines at the interjoint level. The robot has actuated hip joints and knee joints as well as unactuated ankle joints with curved feet. We first show in simulation analysis that stable walking by this robot is possible with various gait patterns and a wide range of walking speed. Then, we implement the controller on a real biped robot, and show in real-time experiments that, by directly changing two controller parameters, the robot can change its walking gait/speed on the fly and can achieve a very fast walking speed.

    @article{geng2010planar,
    abstract = {In this paper, we present both simulation analysis and experimental study of a planar dynamic biped walking robot. The proposed control structure involves an equilibrium point controller at the local joint level and state machines at the interjoint level. The robot has actuated hip joints and knee joints as well as unactuated ankle joints with curved feet. We first show in simulation analysis that stable walking by this robot is possible with various gait patterns and a wide range of walking speed. Then, we implement the controller on a real biped robot, and show in real-time experiments that, by directly changing two controller parameters, the robot can change its walking gait/speed on the fly and can achieve a very fast walking speed.},
    author = {Geng, Tao and Gan, John Q.},
    doi = {10.1109/TMECH.2009.2024742},
    isbn = {0220090416},
    issn = {10834435},
    journal = {IEEE/ASME Transactions on Mechatronics},
    keywords = {Biped robot,Dynamic walking,Equilibrium point (EP) control,Legged locomotion},
    number = {2},
    pages = {253--260},
    publisher = {IEEE},
    title = {{Planar biped walking with an equilibrium point controller and state machines}},
    volume = {15},
    year = {2010}
    }

  • B. A. S. Hasan, J. Q. Gan, and Q. Zhang, “Multi-objective evolutionary methods for channel selection in Brain-Computer Interfaces: Some preliminary experimental results,” in 2010 ieee congress on evolutionary computation (cec’2010), 2010, pp. 3339-3344.
    [BibTeX]
    @inproceedings{hasan2010multi,
    author = {Hasan, Bashar Awwad Shiekh and Gan, John Q and Zhang, Qingfu},
    booktitle = {2010 IEEE Congress on Evolutionary Computation (CEC'2010)},
    organization = {IEEE},
    pages = {3339--3344},
    title = {{Multi-objective evolutionary methods for channel selection in Brain-Computer Interfaces: Some preliminary experimental results}},
    year = {2010}
    }

Older Publications

Peer Reviewed Journal Papers

2009

  • R. Poli, L. Citi, C. Cinel, F. Sepulveda (2009)  ‘Reaction-time Binning: a Simple Method for Increasing the Resolving Power of ERP Averages’.  Psychophysiology, to appear.
  • R. Poli, L. Citi, F. Sepulveda, C. Cinel (2009) ‘Analogue Evolutionary Brain Computer Interfaces’.  IEEE Computational Intelligence Magazine, to appear.
  • T. Geng, J.Q. Gan, and H. Hu, (2009) ‘An EEG-based online brain computer interface for mobile robot control’. International Journal of Advanced Mechatronic Systems , to appear.

  • Y. Khan, F. Sepulveda (2009) ‘ Brain Computer Interface for single-trial EEG classification for wrist movement imagery using spatial filtering in the Gamma band ‘.  IET Signal Processing, to appear.

  • J.W. Yoon, S.J. Roberts, M. Dyson, and J.Q. Gan (2009)  ‘Adaptive classification for brain computer interface systems using sequential Monte Carlo sampling’. Neural Networks, to appear.

  • R. Palaniappan (2009) “Highly fraud resistant two-stage biometric authentication method using thought activity brain waves”.International Journal of Neural Systems, to appear.

  • T. Balli and R. Palaniappan (2009) “On the complexity and energy analyses in EEG between alcoholic and control subjects during delayed matching to sample paradigm”. International Journal on Computational Intelligence and Applications (special issue on Biomedical Signal Sensing and Intelligent Information Processing) – to appear.

  • C.N. Gupta, Y. Khan, R. Palaniappan, F. Sepulveda (2009) ‘Wavelet Framework for Improved Target Detection in Oddball Paradigms Using P300 and Gamma Band Analysis’.  Int. Journal of Biomedical Soft Computing and Human Sciences, to appear.

  • M. Salvaris, F. Sepulveda (2009) ‘Visual modifications on P300 speller BCI paradigm ‘.  Journal of Neural Engineering, 6 046011 (8pp)   doi: 10.1088/1741-2560/6/4/046011

  • C.S.L. Tsui, J.Q. Gan, and S.J. Roberts (2009) ‘A self-paced brain-computer interface for controlling a robot simulator: An online event labelling paradigm and an extended Kalman filter based algorithm for online training’. Medical & Biological Engineering & Computing, vol. 47, no. 3, pp. 257-265.

2008

  • T. Geng, J.Q. Gan, M. Dyson, C.S.L. Tsui, F. Sepulveda (2008) ‘A Novel Design of 4-Class BCI Using Two Binary Classifiers and Parallel Mental Tasks’.  Computational Intelligence and Neuroscience. Vol. 2008, Article ID 437306, 5 pages.

  • A. Vuckovic, F. Sepulveda (2008) ‘Delta Band Contribution in Cue Based Single Trial Classification of Real and Imaginary Wrist Movements”.  Medical & Biological Engineering & Computing, vol. 46(6):529-539.   download

  • A. Vuckovic, F. Sepulveda (2008) ‘Quantification and Visualisation of Differences between Two Motor Tasks Based on Energy Density Maps for BCI Applications’. Clin. Neurophys., Vol. 119(2): 446-458.  download

  • L. Citi, R. Poli, C. Cinel, F. Sepulveda (2008)  ‘P300-based BCI Mouse with Genetically-optimised Analogue Control’.  IEEE Trans. Neur. Sys. Rehab. Eng., vol. 16(1):51 – 61.   download

  •  S.-M. Zhou, J.Q. Gan, and F. Sepulveda (2008) “Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface’. International Journal of Information Sciences, vol. 178, no. 6, pp.1629-1640. download

  • S. Andrews, R. Palaniappan, A. Teoh and L. C. Kiong, “Enhancing P300 component by spectral power ratio principal components for a single trial brain-computer interface,” American Journal of Applied Sciences, vol. 5, no. 6, pp. 639-644, 2008.

2007

  • C. N. Gupta and R. Palaniappan (2007) ‘Enhanced detection of visual evoked potentials in brain-computer interface using genetic algorithm and cyclostationary analysis,” special issue on Brain-Computer Interfaces: Towards Practical Implementations and Potential Applications, Journal of Computational Intelligence and Neuroscience, doi:10.1155/2007/28692.

  • R. Palaniappan, and D. P. Mandic (2007) “Biometric from the brain electrical activity: A machine learning approach,” IEEE Transactions on Pattern Analysis and Machine Intelligence (special issue on biometrics), pp 738-742, vol. 29, no. 4.

  • R. Palaniappan, and D. P. Mandic, “EEG Based Biometric Framework for Automatic Identity Identification,” International Journal of VLSI Signal Processing
    Systems (Special issue on Data Fusion for Medical, Industrial, and Environmental Applications), pp.243-250, no. 49, 2007.

2006

  • R.Palaniappan (2006) ‘Utilizing Gamma Band to Improve Mental Task Based Brain-Computer Interface Design’.    IEEE Trans. Neur. Sys. Rehab. Eng., vol. 14(3):299-303.

  • R. Palaniappan (2006) “Single trial visual event related potential extraction by negentropy maximisation of independent components”, WSEAS Transactions on Signal Processing, pp. 512-517, vol. 2, issue 4.

  • R. Palaniappan (2006) “Towards Optimal Model Order Selection for Autoregressive Spectral Analysis of Mental Tasks Using Genetic Algorithm,” International Journal of Computer Science and Network Security, pp.153-162, vol. 6, no. 1A.

  • R. Palaniappan, “Multiple mental thought parametric classification: a new approach for individual identification,” International Journal of Signal Processing, pp. 222-225, vol. 2, no. 3, 2005.

  • R. Palaniappan and KVR. Ravi, “Improving visual evoked potential feature classification for person recognition using PCA and normalization,” Pattern Recognition Letters, pp.726-733, vol.27, issue 7, 2006.

  • K.V.R. Ravi and R. Palaniappan, “Neural network classification of late gamma band electroencephalogram features,” Soft Computing, pp. 163-169, vol. 10, no.2, 2006.

  • K.V.R. Ravi, R. Palaniappan, and S.H. Heng, “Simplified fuzzy ARTMAP classification of individuals using optimal VEP channels”, International Journal of Knowledge-Based and Intelligent Engineering Systems, pp. 445-452, vol. 10, no. 6, 2006.

2005

  • S. Andrews, N. Kamel, D. Ngo, and R. Palaniappan, “Appropriate Normalisation for Selective Eigen Rate Method in Separating Principal Components of VEP and EEG in BCI,” Multimedia Cyberscape Journal (special issue on Multimedia Data Processing and Compression), pp. 1-6, vol.3 no.4, 2005.

 

Book Chapters

  • F. Sepulveda (2009) ‘An overview of BMIs’.  Chapter in L. Rossini, D. Izzo and L. Summerer, editors: ‘Brain-machine interfaces for space applications: Enhancing astronaut capabilities‘. International Review of Neurobiology, Vol. 86, Burlington: Academic Press, 2009, pp. 93-106. ISBN: 978-0-12-374821-8.

  • R. Palaniappan and L. M. Patnaik, “Identity Verification Using Resting State Brain Signals” book chapter published in M. Quigley (ed.): “Encyclopedia of Information Ethics and Security,” pp.335-341, Information Science Reference, IGI Global, Hershey, PA, 2008.

  • R. Palaniappan, C.S. Syan and P. Raveendran, “Current practices in electroencephalogram based brain-computer interfaces,” book chapter published in M. Khosrow-Pour (ed.): “Encyclopedia of Information Science and Technology, 2nd ed.,” IGI Global, Hershey, PA, USA, 2008 [in press].

  • C. N. Gupta and R. Palaniappan, “Biometric paradigm using visual evoked potential,” book chapter published in M. Khosrow-Pour (ed.): “Encyclopedia of Information Science and Technology, 2nd ed.,” IGI Global, Hershey, PA, USA, 2008 [in press].

  • T. Balli and R. Palaniappan, “Nonlinear approach to brain signal modelling,” book chapter published in M. Khosrow-Pour (ed.): “Encyclopedia of Information Science and Technology, 2nd ed.,” IGI Global, Hershey, PA, USA, 2008 [in press].

  • R. Palaniappan, “Electroencephalogram signals from imagined activities: a novel biometric identifier for a small population,” book chapter published in E. Corchado et al. (eds): “Intelligent Data Engineering and Automated Learning – IDEAL 2006”, Lecture Notes in Computer Science, vol. 4224, pp. 604-611, Springer-Verlag, Berlin Heidelberg, 2006.

  • R. Palaniappan, and D. P. Mandic, “Energy of brain potentials evoked during visual stimulus: a new biometric?,” book chapter published in W. Duch, J.Kacprzyk, E.Oja and S.Zadrozny (eds.): “Artificial Neural Networks: Formal Models and Their Applications – ICANN 2005,” Lecture Notes in Computer Science, vol. 3697, pp.735–740, Springer-Verlag, Berlin Heidelberg, 2005.

 

Peer Reviewed Papers in Conference Proceedings

2009

  • Wilson J J and Palaniappan R (2009) Augmenting a SSVEP BCI through single cycle analysis and phase weighting. In: Neural Engineering, 2009. NER ’09. 4th International IEEE/EMBS Conference on, pp 371-4.

  • B. Awwad Shiekh Hasan and J.Q. Gan, “Sequential EM for unsupervised adaptive Gaussian mixture model based classifier,” Int. Conf. on Machine Learning and Data Mining, Leipzig, Germany, 2009

  • B. Awwad Shiekh Hasan and J.Q. Gan, “Unsupervised adaptive GMM for BCI,” International IEEE EMBS Conf. on Neural Engineering, Antalya, Turkey, 2009, pp. 295-298.

  • M. Dyson, F. Sepulveda, J.Q. Gan, and S.J. Roberts, “Sequential classification of mental tasks vs. idle,” International IEEE EMBS Conf. on Neural Engineering, Antalya, Turkey, 2009, pp. 351-354.

  • M. Asghari Oskoei, J.Q. Gan, and H. Hu, “Adaptive schemes applied to online SVM for BCI data classification,” Annual International Conference of IEEE Engineering in Medicine and Biology Society, Minnesota, USA, 2009.

2008

  • C.S.L. Tsui and J.Q. Gan, “Comparison of three methods for adapting LDA classifiers with BCI applications,” The 4th International Workshop on Brain-Computer Interfaces, Graz, Austria, 2008, pp. 116-121.

  • M. Dyson, T. Balli, J.Q. Gan, R. Palaniappan, and F. Sepulveda, “Approximate entropy for EEG-based movement detection,” The 4th International Workshop on Brain-Computer Interfaces, Graz, Austria, 2008, pp.110-115.

  • T. Geng and J.Q. Gan, “Towards a virtual 4-class synchronous BCI using motor prediction and one motor imagery,” The 4th International Workshop on Brain-Computer Interfaces, Graz, Austria, 2008, pp. 203-207.

  • A. Vuckovic, F. Sepulveda (2008) ‘A four-class BCI based on motor imagination of the right and the left hand wrist ‘. First International Symposium on Applied Sciences on Biomedical and Communication Technologies, 2008. ISABEL ’08.  Aalborg, DK, 25-28 Oct. 2008, 4 pages. Digital Object Identifier   10.1109/ISABEL.2008.4712628

  • T. Geng, J.Q. Gan, and H. Hu, “A self-paced online BCI for mobile robot control,” Sino-European Workshop on Intelligent Robots and Systems, Chongqing, China, 2008.

  • B. Awwad Shiekh Hasan, M. Dyson, T. Balli, and J.Q. Gan, “A study via feature selection on the separability of approximate entropy for brain-computer interfaces,” The UK Workshop on Computational Intelligence (UKCI2008), De Montfort, UK, 2008, pp. 189-194.

  • J.W. Yoon, S.J. Roberts, M. Dyson, and J.Q. Gan, “Sequential Bayesian estimation for adaptive classification,” IEEE Int. Conf. on Multisensor Fusion and Integration for Intelligent Systems (MFI2008), Seoul, Korea, 2008, pp. 601-605. J.W.

  • Yoon, S.J. Roberts, M. Dyson, and J.Q. Gan, “Adaptive classification by hybrid EKF with truncated filtering: Brain computer interfacing,”International Conference on Intelligent Data Engineering and Automated Learning (IDEAL2008), Daejeon, Korea, 2008. Lecture Notes in Computer Science, vol. 5326/2008, pp. 370-377.

  • T. Balli and R. Palaniappan, “EEG time series analysis with exponential autoregressive modelling,” IEEE Canadian Conference on Electrical and Computer Engineering, Niagara Falls, Ontario, Canada, 4-7 May 2008.

  • A. Agapitos, M. Dyson, S. Lucas, F. Sepulveda (2008) ‘Learning to Recognise Mental Activities: Genetic Programming of Stateful Classifiers for Brain-Computer Interfacing’. Proceedings of the Genetic and Evolutionary Computation Conference,   GECCO 2008, Atlanta.

  • C.N. Gupta, J.J. Wilson, R. Palaniappan, and C.S. Syan, “Single trial P300 amplitude for pass-code brain-machine interface design,” International Conference on Advanced Computing, Chikhli, Maharashtra, India, 21-22 February 2008.

  • C.N. Gupta, R. Palaniappan, and S. Swaminathan, “Novel P300 Paradigm – Moving Towards Brain Biometric Systems,” Book of Abstracts, International Symposium of Global trends in BioMedical Informatics Research, Education and Commercialization, Chennai, India, p. 38, 11-12 January 2008.

2007

  • T. Geng and J.Q. Gan, “A 3-class asynchronous BCI for controlling mobile robots,” MAIA BCI Workshop – BCI Meets Robotics: Challenging Issues in Brain-Computer Interaction and Shared Control, Leuven, Belgium, 2007, p. 33

  • F. Sepulveda, M. Dyson, J.Q. Gan, C.S.L. Tsui  ‘A Comparison of Mental Task Combinations for Asynchronous EEG-Based BCIs’.  29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society  EMBC07, Lyon, August 22-26, 2007, pp. 5055-5058.

  • M. Salvaris, F. Sepulveda, ‘Robustness of the Farwell & Donchin BCI protocol to visual stimulus parameter changes’. 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society  EMBC07, Lyon, August 22-26, 2007.

  • T. Geng, M. Dyson, J.Q. Gan, C.S.L. Tsui  ‘A 3-Class Asynchronous BCI Controlling a Simulated Mobile Robot’. 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society  EMBC07, Lyon, August 22-26, 2007, 2524-2527.

  • C.S.L. Tsui and J.Q. Gan, “Asynchronous BCI control of a robot simulator with supervised online training,” International Conference on Intelligent Data Engineering and Automated Learning (IDEAL2007), Birmingham, UK, 2007, pp. 125-134.

  • C.S.L. Tsui, P. Jia, J.Q. Gan, H. Hu, and K. Yuan, “EMG-based hands-free wheelchair control with EOG attention shift detection,” IEEE International Conference on Robotics and Biomimetics (ROBIO2007), Sanya, China, 2007, pp. 1266-1271.

  • K.V.R. Ravi, and R. Palaniappan, “A minimal channel set for individual identification with EEG biometric using genetic algorithm,” Proceedings of International Conference on Computational Intelligence and Multimedia Applications (ICCIMA07), Sivakasi, India, vol. II, pp. 328-333, 13-15 December 2007 (DOI 10.1109/ICCIMA.2007.82).

  • K.V.R. Ravi, R. Palaniappan, C. Eswaran and S. Phon-Amnuaisuk “Data encryption using event-related brain signals,” Proceedings of International Conference on Computational Intelligence and Multimedia Applications (ICCIMA07), Sivakasi, India, vol. I, pp. 540-544, 13-15 December 2007 (DOI 10.1109/ICCIMA.2007.178).

  • S. Andrews, A. Teoh, L. C. Kiong and R. Palaniappan, “Combinational component selection for single trial analysis of visual evoked potential signals for brain computer interface,” Proceedings of 3rd International Colloquium on Signal Processing and its Applications, Melaka, Malaysia, pp.107-109, 9 – 11 March 2007.

  • R. Palaniappan, “Improving Evoked Potential Brain-Computer Interface Design Using Mutation Based Genetic Algorithm”, Proceedings of 1st Indian Conference on Computational Intelligence and Information Security, Madurai, India, pp. 104-108, 25 January 2007.

2006

  • A. Vuckovic, F. Sepulveda, “EEG gamma band information in cue-based single trial classification of four movements about the right wrist”, Challenging Brain-Computer Interfaces, MAIA Workshop, Rome, Italy,  Nov. 9-10, 2006, p. 54.

  • T. Geng, J.Q. Gan, M. Dyson, C.S.L. Tsui, and F. Sepulveda, “EEG-based synchronous parallel BCI,” Challenging Brain-Computer Interfaces,  MAIA Workshop, Rome, Italy,  Nov. 9-10, 2006, p. 41.

  • A. Vuckovic, F. Sepulveda, “EEG Single-trial classification of four classes of imaginary wrist movements based on Gabor coefficients”, 3rd International Workshop on Brain-Computer Interfaces , Graz, Austria, 2006, pp.26-27.

  • J.Q. Gan, “Self-adapting BCI based on unsupervised learning,” 3rd International Workshop on Brain-Computer Interfaces, Graz, Austria, 2006, pp. 50-51.

  • J.Q. Gan, “Feature dimensionality reduction by manifold learning in brain-computer interface design,”  3rd International Workshop on Brain-Computer Interfaces, Graz, Austria, 2006, pp. 28-29.

  • C.S.L. Tsui, A. Vuckovic, R. Palaniappan, F. Sepulveda, and J.Q. Gan, “Narrow band spectral analysis for movement onset detection in asynchronous BCI,” 3rd International Workshop on Brain-Computer Interfaces, Graz, Austria, 2006, pp. 30-31.

  • B. Hubais, F. Sepulveda, I Navarro,. ”Crossectional investigation of wrist movement intention classification in EEG signals”, 3rdInternational Workshop on Brain-Computer Interfaces, Graz, Austria, 2006, pp.38-39.

  • C. Menon, C. Negueruela, J. del Millan, O. Tonet, F. Carpi, M. Broschar, P. Ferrez, A. Buttfield, P. Dario, L. Citi, C. Laschi, M. Tombini, F. Sepulveda, R. Poli, F. Tecchio, P. Rossini, D. de Rossi.  ‘Prospective on Brain-Machine Interfaces  for Space System Control’.  57th Astronautical Congress, Spain, Oct. 2-6, 2006.

  • R.Palaniappan, “Minimising mutual information using genetic algorithm for single trial P300 component extraction,” 18th international EURASIP Biosignal conference, Brno, Czech Republic, 28-30 June, 2006.

  • H. Lakany, P. Worrarjiran, G. Valsan, B. Conway (2006) ‘On feature selection for brain computer interfaces’.  Abstracts of the 28th International Congress of Clinical Neurophysiology. 

  • R. Palaniappan, S.M. Krishnan and C. Eswaran, “Improving Simplified Fuzzy ARTMAP Performance Using Genetic Algorithm for Brain Fingerprint Classification,” 14th International Conference on Advanced Computing and Communications, Mangalore, India, 20-23 December 2006.

  • T. Balli, R. Palaniappan, and D. P. Mandic, “On the linearity/non-linearity of mental activity EEG for brain-computer interface design,” IFMBE Proceedings of 3rd Kuala Lumpur International Conference on Biomedical Engineering, Kuala Lumpur, Malaysia, pp. 451-454, part 10, vol. 15, December 11-14, 2006.

  • R. Palaniappan, “Vision Related Brain Activity for Biometric Authentication,” Proceedings of 32nd Annual Conference of the IEEE Industrial Electronics Society, Paris, France, pp. 3227-3231, Nov. 7-10, 2006.

  • R. Palaniappan and C. N. Gupta, “Genetic algorithm based independent component analysis to separate noise from Electrocardiogram signals,” Proceedings of IEEE International Conference on Engineering of Intelligent Systems, Islamabad, Pakistan, pp. 1-5, 22-23 April 2006.

  • R. Palaniappan, “EEG biometrics: a fact not fiction,” Annual Presentations by Britain’s Top Younger Scientists, Engineers and Technologists, UK National Science Week 2006, House of Commons, London, 13 March 2006, abstract published in Book of Abstracts, pp. 56-57.

2005

  • R. Palaniappan and N. Huan, “Improving the performance of two-state mental task brain-computer interface design using linear discriminant classifier,” EUROCON 2005 conference, Belgrade, Serbia & Montenegro, 21-24 November, 2005.

  • I. Navarro, F. Sepulveda, B. Hubais (2005)    ‘A Comparison of Time, Frequency and ICA Based Features and Five Classifiers for Wrist Movement Classification in EEG Signals’.    27th Conference of the  IEEE Engineering in Medicine and Biology Society, Shanghai. download

  • R.Palaniappan (2005)   ‘Brain Computer Interface Design Using Band Powers Extracted During Mental Tasks‘  2nd International IEEE EMBS Conference on Neural Engineering, Arlington, Virginia, USA, pp. 321-324, 16-19.  download

  • R. Palaniappan, “Identifying individuality using mental task based brain computer interface,” Proceedings of 3rd International Conference on Intelligent Sensing and Information Processing, Bangalore, India, pp. 239-242, 13-17 December, 2005.

  • P. Sharmilakanna, and R. Palaniappan, “EEG artifact reduction in VEP using 2-stage PCA and N4 analysis of alcoholics,” Proceedings of 3rd International Conference on Intelligent Sensing and Information Processing, Bangalore, India, pp.2-7, 13-17 December, 2005.

  • KVR. Ravi, and R. Palaniappan, “Leave-one-out authentication of persons using 40 Hz EEG oscillations,” EUROCON 2005 conference, Belgrade, Serbia & Montenegro, vol. 2, pp.1386-1389, 21-24 November, 2005.

  • R. Palaniappan, D. P. Mandic, and D. Obradovic, “On decision making ability of subjects with long-term intoxicant consumption using single trial visual evoked potential signals,” EUROCON 2005 conference, Belgrade, Serbia & Montenegro, vol. 1, pp.413-416, 21-24 November, 2005.

  • S. Andrews, R. Palaniappan, and N. Kamel, “Single trial VEP source separation through sandwich spectral power ratio method,” 1st International Conference on Computer, Communications and Signal Processing with Special Track on Biomedical Engineering, Kuala Lumpur, Malaysia, pp.1-4, 14-16 November, 2005.

  • S. Andrews, N. Kamel, and R. Palaniappan, “Overcoming accuracy deficiency of filterations in source separation of visual evoked potentials by using principal component analysis,” Abstracts of International Science Congress, Kuala Lumpur, Malaysia, p. 344, 3-6 August, 2005.

  • R. Palaniappan, and N. Huan, “Effects of hidden unit sizes and autoregressive features in mental task classification”, 5th International Enformatika Conference, Prague, Czech Republic, 26-28 August 2005, published in Enformatika Transactions on Engineering, Computing and Technology, vol. 7, pp. 288-293, August 2005.

  • S. Andrews, R. Palaniappan, and N. Kamel, “Single trial VEP source separation by selective eigen rate principal components,” 5th International Enformatika Conference, Prague, Czech Republic, 26-28 August 2005, published in Enformatika Transactions on Engineering, Computing and Technology, vol. 7, pp. 330-333, August 2005.

  • R. Palaniappan, “Discrimination of alcoholic subjects using second order autoregressive modelling of brain signals evoked during visual stimulus perception,” 5th International Enformatika Conference, Prague, Czech Republic, 26-28 August 2005, published in Enformatika Transactions on Engineering, Computing and Technology, vol. 7, pp. 282-287, August 2005.

  • KVR. Ravi, and R. Palaniappan, “Recognising individuals using their brain patterns,” Proceedings of International Conference on Information Technology and Applications, Sydney, Australia, pp.520-523, vol. 2, 4-7 July, 2005.

  • P. Sharmilakanna, and R. Palaniappan, “Noise reduction in visual evoked potential signals using two-levels of principal component analysis,” Book of abstracts, 1st UAE International Conference on Biological and Medical Physics, p.30, 27-30 March, 2005.

  • N. Huan and R. Palaniappan, “Classification of mental tasks using fixed and adaptive autoregressive models of EEG signals,” Proceedings of 2nd International IEEE EMBS Conference on Neural Engineering, Arlington, Virginia, USA, pp. 633-636, 16-19 March, 2005.

2004

  • F. Sepulveda, M. Meckes, B.A. Conway (2004) ‘Cluster Separation Index Suggests Usefulness of Non-Motor EEG Channels in Detecting Wrist Movement Direction Intention’ .  Proceedings of the 2004 IEEE Conference on Cybernetic and Intelligent Systems. download

  • L. Citi, R. Poli, C. Cinel, F. Sepulveda  (2004)  ‘Feature Selection and Classification in Brain Computer Interfaces by a Genetic Algorithm’. Proceedings of the Genetic and Evolutionary Computation Conference – GECCO 2004, Seatle. download

  • S.M. Zhou, J.Q. Gan, F. Sepulveda (2004)   ‘Using Higher-Order Statistics from EEG Signals for Developing Brain-Computer Interface (BCI) Systems’. Proceedings of the 2004 UK Workshop on Computational Intelligence, 6-8 September 2004, Loughborough University.

  • C. Cinel, R. Poli, L. Citi (2004) ‘Possible sources of perceptual errors in p300-based speller paradigm’.  Proceedings of the 2nd International Brain-Computer Interface Workshop and Training Course 2004, Graz.. download

  • M. Meckes, F. Sepulveda, B.A. Conway (2004)  ‘1st Order Class Separability using EEG-Based Features for Classification of Wrist Movements with Direction Selectivity’.  Proceedings of the 26th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, San Francisco. download

  • L. Citi, R. Poli, F. Sepulveda (2004)   ‘An Evolutionary Approach to Feature Selection and Classification in a P300-Based BCI’.  Proceedings of the 2nd International Brain-Computer Interface Workshop and Training Course 2004, Graz. download