{"id":{"repo_id":"regina","oai_identifier":"oai:uregina.scholaris.ca:10294/7875"},"canonical_url":"https://search.dev.ndltd.org/etd/regina/oai:uregina.scholaris.ca:10294/7875","repository":{"repo_id":"regina","name":"University of Regina","base_url":"https://uregina.scholaris.ca/server/oai/request"},"display":{"title":"Motor Imagery Based Brain Computer Interfaces","abstract":"Brain Computer Interface (BCI) is an emerging technology which enables humans to communicate with external devices using their brain signals. Motor imagery classification is one such area in BCI systems where the goal is to detect and classify the motor related intentions of humans using their brain signals. The desired accuracy of BCI systems cannot be achieved without the preprocessing and the extraction of discriminant features from raw brain signals. To this end, this thesis first develops a novel extension of multivariate empirical mode decomposition (MEMD) for the preprocessing of the raw brain signals. MEMD is a mathematical tool that is used to decompose multivariate time signals into a set of basis functions called intrinsic mode functions (IMFs). In order to extract IMFs, MEMD is required to estimate the local mean of multivariate signal by taking the projections of input signal on a dense uniformly sampled hyper-sphere. A novel non-uniform sampling scheme is proposed to estimate the local mean of multivariate signals. The non-uniform samples are generated by linearly transforming the hypersphere into an N dimensional ellipsoid using singular value decomposition (SVD). A number of experiments on synthetic and real-world signals were conducted to show that the non-uniform sampling scheme is helpful to generate meaningful IMFs when the input multichannel signals are highly correlated. In addition, the performance of proposed algorithm was also evaluated in motor imagery based BCI systems. The second part of this thesis talks about the common spatial pattern (CSP) which is commonly used to extract discriminant features from the raw brain signals for motor imagery based BCI systems. The performance of the CSP algorithm relies on the estimation of the covariance matrix which becomes an ill posed problem when the number of training samples is limited. In this thesis, a novel extension of the CSP algorithm is proposed to address the limited sample size problem. The proposed methodology is evaluated on publically available BCI competition III dataset. The results show improved performance of proposed method when compared with the traditional CSP algorithm especially when the number of training samples is limited. keywords: MEMD, non-uniform sampling scheme, common spatial pattern, maximum entropy, motor imagery, BCI competition","abstract_html":"Brain Computer Interface (BCI) is an emerging technology which enables humans to communicate with external devices using their brain signals. Motor imagery classification is one such area in BCI systems where the goal is to detect and classify the motor related intentions of humans using their brain signals. The desired accuracy of BCI systems cannot be achieved without the preprocessing and the extraction of discriminant features from raw brain signals. To this end, this thesis first develops a novel extension of multivariate empirical mode decomposition (MEMD) for the preprocessing of the raw brain signals. MEMD is a mathematical tool that is used to decompose multivariate time signals into a set of basis functions called intrinsic mode functions (IMFs). In order to extract IMFs, MEMD is required to estimate the local mean of multivariate signal by taking the projections of input signal on a dense uniformly sampled hyper-sphere. A novel non-uniform sampling scheme is proposed to estimate the local mean of multivariate signals. The non-uniform samples are generated by linearly transforming the hypersphere into an N dimensional ellipsoid using singular value decomposition (SVD). A number of experiments on synthetic and real-world signals were conducted to show that the non-uniform sampling scheme is helpful to generate meaningful IMFs when the input multichannel signals are highly correlated. In addition, the performance of proposed algorithm was also evaluated in motor imagery based BCI systems. The second part of this thesis talks about the common spatial pattern (CSP) which is commonly used to extract discriminant features from the raw brain signals for motor imagery based BCI systems. The performance of the CSP algorithm relies on the estimation of the covariance matrix which becomes an ill posed problem when the number of training samples is limited. In this thesis, a novel extension of the CSP algorithm is proposed to address the limited sample size problem. The proposed methodology is evaluated on publically available BCI competition III dataset. The results show improved performance of proposed method when compared with the traditional CSP algorithm especially when the number of training samples is limited. keywords: MEMD, non-uniform sampling scheme, common spatial pattern, maximum entropy, motor imagery, BCI competition","abstract_has_math":false,"creators":["Ali, Syed Salman"],"institution":"Faculty of Graduate Studies and Research, University of Regina","degree_name":"Master of Applied Science (MASc)","degree_level":"Master's","degree_discipline":"Engineering - Electronic Systems","degree_department":null,"school":null,"contributors":[],"advisors":["Zhang, Lei"],"committee_chairs":[],"committee_members":["Bais, Abdul"],"year":2017,"date_issued":"2017-05","date_published":"2017-05","updated_at":"2026-07-24T04:03:41Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.82465/4584"],"render_values":[{"text":"https://doi.org/10.82465/4584","href":"https://doi.org/10.82465/4584","code":true}]}]},"links":{"outbound_url":"https://hdl.handle.net/10294/7875","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Zhang, Lei"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Bais, Abdul"]},{"key":"dc:creator","label":"Author","values":["Ali, Syed Salman"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2017-12-06T20:34:45Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2017-12-06T20:34:45Z"]},{"key":"dc:date.issued","label":"Date","values":["2017-05"]},{"key":"dc:publisher","label":"Institution","values":["Faculty of Graduate Studies and Research, University of Regina"]},{"key":"dc:type","label":"Dc Type","values":["master thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering - Electronic Systems"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Master's"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Master of Applied Science (MASc)"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Faculty of Graduate Studies and Research, University of Regina"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.82465/4584"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://hdl.handle.net/10294/7875"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Applied Science in Electronic Systems Engineering, University of Regina. 67 p."]},{"key":"dc:description.abstract","label":"Abstract","values":["Brain Computer Interface (BCI) is an emerging technology which enables humans to communicate with external devices using their brain signals. Motor imagery classification is one such area in BCI systems where the goal is to detect and classify the motor related intentions of humans using their brain signals. The desired accuracy of BCI systems cannot be achieved without the preprocessing and the extraction of discriminant features from raw brain signals. To this end, this thesis first develops a novel extension of multivariate empirical mode decomposition (MEMD) for the preprocessing of the raw brain signals. MEMD is a mathematical tool that is used to decompose multivariate time signals into a set of basis functions called intrinsic mode functions (IMFs). In order to extract IMFs, MEMD is required to estimate the local mean of multivariate signal by taking the projections of input signal on a dense uniformly sampled hyper-sphere. A novel non-uniform sampling scheme is proposed to estimate the local mean of multivariate signals. The non-uniform samples are generated by linearly transforming the hypersphere into an N dimensional ellipsoid using singular value decomposition (SVD). A number of experiments on synthetic and real-world signals were conducted to show that the non-uniform sampling scheme is helpful to generate meaningful IMFs when the input multichannel signals are highly correlated. In addition, the performance of proposed algorithm was also evaluated in motor imagery based BCI systems. The second part of this thesis talks about the common spatial pattern (CSP) which is commonly used to extract discriminant features from the raw brain signals for motor imagery based BCI systems. The performance of the CSP algorithm relies on the estimation of the covariance matrix which becomes an ill posed problem when the number of training samples is limited. In this thesis, a novel extension of the CSP algorithm is proposed to address the limited sample size problem. The proposed methodology is evaluated on publically available BCI competition III dataset. The results show improved performance of proposed method when compared with the traditional CSP algorithm especially when the number of training samples is limited. keywords: MEMD, non-uniform sampling scheme, common spatial pattern, maximum entropy, motor imagery, BCI competition"]},{"key":"dc:title","label":"Title","values":["Motor Imagery Based Brain Computer Interfaces"]}]}],"canonical_facts":{"dc:contributor.advisor":["Zhang, Lei"],"dc:contributor.committeemember":["Bais, Abdul"],"dc:creator":["Ali, Syed Salman"],"dc:date.accessioned":["2017-12-06T20:34:45Z"],"dc:date.available":["2017-12-06T20:34:45Z"],"dc:date.issued":["2017-05"],"dc:description":["A Thesis Submitted to the Faculty of Graduate Studies and Research In Partial Fulfillment of the Requirements for the Degree of Master of Applied Science in Electronic Systems Engineering, University of Regina. 67 p."],"dc:description.abstract":["Brain Computer Interface (BCI) is an emerging technology which enables humans to communicate with external devices using their brain signals. Motor imagery classification is one such area in BCI systems where the goal is to detect and classify the motor related intentions of humans using their brain signals. The desired accuracy of BCI systems cannot be achieved without the preprocessing and the extraction of discriminant features from raw brain signals. To this end, this thesis first develops a novel extension of multivariate empirical mode decomposition (MEMD) for the preprocessing of the raw brain signals. MEMD is a mathematical tool that is used to decompose multivariate time signals into a set of basis functions called intrinsic mode functions (IMFs). In order to extract IMFs, MEMD is required to estimate the local mean of multivariate signal by taking the projections of input signal on a dense uniformly sampled hyper-sphere. A novel non-uniform sampling scheme is proposed to estimate the local mean of multivariate signals. The non-uniform samples are generated by linearly transforming the hypersphere into an N dimensional ellipsoid using singular value decomposition (SVD). A number of experiments on synthetic and real-world signals were conducted to show that the non-uniform sampling scheme is helpful to generate meaningful IMFs when the input multichannel signals are highly correlated. In addition, the performance of proposed algorithm was also evaluated in motor imagery based BCI systems. The second part of this thesis talks about the common spatial pattern (CSP) which is commonly used to extract discriminant features from the raw brain signals for motor imagery based BCI systems. The performance of the CSP algorithm relies on the estimation of the covariance matrix which becomes an ill posed problem when the number of training samples is limited. In this thesis, a novel extension of the CSP algorithm is proposed to address the limited sample size problem. The proposed methodology is evaluated on publically available BCI competition III dataset. The results show improved performance of proposed method when compared with the traditional CSP algorithm especially when the number of training samples is limited. keywords: MEMD, non-uniform sampling scheme, common spatial pattern, maximum entropy, motor imagery, BCI competition"],"dc:identifier.doi":["https://doi.org/10.82465/4584"],"dc:identifier.uri":["https://hdl.handle.net/10294/7875"],"dc:language.iso":["en"],"dc:publisher":["Faculty of Graduate Studies and Research, University of Regina"],"dc:title":["Motor Imagery Based Brain Computer Interfaces"],"dc:type":["master thesis"],"thesis:degree_discipline":["Engineering - Electronic Systems"],"thesis:degree_level":["Master's"],"thesis:degree_name":["Master of Applied Science (MASc)"],"thesis:institution_name":["Faculty of Graduate Studies and Research, University of Regina"]},"updated_at":"2026-07-24T04:03:41Z"}