FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3081132571> ?p ?o ?g. }

• W3081132571 endingPage "4749" @default.
• W3081132571 startingPage "4749" @default.
• W3081132571 abstract "The common spatial pattern (CSP) is a very effective feature extraction method in motor imagery based brain computer interface (BCI), but its performance depends on the selection of the optimal frequency band. Although a lot of research works have been proposed to improve CSP, most of these works have the problems of large computation costs and long feature extraction time. To this end, three new feature extraction methods based on CSP and a new feature selection method based on non-convex log regularization are proposed in this paper. Firstly, EEG signals are spatially filtered by CSP, and then three new feature extraction methods are proposed. We called them CSP-wavelet, CSP-WPD and CSP-FB, respectively. For CSP-Wavelet and CSP-WPD, the discrete wavelet transform (DWT) or wavelet packet decomposition (WPD) is used to decompose the spatially filtered signals, and then the energy and standard deviation of the wavelet coefficients are extracted as features. For CSP-FB, the spatially filtered signals are filtered into multiple bands by a filter bank (FB), and then the logarithm of variances of each band are extracted as features. Secondly, a sparse optimization method regularized with a non-convex log function is proposed for the feature selection, which we called LOG, and an optimization algorithm for LOG is given. Finally, ensemble learning is used for secondary feature selection and classification model construction. Combing feature extraction and feature selection methods, a total of three new EEG decoding methods are obtained, namely CSP-Wavelet+LOG, CSP-WPD+LOG, and CSP-FB+LOG. Four public motor imagery datasets are used to verify the performance of the proposed methods. Compared to existing methods, the proposed methods achieved the highest average classification accuracy of 88.86, 83.40, 81.53, and 80.83 in datasets 1–4, respectively. The feature extraction time of CSP-FB is the shortest. The experimental results show that the proposed methods can effectively improve the classification accuracy and reduce the feature extraction time. With comprehensive consideration of classification accuracy and feature extraction time, CSP-FB+LOG has the best performance and can be used for the real-time BCI system." @default.
• W3081132571 created "2020-09-01" @default.
• W3081132571 creator A5022735755 @default.
• W3081132571 creator A5028952297 @default.
• W3081132571 creator A5040009629 @default.
• W3081132571 creator A5057697869 @default.
• W3081132571 creator A5065131815 @default.
• W3081132571 creator A5087957048 @default.
• W3081132571 date "2020-08-22" @default.
• W3081132571 modified "2023-10-03" @default.
• W3081132571 title "The CSP-Based New Features Plus Non-Convex Log Sparse Feature Selection for Motor Imagery EEG Classification" @default.
• W3081132571 cites W1147354400 @default.
• W3081132571 cites W1635976235 @default.
• W3081132571 cites W1970070014 @default.
• W3081132571 cites W1982802415 @default.
• W3081132571 cites W1983200016 @default.
• W3081132571 cites W2001725812 @default.
• W3081132571 cites W2005521760 @default.
• W3081132571 cites W2039930961 @default.
• W3081132571 cites W2040061778 @default.
• W3081132571 cites W2057311210 @default.
• W3081132571 cites W2090262261 @default.
• W3081132571 cites W2094017272 @default.
• W3081132571 cites W2099509424 @default.
• W3081132571 cites W2100556411 @default.
• W3081132571 cites W2100874881 @default.
• W3081132571 cites W2119387367 @default.
• W3081132571 cites W2128404967 @default.
• W3081132571 cites W2131321253 @default.
• W3081132571 cites W2135046866 @default.
• W3081132571 cites W2152119085 @default.
• W3081132571 cites W2153635508 @default.
• W3081132571 cites W2154774916 @default.
• W3081132571 cites W2155617375 @default.
• W3081132571 cites W2165892205 @default.
• W3081132571 cites W2168500935 @default.
• W3081132571 cites W2278483878 @default.
• W3081132571 cites W2291176881 @default.
• W3081132571 cites W2338065876 @default.
• W3081132571 cites W2410264812 @default.
• W3081132571 cites W2422365436 @default.
• W3081132571 cites W2423195739 @default.
• W3081132571 cites W2521878393 @default.
• W3081132571 cites W2562754841 @default.
• W3081132571 cites W2736583283 @default.
• W3081132571 cites W2740113900 @default.
• W3081132571 cites W2767782829 @default.
• W3081132571 cites W2772283936 @default.
• W3081132571 cites W2783339817 @default.
• W3081132571 cites W2794345050 @default.
• W3081132571 cites W2795869137 @default.
• W3081132571 cites W2796435388 @default.
• W3081132571 cites W2800566345 @default.
• W3081132571 cites W2802723950 @default.
• W3081132571 cites W2808098316 @default.
• W3081132571 cites W2885543304 @default.
• W3081132571 cites W2886697509 @default.
• W3081132571 cites W2888874411 @default.
• W3081132571 cites W2892832231 @default.
• W3081132571 cites W2893415555 @default.
• W3081132571 cites W2894424125 @default.
• W3081132571 cites W2911969890 @default.
• W3081132571 cites W2913846632 @default.
• W3081132571 cites W2924079966 @default.
• W3081132571 cites W2944479754 @default.
• W3081132571 cites W2953384096 @default.
• W3081132571 cites W2955569539 @default.
• W3081132571 cites W2955714720 @default.
• W3081132571 cites W2962943048 @default.
• W3081132571 cites W2989739667 @default.
• W3081132571 cites W2998808968 @default.
• W3081132571 cites W3002531416 @default.
• W3081132571 cites W3003030341 @default.
• W3081132571 cites W3004827935 @default.
• W3081132571 cites W3007075516 @default.
• W3081132571 cites W3019576349 @default.
• W3081132571 cites W3021466180 @default.
• W3081132571 cites W3021985989 @default.
• W3081132571 cites W3026899257 @default.
• W3081132571 cites W3027581678 @default.
• W3081132571 cites W3038257312 @default.
• W3081132571 cites W3106266785 @default.
• W3081132571 cites W4244393449 @default.
• W3081132571 cites W4292363360 @default.
• W3081132571 doi "https://doi.org/10.3390/s20174749" @default.
• W3081132571 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7506901" @default.
• W3081132571 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32842635" @default.
• W3081132571 hasPublicationYear "2020" @default.
• W3081132571 type Work @default.
• W3081132571 sameAs 3081132571 @default.
• W3081132571 citedByCount "12" @default.
• W3081132571 countsByYear W30811325712021 @default.
• W3081132571 countsByYear W30811325712022 @default.
• W3081132571 countsByYear W30811325712023 @default.
• W3081132571 crossrefType "journal-article" @default.
• W3081132571 hasAuthorship W3081132571A5022735755 @default.
• W3081132571 hasAuthorship W3081132571A5028952297 @default.
• W3081132571 hasAuthorship W3081132571A5040009629 @default.

• next