{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/fast-and-accurate-multiclass-inference-for-mi","title":"Fast and Accurate Multiclass Inference for MI-BCIs Using Large Multiscale Temporal and Spectral Features","arxiv_id":"1806.06823","date":"2018-06-18","proceeding":null,"authors":["Michael Hersche","Tino Rellstab","Pasquale Davide Schiavone","Lukas Cavigelli","Luca Benini","Abbas Rahimi"],"abstract":"Accurate, fast, and reliable multiclass classification of\nelectroencephalography (EEG) signals is a challenging task towards the\ndevelopment of motor imagery brain-computer interface (MI-BCI) systems. We\npropose enhancements to different feature extractors, along with a support\nvector machine (SVM) classifier, to simultaneously improve classification\naccuracy and execution time during training and testing. We focus on the\nwell-known common spatial pattern (CSP) and Riemannian covariance methods, and\nsignificantly extend these two feature extractors to multiscale temporal and\nspectral cases. The multiscale CSP features achieve 73.70$\\pm$15.90% (mean$\\pm$\nstandard deviation across 9 subjects) classification accuracy that surpasses\nthe state-of-the-art method [1], 70.6$\\pm$14.70%, on the 4-class BCI\ncompetition IV-2a dataset. The Riemannian covariance features outperform the\nCSP by achieving 74.27$\\pm$15.5% accuracy and executing 9x faster in training\nand 4x faster in testing. Using more temporal windows for Riemannian features\nresults in 75.47$\\pm$12.8% accuracy with 1.6x faster testing than CSP.","url_abs":"http://arxiv.org/abs/1806.06823v2","url_pdf":"http://arxiv.org/pdf/1806.06823v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"fast-and-accurate-multiclass-inference-for-mi","repo_url":"https://github.com/MultiScale-BCI/IV-2a","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"fast-and-accurate-multiclass-inference-for-mi","repo_url":"https://github.com/kusumikakd/EEG_Multiclass","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"brain-computer-interface","task_name":"Brain Computer Interface"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"motor-imagery","task_name":"Motor Imagery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}