{"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/deep-learning-based-electroencephalography","title":"Deep learning-based electroencephalography analysis: a systematic review","arxiv_id":"1901.05498","date":"2019-01-16","proceeding":null,"authors":["Yannick Roy","Hubert Banville","Isabela Albuquerque","Alexandre Gramfort","Tiago H. Falk","Jocelyn Faubert"],"abstract":"Electroencephalography (EEG) is a complex signal and can require several\nyears of training to be correctly interpreted. Recently, deep learning (DL) has\nshown great promise in helping make sense of EEG signals due to its capacity to\nlearn good feature representations from raw data. Whether DL truly presents\nadvantages as compared to more traditional EEG processing approaches, however,\nremains an open question. In this work, we review 156 papers that apply DL to\nEEG, published between January 2010 and July 2018, and spanning different\napplication domains such as epilepsy, sleep, brain-computer interfacing, and\ncognitive and affective monitoring. We extract trends and highlight interesting\napproaches in order to inform future research and formulate recommendations.\nVarious data items were extracted for each study pertaining to 1) the data, 2)\nthe preprocessing methodology, 3) the DL design choices, 4) the results, and 5)\nthe reproducibility of the experiments. Our analysis reveals that the amount of\nEEG data used across studies varies from less than ten minutes to thousands of\nhours. As for the model, 40% of the studies used convolutional neural networks\n(CNNs), while 14% used recurrent neural networks (RNNs), most often with a\ntotal of 3 to 10 layers. Moreover, almost one-half of the studies trained their\nmodels on raw or preprocessed EEG time series. Finally, the median gain in\naccuracy of DL approaches over traditional baselines was 5.4% across all\nrelevant studies. More importantly, however, we noticed studies often suffer\nfrom poor reproducibility: a majority of papers would be hard or impossible to\nreproduce given the unavailability of their data and code. To help the field\nprogress, we provide a list of recommendations for future studies and we make\nour summary table of DL and EEG papers available and invite the community to\ncontribute.","url_abs":"http://arxiv.org/abs/1901.05498v2","url_pdf":"http://arxiv.org/pdf/1901.05498v2.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":"deep-learning-based-electroencephalography","repo_url":"https://github.com/Mingyuan-Zhu/BCI_practice","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"deep-learning-based-electroencephalography","repo_url":"https://github.com/hubertjb/dl-eeg-review","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-learning-based-electroencephalography","repo_url":"https://github.com/kylemath/DeepEEG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"brain-decoding","task_name":"Brain Decoding"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1901.05498","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.05498"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hubertjb/dl-eeg-review","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kylemath/DeepEEG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Mingyuan-Zhu/BCI_practice","reach":{"status":"ok"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"2b492fa38b70415c","entry":"lstrip","repo":"hubertjb/dl-eeg-review","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/hubertjb/dl-eeg-review/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2b492fa38b70415c"}},{"code_sha256_prefix":"95156b80a65687e5","entry":"replace_nans_in_column","repo":"hubertjb/dl-eeg-review","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/hubertjb/dl-eeg-review/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"95156b80a65687e5"}},{"code_sha256_prefix":"c38cc953c024596a","entry":"tex_escape","repo":"hubertjb/dl-eeg-review","repo_kind":"listed","path":"code/utils.py","file_url":"https://github.com/hubertjb/dl-eeg-review/blob/HEAD/code/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c38cc953c024596a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}