{"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/converting-your-thoughts-to-texts-enabling","title":"Converting Your Thoughts to Texts: Enabling Brain Typing via Deep Feature Learning of EEG Signals","arxiv_id":"1709.08820","date":"2017-09-26","proceeding":null,"authors":["Xiang Zhang","Lina Yao","Quan Z. Sheng","Salil S. Kanhere","Tao Gu","Dalin Zhang"],"abstract":"An electroencephalography (EEG) based Brain Computer Interface (BCI) enables\npeople to communicate with the outside world by interpreting the EEG signals of\ntheir brains to interact with devices such as wheelchairs and intelligent\nrobots. More specifically, motor imagery EEG (MI-EEG), which reflects a\nsubjects active intent, is attracting increasing attention for a variety of BCI\napplications. Accurate classification of MI-EEG signals while essential for\neffective operation of BCI systems, is challenging due to the significant noise\ninherent in the signals and the lack of informative correlation between the\nsignals and brain activities. In this paper, we propose a novel deep neural\nnetwork based learning framework that affords perceptive insights into the\nrelationship between the MI-EEG data and brain activities. We design a joint\nconvolutional recurrent neural network that simultaneously learns robust\nhigh-level feature presentations through low-dimensional dense embeddings from\nraw MI-EEG signals. We also employ an Autoencoder layer to eliminate various\nartifacts such as background activities. The proposed approach has been\nevaluated extensively on a large- scale public MI-EEG dataset and a limited but\neasy-to-deploy dataset collected in our lab. The results show that our approach\noutperforms a series of baselines and the competitive state-of-the- art\nmethods, yielding a classification accuracy of 95.53%. The applicability of our\nproposed approach is further demonstrated with a practical BCI system for\ntyping.","url_abs":"http://arxiv.org/abs/1709.08820v1","url_pdf":"http://arxiv.org/pdf/1709.08820v1.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":"converting-your-thoughts-to-texts-enabling","repo_url":"https://github.com/karaposu/Brain_typing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"converting-your-thoughts-to-texts-enabling","repo_url":"https://github.com/xiangzhang1015/Brain_typing","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"brain-computer-interface","task_name":"Brain Computer Interface"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"motor-imagery","task_name":"Motor Imagery"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}