{"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/eeg-signal-dimensionality-reduction-and-1","title":"EEG Signal Dimensionality Reduction and Classification using Tensor Decomposition and Deep Convolutional Neural Networks","arxiv_id":"1908.10432","date":"2019-08-27","proceeding":"arXiv:1908.10432 2019 8","authors":[],"abstract":"A new deep learning-based electroencephalography (EEG) signal analysis\nframework is proposed. While deep neural networks, specifically convolutional\nneural networks (CNNs), have gained remarkable attention recently, they still\nsuffer from high dimensionality of the training data. Two-dimensional input\nimages of CNNs are more vulnerable to be redundant versus one-dimensional input\ntime-series of conventional neural networks. In this study, we propose a new\ndimensionality reduction framework for reducing the dimension of CNN inputs\nbased on the tensor decomposition of the time-frequency representation of EEG\nsignals. The proposed tensor decomposition-based dimensionality reduction\nalgorithm transforms a large set of slices of the input tensor to a concise set\nof slices which are called super-slices. Employing super-slices not only\nhandles the artifacts and redundancies of the EEG data but also reduces the\ndimension of the CNNs training inputs. We also consider different\ntime-frequency representation methods for EEG image generation and provide a\ncomprehensive comparison among them. We test our proposed framework on HCB-MIT\ndata and as results show our approach outperforms other previous studies.","url_abs":"http://arxiv.org/abs/1908.10432v1","url_pdf":"http://arxiv.org/pdf/1908.10432v1.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":[],"tasks":[{"task_slug":"dimensionality-reduction","task_name":"Dimensionality Reduction"},{"task_slug":"eeg-1","task_name":"EEG"},{"task_slug":"eeg","task_name":"Electroencephalogram (EEG)"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"tensor-decomposition","task_name":"Tensor Decomposition"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/seizure-detection-on-chb-mit","task":"Seizure Detection","dataset":"CHB-MIT","model":"TF-Tensor-CNN","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy":"89.63%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}