{"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-residual-bidir-lstm-for-human-activity","title":"Deep Residual Bidir-LSTM for Human Activity Recognition Using Wearable Sensors","arxiv_id":"1708.08989","date":"2017-08-22","proceeding":null,"authors":["Yu Zhao","Rennong Yang","Guillaume Chevalier","Maoguo Gong"],"abstract":"Human activity recognition (HAR) has become a popular topic in research\nbecause of its wide application. With the development of deep learning, new\nideas have appeared to address HAR problems. Here, a deep network architecture\nusing residual bidirectional long short-term memory (LSTM) cells is proposed.\nThe advantages of the new network include that a bidirectional connection can\nconcatenate the positive time direction (forward state) and the negative time\ndirection (backward state). Second, residual connections between stacked cells\nact as highways for gradients, which can pass underlying information directly\nto the upper layer, effectively avoiding the gradient vanishing problem.\nGenerally, the proposed network shows improvements on both the temporal (using\nbidirectional cells) and the spatial (residual connections stacked deeply)\ndimensions, aiming to enhance the recognition rate. When tested with the\nOpportunity data set and the public domain UCI data set, the accuracy was\nincreased by 4.78% and 3.68%, respectively, compared with previously reported\nresults. Finally, the confusion matrix of the public domain UCI data set was\nanalyzed.","url_abs":"http://arxiv.org/abs/1708.08989v2","url_pdf":"http://arxiv.org/pdf/1708.08989v2.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-residual-bidir-lstm-for-human-activity","repo_url":"https://github.com/guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"deep-residual-bidir-lstm-for-human-activity","repo_url":"https://github.com/Liut2016/stackedResBiLSTM","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"deep-residual-bidir-lstm-for-human-activity","repo_url":"https://github.com/guillaume-chevalier/LSTM-Human-Activity-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"deep-residual-bidir-lstm-for-human-activity","repo_url":"https://github.com/ibrahimalimetin/HDAD-iGAV-Dataset-and-its-Benchmarking-GUI-with-Deep-Learning-Techniques-for-HAR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"activity-recognition","task_name":"Activity Recognition"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"}],"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}