{"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/understanding-and-improving-deep-neural","title":"Understanding and Improving Deep Neural Network for Activity Recognition","arxiv_id":"1805.07020","date":"2018-05-18","proceeding":null,"authors":["Li Xue","Si Xiandong","Nie Lanshun","Li Jiazhen","Ding Renjie","Zhan Dechen","Chu Dianhui"],"abstract":"Activity recognition has become a popular research branch in the field of\npervasive computing in recent years. A large number of experiments can be\nobtained that activity sensor-based data's characteristic in activity\nrecognition is variety, volume, and velocity. Deep learning technology,\ntogether with its various models, is one of the most effective ways of working\non activity data. Nevertheless, there is no clear understanding of why it\nperforms so well or how to make it more effective. In order to solve this\nproblem, first, we applied convolution neural network on Human Activity\nRecognition Using Smart phones Data Set. Second, we realized the visualization\nof the sensor-based activity's data features extracted from the neural network.\nThen we had in-depth analysis of the visualization of features, explored the\nrelationship between activity and features, and analyzed how Neural Networks\nidentify activity based on these features. After that, we extracted the\nsignificant features related to the activities and sent the features to the\nDNN-based fusion model, which improved the classification rate to 96.1%. This\nis the first work to our knowledge that visualizes abstract sensor-based\nactivity data features. Based on the results, the method proposed in the paper\npromises to realize the accurate classification of sensor- based activity\nrecognition.","url_abs":"http://arxiv.org/abs/1805.07020v1","url_pdf":"http://arxiv.org/pdf/1805.07020v1.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":"understanding-and-improving-deep-neural","repo_url":"https://github.com/manish-vi/Human-Activity-Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"understanding-and-improving-deep-neural","repo_url":"https://github.com/manu-vishwakarma/human-activity-detection","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":"classification","task_name":"General Classification"},{"task_slug":"human-activity-recognition","task_name":"Human Activity Recognition"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}