{"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/human-activity-recognition-based-on-wearable","title":"Human Activity Recognition Based on Wearable Sensor Data: A Standardization of the State-of-the-Art","arxiv_id":"1806.05226","date":"2018-06-13","proceeding":null,"authors":["Artur Jordao","Antonio C. Nazare Jr.","Jessica Sena","William Robson Schwartz"],"abstract":"Human activity recognition based on wearable sensor data has been an\nattractive research topic due to its application in areas such as healthcare\nand smart environments. In this context, many works have presented remarkable\nresults using accelerometer, gyroscope and magnetometer data to represent the\nactivities categories. However, current studies do not consider important\nissues that lead to skewed results, making it hard to assess the quality of\nsensor-based human activity recognition and preventing a direct comparison of\nprevious works. These issues include the samples generation processes and the\nvalidation protocols used. We emphasize that in other research areas, such as\nimage classification and object detection, these issues are already\nwell-defined, which brings more efforts towards the application. Inspired by\nthis, we conduct an extensive set of experiments that analyze different sample\ngeneration processes and validation protocols to indicate the vulnerable points\nin human activity recognition based on wearable sensor data. For this purpose,\nwe implement and evaluate several top-performance methods, ranging from\nhandcrafted-based approaches to convolutional neural networks. According to our\nstudy, most of the experimental evaluations that are currently employed are not\nadequate to perform the activity recognition in the context of wearable sensor\ndata, in which the recognition accuracy drops considerably when compared to an\nappropriate evaluation approach. To the best of our knowledge, this is the\nfirst study that tackles essential issues that compromise the understanding of\nthe performance in human activity recognition based on wearable sensor data.","url_abs":"http://arxiv.org/abs/1806.05226v3","url_pdf":"http://arxiv.org/pdf/1806.05226v3.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":"human-activity-recognition-based-on-wearable","repo_url":"https://github.com/arturjordao/WearableSensorData","is_official":1,"mentioned_in_paper":1,"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"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}