{"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/finding-the-missing-data-a-bert-inspired","title":"Finding the Missing Data: A BERT-inspired Approach Against Package Loss in Wireless Sensing","arxiv_id":"2403.12400","date":"2024-03-19","proceeding":null,"authors":["Zijian Zhao","TingWei Chen","Fanyi Meng","Hang Li","Xiaoyang Li","Guangxu Zhu"],"abstract":"Despite the development of various deep learning methods for Wi-Fi sensing, package loss often results in noncontinuous estimation of the Channel State Information (CSI), which negatively impacts the performance of the learning models. To overcome this challenge, we propose a deep learning model based on Bidirectional Encoder Representations from Transformers (BERT) for CSI recovery, named CSI-BERT. CSI-BERT can be trained in an self-supervised manner on the target dataset without the need for additional data. Furthermore, unlike traditional interpolation methods that focus on one subcarrier at a time, CSI-BERT captures the sequential relationships across different subcarriers. Experimental results demonstrate that CSI-BERT achieves lower error rates and faster speed compared to traditional interpolation methods, even when facing with high loss rates. Moreover, by harnessing the recovered CSI obtained from CSI-BERT, other deep learning models like Residual Network and Recurrent Neural Network can achieve an average increase in accuracy of approximately 15\\% in Wi-Fi sensing tasks. The collected dataset WiGesture and code for our model are publicly available at https://github.com/RS2002/CSI-BERT.","url_abs":"https://arxiv.org/abs/2403.12400v1","url_pdf":"https://arxiv.org/pdf/2403.12400v1.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":"finding-the-missing-data-a-bert-inspired","repo_url":"https://github.com/rs2002/csi-bert","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"action-classification","task_name":"Action Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"person-identification","task_name":"Person Identification"}],"methods":[{"method_slug":"focus","method_name":"Focus"},{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[{"slug":"wigesture","name":"WiGesture","full_name":"Wireless Sensing Dataset for Gesture Recognition and People ID Identification with ESP32"}],"methods_introduced":[],"results":[{"leaderboard":"/sota/action-classification-on-wigesture","task":"Action Classification","dataset":"WiGesture","model":"CSI-BERT","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy (% )":"76.91"},"uses_additional_data":false},{"leaderboard":"/sota/person-identification-on-wigesture","task":"Person Identification","dataset":"WiGesture","model":"CSI-BERT","rank_in_archive_order":3,"of":3,"metrics":{"Accuracy (% )":"93.94"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}