SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing
Over the recent years, WiFi sensing has been rapidly developed for privacy-preserving, ubiquitous human-sensing applications, enabled by signal processing and deep-learning methods. However, a comprehensive public benchmark for deep learning in WiFi sensing, similar to that available for visual reco...
Saved in:
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2023
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/168718 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-168718 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1687182023-06-16T15:40:38Z SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing Yang, Jianfei Chen, Xinyan Zou, Han Lu, Chris Xiaoxuan Wang, Dazhuo Sun, Sumei Xie, Lihua School of Electrical and Electronic Engineering Engineering::Electrical and electronic engineering WiFi Sensing Benchmarking Over the recent years, WiFi sensing has been rapidly developed for privacy-preserving, ubiquitous human-sensing applications, enabled by signal processing and deep-learning methods. However, a comprehensive public benchmark for deep learning in WiFi sensing, similar to that available for visual recognition, does not yet exist. In this article, we review recent progress in topics ranging from WiFi hardware platforms to sensing algorithms and propose a new library with a comprehensive benchmark, SenseFi. On this basis, we evaluate various deep-learning models in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, and feature transferability. Extensive experiments are performed whose results provide valuable insights into model design, learning strategy, and training techniques for real-world applications. In summary, SenseFi is a comprehensive benchmark with an open-source library for deep learning in WiFi sensing research that offers researchers a convenient tool to validate learning-based WiFi-sensing methods on multiple datasets and platforms. Nanyang Technological University Published version This research is supported by NTU Presidential Postdoctoral Fellowship, ‘‘Adaptive Multi-modal Learning for Robust Sensing and Recognition in Smart Cities’’ project fund (020977-00001), at the Nanyang Technological University, Singapore. 2023-06-16T04:47:10Z 2023-06-16T04:47:10Z 2023 Journal Article Yang, J., Chen, X., Zou, H., Lu, C. X., Wang, D., Sun, S. & Xie, L. (2023). SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing. Patterns, 4(3), 100703-. https://dx.doi.org/10.1016/j.patter.2023.100703 2666-3899 https://hdl.handle.net/10356/168718 10.1016/j.patter.2023.100703 36960448 2-s2.0-85149874193 3 4 100703 en 020977-00001 Patterns © 2023 The Author(s). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). application/pdf |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering WiFi Sensing Benchmarking |
spellingShingle |
Engineering::Electrical and electronic engineering WiFi Sensing Benchmarking Yang, Jianfei Chen, Xinyan Zou, Han Lu, Chris Xiaoxuan Wang, Dazhuo Sun, Sumei Xie, Lihua SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
description |
Over the recent years, WiFi sensing has been rapidly developed for privacy-preserving, ubiquitous human-sensing applications, enabled by signal processing and deep-learning methods. However, a comprehensive public benchmark for deep learning in WiFi sensing, similar to that available for visual recognition, does not yet exist. In this article, we review recent progress in topics ranging from WiFi hardware platforms to sensing algorithms and propose a new library with a comprehensive benchmark, SenseFi. On this basis, we evaluate various deep-learning models in terms of distinct sensing tasks, WiFi platforms, recognition accuracy, model size, computational complexity, and feature transferability. Extensive experiments are performed whose results provide valuable insights into model design, learning strategy, and training techniques for real-world applications. In summary, SenseFi is a comprehensive benchmark with an open-source library for deep learning in WiFi sensing research that offers researchers a convenient tool to validate learning-based WiFi-sensing methods on multiple datasets and platforms. |
author2 |
School of Electrical and Electronic Engineering |
author_facet |
School of Electrical and Electronic Engineering Yang, Jianfei Chen, Xinyan Zou, Han Lu, Chris Xiaoxuan Wang, Dazhuo Sun, Sumei Xie, Lihua |
format |
Article |
author |
Yang, Jianfei Chen, Xinyan Zou, Han Lu, Chris Xiaoxuan Wang, Dazhuo Sun, Sumei Xie, Lihua |
author_sort |
Yang, Jianfei |
title |
SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
title_short |
SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
title_full |
SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
title_fullStr |
SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
title_full_unstemmed |
SenseFi: a library and benchmark on deep-learning-empowered WiFi human sensing |
title_sort |
sensefi: a library and benchmark on deep-learning-empowered wifi human sensing |
publishDate |
2023 |
url |
https://hdl.handle.net/10356/168718 |
_version_ |
1772826416449060864 |