Smart City Gnosys

Smart city article details

Title	Lightweight Regularized Multi - Label Indoor Human Activity Recognition With Csi Fingerprints
ID_Doc	35273
Authors	Miao F.; Huang Y.; Qian W.; Lu Z.; Lin Y.; Gui G.
Year	2024
Published	16th International Conference on Wireless Communications and Signal Processing, WCSP 2024
DOI	http://dx.doi.org/10.1109/WCSP62071.2024.10827309
Abstract	In the rapid advancement of smart cities and smart homes, indoor human activity recognition (HAR) has gained significant importance for applications in security monitoring, health monitoring, and smart home control. This paper presents a lightweight regularized multi-label HAR method using Channel State Information (CSI) from Wi-Fi signals. We implement and evaluate a CNN-2D model enhanced with squeeze-and-Excitation (SE) module, designed for activity recognition and indoor localization in multi-user environments. The model utilizes adaptive attention mechanisms and regularization techniques to efficiently handle complex multi-label learning tasks. Comprehensive experiments on the WiMANS dataset demonstrate that our model achieves superior accuracy and efficiency, making it suitable for deployment in resource-constrained environments such as edge devices and IoT sensors. This work provides a practical solution for scalable, real-time HAR applications in smart environments. © 2024 IEEE.
Author Keywords	channel state information; Human activity recognition; regularized multi-label; WiMANS dataset

Similar Articles

Id	Similarity	Authors	Title	Published
35282	0.929	Lu J.; Miao F.; Wan H.; Lu Z.; Huang Y.; Gui G.	Lightweight Two-Stream Convolution-Augmented Transformer For Multi-Task Human Activity Recognition Using Wi-Fi Sensing	2024 6th International Conference on Robotics, Intelligent Control and Artificial Intelligence, RICAI 2024 (2024)
16779	0.901	Moshiri P.F.; Nabati M.; Shahbazian R.; Ghorashi S.A.	Csi-Based Human Activity Recognition Using Convolutional Neural Networks	ICCKE 2021 - 11th International Conference on Computer Engineering and Knowledge (2021)
13628	0.883	Abuhoureyah F.; Wong Y.C.; Al-Taweel M.H.; Abdullah N.I.	Challenges And Opportunities To Location Independent Human Activity Recognition Utilizing Wi-Fi Sensing	International Journal of Electrical and Computer Engineering, 15, 1 (2025)
19832	0.88	Damodaran N.; Schäfer J.	Device Free Human Activity Recognition Using Wifi Channel State Information	Proceedings - 2019 IEEE SmartWorld, Ubiquitous Intelligence and Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Internet of People and Smart City Innovation, SmartWorld/UIC/ATC/SCALCOM/IOP/SCI 2019 (2019)
37958	0.879	Xia M.; Que S.; Liu N.; Wang Q.; Li T.	Motion Pattern Recognition Via Cnn-Lstm-Attention Model Using Array-Based Wi-Fi Csi Sensors In Gnss-Denied Areas	Electronics (Switzerland), 14, 8 (2025)
3864	0.878	Khan M.M.U.; Shams A.B.; Raihan M.S.	A Prospective Approach For Human-To-Human Interaction Recognition From Wi-Fi Channel Data Using Attention Bidirectional Gated Recurrent Neural Network With Gui Application Implementation	Multimedia Tools and Applications, 83, 22 (2024)
29570	0.853	Kalimuthu S.; Perumal T.; Marlisah E.; Yaakob R.; Vidhyasagar B.S.; Ismail N.H.	Human Activity Recognition Based On Device-Free Wi-Fi Sensing: A Comprehensive Review	Malaysian Journal of Computer Science, 37, 3 (2024)
4555	0.85	Zhou Y.; Xie C.; Sun S.; Zhang X.; Wang Y.	A Self-Supervised Human Activity Recognition Approach Via Body Sensor Networks In Smart City	IEEE Sensors Journal, 24, 5 (2024)