Human Activity Recognition Across Scenes and Categories Based on CSI
- 1 December 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. PP (15361233) , 1
Abstract
Activity recognition based on channel state information (CSI) plays an increasingly important role in human computer interaction. However most CSI activity recognition systems need to re-collect a large amount of samples and retrain model when they are used in new environments or recognize new types of activities, which greatly reduces the practicality of CSI activity recognition. To address this problem we design an adaptable CSI activity recognition system based on meta-learning, which only needs to fine-tune model with very little train effort when it is used in new environments or recognize new types of activities. To prevent the loss of CSI time information after feature extraction with multi-layer CNN, we add time encoding on CSI data as the input of CNN neural network. Considering that CSI data may be labeled incorrectly during labeling process, we improve categorical cross entropy loss(CCE) to enhance the system's robustness to these mislabeled data. We test our system on the gesture dataset and the body activity dataset, and the experimental results show that our system achieves average accuracy of 72% with 1 sample of each new activity and 89.6% with 5 samples of each new activity.Keywords
This publication has 30 references indexed in Scilit:
- IndoTrackProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2017
- RT-Fall: A Real-Time and Contactless Fall Detection System with Commodity WiFi DevicesIEEE Transactions on Mobile Computing, 2016
- WiDraw2015
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition2015
- 3D ActionSLAM: wearable person tracking in multi-floor environmentsPersonal and Ubiquitous Computing, 2014
- Indoor Tracking and Navigation Using Received Signal Strength and Compressive Sensing on a Mobile DeviceIEEE Transactions on Mobile Computing, 2012
- Tool releaseACM SIGCOMM Computer Communication Review, 2011
- 802.11 with multiple antennas for dummiesACM SIGCOMM Computer Communication Review, 2010
- Elderly persons’ perception and acceptance of using wireless sensor networks to assist healthcareInternational Journal of Medical Informatics, 2009
- Automatic tracking of human motion in indoor scenes across multiple synchronized video streams2002