A Novel Deep Multifeature Extraction Framework Based on Attention Mechanism Using Wearable Sensor Data for Human Activity Recognition
- 9 February 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (7) , 7188-7198
Abstract
Human activity recognition (HAR) utilizing wearable sensors is a prominent topic in academia, and has been widely used in health monitoring, medical treatment, motion analysis, and other fields. Although HAR technology based on deep learning has made some progress, there are still some problems such as incomplete feature extraction and low utilization rate of features, which may result in false recognition. To settle the problems, we propose a novel deep multi-feature extraction framework based on attention mechanism (DMEFAM), which includes the temporal attention feature extraction layer (TAFEL), the channel and spatial attention feature extraction layer (CSAFEL), and the output layer. The TAFEL is comprised of bidirectional gated recurrent units (Bi-GRU) and self-attention (SA) mechanism, and the CSAFEL is comprised of convolutional block attention module (CBAM) and residual network-18 (ResNet-18). In this framework, the combination of deep learning neural networks, SA mechanism, and CBAM assigns different important degrees to features, increases the diversities of feature extraction, and improves the accuracy of HAR. To improve the practicability of the proposed framework, a daily and aggressive activity dataset (DAAD) is collected by our laboratory for performance evaluation. The experiments are conducted on the wireless sensor data mining laboratory (WISDM) dataset, the University of California Irvine-HAR (UCI-HAR) dataset, and the collected DAAD dataset. The results show that the proposed DMEFAM can upgrade the recognition performance effectually, compared to other advanced HAR frameworks, with recognition accuracies of 97.9%, 96.0% and 99.2% on the WISDM dataset, the UCI-HAR dataset, and the DAAD dataset, respectively.Keywords
Funding Information
- National Key Research and Development Program of China (2020YFC0833200)
- Natural Science Foundation of Shandong Province of China (ZR2020MF139)
This publication has 30 references indexed in Scilit:
- Real-Time Human Activity Recognition System Based on Capsule and LoRaIEEE Sensors Journal, 2020
- Adversarial Multi-view Networks for Activity RecognitionProceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, 2020
- Smartphone Sensor-Based Human Activity Recognition Using Feature Fusion and Maximum Full a PosterioriIEEE Transactions on Instrumentation and Measurement, 2019
- Activity Recognition with Wearable Accelerometers using Deep Convolutional Neural Network and the Effect of Sensor Placement2019
- AttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition2019
- IoT Wearable Sensor and Deep Learning: An Integrated Approach for Personalized Human Activity Recognition in a Smart Home EnvironmentIEEE Internet of Things Journal, 2019
- Activity Recognition Using Smartphone Sensors, Robust Features, and Recurrent Neural Network2019
- Human Activity Recognition Based on Wearable Sensor Using Hierarchical Deep LSTM NetworksCircuits, Systems, and Signal Processing, 2019
- Sensor-Based Daily Activity Understanding in Caregiving Center2019
- Activity recognition using cell phone accelerometersACM SIGKDD Explorations Newsletter, 2011