A Human Activity Recognition Method Based on Lightweight Feature Extraction Combined With Pruned and Quantized CNN for Wearable Device
- 12 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 69 (3) , 657-670
Abstract
Human Activity Recognition (HAR) is becoming an essential part of human life care. Existing HAR methods are usually developed using a two-level approach, wherein a first-level Machine Learning (ML) classifier is employed to distinguish the static and dynamic activities, followed by a second-level classifier to identify the specific activity. These approaches are not suitable for wearable devices, due to the high computational and memory consumption. Our rigorous analysis of various HAR datasets opens up a new possibility that static or dynamic activities can be discriminated against through a simple statistical technique. Therefore, we propose to utilize a statistical feature extraction technique to replace the first-level ML classifier, thus achieving more lightweight computation. Next, we employ Random Forest (RF) and Convolutional Neural Networks (CNN) to classify the specific activities, achieving higher accuracy compared to the state-of-the-art results. We further reduce the computation and memory consumption of the above combined approach by applying pruning and quantizing techniques to CNN (PQ-CNN). Experimental results show the proposed lightweight HAR method achieved an F1 score of 0.9417 and 0.9438 for unbalanced and balanced datasets, respectively. On top of lightweight and accuracy, the proposed HAR method is practical for wearable devices by using a single accelerometer.Keywords
Funding Information
- High-Potential Individuals Global Training Program of the Institute of Information communications Technology Planning and Evaluation (2021-0-00540)
- National Research Foundation of Korea
- Korean Government through Ministry of Science and ICT (2019H1D3A1A01102607, 2020R1A2B5B01002145)
This publication has 45 references indexed in Scilit:
- Segmentation and Recognition of Basic and Transitional Activities for Continuous Physical Human ActivityIEEE Access, 2019
- DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity RecognitionIEEE Access, 2018
- Divide and Conquer-Based 1D CNN Human Activity Recognition Using Test Data SharpeningSensors, 2018
- Ensemble learning: A surveyWIREs Data Mining and Knowledge Discovery, 2018
- Recognizing Detailed Human Context in the Wild from Smartphones and SmartwatchesIEEE Pervasive Computing, 2017
- Big data small footprintProceedings of the VLDB Endowment, 2014
- Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor UnitsThe Computer Journal, 2013
- Introducing a New Benchmarked Dataset for Activity Monitoring2012
- Activity recognition using cell phone accelerometersACM SIGKDD Explorations Newsletter, 2011
- SVM Classification for Large Data Sets by Considering Models of Classes Distribution2007