Fusion of wearable and contactless sensors for intelligent gesture recognition

Liang, X., Li, H., Wang, W., Liu, Y., Ghannam, R. , Fioranelli, F. and Heidari, H. (2019) Fusion of wearable and contactless sensors for intelligent gesture recognition. Advanced Intelligent Systems, 1(7), 1900088. (doi: 10.1002/aisy.201900088)

193482.pdf - Published Version
Available under License Creative Commons Attribution.



This paper presents a novel approach of fusing datasets from multiple sensors using a hierarchical support vector machine algorithm. The validation of this method was experimentally carried out using an intelligent learning system that combines two different data sources. The sensors are based on a contactless sensor, which is a radar that detects the movements of the hands and fingers, as well as a wearable sensor, which is a flexible pressure sensor array that measures pressure distribution around the wrist. A hierarchical support vector machine architecture has been developed to effectively fuse different data types in terms of sampling rate, data format and gesture information from the pressure sensors and radar. In this respect, the proposed method was compared with the classification results from each of the two sensors independently. Datasets from 15 different participants were collected and analyzed in this work. The results show that the radar on its own provides a mean classification accuracy of 76.7%, while the pressure sensors provide an accuracy of 69.0%. However, enhancing the pressure sensors’ output results with radar using the proposed hierarchical support vector machine algorithm improves the classification accuracy to 92.5%.

Item Type:Articles
Glasgow Author(s) Enlighten ID:Ghannam, Professor Rami and Fioranelli, Dr Francesco and Heidari, Professor Hadi and Li, Haobo and Liang, Xiangpeng and Liu, Miss Yuchi
Authors: Liang, X., Li, H., Wang, W., Liu, Y., Ghannam, R., Fioranelli, F., and Heidari, H.
College/School:College of Science and Engineering > School of Engineering > Electronics and Nanoscale Engineering
College of Science and Engineering > School of Engineering > Systems Power and Energy
Journal Name:Advanced Intelligent Systems
ISSN (Online):2640-4567
Published Online:22 August 2019
Copyright Holders:Copyright © 2019 John Wiley & Sons
First Published:First published in Advanced Intelligent Systems 1(7):1900088
Publisher Policy:Reproduced under a Creative Commons License

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
3028770Magnetic Diagnostics Setup for Lab-on-Chip ApplicationHadi HeidariThe Royal Society (ROYSOC)RSG\R1|180269ENG - Electronics & Nanoscale Engineering
3048960EPSRC-IAA: Early Stage Commercialisation of a PET Imaging Agent for the Detection of Cardiovascular Disease and CancerAndrew SutherlandEngineering and Physical Sciences Research Council (EPSRC)EP/R511705/1Chemistry
3015260Intelligent RF Sensing for Fall and Health PredictionFrancesco FioranelliEngineering and Physical Sciences Research Council (EPSRC)EP/R041679/1ENG - Systems Power & Energy