Multimodal fusion of IMUs and EPS body-worn sensors for scratch recognition

Jocys, Zygimantas, Pour Yazdan Panah Kermani, Arash and Roggen, Daniel (2020) Multimodal fusion of IMUs and EPS body-worn sensors for scratch recognition. EAI PervasiveHealth 2020 - 14th EAI International Conference on Pervasive Computing Technologies for Healthcare, Atlanta, United States, October 6-8, 2020. Published in: Badram, Jakob, Chung, Chia-Fang, Jacobs, Maia, Morrisey, Kellie, Orji, Rita, Song, Junehwa and Yarosh, Lana, (eds.) PervasiveHealth '20: Proceedings of the 14th EAI International Conference on Pervasive Computing Technologies for Healthcare. 325-335. Association for Computing Machinery, New York, NY, United States. ISBN 9781450375320

[img] PDF - Accepted Version
Download (8MB)

Abstract

In order to develop and evaluate the extent to which itching affects a person's daily life, it is useful to develop automated means to recognise the action of scratching. We present an investigation of sensors and algorithms to realise a wearable scratch detection device. We collected a dataset, where each user wore 4 inertial measurement unit (IMU) sensors and one electric potential sensor (EPS). Data were collected from nine users, where each user followed a 40-min protocol, which involved scratching different parts of head, shoulder, and leg, as well as other activities such as walking, drinking water, brushing teeth, and typing to a computer. The dataset contained 813 scratching instances and 5 h 15 min of recorded data. We investigated the trade-offs between the number of devices worn (comfort) and accuracy. We trained the k-NN and random forest algorithms by using between 1 and 5 features per channel. We concluded that a scratch could be detected with 80.7% accuracy by using the random forest algorithm on hand coordinates, which required four devices. However, an f1 score of 70% could be achieved with k-NN with IMU and EPS data, which only required one device. Moreover, the fusion of IMU data with EPS data improved the accuracy and reduced the deviation between the folds. This expanded the state-of-the-art method by opening up new trade-offs between accuracy and comfort for future research

Item Type: Conference Proceedings
Schools and Departments: School of Engineering and Informatics > Engineering and Design
School of Engineering and Informatics > Informatics
Research Centres and Groups: Sensor Technology Research Centre
Subjects: Q Science > Q Science (General) > Q0300 Cybernetics
T Technology > TK Electrical engineering. Electronics Nuclear engineering
Depositing User: Daniel Roggen
Date Deposited: 13 Mar 2020 08:45
Last Modified: 10 Feb 2021 10:30
URI: http://sro.sussex.ac.uk/id/eprint/90391

View download statistics for this item

📧 Request an update
Project NameSussex Project NumberFunderFunder Ref
Automated recognition of hair touch and scalp scratching through novel sensing modalities, sensor fusion and machine learning approachesG2738UNILEVERMA-2017-02004N