Unsupervised classification of human activity with hidden semi-Markov models

Cavallo, Francesca, Toumazou, Christofer and Nikolic, Konstantin ORCID: https://orcid.org/0000-0002-6551-2977 (2022) Unsupervised classification of human activity with hidden semi-Markov models. Applied System Innovation, 5 (4). p. 83.

[thumbnail of asi-05-00083-v3.pdf]
Preview
PDF
asi-05-00083-v3.pdf - Published Version
Available under License Creative Commons Attribution.

Download (1MB) | Preview

Abstract

The modern sedentary lifestyle is negatively influencing human health, and the current guidelines recommend at least 150 min of moderate activity per week. However, the challenge is how to measure human activity in a practical way. While accelerometers are the most common tools to measure activity, current activity classification methods require calibration studies or labelled datasets—requirements that slow the research progress. Therefore, there is a pressing need to classify and quantify human activity efficiently. In this work, we propose an unsupervised approach to classify activities from accelerometer data using hidden semi-Markov models. We tune and infer the model parameters on accelerometer data from the UK Biobank and select the optimal model based on features used and informativeness of the prior. The best model achieves an average correlation of 0.4 between the inferred activities and the reference ones, with the overall physical activity obtaining a correlation of 0.8. Additionally, to prove the clinical significance of the method, we validate it by performing a linear regression between the inferred activities and anthropometric measures such as BMI and waist circumference. We show that for a sedentary behaviour and total physical activity, the proposed method achieves comparable regression coefficients to the reference labelled dataset. Moreover, the proposed method achieves a good agreement with a labelled dataset for daily time spent in a sedentary behaviour and total physical activity. The unsupervised nature of the method allows for a data-driven classification that does not require calibration studies or labelled datasets and can thus facilitate both clinical research as well as lifestyle recommendations.

Item Type: Article
Identifier: 10.3390/asi5040083
Keywords: activity classification; accelerometer; hidden Markov models; wearable sensors; UK Biobank
Subjects: Construction and engineering > Electrical and electronic engineering
Computing > Intelligent systems
Related URLs:
Depositing User: Konstantin Nikolic
Date Deposited: 28 Nov 2022 10:46
Last Modified: 06 Feb 2024 16:13
URI: https://repository.uwl.ac.uk/id/eprint/9657

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu