A Cross-Day Analysis of EMG Features, Classifiers, and Regressors for Swallowing Events Detection and Fluid Intake Volume Estimation

Abstract

Dehydration is a common problem among older adults. It can seriously affect their health and wellbeing and sometimes leads to death, given the diminution of thirst sensation as we age. It is, therefore, essential to keep older adults properly hydrated by monitoring their fluid intake and estimating how much they drink. This paper aims to investigate the effect of surface electromyography (sEMG) features on the detection of drinking events and estimation of the amount of water swallowed per sip. Eleven individuals took part in the study, with data collected over two days. We investigated the best combination of a pool of twenty-six time and frequency domain sEMG features using five classifiers and seven regressors. Results revealed an average F-score over two days of 77.5±1.35% in distinguishing the drinking events from non-drinking events using three global features and 85.5±1.00% using three subject-specific features. The average volume estimation RMSE was 6.83±0.14 mL using one single global feature and 6.34±0.12 mL using a single subject-specific feature. These promising results validate and encourage the potential use of sEMG as an essential factor for monitoring and estimating the amount of fluid intake.

Keywords

• dehydration
• electromyography sensors
• EMG features
• fluid intake
• drinking
• classification