A wearable sensors dataset for stress & boredom associated activity recognition

Abstract

This article presents a dataset of activities associated with stress and boredom obtained through wearable sensors. Data was collected from 40 right-handed participants aged 20 to 25, evenly split between males and females. Each individual wore a smart device on their dominant arm's wrists to facilitate the capture of data. This dataset covers five activities associated with stress and boredom, namely, smoking, eating, nail biting, face touching, and staying still. These activities were selected for their potential psychological implications and captured in an uncontrolled environment to mimic real-life scenarios. The data provides a unique resource for developing machine learning models aimed at recognizing these behaviors, which could lead to real-time analysis and interventions for stress. A custom holder was used to hold the device on the wrists in order to ensure that all participants had consistent orientation and placement. This holder was situated just above the wrist joint, a location typically associated with the placement of smartwatches. The dataset provides a unique opportunity for developing machine learning models for stress & boredom associated activities recognition apart from real-time symptomatic analysis of stress and boredom.

Keywords

• Motion sensor
• Smart devices
• Mental health
• Time series
• Activity recognition