Can heart rate sequences from wearable devices predict day-long mental states in higher education students: a signal processing and machine learning case study at a UK university

The mental health of students in higher education has been a growing concern, with increasing evidence pointing to heightened risks of developing mental health condition. This research aims to explore whether day-long heart rate sequences, collected continuously through Apple Watch in an open enviro...

Full description

Saved in:
Bibliographic Details
Published in:Brain informatics 2024-12, Vol.11 (1), p.29-18
Main Author: Chen, Tianhua
Format: Article
Language:English
Subjects:
Algorithms
Artificial Intelligence
Case studies
Cognitive Psychology
College students
Colleges & universities
Computation by Abstract Devices
Computer Science
Data collection
Data mining
Education
Education, Higher
Fourier transforms
Health
Health Informatics
Heart beat
Heart Rate
Higher education
Machine learning
Mental disorders
Mental Health
Neurosciences
Sequences
Signal Processing
Smartwatches
Stress
Stress (Psychology)
Student Wellbeing
Students
Wavelet analysis
Wearable
Wearable technology
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The mental health of students in higher education has been a growing concern, with increasing evidence pointing to heightened risks of developing mental health condition. This research aims to explore whether day-long heart rate sequences, collected continuously through Apple Watch in an open environment without restrictions on daily routines, can effectively indicate mental states, particularly stress for university students. While heart rate (HR) is commonly used to monitor physical activity or responses to isolated stimuli in a controlled setting, such as stress-inducing tests, this study addresses the gap by analyzing heart rate fluctuations throughout a day, examining their potential to gauge overall stress levels in a more comprehensive and real-world context. The data for this research was collected at a public university in the UK. Using signal processing, both original heart rate sequences and their representations, via Fourier transformation and wavelet analysis, have been modeled using advanced machine learning algorithms. Having achieving statistically significant results over the baseline, this provides a understanding of how heart rate sequences alone may be used to characterize mental states through signal processing and machine learning, with the system poised for further testing as the ongoing data collection continues.
ISSN:2198-4018
2198-4026
DOI:10.1186/s40708-024-00243-w