Personalized Mobile Sensing for Predicting Recurrent Stress Events using Self-Supervised Pre-Training

Simple item page
dc.contributor.advisorWashington, Peter
dc.contributor.authorIslam, Tanvir
dc.contributor.departmentComputer Science
dc.date.accessioned2025-02-20T22:36:36Z
dc.date.available2025-02-20T22:36:36Z
dc.date.issued2024
dc.description.degreeM.S.
dc.identifier.urihttps://hdl.handle.net/10125/110181
dc.subjectComputer science
dc.titlePersonalized Mobile Sensing for Predicting Recurrent Stress Events using Self-Supervised Pre-Training
dc.typeThesis
dcterms.abstractStress is widely recognized as a major contributor to a variety of health issues. Stress prediction using biosignal data recorded by wearables is a key area of study in mobile sensing research because real-time stress prediction can enable digital interventions to immediately react at the onset of stress, helping to avoid many psychological and physiological symptoms such as heart rhythm irregularities. Electrodermal activity (EDA) is often used to measure stress. However, major challenges with the prediction of stress using machine learning include the subjectivity and sparseness of the labels, a large feature space, relatively few labels, and a complex nonlinear and subjective relationship between the features andoutcomes. To tackle these issues, I examine the use of model personalization: training a separate stress prediction model for each user. To allow the neural network to learn the temporal dynamics of each individual’s baseline biosignal patterns, thus enabling personalization with very few labels, I pre-train a 1-dimensional convolutional neural network (1D CNN) using self-supervised learning (SSL). I evaluate my method using the Wearable Stress and Affect Detection (WESAD) dataset. I fine-tune the pre-trained networks to the stress prediction task and compare against equivalent models without any self-supervised pre-training. Embeddings learned using pre-training method outperform supervised baselines with signif- icantly fewer labeled data points: the models trained with SSL require less than 30% of the labels to reach equivalent performance without personalized SSL. Apart from this single modality, to make a comparison, I have developed a multi-modal personalized stress predic- tion system using wearable biosignals (EDA), electrocardiogram (ECG), electromyography (EMG), respiration (RESP), core body temperature (TEMP), and three-axis acceleration (ACC) data using the same dataset. This study demonstrates that SSL models outperform non-SSL models while utilizing less than 5% of the annotations while using multi-modal biosignals. This personalized learning method can enable precision health systems which are tailored to each subject and require few annotations by the end user, thus allowing for the mobile sensing of increasingly complex, heterogeneous, and subjective outcomes such as stress.
dcterms.extent40 pages
dcterms.languageen
dcterms.publisherUniversity of Hawai'i at Manoa
dcterms.rightsAll UHM dissertations and theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission from the copyright owner.
dcterms.typeText
local.identifier.alturihttp://dissertations.umi.com/hawii:12358

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Islam_hawii_0085O_12358.pdf
Size:
11.69 MB
Format:
Adobe Portable Document Format
Download

Collections

M.S. - Computer Science