Date of Submission

Fall 12-9-2023

Degree Type

Thesis

Degree Name

Master of Science in Computer Science (MSCS)

Department

Computer Science

Committee Chair/First Advisor

Nasrin Dehbozorgi

Track

Others

Machine Learning

Chair

Nasrin Dehbozorgi

Committee Member

Femi Ojo

Committee Member

Maria Valero

Abstract

Students frequently face heightened stress due to academic and social pressures, particularly in de- manding fields like computer science and engineering. These challenges are often associated with serious mental health issues, including ADHD (Attention Deficit Hyperactivity Disorder), depression, and an increased risk of suicide. The average student attention span has notably decreased from 21⁄2 minutes to just 47 seconds, and now it typically takes about 25 minutes to switch attention to a new task (Mark, 2023). Research findings suggest that over 95% of individuals who die by suicide have been diagnosed with depression (Shahtahmasebi, 2013), and almost 20% of students acknowledge experiencing signifi- cant suicidal thoughts, with 9% having made suicide attempts (Benton, 2022). Another medical imaging study indicates that meditation might combat or even prevent the psychological and physiological factors contributing to stress and depression (Annells, Kho, & Bridge, 2016). Chronic stress has been linked to an increased risk of depression, and effectively managing stress can help reduce this risk (McGonagle & Kessler, 1990) and potentially decrease suicide rates (Rosiek, Rosiek-Kryszewska, Leksowski, & Lek- sowski, 2016).

In this study, we developed the ChakraMarmaKosha Meditation (CM-II), a novel guided meditation technique. CM-II consists of three stages: Emotional Review, Analyzing Challenges, and Rehearsing Solutions. Each stage is enhanced with voice guidance and flute music, specifically composed in the Indian Raga ‘Hindol’ to aid the meditation process. Additionally, we developed a machine learning model to predict and measure shifts in attention through EEG (Electroencephalogram) spectral analysis. This program was further refined to assess HRV (Heart Rate Variability) metrics from heart pulse data, enabling a detailed analysis of stress patterns over time.

In an experiment involving 15 students in a lab setting, participants went through a 61-minute session comprising 8-minute pre and post attention tests and a 45-minute CM-II meditation. Throughout the session, EEG and heart pulse data were recorded using Muse 2 and emWave Pro devices, respectively, to assess changes in attention and stress levels. The EEG spectral ratio analysis demonstrated a notable rise in attention among participants during meditation, and HRV analysis showed improvement in stress levels and activation of the parasympathetic nervous system. These findings were substantiated by statistically significant results in the online attention test, where the Reasoning and Flanker tests showed p-values of 0.0077 and 0.0035, respectively, indicating a meaningful impact of the meditation on attention levels.

By combining meditation, music, and data science, this research offers an approach to improving mental health among college students. It underscores the importance of early identification, monitoring, and intervention in stress and mental health in higher education, aiming to reduce stress and improve student attention. However, the current study’s reliance on expensive, connected devices limits its accessibility. To address this challenge, moving ahead, we would develop a smartphone app utilizing Remote Photoplethysmography (RPPG) technology, allowing real-time stress monitoring through a selfie camera of smartphone users.

Download

Share

COinS