Use of EEG-Based Machine Learning to Predict Music-Related Brain Activity - Undergraduate Thesis

Aug 5, 2026

Music has strong emotional and cognitive effects and is widely regarded as capable of influencing the brain physically and emotionally. Building on clinically relevant music therapy and its neuroplastic mechanisms, this thesis investigates whether musical thoughts can be decoded using machine learning from EEG recordings. EEG data were collected while participants focused on five melodies, and models were trained on labeled datasets to predict which melody subjects were thinking of. Prediction accuracy ranged from 45% to 80%, suggesting potential for examining neuroplasticity and supporting future music-based brain-computer interfaces.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages52

Reading Time2 h 11 min

AccessFree to download

Abstract

Introduction

Music Therapy

Brain Organization-From Neurons to Lobes

Neuroplasticity

Why Study This Topic? Conclusions From Part 1

Methods

Brain Visualization Techniques

EEG Device Selection and Options

Machine Learning for EEG Data

Applied Use of Machine Learning-XGBoost Classification

Applied Use of Machine Learning-Microsoft Azure

EEG Data and Rhythms-Brainwaves

Experimental Design

Overview, Setup, Data Collection and Organization

Data Analysis Methods

Results

Discussion

Limitations

Conclusion

University of Lynchburg Digital Showcase @ University of Lynchburg | Undergraduate Theses and Capstone Projects | Student Publications | | --- | --- | | Spring 5-1-2023
Use of EEG-Based Machine Learning to Predict Music-Related Brain Activity
Charles Skutt
University of Lynchburg, [skuttc389@lynchburg.edu](skuttc389@lynchburg.edu)
Follow this and additional works at: [https://digitalshowcase.lynchburg.edu/utcp](https://digitalshowcase.lynchburg.edu/utcp)
Part of the Music Therapy Commons, and the Psychology Commons | | Recommended Citation Skutt, Charles, "Use of EEG-Based Machine Learning to Predict Music-Related Brain Activity" (2023) . Undergraduate Theses and Capstone Projects. 266. [https://digitalshowcase.lynchburg.edu/utcp/266](https://digitalshowcase.lynchburg.edu/utcp/266) This Thesis is brought to you for free and open access by the Student Publications at Digital Showcase @ University of Lynchburg. It has been accepted for inclusion in Undergraduate Theses and Capstone Projects by an authorized administrator of Digital Showcase @ University of Lynchburg. For more information, please contact [digitalshowcase@lynchburg.edu](digitalshowcase@lynchburg.edu). Use ofEEG-Based Machine Learning to Predict Music-Related Brain Activity Charles Skutt Senior Honors Project Submitted in partial fulfillment of the graduation requirements of the Westover Honors College Westover Honors College May, 2023 | David O. Freier, PhD | | --- | | Price Blair, PhD | Cynthia Ramsey, DMA Abstract Introduction 1 Music Therapy 1.1 Music Therapy and Mental Disorders 1.2 Music Therapy and Neurorehabilitation 2 Brain Organization-From Neurons to Lobes 3 Neuroplasticity 3.1 Neuroplasticity-Neurons and Networks 3.2 Neuroplasticity-Neurotransmitters 3.3 Neuroplasticity-Larger Impacts 3.4 Neuroplasticity and Music-Overview 3.5 Neuroplasticity and Music-Neurotransmitters 3.7 Neuroplasticity-Application 4-So, Why Study This Topic? Conclusions From Part 1 Methods Brain Visualization Techniques EEG Device Selection EEG Device Options Machine Learning for EEG Data Overview of Machine Learning Applied Use of Machine Learning-XGBoost Classification Applied Use of Machine Learning-Microsoft Azure EEG Data and Rhythms-Brainwaves Experimental Design: Overview Setup Data Collection Methods Data Organization Methods Data Analysis Methods Results Discussion Limitations Conclusion Abstract Music has many awe-inspiring characteristics. Some may refer to it as a “universal language” with the ability to transcend the barriers of speech, while others may describe its ability to evoke intense emotional experiences for the listener. Regardless of the description, it is a commonly held view that music can have many profound effects. Studies of music’s effects have found these beliefs to be more than pure conjecture, finding that music interacts with and changes our brains in physical and emotional ways. Music can even have clinical applications, such as music therapy. This type of therapy has been shown to be beneficial in many areas, ranging from stroke rehabilitation to mental health treatment. The mechanisms behind music’s therapeutic benefit has to do with neuroplastic effects; Being able to harness this benefit in a therapeutic setting could make treatments for mental disorders and brain injuries even more effective. This thesis aimed to discover whether musical thoughts could be interpreted using machine learning, potentially opening the door to the use of thought-based musical training for therapeutic benefit. For this study, EEG data was collected while people were thinking of 5 melodies, then machine learning models were trained on labeled datasets. The models were then tasked with categorizing unlabeled sets ofEEG data-in other words, predicting which melody a subject was thinking of while the data was being recorded. The accuracy of the predictio

FAQs

What is the main goal of this thesis?

To determine whether music-related thoughts can be interpreted from EEG data using machine learning, enabling prediction of which melody a subject is thinking about during recording.

How was the EEG data used in the machine learning workflow?

EEG data were collected while participants focused on five melodies, then machine learning models were trained on labeled datasets and used to classify unlabeled EEG segments.

What level of prediction accuracy did the models achieve?

Model accuracy ranged from about 45% to 80%, corresponding to roughly 2–4 times better performance than random guessing.

Aug 5, 2026

Upload by Emma Wilson