Comparative Analysis of Classification Models for EEG data in Avatar project

Author

• Merina KhimbajaFollow

Date of Award

3-2026

Culminating Project Type

Thesis

Styleguide

apa

Degree Name

Computer Science: M.S.

Department

Computer Science and Information Technology

College

School of Science and Engineering

First Advisor

Adriano Cavalcanti

Second Advisor

Jalal Khalil

Third Advisor

Jie Meichsner

Creative Commons License

This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Keywords and Subject Headings

Gaussian Naïve Bayes, Deep Learning, Support Vector Machine (SVM), OpenBCI, Brain-computer Interface, TensorFlow, Avatar

Abstract

The brain-computer interface is a contemporary technology that communicates between the human brain and external devices. The project explores the implementation and comparison of two machine learning models for EEG signals that come from the OpenBCI headset, to make piloting predictions, and a drone control system. The machine learning models that are compared in this paper are Gaussian Naïve Bayes Algorithm, Deep Learning and Support vector Machine (SVM) machine learning models. Gaussian naïve Bayes algorithm works well even with relatively small dataset; it is lightweight but since it depends on simple parametric forms it has lower capacity. Deep learning on the other hand typically requires a large, labeled dataset but has high capacity and can perform well in complex sequences.  This project demonstrates application of these models in the Avatar project and analyzes the best approach for EEG datasets.

Keywords---Gaussian Naïve Bayes, Deep Learning, Support Vector Machine (SVM), OpenBCI, Brain-computer Interface, TensorFlow, Avatar

Comments/Acknowledgements

I would like to express my sincere gratitude to the faculty and staff of the Department of Computer Science and Information Technology at St. Cloud State University for their immense support and guidance throughout my academic journey. I would also like to thank Dr. Adriano Cavalcanti for his continuous support and mentorship during implementation of this project.

Recommended Citation

Khimbaja, Merina, "Comparative Analysis of Classification Models for EEG data in Avatar project" (2026). Culminating Projects in Computer Science and Information Technology. 72.
https://repository.stcloudstate.edu/csit_etds/72