Date of Award
11-2025
Culminating Project Type
Starred Paper
Styleguide
ieee
Degree Name
Computer Science: M.S.
Department
Computer Science and Information Technology
College
School of Science and Engineering
First Advisor
Dr. Adriano Cavalcanti
Second Advisor
Dr. Akalanka Bandara Mailewa
Third Advisor
Dr.Mark Schmidt
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Keywords and Subject Headings
Deep Learning, Brain-Computer Interface (BCI), EEG Signals / EEG Data, Convolutional Neural Network (CNN), 1D Convolutional Neural Network (1D-CNN), Neural Network, Machine Learning Models, Model Performance, Confusion Matrix, F1 Score, Adam Optimizer
Abstract
This study presents a novel approach using a one dimensional convolutional neural network (1DCNN) to translate electroencephalography (EEG) signals into drone control commands. The model accurately recognizes and classifies six movement commands - forward, backward, left, right, takeoff and land by detecting distinct brainwave patterns. Using a 16 channel headset with a 125 Hz sampling rate, we collected 2,498,750 EEG records. After rigorous preprocessing and feature extraction, the trained 1D CNN model achieved a remarkable 99.27% classification accuracy in mapping brain signals to corresponding commands. These results highlight the potential of this method to advance brain-computer interface (BCI) technologies, enabling more intuitive and efficient EEG based drone control systems.
Recommended Citation
Darsi, Divya Prathyusha, "Deep Learning Driven Control for Cyber Physical Avatars" (2025). Culminating Projects in Computer Science and Information Technology. 75.
https://repository.stcloudstate.edu/csit_etds/75
