DEPARTMENT OF ELECTRONICS AND COMMUNICATION ENGINEERING
Galgotias College of Engineering and Technology , [Link] (U.P)
Real time Game Controlling Using
EEG Signal Classification
[Link] ECE Final Year Project (Zeroth
Review)
Under the Mentorship of Group Members:
Ms. Sakshi Mittal Anwesha (2200970310043)
[AP – III] Aditya Kumar(2200970310018)
Anurag Singh(2200970310041)
Your TABLE OF CONTENT h
ere
• Introduction
• Motivation
• Problem Identification
and Objectives
• Methodology/Flowchart
• Tool Used(Hardware/Software)
• Plan of Action
• References
Introduction to Brain-Computer Interfaces
Brain-Computer Interface (BCI)
• Direct communication pathway between the brain and an external device.
• Enables control of applications using thought alone.
Electroencephalography (EEG)
• Non-invasive method to record electrical activity of the brain.
• Measures voltage fluctuations resulting from ionic current within the neurons using
This project explores the use of EEG-based Brain-Computer Interface (BCI) to control a computer
game using brain signals instead of traditional input devices. EEG signals are recorded through
electrodes placed on the scalp, processed using Arduino and BioAmp hardware, and then classified
into two mental states: Attentive and Relaxed. These states are mapped to game controls — when
the player is attentive, the car moves forward; when relaxed, the car brakes.
Motivation Behind Brainwave-Controlled Gaming
Interest in Human-Computer Gaming Innovation
Neurotechnology Interaction Pioneering new forms of
Deep curiosity in how the Exploring novel ways to immersive and accessible
brain interacts with enhance user experience and gaming experiences.
technology and its potential accessibility beyond
for innovative applications. conventional input methods.
To understand and apply this technology, we aim to bridge the gap between human thought and digital control,
unlocking new possibilities in various domains.
Problem Statement & Project Objectives
Problem Statement Project Objectives
Traditional input devices often limit accessibility and innovation in human-computer interaction. Can
1
EEG-based BCI provide a viable and intuitive alternative for controlling applications like video
games?
EEG Signal Acquisition
To accurately acquire raw EEG signals using readily available hardware.
Signal Processing & Classification
To preprocess EEG data and classify it into "attentive" and "relaxed" states.
Real-time Game Control
To integrate classified brain signals for real-time control of a racing video game.
Machine Learning Model
To train and refine an ML model for enhanced classification accuracy and robustness.
Methodology: System Flow
EEG Signals
Raw brainwave data captured from the user's scalp.
Acquisition
Data collected via BioAmp + Arduino hardware setup.
Preprocessing
Filtering and cleaning of raw EEG signals.
Classification
ML model identifies 'attentive' or 'relaxed' states.
Game Control
Translating classified states into game commands.
Methodology: Detailed Steps
Hardware Setup
Assembling and connecting Arduino Uno and BioAmp EXG Pill with electrodes.
Signal Acquisition & Filtering
Implementing code for real-time EEG signal capture and noise reduction.
Data Collection
Systematic collection of EEG data for 'attentive' (e.g., focused on a task) and 'relaxed' (e.g., eyes closed) states from multiple subjects.
Machine Learning Model Training
Developing and training a classification model on collected data using Google Colab for optimal accuracy.
Real-time Classification & Game Integration
Implementing the trained model for live classification and mapping outputs to game controls (move/brake).
Tools & Technologies Utilized
Hardware Components Software & Platforms
• Arduino Uno: Microcontroller for data acquisition. • Arduino IDE: For programming the Arduino board.
• BioAmp EXG Pill: Compact, high-performance bio-signal amplifier. • Python 3.11: Main programming language for data processing and ML.
• EEG Electrodes & Gels: For precise signal capture from the scalp. • VS Code: Integrated Development Environment.
• Google Colab: Cloud-based platform for ML model training.
Project Plan of Action (Aug 2025 - May 2026)
Aug–Sep 2025
Hardware setup & EEG acquisition system calibration.
Oct–Nov 2025
Extensive data collection & preprocessing of EEG signals.
Dec–Jan 2026
Machine Learning model training, validation, and testing.
Feb–Mar 2026
Integration with racing game & initial demo preparation.
Apr–May 2026
Final system testing, performance analysis, and
comprehensive report writing.
Key References
• Liao, LD., Chen, CY., Wang, IJ. et al. Gaming control using a wearable
and wireless EEG-based brain-computer interface device with novel dry
foam-based sensors. J NeuroEngineering Rehabil 9, 5 (2012).
[Link]
• Umang Bansal, “Controlling Video Game Using Brainwaves (EEG),”
Instructables Project, 2023. Link
• A. Khong, L. Jiangnan, K. P. Thomas and A. P. Vinod, "BCI based
multiplayer 3-D game control using EEG for enhancing attention and
memory," 2014 IEEE International Conference on Systems, Man, and
Cybernetics (SMC), San Diego, CA, USA, 2014, pp. 1847-1852, doi:
10.1109/SMC.2014.6974189. keywords:
{Games;Electroencephalography;Entropy;Neurofeedback;Graphical
user interfaces;Keyboards;Brain;Neurofeedback;multi-
player;attention;Barin-Computer Interface (BCI)},
• M. N. Giannakos, K. Sharma and E. Niforatos, "Exploring EEG signals
during the different phases of game-player interaction," 2019 11th
International Conference on Virtual Worlds and Games for Serious
Applications (VS-Games), Vienna, Austria, 2019, pp. 1-8, doi:
10.1109/VS-Games.2019.8864519.
Next Steps & Future Scope
Project Milestones Ahead Broader Impact & Future Research
• Refine ML model for increased accuracy and robustness • Explore applications in assistive technology for
across diverse users. individuals with motor impairments.
• Optimize real-time performance for minimal latency in • Integrate more complex game mechanics with a wider
game control. range of brain states.
• Conduct extensive user testing and gather feedback for • Investigate multi-user BCI systems for collaborative
iterative improvements. gaming experiences.
• Potential for neurofeedback training in cognitive
enhancement.
Thank You. Questions?
