View Proposal

---

Proposer

Heba Elshimy

Title

Real-time Hand Movement Intent Detection from EEG Signals Using Machine Learning and Deep Learning Models

Goal

Develop and evaluate efficient ML/DL models for detecting hand movement intentions from EEG signals

Description

This project involves analyzing the Grasp-and-Lift EEG dataset containing 32-channel EEG recordings from 12 subjects performing six distinct hand movement actions (HandStart, FirstDigitTouch, BothStartLoadPhase, LiftOff, Replace, BothReleased). The student will explore various approaches to EEG signal preprocessing, feature extraction, and classification using modern machine learning techniques. The project can be approached as either a multi-label classification problem (detecting which actions are active at each timestamp) or a sequence prediction task (predicting action transitions).

Resources

Datasets: - https://www.kaggle.com/competitions/grasp-and-lift-eeg-detection/data - https://github.com/meagmohit/EEG-Datasets

Background

Python, pytorch, some ml and dl architectures

Url

Difficulty Level

Moderate

Ethical Approval

None

Number Of Students

1

Supervisor

Heba Elshimy

Keywords

machine learning, deep learning, signal processing, eeg

Degrees

Bachelor of Science in Computer Science
Bachelor of Science in Computer Systems
Bachelor of Science in Computer Science (Cyber Security)
Bachelor of Science in Statistical Data Science