Link to paper:
10.1109/BMEiCON60347.2023.10322025
Mind to Motion: EEG-Based Classification of Motor Imagery and Actual Hand Movements Using LSTM Models
Apoorva Sunil Chakkamallisery
Project Timeline
Jun 2022 - Jan-2023
OVERVIEW
Developed an EEG-based LSTM classification model to differentiate motor imagery from real hand movements, achieving 62.5% accuracy in imagery vs. action and 72.5% accuracy in rest vs. action, advancing applications in BCI and motor rehabilitation.
HighlightS
- The project received an honorable mention in the Research, Invention, and Creative Work Award for the academic year 2022 by Rangsit University, Thailand.
- Presented the paper at '2023 15th Biomedical Engineering International Conference (BMEiCON'23)' held by IEEE in Tokyo, Japan.
SKILLS
EEG Signal Processing & AcquisitionData preprocessing techniquesDeep Learning Machine Learning Workflow
ADDITIONAL CONTENTS
Apoorva Sunil Chakkamallisery
Biomedical Engineer
MEng Biomedical Engineering student at College of Engineering Boston University, passionate about bringing healthcare technologies from concept to impact. I have 2 years of research experience in EEG signal acquisition and analysis and am now transitioning toward product development and product management. I’m especially interested in how engineering, design, and strategy come together to create user-centered medical technologies that improve patient outcomes.
MEng Biomedical Engineering student at College of Engineering Boston University, passionate about bringing healthcare technologies from concept to impact. I have 2 years of research experience in EEG signal acquisition and analysis and am now transitioning toward product development and product management. I’m especially interested in how engineering, design, and strategy come together to create user-centered medical technologies that improve patient outcomes.
| lowinertia |
Build Your Engineering Portfolio