Optogenetics using light to excite the brain
Optogentics
Neuroscience
Hi, I'm Thamilezai Ananthakumar.
Self-motivated and quick-learning biomedical engineering undergraduate with a strong passion for applying advanced technologies such as machine learning, biosignal processing, digital twins, and wearable devices to develop innovative healthcare solutions.
About
I am a Biomedical Engineering undergraduate student at the University of Moratuwa, deeply passionate about advancing the field of biomedical research. I have a particular interest in biosignal processing, machine learning, wearable technologies, digital twin modeling, and physiological modeling. I am a dedicated and curious learner who always strives to deliver 100% in every project I undertake, with the goal of contributing to innovative and impactful healthcare solutions.
During my undergraduate studies, I have gained hands-on experience with a range of technologies including Python, C++, MATLAB, SolidWorks, Altium Designer, Arduino, ESP32, Raspberry Pi, Atmel Studio, and Verilog. I have also worked with machine learning and IoT tools such as TensorFlow, TensorFlow Lite, Scikit-learn, ThingSpeak, Node-RED, and LTspice.
I am passionate about solving real-world problems that shape the future of healthcare.
- Research Interests: Biosignal Processing,Digital Twins in Healthcare,Physiological Modeling,Wearable Healthcare Technologies,Neuroscience
Looking for an opportunity to work in a challenging position combining my skills in Biomedical Engineering, which provides professional development, interesting experiences, and personal growth.
Education
Jaffna Vembadi Girls' High School
Jaffna, Sri Lanka
Qualification: G.C.E. Ordinary Level
Results: 9 A Grades (English Medium)
Year: 2018
Qualification: G.C.E. Advanced Level
Results: 3 A Grades (Mathematics, Physics, Chemistry - English Medium)
Year: 2021
Notable Achievements:
- National Ranked 274 in 31000 Candidate (G.C.E Advanced Level)
University of Moratuwa
Moratuwa, Sri Lanka
Degree: Bachelor of Science in Computer Science and Engineering
CGPA: 3.904/4.0 (Dean's List in all three semesters)
Relevant Courseworks:
- Data Structures and Algorithms
- Physiological Modelling
- Anatomy and physiology for Engineers
- Signal and System
- Biomedical Instrumentation
- Linear Algebra
- Calculus
- Numerical Methods
Tools and Technologies
Python
MATLAB
NumPy
Pandas
scikit-learn
matplotlib
Neurokit2
Keras
TensorFlow
Streamlit
Google Colab
Overleaf
Arduino
Raspberry pi
Atmel Studio
Altium
SolidWorks
LTspice
Node-RED
ThingSpeak
Projects
Cardiologist Assistant
Real-Time ECG PPG Monitor
Accomplishments
- Tools: Python, , Neurokit2, Streamlit
- ECG and PPG signals using biosensors (ECG electrodes and IR-based PPG sensor).
- Extracted key cardiac parameters including T, P, and R peak detection from ECG.
- Calculated Heart Rate (HR), Heart Rate Variability (HRV), and Pulse Transit Time (PTT).
- Estimated Blood Pressure (BP) using PTT derived from ECG and PPG signals.
- Responsive Streamlit web app for real-time visualization of ECG/PPG signals.
- Early detection of cardiac anomalies such as arrhythmia using HRV analysis.
EMG Signal Filtering Circuit
Anlog Filter fo EMG with mini web-based oscilloscope
Muscle Cramp Detector
Non-Invasive Muscle Cramp Detection System Using Physiological Sensors
Accomplishments
- Tools: Altium, Solidwork, MATLAB, ESP32, ThingSpeak
- Non-invasive muscle cramp detection system by integrating EMG sensor, Temperature sensor
- Continuously monitors EMG signals, skin temperature, and tissue oxygen saturation (StO2)
- processes the data using MATLAB on ThingSpeak, and provides real-time alerts
Implementing a Complete Embedded System for a MediBox
Designed and implemented an IoT-based MediBox for remote health monitoring using ESP32 and Node-RED
Vein-Detection-Using-IR
Developed a real-time vein detection system using an ESP32-CAM with IR illumination and wireless video streaming.
Skin disease Prediction using Transfer learning
Skin disease detection using MobileNet, optimized for real-time edge deployment on Raspberry Pi.
Accomplishments
- Tools: Streamlit, NumPy, Pandas, Python, MobilNet, TensorFlow, TensorFlowlite, Raspberry pi 4B
- Developed a skin disease classification system using deep learning (MobileNet) with high accuracy(99%).
- Deployed via a Streamlit web app for image-based predictions.
- Raspberry Pi 4B for real-time detection using a camera.
- Optimized with TensorFlow Lite (2.4MB model) for efficient performance on edge devices.
Thyroid Prediction Model
Thyroid disease prediction using logistic regression with 97% accuracy.
Blog and Publications
Contact
I am Thamilezai Ananthakumar. If you'd like to discuss anything, feel free to contact me at any time. I wish to help you with Biomedical engineering-related tasks.