Autonomous Carrom Robot
The project is a realization of an automated smart carrom-playing robot which continuously analyses the board configuration using a vision feed and image processing and plays a series of best possible shots to complete a game.
This leverages the knowledge of reinforcement learning in implementing a strategic gameplay.
- Research by Naveen Karunanayake, Achintha Wijesinghe & Chameera Wijethunga
Based on Publication:
"Towards a Smart Opponent for Board Games: Learning beyond Simulations," in Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, Toronto, Canada (virtual), 2020
Non-invasive Cuff-less Blood pressure estimation/ Cardio-vascular disease prediction from a light signal (PPG)
5.1mmHG Accuracy for Blood Pressure estimation.
Identifying the Optimum Region of the Human Sole to Extract the PPG Signal for Pulse Rate Estimation, ICSPS 2017, Nov 2017, Auckland, New Zealand
Identifying upper arm injuries due to throwing
Unsupervised clustering algorithms to features extracted on Electromyography and player statistics.
A Low-Cost Wearable System to Analyze the Human Arm for Predicting Injuries Due to Throwing, 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC’19), Berlin, Germany
Level Set Image Segmentation using Python
Python implements a new level set formulation, called distance regularized level set evolution (DRLSE), proposed by Chunming Li et al's in the paper "Distance Regularized Level Set Evolution and its Application to Image Segmentation", IEEE Trans. Image Processing, vol. 19 (12), 2010Visit the Repository
Image Enhancing Software to test image pre-processing functions
Image enhancement application based on 'OpenCV' and 'PyQt4'. You can use this as a small image enhancement software for day-to-day work and can be used to do pre-processing for images before feeding into a Neural Network.Visit the Repository
AI to play Google Chrome T-Rex game in python
Yolo wrapper for pythonVisit the Repository
Image Morphing application using PythonVisit the Repository
Integer Sequence Learning
Tensor-flow code for the Integer Sequence Learning problem that is described in Kaggle.Visit the Repository
Classification of MNIST digits by Inception CNN modules.
Tensor-flow based classification of MNIST digits by convolutional neural networks (CNN) with Dropout and Inception layers.Visit the Repository