Chathurika Gamage

Research Interests

  • Deep Learning
  • Medical Imaging,
  • Data Science
  • Bioinformatics
  • Information Retrieval
  • Natural Language Processing


Projects


Autonomous Diabetic Foot Ulcer Analyzer Through Deep Learning

The project aims at autonomous segmentation and classification of diabetic foot ulcers imagery through deep learning. Mask-RCNN model use for image segmentation and

CNN based feature extraction approach was implemented to predict six-class severity stages of diabetic foot ulcers.

Tools & Tech: Deep Learning, Transfer Learning, Python, Keras, Flask, Jupyter Notebook, Angular.js


Anomalies Classification in Gastrointestinal Tract through Endoscopic Imagery with Deep Learning

In this research work we develop a prediction model to classify eight-class anomalies in gastrointestinal tract using endoscopic images through an ensemble of deep CNNs.

Tools & Tech: Deep Learning, Transfer Learning, Python, Keras, TensorFlow, Jupyter Notebook


Leaf and stem classification module for a tea sorting machine

A real-time stem and leaf classification machine learning module for tea sorting machine. This was being developed as a decision-making part of the machine and user allows to sort out the stems and leaf for two bins. The project involves evaluating image pre-processing algorithms and contour detection algorithms. Furthermore, it has been proposed a solution to select color components from existing color spaces which have highest discriminating power, deriving new color components by applying feature selection algorithms and calculating classification threshold and accuracy for each feature. The threshold values of the classification points will be used to differentiate stems and leaves as a single layer neural network, which is more lightweight than a multi-layer neural network, which will also give higher accuracy.

Tools & Tech: MATLAB & SIMULINK, JAVA, Machine Learning, Computer Vision


KDD Cup 2016 - Forecast inventory demand based on historical sales data

Kaggle project was done for Data Mining module. This was held with Grupo Bimbo. The project was to build a model to forecast inventory demand for the next week based on last 7-week data.

Tools & Tech: R, R-studio


Digit Recognizer for MNIST data set

Kaggle project to correctly identify digits from a dataset of tens of thousands of handwritten images.

Tools & Tech: R, R-studio


Mobile and Server-side Application for Train Ticket Reservation

This project consists of three main parts. An Android mobile application for the travelers, REST API, Website for the Railway department. This system facilitates travelers to reserve train tickets and get details about railway transportation using the mobile.

Tools & Tech: Android, MySQL, REST, PHP, Javascript, CSS, HTML