An IRB-approved study in collaboration with a private hospital on the comparison of the accuracy of AI-Powered Medical Image Analysis vs digital mammogram for breast cancer detection.  The objective of the study is to create an assistive tool for medical practitioners in analyzing medical imaging for a faster and more accurate diagnosis of each specific cancer using medical images, and pathology reports. 

In this paper, a streamlined working pipeline for an end-to-end deep reinforcement learning framework for autonomous driving was introduced. It integrates the usage of a choice combination of Algorithm-Policy for training the simulator by streamlining the integration of Microsoft AirSim, OpenGym, and Stable-Baselines. The pipeline is tested for goal reaching (represented by waypoints) with penalized collision. Several algorithm-policy combinations were tested and performance was measured using success rate (reaching the goal), number of collisions, and goal distance. Several of the models reached 30% to 100% success rates over 100 test episodes demonstrating the learning of autonomous goal reaching and collision avoidance. 

A tracking system was developed with a novel approach for localization and tracking of multiple players using several static cameras.  We use the localized track of the player and project it to its corresponding top view for visualization.  Image segmentation techniques, camera calibration, and clustering were used to develop the tracking system.  The system is supervised, and uses initial input from the user.  This was applied on a football game using three (3) off-the-shelf wide angle cameras.