I am a graduate Electrical and Computer Engineering student with industry experience in engineering and machine learning. I have recieved a bachelor's degree in Electrical and Computer Engineering from Rowan University. I have completed all requirements for the Master of Science in Electrical and Computer Engineering degree pending a successful thesis defense. I have an interest in machine learning have completed multilple machine learning based classes including, Introduction to Machine Learning, Deep Learning, Reinforcement Learning, and Graduate Machine Learning 1.

I have authored a paper which has been published in the Journal of the International Neuropsycologial Society (JINS) 2020. This paper describes the application of machine learning to the digitial clock drawing test to classify patients with the correct level of cognitive impairment.

I have authored a paper which has been published in the journal for Silicon Carbide and Related Materials 2017. I have also presented a poster on these findings at the International Conference on Silicon Carbide and Related Materials in Washington DC.

Variants of this paper have been submitted to the "Journal of the International Neuropsychological Society" and "Alzheimer's & Dementia". This paper uses clock drawing data collected from over 100 patients. Each clock contains over 200 different features. Our research included using Information Theoretic, Embedded, and Wrapper based features selection algorithms to select the best features from the set. These features were then applied to different classifiers to record the classification accuracy. When trying to distinguish between different classes of Mild Cognitive Impairment (MCI) and Alzheimer's the classifiers achieved accuracies above 85%. One application of these findings is that a physician can yearly administer the simple 2 minute clock drawing test, and based on the results, can recommend a patient for further screening.

This is my term paper for the deep learning and data mining class at Rowan University. Dota 2 is an online game with a very complex state space making it very difficult to predict the outcome of matches. This paper covers the process of collecting over 800,000 games from the Dota 2 API and designing a neural network to predict the winner. The neural network was designed to take the 5 heroes picked on each team and the game duration as inputs and try to predict the winner based only on this information. The network achieved an accuracy of 80%.

This is my term paper for the introduction to machine learning engineering clinic at Rowan University. For this project I have taken over 100 different images covering 7 different buildings on campus. I have constructed and trained a convolutional neural network (CNN) to classify these images. This network achieved a classification accuracy of 89.2%.

This is my term paper for the computer architecture class at Rowan University. For this project my team and I have constructed a 16 bit Harvard architecture processor. The linked document covers the design and testing of this processor in extensive detail.