Mohammad Hassanzadeh
Machine Learning Approaches in Biomedical Science

Abstract

In this talk, I will first present an overview of my current research activities in machine learning, with applications spanning automotive systems, autonomous vehicles, cybersecurity, energy systems, computer vision, and other multidisciplinary domains.

I will then focus on my contributions in biomedical science, particularly in medical imaging and infectious disease analysis. I will discuss several data preprocessing and feature engineering techniques, including data processing, signal processing, image processing, and statistical modeling, that I employ prior to the application of machine learning algorithms.

Next, I will introduce a range of machine learning architectures that I have designed and utilized in my research, including hybrid, bimodal, fusion-based, and ensemble models. I will illustrate how core deep learning components such as multilayer perceptrons, convolutional neural networks, recurrent neural networks, graph neural networks, and transformer-based models serve as the fundamental building blocks of these frameworks.

Finally, I will demonstrate how the resulting models and methodologies contribute to the study and understanding of infectious diseases, with case studies involving COVID-19, influenza, hepatitis, and dengue, highlighting their potential impact on disease classification, prediction, and public health decision-making.