Nair Ul Islam

Conducted advanced analysis on neuroimaging data, including T1 and fMRI images, to develop early and accurate detection methods for Parkinson’s Disease (PD). Utilized tools such as FSL, SPM, and CAT for image preprocessing and analysis. Developed highly accurate and efficient predictive models for PD diagnosis, achieving model accuracies ranging from 86% to 93%. Created a regression model to forecast solar energy generation potential from the organization’s rooftop-installed solar panels. Optimized an SVM algorithm for diabetes classification on the PIMA dataset.

Research focused on the development of AI systems for the early prediction and analysis of Parkinson’s Disease using advanced neuroimaging techniques. Extensive use of TensorFlow and Keras for building and optimizing predictive models based on MRI data. Employed neuroimaging tools and libraries including FSL, SPM, CAT, CONN, along with Python libraries like Nibabel and Nilearn.

Specialized in Machine Learning and Data Science with a focus on healthcare applications. Dissertation: ”A Machine Learning Approach for Care in Patients with Chronic Diseases.”

Core subjects included Data structures, Mathematics, Algorithms, Operating Systems