• Adaptive-learning model predictive control for complex physiological systems: Automated insulin delivery in diabetes•Integrating MPC with Learning-Based and Adaptive Methods to Enhance Safety, Performance and Reliability in Automated Insulin Delivery• Application of Neural Networks for Heart Rate Monitoring• Leveraging Plasma Insulin Estimates and Wearable Technologies to Develop an Automated Insulin Delivery System in Type 1 Diabetes• Developing an algorithm that can determine the type of physical activity (PA) and quantify the intensity can allow precision medicine approaches, such as automated insulin delivery systems that modulate insulin administration in response to PA• Improving the accuracy of blood glucose concentration (BGC) estimation affects insulin dosing decisions. Wristband biosignals (Empatica E4) are used to estimate physical activity type and intensity, and psychological stress to enhance BGC prediction accuracy.

• Teaching assistant of "Tech for the Treatment of Diabetes" offered by the Department of Chemical and Biological Engineering at IIT

• Working on an adaptive-learning model predictive control (AL-MPC) framework for incorporating disturbance prediction, model uncertainty quantification, pattern learning, and recursive subspace identification for use in controlling complex dynamic systems with periodically recurring large random disturbances.

• Teaching Assistant of "Tech for the Treatment if Diabetes" offered by the department of Chemical and Biological Engineering at IIT for undergraduate study

• Artifact removal from data generated by nonlinear systems: Heart rate estimation from blood volume pulse signal

• Obesity: developing a thermodynamic model for long-horizon prediction of weight loss in obese and prediabetic people with respect to weekly dosage of GLP-1 Liraglutide•Multiscale Modeling: Integrating deep NN predictive model, built on the peptide/protein chains and animal-to-human PK response, with type-2 diabetes human digital twin for narrowing down the number of GLP-1-based drug candidates•Scientific Modeling: Improving the prediction capability of a type-2 PK-PD physiological model by investigating parameter sensitivity, parameter identifiability, and Bayesian optimization•Parallelized Human Digital Twin: Refactoring T2D physiological model, CGM sensor noise model, and insulin titration algorithm by introducing the vectorized solution of models and modules

• Research Project: Application of Adaptive Fuzzy Logic Systems in Controller Design of Nonlinear Systems

•Process Control Engineering Lab for the class of Fall 2014 and Spring 2015