Research
Big Data Analytics for Smart Grid
With the promises of smart grids, power can be more efficiently and reliably generated, transmitted, and consumed over conventional electricity systems.An important issue in smart grids is on managing Demand Response to reduce peak electricity load and better utilize renewable energies to reduce our dependence on hydrocarbon. Distributed Power Systems State Estimation and Smart Home Scheduling are two important problems of Smart Grid. We have developed a a robust statistical approach to distributed power system state estimation (DPSSE) under bad data based on iterative reweight least squares (IRWLS) method and an improved alternating direction method of multipliers (ADMM) framework. It is more robust to adverse outliers during power system state estimation. Moreover, it supports recursive monitoring of measurement devices and inpainting of missing data
Gene Microarray Analysis for AI-assisted Healthcare
Cancer is a leading cause of death worldwide and is often hard to detect in early stages. It is important to devise noninvasive biomarker which can provide conclusive diagnosis of early detection. We have developed novel consensus gene selection criteria for partial least squares-based gene microarray analysis. It facilitates the preliminary identification of meaningful pathways and genes for a specific disease.
AI assisted Sleep Diagnosis for Health Monitoring
Sleep disorders are widespread health problems that reduce quality of life, increase risks for psychiatric and medical disease and raise health care utilization and costs among affected individuals worldwide. An electroencephalogram (EEG) is a recording of brain activity and it is one of the key measures on evaluating the quality of sleep of a patient. We are working on a EEG-based deep neural network based automated sleep testing method and it has the potential to streamline day-to-day operations and therefore optimize direct patient care by the healthcare professionals.
Estimation of Brain connectivity and Gene interactions
The reconstruction of brain connectivites and gene interactions help to improve the understanding of underlying brian mechanisms and celluar processes. Many important biological phenomena are attributed to these correlated brian connectivities and gene expressions. The identification of these interactions, some of which carry signatures to clinical relevant physiological effects, sheds light on the development of various clinical applications.
