Embedded Files
Research Area #1
Research Area #1
Battery Management Systems (BMS) for Electric Vehicles (EV)
Battery Management Systems (BMS) for Electric Vehicles (EV)
EV battery packs consist of tens of thousands of cells, requiring continuous monitoring to ensure safety, reliability, and performance. My research focuses on improving battery management systems algorithms, state estimation, and battery characterization methods, bridging theory and practical application.
I am actively engaged in the following areas of BMS research:
Open-Circuit Voltage (OCV) modeling and estimation – Modeling battery voltage for accurate state estimation.
State-of-Health (SOH) modeling and estimation – Understanding battery degradation and predicting lifespan.
State and Parameter Estimation – Algorithms for SOC, SOH, SOP, SOE estimation under realistic conditions.
Thermal Management Systems – Strategies for safe and efficient temperature regulation.
Charging – Efficient, safe, and fast charging methods.
BMS Evaluation – Testing and validating BMS performance in practical scenarios.
These topics represent my current research work as well as future directions where I aim to contribute to safer, more reliable, and high-performance EV battery systems.
Research Area #2
Research Area #2
Driver Monitoring Systems (DMS) for Autonomous Vehicles (AV)
Driver Monitoring Systems (DMS) for Autonomous Vehicles (AV)
In today’s world, a growing number of vehicles are being equipped with advanced driver assistance technologies. These technologies offer varying levels of automation, from basic assistance (level 0) to partial automation (levels 1 and 2), with level 3 automation on the horizon. This means that more cars with different levels of self-driving capability will soon be sharing the roads. Despite these advancements, it remains crucial for human drivers to stay alert and engaged while behind the wheel. Even as vehicles become more autonomous, human oversight is still necessary to ensure safe driving conditions.
Objectives
Objectives
One of the main goals is to produce an automated method for cognitive load assessment that would allow the measures to have a high potential for being implemented and used in real time.
Research Area #3
Research Area #3
Low-Cost System for Identifying Vision Disorders
Low-Cost System for Identifying Vision Disorders
Oculomotor Dysfunctions (OMD) affect up to 30% of the population and are particularly concerning in children, where undiagnosed visual impairments can significantly affect academic performance and cognitive development. Despite this prevalence, accessible and affordable screening tools remain limited.
Objectives
Objectives
My work develops a low-cost, scalable platform called EyeFollow for assessing OMD. It integrates clinically co-designed visual stimuli, modular eye-tracking hardware, and model-based Kalman filtering to provide reliable, quantitative, and clinically interpretable metrics.
Page updated
Google Sites
Report abuse