Research Interest

My research interests lie at the intersection of data science, machine learning, and their applications in the Manufacturing, Energy, and Healthcare domains.

Production systems

Advancements in Online Reinforcement Learning for Industrial Engineering Applications:

• Predictive Maintenance: Leveraging online RL to anticipate equipment failures, reduce downtime, and extend asset life cycles through adaptive learning strategies.

• Dynamic Scheduling: Applying reinforcement learning models to optimize job-shop and flow-shop scheduling in real time, enhancing responsiveness to demand variability and resource constraints.

• Process Optimization: Utilizing online RL to continuously improve manufacturing and service processes, enabling data-driven decision-making and efficiency gains under uncertainty.

Energy generation and consumption

• Develop ML models to optimize energy consumption, predict equipment failures, and forecast both generation and consumption.

• Apply deep reinforcement learning for energy management and adaptive HVAC systems.

• Advance renewable energy integration using data-driven methods.

• Leverage big data analytics to improve the efficiency and sustainability of energy systems.

Healthcare systems

• Predictive Modeling for Chronic Conditions: Build and validate models to anticipate disease progression and adverse events.

• Personalized Care: Develop patient-level risk stratification and treatment recommendation frameworks.

• Transfer Learning: Adapt models across cohorts and institutions to improve accuracy and reduce data requirements.