Machine Learning & Safety Analytics Lab

The majority of my research is focused on how to improve safety outcomes in occupational incidents and injuries. To that end, I use analytical approaches such as machine learning and deep learning models to understand patterns of occupational patterns in industrial environment. I also study the applications of supportive assistive exoskeletons and wearable sensors for ergonomics risk assessment, injury analytics and prevention, biomechanics exertions, and psychomotor analytics in occupational tasks. The results of this ongoing research has been published in various journals such as Safety Science, Applied Sciences, Safety, International Journal of Environmental Research and Public Health, and conferences such as North American Manufacturing Research Conference, International Conference on Applied Human Factors and Ergonomics, International Conference on Intelligent Human Systems Integration, and Annual Conference of Association of Technology Management & Applied Engineering. 

I have also given an invited talk on "Predicting patterns of severe injuries in agribusiness industries using latent class analysis and neural networks'' in the Business Analytics Symposium, organized by Iowa State University, in  Des Moines, Iowa,  in April 2019.

A crucial part of condition monitoring and predictive maintenance in industrial systems depends on preventing machine failure that lead to accidents, downtime and production failure. Therefore, using fast and efficient analytical approaches that contribute to planning for maintenance and condition monitoring is significant for improving quality and reliability of industrial systems. In this line of research, I work on intelligent fault diagnosis methods using vibration signal analysis and machine learning/deep learning models for fault detection of bearing in induction motors. This has several challenges. First, a combination of various data preprocessing methods is required for preparing vibration time-series data as input for training machine learning models. In addition, there is no specific number(s) of features or one methodology for data transformation that guarantee reliable fault diagnosis results. This research addresses the challenges through various methodologies. The results of this ongoing research has been published in various conferences such as International Conference on Advanced Production Management and Process Control, Future of Information and Communication Conference, International Conference on Intelligent Human Systems Integration, and Annual Conference of Association of Technology Management & Applied Engineering. 

I have also been invited as a panelist in the "Hidden Challenges in Industry-Academia Collaboration'' panel, organized as the NSF Industry-Academia Collaboration in Advanced Manufacturing Workshop in MSEC2022 annual conference in Purdue University in June 2022.

This collaborative research (with Aerospace Engineering) focuses on the use of machine learning and deep learning models to create surrogate models in various applications including finite element analysis. The results of this ongoing research has been published in journals such as Sensors, and conferences such as AIAA SciTech Forums and International Workshop for Structural Health Monitoring. I have also given an invited talk on "Applied Machine Learning in Improving Industrial Systems'' for a Research Seminar course in the Department of Aerospace Engineering & Mechanics, University of Minnesota in December 2022.

• Developing Latent Demand Methodology for Optimized Location Selection of Active Transportation Facilities (Research Consultant; $108,000 funded for 8/20/2023 to 12/31/2024)

• SCU Undergraduate Research Grant (PI; $2,000 funded for Spring 2024)

• School of Engineering's 2024 Kuehler Undergraduate Research Program  (Co-I; $8,475 funded for Summer 2024)

• Assessing the Impact of AI and Assistive Technologies on Entrepreneurial Growth and Workforce Inclusion in Manufacturing (PI; $19,917 funded for 7/20/2024 to 12/31/2025 by Ciocca Center for Innovation & Entrepreneurship)

• Deep Learning for Process Monitoring in Semiconductor Manufacturing (Co-PI; $163,000 funded for 9/01/2022 to 12/31/2023)

• Evaluation Plan Development for DMV (Co-PI; $50,000 funded for 12/20/2021 to 5/31/2022)

• Machine Learning in Autonomous Systems (Co-PI; $100,000 funded for 1/1/2020 to 5/31/2022)

• Machine Learning for Quality Improvement in Industrial Operations (PI; $180,000 funded for 8/01/2020 to 6/31/2022)

• Machine Learning for PID Controller Optimization (PI; $100,000 funded for 8/01/2020 to 6/31/2022)

• Hybrid Machine Learning Models for Transportation Safety Enhancement (PI; $75,000 funded for 5/15/2020 to 7/31/2021)