Jinghao Yang
he/him/his
Assistant Professor
Electrical and Computer Engineering
The University of Texas Rio Grande Valleyu
Biography
Dr. Jinghao Yang earned his Ph.D. in Electrical Engineering from Texas A&M University in 2022, following a Ph.D. in Mechatronics Engineering from Dalian University of Technology in 2018. His academic journey began with a B.S. in Mechanical Manufacturing and Automation from Northeastern University in 2012. Currently, he holds the position of Assistant Professor in UTRGV. Before joining the university, he was a Senior Vision Systems Engineer at Tesla, Inc. His research is primarily focused on the development of precision, intelligent, and flexible multi-scale sensors leveraging computer vision and AI, as well as real-time, non-destructive, and label-free multifunctional measuring and sensing technologies for onsite and remote monitoring and controlling. Dr. Yang published articles in the journals of optics, sensing, and instrument area, such as Optics Express and IEEE Sensors Journal, as well as in Sensors and Actuators A: Physical. He also holds over 20 Chinese patents.
Degrees Earned
Ph.D., Electrical Engineering, 2021 Ph.D., Mechatronics Engineering, 2018 BS, Mechanical Manufacturing and Automation, 2012
Research Areas
Computer Science; Engineering; Machine Learning/AI
Research Interests
My research focuses on AI-enhanced Intelligent Machine Vision and Smart Sensing technology. I am particularly interested in developing the smart multi-modal sensing system for various applications. In my previous work, I have investigated the utilization of AI and computer vision for sensing in harsh environments, which has led to several prototypes of smart monitoring instruments. My current research explores the embedded intelligence and AI-enhanced sensing and monitoring in manufacturing operations and health care. I am passionate about this work because this can provide essential insight and data, serving as the foundation for a sustained research program at the intersection of AI, machine vision, and instruments, leading to robust and efficient operations in different applications. In my future career, I aim to focus on AI-enhanced multi-scale sensing, Digital Twin-enhanced IoT, and LLM-driven monitoring and control.
Topical Areas
Artificial Intelligence and Intelligent Systems; Infrastructure and Instrumentation; Mechanical Engineering
Research Synergy
My research in AI-enhanced machine vision and smart sensing provides a strong foundation for synergistic collaboration across all four of my selected topical areas: Artificial Intelligence and Intelligent Systems, Electrical, Electronic, and Information Engineering, Infrastructure and Instrumentation, and Mechanical Engineering. My work is fundamentally enabling, designed to create intelligent instruments and data streams that can intersect with and enhance a wide variety of advanced research projects, such as those available through the NAIRR Pilot. A particularly strong synergy exists with the Artificial Intelligence and Intelligent Systems project, "Self-Supervised Segmentation and Physics-Guided Diffusion Synthesis Using Vision Transformers for Quality Control in Laser Additive Manufacturing"(NAIRR250183). This work aims to advance autonomous quality control in additive manufacturing by leveraging recent breakthroughs in transformer-based computer vision and generative AI, and my expertise in developing multi-modal sensing systems could introduce a novel dimension to their work. For example, my team and I could collaborate to integrate hyperspectral sensing with their existing imaging, creating a richer dataset that allows AI models to detect defects that are invisible to traditional sensing method. This directly combines my interest in smart monitoring instruments with their AI-driven additive manufacturing discovery, creating a clear link between the Infrastructure and Instrumentation and AI fields. In Mechanical Engineering, my research directly complement the project on "Foundation Models for Advanced Cybermanufacturing" (NAIRR240376). While the G-Forge project operates in the cybermanufacturing domain by analyzing G-Code, my work provides the essential physical part for monitoring the real-world outcomes of that code. A collaboration could create a powerful cyber-physical feedback loop, where my vision and sensing systems provide the real-time process data and quality inspection results needed to validate and train G-Forge's AI models. This synergy of connecting code to physical consequences would directly accelerate the development of G-Forge's advanced diagnostic and debugging capabilities. My research acts as a technological bridge, capable of providing the essential data and intelligent insights needed to accelerate progress in various fields. My goal within the Sustainable Research Pathway is to leverage my expertise in smart sensing to build these bridges, creating beneficial collaborations and providing my students with an invaluable, cross-disciplinary research experience.
Motivation
The Sustainable Research Pathway 2025 is particularly attractive to me because it emphasizes collaboration and mentorship. Based on my previous experience, it is difficult to solve complex AI problems individually. While my institution has a growing AI program, it lacks the expertise available through the NAIRR network. I believe Sustainable Research Pathway 2025 will be a supportive and collaborative community that is essential for making meaningful progress on these challenges. For my two PhD students, this is an essential opportunity for them to contribute to a national-level project, and I am eager to connect them with other researchers through Sustainable Research Pathway 2025. Participating Sustainable Research Pathway 2025 will help me collect preliminary data and establish long-term collaborations for future research and grant proposal development. I am confident that the resources, mentorship, and collaborations offered through this pathway will be a significant help for my career and future research, which will help me to grow as both a researcher and a mentor. Moreover, I am excited to contribute my own experience to this research ecosystem in the future.
Supervising Students Plan
My plan for supervising my student team is based on structured mentorship, clear communication, and professional development. Before the summer program begins, we will hold several meetings to align the students' learning objectives with the target project. We will identify the necessary technical skills for the target project and establish expectations for teamwork and communication, preparing the whole team for the program's first day. Throughout the 10-week onsite summer experience, my mentorship will be hands-on and structured. We will have a daily conclusion to record progress and address immediate issues. Additionally, we will hold a weekly group meeting to review progress, discuss relevant literature, and plan for the upcoming week. A key component of my mentorship is to encourage students to take ownership of their research, solve problems independently, and propose their own research ideas. Besides the research, I will also spend time on their professional development, helping them establish their network, refine their presentation skills, and explore future career directions. After the 10-week program, I will work with my team to share the preliminary results by preparing a conference paper and presenting our findings. As their PhD supervisor at UTRGV, I will continue to provide academic and career advice, write letters of recommendation if needed, and support the students' success in their future research and careers.
Student Merit
I have selected Martha Asare, a second-year PhD student in my research group, for this team. Since she began her PhD program in Fall 2024, Martha has shown a strong ability in developing smart machine vision algorithms for AI-enhanced Quality Assessment for Manufacturing. She is well prepared for this program, with a strong knowledge of CNN and Transformer-based AI models, which she recently applied to develop a novel defect detection system for Additive Manufacturing in my lab. I am confident that the collaborative and hands-on environment of the Sustainable Research Pathway is a good chance for her to apply her knowledge to a large-scale project and grow into an independent researcher. The second member of my team is Zhugang Liu, a first-year PhD student who has already become a key member of my lab. Working on our intelligent robot project together, Zhugang has shown significant growth and leadership in solving a challenging problem involving robot-enabled Quality Assessment for Additive Manufacturing. He is proficient in the Vision-Language Model and robot control and has an analytical mindset essential for complex AI research. I chose Zhugang for this opportunity because of his passion for applying his research to national-level challenges. This program aligns with his career goal to become a faculty member after graduation, and I believe this will be a valuable experience in shaping his future research career. Together, Martha's deep AI model knowledge and Zhugang's robotics skills will form a skilled and highly motivated faculty-student team, ready to make contributions to the Sustainable Research Pathway 2025 program.
Lightning Talk Title
Towards Smart Manufacturing: Real-Time Intelligent Sensing in Additive Manufacturing
Keywords
Smart Manufacturing, AI, Digital Twin, Computer Vision, Intelligent Autonomous Sensing System