Research Presentations
Hui Yang
Harold and Inge Marcus Career Associate Professor
The Harold and Inge Marcus Department of
Industrial and Manufacturing Engineering
The Pennsylvania State University, University Park

This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All person copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Physics-driven Spatiotemporal Regularization for High-dimensional Predictive Modeling

Abstract: Rapid advancement of distributed sensing and imaging technology brings the proliferation of high-dimensional spatiotemporal data, i.e., y(s; t) and x(s; t) in manufacturing and healthcare systems. Traditional regression is not generally applicable for predictive modeling in these complex structured systems. For example, infrared cameras are commonly used to capture dynamic thermal images of 3D parts in additive manufacturing. The temperature distribution within parts enables engineers to investigate how process conditions impact the strength, residual stress and microstructures of fabricated products. The ECG sensor network is placed on the body surface to acquire the distribution of electric potentials y(s; t), also named body surface potential mapping (BSPM). Medical scientists call for the estimation of electric potentials x(s; t) on the heart surface from BSPM y(s; t) so as to investigate cardiac pathological activities (e.g., tissue damages in the heart). However, spatiotemporally varying data and complex geometries (e.g., human heart or mechanical parts) defy traditional regression modeling and regularization methods. This talk will present a novel physics-driven spatiotemporal regularization (STRE) method for high-dimensional predictive modeling in complex manufacturing and healthcare systems. This model not only captures the physics-based interrelationship between time-varying explanatory and response variables that are distributed in the space, but also addresses the spatial and temporal regularizations to improve the prediction performance. In the end, we will introduce our lab at Penn State and future research directions will also be discussed.

Click here for presentation slides     DOI: 10.13140/RG.2.2.10914.73920

Sensor-based Modeling and Control of Nonlinear Dynamics in Complex Cardiovascular Systems - Better Heart Beats Through Engineering

Abstract: Industry in the 21st century is investing in a variety of sensor networks and dedicated data centers to increase information visibility. Advanced sensing captures a wealth of information on the condition and status of a product, process or a system. As a result, we are facing spatially and temporally data-rich environments. The next major challenge is in harnessing the big data to bring substantial improvements to the design and operations, particular in quality and integrity assurance, of complex systems. This talk will present an integral approach of physics-based modeling and sensor-based informatics to advance knowledge discovery and innovation in complex systems. First, I will describe a new physical-statistical modeling approach for efficient and effective computer experiments and optimization of cardiac models. Computer modeling and experiments provide physiologists and cardiologists an indispensable tool to characterize and model cardiac functions in health and in disease, as well as to optimize medical decision making. In this study, an easy-to-evaluate surrogate model is developed for faster approximation and calibration of cardiac models to investigate glycosylation-altered kinetics of Na+ ion channels and the causal effects on cardiac cells. Second, I will talk about a new approach of sparse particle filtering for modeling spatiotemporal dynamics of big data in distributed sensor networks. Distributed sensing gives rise to spatially-temporally big data. Realizing the full potentials of distributed sensing calls for space-time data fusion in the dynamically-evolving physical environment. In this study, we developed a sparse particle filtering model to recursively estimate and update latent state variables for predicting nonlinear stochastic dynamics and modeling close interactions between spatial and temporal processes in distributed sensor networks. In the end, future research directions will be discussed.

Click here for presentation slides    DOI: 10.13140/RG.2.2.14873.11362

Mining Dynamic Recurrences in Nonlinear and Nonstationary Systems for Feature Extraction, Process Monitoring and Fault Diagnosis

Abstract: Nonlinear dynamics arise whenever multifarious entities of a system cooperate, compete, or interfere. Effective monitoring and control of nonlinear dynamics will increase system quality and integrity, thereby leading to significant economic and societal impacts. In order to cope with system complexity and increase information visibility, modern industries are investing in a variety of sensor networks and dedicated data centers. Real-time sensing gives rise to “big data”. Realizing the full potential of “big data” for advanced quality control requires fundamentally new methodologies to harness and exploit complexity. This talk will present novel nonlinear methodologies that mine dynamic recurrences from in-process big data for real-time system informatics, monitoring, and control. Recurrence (i.e., approximate repetitions of a certain event) is one of the most common phenomena in natural and engineering systems. For examples, the human heart is near-periodically beating to maintain vital living organs. Stamping machines are cyclically forming sheet metals during production. Process monitoring of dynamic transitions in complex systems (e.g., disease conditions or manufacturing quality) is more concerned about aperiodic recurrences and heterogeneous recurrence variations. However, little has been done to investigate heterogeneous recurrence variations and link with the objectives of process monitoring and anomaly detection. This talk will present the state of art in nonlinear recurrence analysis and a new heterogeneous recurrence methodology for monitoring and control of nonlinear stochastic processes. Specifically, the developed methodologies will be demonstrated in both manufacturing and healthcare applications. The proposed methodology is generally applicable to a variety of complex systems exhibiting nonlinear dynamics, e.g., precision machining, sleep apnea, aging study, nanomanufacturing, biomanufacturing. In the end, future research directions will be discussed. 

Click here for presentation slides    DOI: 10.13140/RG.2.2.17625.62566

Self-organizing Network for Variable Clustering and Predictive Modeling

Abstract: Rapid advancement of sensing and information technology brings the big data, which presents a gold mine of the 21st century to advance knowledge discovery. However, big data also brings significant challenges for data-driven decision making. In particular, it is common that a large number of variables (or predictors, features) underlie the big data. Complex interdependence structures among variables challenge the traditional framework of predictive modeling. This paper presents a new methodology of self-organizing network for variable clustering and predictive modeling. Specifically, we developed a new approach, namely nonlinear coupling analysis to measure nonlinear interdependence structures among variables. Further, all the variables are embedded as nodes in a complex network. Nonlinear-coupling forces move these nodes to derive a self-organizing topology of network. As such, variables are clustered as sub-network communities in the space. Experimental results demonstrated that the proposed method not only outperforms traditional variable clustering algorithms such as hierarchical clustering and oblique principal component analysis, but also effectively identify interdependent structures among variables and further improves the performance of predictive modeling. The proposed new methodology of self-organizing variable clustering is generally applicable for data-driven decision making in many disciplines that involve a large number of highly-redundant variables.

Click here for presentation slides    DOI: 10.13140/RG.2.2.17946.75205

Whole Heart Modeling – Spatiotemporal Dynamics of Electrical Wave Conduction and Propagation

Abstract: Cardiac electrical activities are varying in both space and time. Human heart consists of a fractal network of muscle cells, Purkinje fibers, arteries and veins. Whole-heart modeling of electrical wave conduction and propagation involves a greater level of complexity. Our previous work developed a computer model of the anatomically realistic heart and simulated the electrical conduction with the use of cellular automata and parallel computing. However, simplistic assumptions and rules limit its ability to provide an accurate approximation of real-world dynamics on the complex heart surface, due to sensitive dependence of nonlinear dynamical systems on initial conditions. In this paper, we propose new reaction-diffusion methods and pattern recognition tools to simulate and model spatiotemporal dynamics of electrical wave conduction and propagation on the complex heart surface, which include (i) whole heart model; (ii) 2D isometric graphing of 3D heart geometry; (iii) reaction diffusion modeling of electrical waves in 2D graph, and (iv) spatiotemporal pattern recognition. Experimental results show that the proposed numerical solution has strong potentials to model the space-time dynamics of electrical wave conduction in the whole heart, thereby achieving a better understanding of disease-altered cardiac mechanisms.

Click here for presentation slides    DOI: 10.13140/RG.2.2.24336.51200



Dr. Hui Yang is the Harold and Inge Marcus Career Associate Professor in the Harold and Inge Marcus Department of Industrial and Manufacturing Engineering at The Pennsylvania State University, University Park, PA. Prior to joining Penn State in 2015, he was an Assistant Professor in the Department of Industrial and Management Systems Engineering at the University of South Florida from 2009 to 2015. He is a recipient of 2015 Outstanding Faculty Award at the University of South Florida.

Dr. Yang's research interests focus on sensor-based modeling and analysis of complex systems for process monitoring, process control, system diagnostics, condition prognostics, quality improvement, and performance optimization. His research program is supported by National Science Foundation (including the prestigious NSF CAREER award), Lockheed Martin, NSF Center for e-Design, NSF Center for Healthcare Organization Transformation, and equipment grants from NSF and State of Florida for laboratory computing infrastructure improvement.

Dr. Yang is the president (2017-2018) of IISE Data Analytics and Information Systems Society, the president (2015-2016) of INFORMS Quality, Statistics and Reliability (QSR) society, and the program chair of 2016 Industrial and Systems Engineering Research Conference (ISERC). He is also an associate editor for IISE Transactions, IEEE Journal of Biomedical and Health Informatics (JBHI), IEEE Robotics and Automation Letters (RA-L), Quality Technology and Quality Management, Proceedings of 2018 IEEE Conference on Biomedical and Health Informatics, Proceedings of 2018 IEEE International Conference on Automation Science and Engineering, and Proceedings of 2017 IEEE International Conference on Automation Science and Engineering. He has also co-authored the book Healthcare Analytics: From Data to Knowledge to Healthcare Improvement, John Wiley & Sons, 2016. In addition, he serves as a referee for a diverse set of top tier research journals such as Nature, Physical Review, IEEE Transactions on Biomedical Engineering, IEEE Journal of Biomedical and Health Informatics, Biophysical Journal, IIE Transactions, Technometrics, and IEEE Transactions on Automation Science and Engineering. He is a professional member of IEEE, IEEE EMBS, INFORMS, IIE, ASEE and American Heart Association (AHA).