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 this DOI link for presentation slides    DOI: 10.13140/RG.2.2.24336.51200
[1] H. Yang, Y. Chen, and F. M. Leonelli, “Whole heart modeling – spatiotemporal dynamics of electrical wave conduction and propagation,” Proceedings of 2016 IEEE Engineering in Medicine and Biology Society Conference (EMBC), August 16-20, 2016, Orlando, FL, United States. DOI: https://doi.org/10.1109/10.1109/EMBC.2016.7591990
[2] Y. Chen, and H. Yang, “Numerical simulation and pattern characterization of spatiotemporal dynamics on fractal surfaces for the whole-heart modeling applications,” European Physical Journal, 2016. DOI: https://doi.org/10.1140/epjb/e2016-60960-6
[3] B. Yao, R. Zhu, and H. Yang, “Characterizing the Location and Extent of Myocardial Infarctions with Inverse ECG Modeling and Spatiotemporal Regularization,” IEEE Journal of Biomedical and Health Informatics, page 1-11, 2017, DOI:https://doi.org/10.1109/JBHI.2017.2768534
[4] B. Yao and H. Yang, “Physics-driven spatiotemporal regularization for high-dimensional predictive modeling,” Nature - Scientific Reports 6, 39012, 2016. DOI: https://www.nature.com/articles/srep39012

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. 

Please click this DOI link for presentation slides    DOI: 10.13140/RG.2.2.17625.62566

Abstract: Industry in the 21^st 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.

Please click this DOI link for presentation slides    DOI: 10.13140/RG.2.2.14873.11362

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.

Please click this DOI link for presentation slides     DOI:10.13140/RG.2.2.10914.73920
[1] B. Yao, and H. Yang, “Spatiotemporal Regularization for Inverse ECG Modeling,” IISE Transactions Health Systems Engineering, 2020. DOI: https://doi.org/10.1080/24725579.2020.1823531
[2] B. Yao, R. Zhu, and H. Yang, “Characterizing the Location and Extent of Myocardial Infarctions with Inverse ECG Modeling and Spatiotemporal Regularization,” IEEE Journal of Biomedical and Health Informatics, page 1-11, 2017, DOI: https://doi.org/10.1109/JBHI.2017.2768534
[3] B. Yao and H. Yang, “Physics-driven spatiotemporal regularization for high-dimensional predictive modeling,” Nature - Scientific Reports 6, 39012, 2016. DOI: https://www.nature.com/articles/srep39012
[4] B, Yao and H. Yang, “Mesh Resolution Impacts the Accuracy of Inverse and Forward ECG problems,” Proceedings of 2016 IEEE Engineering in Medicine and Biology Society Conference (EMBC), August 16-20, 2016, Orlando, FL, United States. DOI: https://doi.org/10.1109/EMBC.2016.7591615

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.

Please click this DOI link for presentation slides    DOI: 10.13140/RG.2.2.17946.75205

Invited keynote talk in the NERCCS 2018: The First Northeast Regional Conference on Complex Systems, April 11-14, 2018
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 sensor-based nonlinear dynamical methodologies for real-time system informatics, monitoring, and control. Specifically, the developed methodologies will be demonstrated in both advanced manufacturing and smart health applications. The proposed methodology is generally applicable to a variety of complex systems exhibiting nonlinear dynamics, e.g., additive manufacturing, cardiovascular systems, precision machining, sleep apnea, biomanufacturing. In the end, future research directions will be discussed.

Abstract: Wireless sensor network has emerged as a key technology for monitoring space-time dynamics of complex systems, e.g., environmental sensor network, battlefield surveillance network, and body area sensor network. However, sensor failures are not uncommon in traditional sensing systems. As such, we propose the design of stochastic sensor networks to allow a subset of sensors at varying locations within the network to transmit dynamic information intermittently. Realizing the full potential of stochastic sensor network hinges on the development of novel information-processing algorithms to support the design and exploit the uncertain information for decision making. This paper presents a new approach of sparse particle filtering to model spatiotemporal dynamics of big data in the stochastic sensor network. Notably, we developed a sparse kernel-weighted regression model to achieve a parsimonious representation of spatial patterns. Further, the parameters of spatial model are transformed into a reduced-dimension space, and thereby sequentially updated with the recursive Bayesian estimation when new sensor observations are available over time. Therefore, spatial and temporal processes closely interact with each other. Experimental results on real-world data and different scenarios of stochastic sensor networks (i.e., spatially, temporally, and spatiotemporally dynamic networks) demonstrated the effectiveness of sparse particle filtering to support the stochastic design and harness the uncertain information for modeling space-time dynamics of complex systems.
[1] A. Meyers, and H. Yang, “Markov Chains for Fault-Tolerance Modeling of Stochastic Networks,” IEEE Transactions on Automation Science and Engineering, 2021. DOI: https://doi.org/10.1109/TASE.2021.3093035
[2] Y. Chen, and H. Yang, “Sparse modeling and recursive prediction of space-time dynamics in stochastic sensor networks,” IEEE Transactions on Automation Science and Engineering, Vol. 13, No. 1, p. 215-226, 2016, DOI: https://doi.org/10.1109/TASE.2015.2459068
[3] Y. Chen, G. Liu, and H. Yang, “Sparse particle filtering for modeling space-time dynamics in distributed sensor networks,” Proceedings of the 10th Annual IEEE Conference on Automation Science and Engineering (CASE) p. 626-631, August 18-22, 2014, Taipei, Taiwan. DOI: http://dx.doi.org/10.1109/CoASE.2014.6899393

H. Yang, One-day workshop on "Nonlinear Dynamics, Recurrence Analysis, and Complex Networks", Georgia Institute of Technology – IsyE Department, Atlanta, GA, Nov. 9, 2012. The topics are listed as follows:
Part I – Nonlinear dynamical systems and chaos
Part II – Recurrence analysis of complex systems
Part III – Multiscale recurrence analysis
Part IV – Recurrence and complex networks
Matlab Toolboxes
(1) Toolbox of recurrence plot and recurrence quantification analysis
(2) Toolbox of heterogeneous recurrence analysis

Abstract: Additive manufacturing (AM) provides a greater level of flexibility to produce a 3D part with complex geometries directly from the design. However, the widespread application of AM is currently hampered by technical challenges in process repeatability and quality control. To enhance the in-process information visibility, advanced sensing is increasingly invested for real-time AM process monitoring. The proliferation of in-situ sensing data calls for the development of analytical methods for the extraction of features sensitive to layerwise defects, and the exploitation of pertinent knowledge about defects for in-process quality control of AM builds. As a result, there are increasing interests and rapid development of sensor-based models for the characterization and estimation of layerwise defects in the past few years. However, very little has been done to go from sensor-based modeling of defects to the suggestion of in-situ corrective actions for quality control of AM builds. In this talk, we present a new sequential decision-making framework for in-situ control of AM processes through the constrained Markov decision process (CMDP), which jointly considers the conflicting objectives of both total cost (i.e., energy or time) and build quality. Experimental results show that the CMDP formulation provides an effective policy for executing corrective actions to repair and counteract incipient defects in AM before completion of the build.
IISE Quality Control and Reliability Engineering (QCRE) Society Webinar, 10/13, 2021

Abstract: Advanced manufacturing is moving towards a new paradigm of ‘low-volume-high-mix’ production. There is an urgent need to develop effective representations of real-world 3D objects and further enable the matching and retrieval of engineering designs. This paper presents a new self-organizing network representation of 3D objects. Each voxel of the 3D object is a node in a network, and the edge is dependent on node closeness in space. Then, the network is self-organized by balancing attractive and repulsive forces between the nodes. Experimental results show the effectiveness of network representation by reassembling the geometry of 3D objects.

Hui Yang, Runsang Liu, Soundar Kumara, “Self-organizing network modelling of 3D objects,” CIRP Annals, 2020. DOI: https://doi.org/10.1016/j.cirp.2020.04.099

Abstract: Physics-based principles (e.g., heat transfer, bioelectromagnetism theorems) generally help predict complex dynamics in manufacturing and healthcare systems. For example, mechanical engineers leverage infrared cameras and heat-transfer physics to predict thermal distribution within 3D builds in additive manufacturing. Medical scientists use bioelectromagnetism physics to predict heart-surface electric potentials and investigate cardiac pathological activities (e.g., tissue damages in the heart). However, physics-based principles do not account for real-world uncertainties, thereby often generating predictions that have discrepancies from sensor observations. Such uncertainties may be introduced by simplified physical assumptions, geometric variations, measurement noises, and other extraneous factors. 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.

Please click this DOI link for presentation slides     DOI: 10.13140/RG.2.2.10914.73920
B. Yao, and H. Yang, “Spatiotemporal Regularization for Inverse ECG Modeling,” IISE Transactions Health Systems Engineering, 2020. DOI: https://doi.org/10.1080/24725579.2020.1823531
B. Yao, R. Zhu, and H. Yang, “Characterizing the Location and Extent of Myocardial Infarctions with Inverse ECG Modeling and Spatiotemporal Regularization,” IEEE Journal of Biomedical and Health Informatics, page 1-11, 2017, DOI: https://doi.org/10.1109/JBHI.2017.2768534
B. Yao and H. Yang, “Physics-driven spatiotemporal regularization for high-dimensional predictive modeling,” Nature - Scientific Reports 6, 39012, 2016. DOI: https://www.nature.com/articles/srep39012
B, Yao and H. Yang, “Mesh Resolution Impacts the Accuracy of Inverse and Forward ECG problems,” Proceedings of 2016 IEEE Engineering in Medicine and Biology Society Conference (EMBC), August 16-20, 2016, Orlando, FL, United States. DOI: https://doi.org/10.1109/EMBC.2016.7591615

Penn State College of Medicine Researach Quality Assurance Seminar
Abstract: The Internet of Things (IoT) has propelled the evolution of medical sensing technologies to greater heights. Thus, traditional health systems have been transformed into new data-rich environments. This provides an unprecedented opportunity to develop new analytical methods and tools towards a new paradigm of digital medicine. However, big data arising from healthcare system also pose a significant challenge for efficient and effective sensor-based information processing and medical decision making. In this talk, we will present novel methods and tools about in-silico modeling, experiments and analytics for medical discoveries and healthcare innovations. Specifically, we will demonstrate digital health networks, biophysics-driven models, sensor-based models, statistical models, as well as optimization models to improve the understanding of disease-altered physiological dynamics. Further, treatment plans can be optimized, and life-saving interventions can be delivered in a timely manner. Finally, new pharmaceutical approaches can be designed by imposing genetical and molecular changes that counterbalance the dysfunction due to disease progressions. The new generation of digital medicine is strongly promised to improve the health of our society in the US and in the world.

The Industrial Internet of Things (IIoT) has revolutionized the way manufacturers across the country are using data and thinking about their operations. But, as the connectivity grows, so does the risk for cyber attacks. How can cloud computing and AI help keep that data secure? Join MxD, University of West Florida, and Penn State University on February 25 as we discuss current research in the space. Attendees will have the opportunity to ask questions and engage with the speakers about their current efforts!

Abstract: Automated optical inspection (AOI) is increasingly advocated for in situ quality monitoring of additive manufacturing (AM) processes. The availability of layerwise imaging data improves the information visibility during fabrication processes and is thus conducive to performing online certification. However, few, if any, have investigated the high-speed contact image sensors (CIS) (i.e., originally developed for document scanners and multifunction printers) for AM quality monitoring. In addition, layerwise images show complex patterns and often contain hidden information that cannot be revealed in a single scale. A new and alternative approach will be to analyze these intrinsic patterns with multiscale lenses. Therefore, the objective of this talk is to design and develop an AOI system with contact image sensors for multiresolution quality inspection of layerwise builds in additive manufacturing. First, we retrofit the AOI system with contact image sensors in industrially relevant 95 mm/s scanning speed to a laser-powder-bed-fusion (LPBF) machines. Then, we design the experiments to fabricate nine parts under a variety of factor levels (e.g., gas flow blockage, re-coater damage, laser power changes). In each layer, the AOI system collects imaging data of both recoating powder beds before the laser fusion and surface finishes after the laser fusion. Second, layerwise images are pre-preprocessed for alignment, registration, and identification of regions of interests (ROIs) of these nine parts. Then, we leverage the wavelet transformation to analyze ROI images in multiple scales and further extract salient features that are sensitive to process variations, instead of extraneous noises. Third, we perform the paired comparison analysis to investigate how different levels of factors influence the distribution of wavelet features. Finally, these features are shown to be effective in predicting the extent of defects in the computed tomography (CT) data of layerwise AM builds. The proposed framework of multiresolution quality inspection is evaluated and validated using real-world AM imaging data. Experimental results demonstrated the effectiveness of the proposed AOI system with contact image sensors for online quality inspection of layerwise builds in AM processes.

Yang, H., Reijonen, J., and Revuelta, A. (June 7, 2023). "Multiresolution Quality Inspection of Layerwise Builds for Metal 3D Printer and Scanner." ASME Journal of Manufacturing Science and Engineering. October 2023; 145(10): 101004. DOI: https://doi.org/10.1115/1.4057013

Abstract: Modern industry is investing in new digital technologies, such as Internet of Things (IoT), advanced sensing and computing, to propel quality innovations in products and services. Real-time flow of sensing data gives rise to data-rich environments and an unprecedented opportunity to realize a new generation of digital twin (DT) in cyberspace. In a digital twin, physical dynamics are reflected in cyberspace through advanced sensing, information processing, and computer modeling. In the feedback loop, analytics in cyberspace (e.g., artificial intelligence and machine learning) exploits the acquired knowledge and useful information from sensing data for optimal actions to the physical world. This webinar will present our continuous research efforts on the “sensing-modeling-optimization” framework to build new cyber-physical digital twins in disparate disciplines of manufacturing and healthcare. Specifically, I will talk about recent research studies in joint work with my current and former PhD students (Alexander Krall, Hankang Lee and Bing Yao), including (1) sensor DT for statistical quality control (IISE Transactions)
https://doi.org/10.1080/24725854.2022.2148779
(2) factory DT for process optimization (ASME Journal of Manufacturing Science and Engineering)
http://dx.doi.org/10.1115/1.4063234
(3) heart DT for smart health (Springer Book on “Sensing, Modeling and Optimization of Cardiac Systems)
https://link.springer.com/book/9783031359514
The next generation of digital twin is strongly promised to innovate quality engineering, manufacturing processes, and healthcare services. At the end of this talk, future research directions will be discussed.

Abstract: The emergence of nonlinear and nonstationary dynamics is common when multiple entities collaborate, compete, or interfere in manufacturing and service operations. Operational management calls upon effective monitoring, modeling and control of in-process nonlinear dynamics. This, in turn, can result in significant economic and societal benefits. Nevertheless, traditional reductionist approaches often fall short in comprehending nonlinear dynamical systems. Also, the theory of nonlinear dynamics is mainly studied in mathematics and physics. A critical gap remains in the knowledge base that pertains to integrating nonlinear dynamics research with operations engineering. The need to leverage nonlinear dynamics has become increasingly urgent for the development of high-quality products and services. This tutorial presents a review of nonlinear dynamics methods and tools for real-time system informatics, monitoring and control. Specifically, we discuss the characterization and modeling of recurrence dynamics, network dynamics, and self-organizing dynamics hidden in operational data for process improvement. Further, we contextualize the theory of nonlinear dynamics with real-world case studies and discuss future opportunities to improve the monitoring and control of manufacturing and service operations. We posit this work will help catalyze more in-depth investigations and multi-disciplinary research efforts at the intersection of nonlinear dynamics and data mining for operational excellence.

H. Yang, "Mining Nonlinear Dynamics in Operational Data for Process Improvement." INFORMS TutORials in Operations Research, 109-132, 2023, 101004. DOI: https://doi.org/10.1287/educ.2023.0261

Abstract: Industry 4.0 drives exponential growth in the amount of operational data collected in factories. These data are commonly distributed and stored in different business units or cooperative companies. Such data-rich environments increase the likelihood of cyber attacks, privacy breaches, and security violations. Also, this poses significant challenges on developing machine learning models on sensitive data that are distributed among different business units. To fill this gap, this paper presents a novel privacy-preserving framework to enable federated learning on siloed and encrypted data for smart manufacturing. Specifically, we leverage fully homomorphic encryption (FHE) to allow for computation on ciphertexts and generate encrypted results which, when decrypted, match the results of mathematical operations performed on the plaintexts. Multi-layer encryption and privacy protection reduce the likelihood of data breaches while maintaining the prediction performance of machine learning models. Experimental results in real-world case studies show that the proposed framework yields superior performance to reduce the risk of cyber attacks and harness siloed data for smart manufacturing.

Kuo, T., and Yang, H. (May 31, 2024). "Federated Learning on Distributed and Encrypted Data for Smart Manufacturing." ASME Journal of Computing and Information Science in Engineering, 24(7): 071007. DOI: https://doi.org/10.1115/1.4065571