Shouyi Wang received the B.S. degree in control science and engineering from Harbin Institute of Technology, Harbin, China, in 2003 and the M.S. degree in systems and control engineering from Delft University of Technology, Delft, the Netherlands, in 2005 and the Ph.D. degree in Industrial and Systems Engineering from Rutgers University, Piscataway, NJ in 2012. From 2011-2013, he was a research scientist in the Department of Industrial and Systems Engineering and the Integrated Brain Imaging Center at School of Medicine, University of Washington, Seattle. Currently, he is an Assistant Professor of Industrial and Manufacturing Systems Engineering at University of Texas at Arlington, Arlington, TX. His current research interests include big data analytics, data mining, machine learning, pervasive computing, healthcare/medical decision-making systems, multivariate time-series modeling and forecasting, real-time monitoring and early warning systems.
CBS News Reported our Brain Computer Interface and Emotion Management Research Project
PET/CT provides a valuable tool for defining target tumour volumes and assessing therapy response. Its quantitative accuracy, however, is limited by respiratory-induced tumour motion. While respiratory gating can help compensate for such motion, its effectiveness varies greatly between individual patients. But could information from a patient's breathing trace help predict whether they could benefit from gated PET/CT?
A UT Arlington assistant engineering professor has developed a computational model that can more accurately predict when an epileptic seizure will occur next based on the patient's personalized medical information.
I am interested in interdisciplinary research that is critical to address many complex real-world problems. In my research activity, I have been actively collaborating with researchers and scientists in the areas of data mining, machine learning, operations research, statistics, bioinformatics, medical imaging, and neuroscience. I have a great interest to develop innovative theoretical and technical solutions for complex data and engineering problems. My current active research areas are:
1. Theoretical and Methodology Research for Biomedical Data Mining Problems with Big Data Sets. Research areas include data representation, feature extraction, feature selection, classification, optimization, pattern recognition, and adaptive online learning algorithms.
2. Intelligent Online Monitoring, Event Detection, and Early Warning/Prediction Systems. Applications include personalized epileptic seizure prediction, early diagnosis of brain diseases, and abnormality detection from any interested biomedical time series data.
3 EEG-based Brain-Computer Interface and Human-Machine Systems. Research areas include mental state detection in real driving environment, EEG-based information retrieval system during web searching, and reliable signal processing systems for EEG-based human-machine communication.
4 Diagnostic Imaging Analysis and Applications. Research areas include respiratory motion pattern analysis to achieve personalized PET/CT Scan for different patient groups, and pattern recognition of cognitive activities using functional MRI (fMRI).
5 Personalized Healthcare System with Wearable Body Sensor Networks. Now it is possible to apply mobile monitoring devices to each individual patient and provide personalized diagnostic, medical and treatment plans. I am greatly interested to develop effective information systems for multi-sensory data fusion, and personalized monitoring and feedback healthcare information systems based on tracking time series data.
Talk at The 30th AAAI Conference on Artificial Intelligence (AAAI 2016)
Invited Talk at The 3rd International Workshop on Persistent and Photostimulable Phosphors (PPP2015)
Demonstration at International Conference for High Performance Computing, Networking, Storage and Analysis (SC15)
Talk at The 5th International Workshop on Pattern Recognition in Neuroimaging (PRNI 2015)
Talk at Annual Meeting of Cognitive Neuroscience Society (CNS)
Talk at The Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI 2015)
Invited Talk and Session Chair at INFORMS 2014
Talk at Brain KDD 2014.
Invited Talk at UTA CSE Colloquiums, Arlington, TX.
Enhancing Clinical Utility of Respiratory-gated PET/CT Imaging using Patient Classification
A respiratory-gated (RG) method allows patients with lung tumors to breathe normally in PET/CT scan while minimizing respiratory motion effects. However, not all patients can benefit from the RG method. We constructed a prediction model to predict the effectiveness of the RG method on each individual patient only using features extracted from respiratory motion traces. The technique can be used to classify patient groups and assign the most appropriate strategy for each patient in PET/CT scan.
A Probabilistic Prediction Framework for Personalized Online Prediction of Epileptic Seizures,
INFORMS, Phoenix, AZ, October 2012.
Online Monitoring and Prediction of Complex Time Series Events. Phoenix, AZ, USA, Oct 2012.
An Efficient Approach for Automated Online Segmentation of Time Series, International INFORMS, Beijing, China, June 2012.
A Gradient-Based Adaptive Learning Framework for an Online Seizure Prediction, INFORMS, Charlotte, NC, November 2011.
A Novel Reinforcement Learning Framework for Online Adaptive Seizure Prediction, IEEE International Conference on Bioinformatics & Biomedicine, Hong Kong, December 2010.
Patients with lung tumors generally cannot bear a breath-holding process in PET/CAT Scan. They have to breathe normally during a scan and an expensive way has to be applied to process the PET/CT imaging. To minimize respiratory motion artifacts an efficient quiescent period gating (QPG) method was developed at UW medical center to extract PET/CT data from the end-expiration quiescent period. However, it has been found that some portion of subjects cannot benefit from the QPG method. In this project, we studied the respiratory pattern effects on the PET/CT imaging quality, made extensive statistical pattern analysis and multivariate regression analysis, and finally constructed an important clinical recommendation system to discriminate the benefit and non-benefit subjects for the QPG scan approach. The paper on this work has been submitted to Physics in Medicine and Biology in June 2013.
This research is to develop new mathematical models to predict events from nonstationary multivariate time series data. Time series data accounts for a large fraction of the world’s supply of data, and have very broad applications in engineering, economy, industrial manufactory, finance, management and many other fields. However, most of the current time series methods make an assumption of stationarity. They are unable to identify complex temporal patterns from nonstationary time series that are nonperiodic, nonlinear, irregular, and chaotic. Thus this research is motivated to develop new efficient approaches to analyze nonstationary time series patterns and predict critical events. Three original and fundamental contributions have been made in the research.
1. A novel piecewise-linear approximation algorithm for time series data using a data-driven decomposition strategy. The algorithm is capable of obtaining a piecewise-linear model for any arbitrary time series (stationary or nonstationary) efficiently and robustly at a very low computational cost. This work has been submitted to Pattern Recognition Letters.
2. An efficient online monitoring and segmentation framework for time series temporal patterns. The algorithm is an extension of the piecewise-linear approximation algorithm. It is capable of processing and segmentation of online time series streams in time O(1) using a set of closed-form mathematical formulas.
3. An adaptive learning framework for online pattern discovery and event prediction in multivariate time series data. The framework integrates time series segmentation, temporal pattern extraction, adaptive learning, and probability theory into an online pattern discovery and prediction system. This is a general pattern discovery framework, and has been evaluated on two challenging EEG prediction problems: epileptic seizure prediction and mental-state prediction. The proposed approach generated the most promising prediction results in both problems compared the current existing approaches.
The link between mental states/cognitive activities and brainwave recordings is of paramount importance with practical scientific and clinical implications. However, EEG-based brainwave patterns are extremely difficult to decode due to the nonstationary and chaotic properties. We conducted three related research projects on this problem category. In the first project, we successfully developed a data-mining framework to analyze EEG patterns and identify the mental state prior to erroneous keystrokes during a human typing experiment in critical tasks. This work has been published in IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans. In the second project, an adaptive pattern-learning framework was constructed to detect the mental states from drivers in a simulated driving environment. This work is to be submitted to IEEE Transactions on Intelligent Transportation Systems in Aug. 2013. The third project is a Google-funded project. We constructed an information retrieval system to identify cognitive and memory workload in different levels of task engagement using an EEG-based brain-computer interface.
Due to the great inter-individual variability, there has been a desperate need for personalized seizure prediction for patients with epilepsy using Electroencephalogram (EEG) recordings. However, it has been an unsolved challenging problem for long since it is extremely difficult to capture predictive patterns for each individual from chaotic multi-channel EEG time series. I made an important methodology breakthrough in this area by constructing an online adaptive pattern-learning framework. The proposed new approach combines feature extraction, feature selection, pattern modeling and identification, adaptive online learning, and feedback control theory to achieve personalized pattern learning and prediction. This study is among the pioneer studies to investigate adaptive learning mechanisms for epileptic seizure prediction, and has achieved very promising prediction performance on 10 patients with epilepsy. This work has been accepted for publication in IEEE Transactions on Knowledge and Data Engineering. This work also won the Finalist of INFORMS 2012 Data Mining Best Student Paper Award
Organization Committee, the International Conference on Brain Informatics & Health (BIH), Omaha, NE, 2016.
International Workshop on Big Data Neuroimaging Analytics for Brain and Mental Health, Omaha, NE, 2016.
Editor for the new Data Mining Book “Data Analytics - Models and Applications in Matlab” by Springer, planned book publication in 2017.
Guest Editor, Annals of Operations Research, Special Volume: Applied Optimization and Data Mining: Theory and Applications (2014 – Present), to be published in 2016.
Industrial and Manufacturing Systems Engineering Research Committee, The University of Texas at Arlington. 2013–present
Faculty of the Center On Stochastic Modeling, Optimization, & Statistics (COSMOS). 2013-present