Computer science research and education have become increasingly data-intensive as a result of the proliferation of digital technologies. Novel computational tools of mining and analyzing large-scale data are capable of revealing new knowledge and fundamental insights in many science and engineering domains. Our main goal is to conduct both theoretical and practical research in the areas of pattern recognition, data mining, and multimedia analysis, with a special focus on biomedical imaging. More specifically, our recent theoretical work mainly lies in the areas of
(Heterogeneous) Data clustering
Advanced statistical learning such as semi-supervised learning, multiple-instance learning and decision tree inductions
Human computer interactions
We have successfully applied the theoretical results to many real-world applications, including multimedia content analysis, knowledge discovery from visual patterns in financial data, and medical imaging informatics. A major characteristic of our research at WSU is its multidisciplinary nature. By cross-fertilizing ideas and rapid, seamless transition of basic research findings to practical applications, multidisciplinary projects build the foundation for highly innovative research. We have established strong, well-integrated collaborations with faculty not only within Department of Computer Science, but also at School of Medicine and College of Engineering. The long-term collaboration has already produced many joint publications, research grants, and co-advising of graduate students. Moreover, We have also partnered with major hospitals in Metro Detroit area such as the Harper University Hospital, the Children's Hospital of Michigan, and the Henry Ford Hospital, to produce high quality research results with potential benefits to a large population.
Our research results have been published in premium computer science journals including IEEE Transactions on Computers, IEEE Transactions on Neural Networks, IEEE Transactions on Fuzzy Systems, and ACM Multimedia Systems Journal. In addition, our collaborative research has also produced articles in tier-1 journals in fields other than computer science, such as Journal of Magnetic Resonance Imaging in biomedical imaging and Financial Analyst Journal in finance. We have published over 40 conference papers, some of which appeared in rank 1 conferences with high visibility, such as ACM Multimedia (ACM MM) 2007, 2005, IEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2006, IEEE Conference on Data Mining (ICDM) 2006, 2007.
External Research Funding
Our research is multidisciplinary in nature and is continuously supported by Federal and State Governments and Industries. The project, titled “HyperEye: Susceptibility Weighted Imaging-based Informatics Tools for Brain Tumor Studies”, was funded over $800,000 by the 21st Century Jobs Fund, State of Michigan in 2006. The ultimate goal of this project is to automate the knowledge discovery process based on novel imaging technology, specialized image content analysis, and intelligent learning methods. The novel imaging techniques and tumor analysis tools developed in this project will provide rapid and reliable solutions for modeling, quantification, and analysis of brain tumors, and hold great potential for new diagnostic approaches in clinical practice and research. We also have two grants awarded by National Science Foundation (NSF) in 2007 and 2005, respectively. In the project, titled “Integrated Modeling and Learning of Multimodality Data across Subjects for Brain Disorder Study”, we will develop a novel, rigorous framework for integrated modeling and analysis of multimodality neuroimaging data through advanced statistical learning. In the project “Instrument Acquisition for Endangered Languages Research: Development of an Ontology-Based Toolbox”, we have designed and implemented multimedia data management tools to make endangered language data accessible, searchable and interpretable for future generations. I also have grants from Michigan Life Science Corridor and ABP Investments. The total amount of these grants exceeds $5,000,000.
We are actively seeking well-motivated Ph. D. students/Post-docs to work on different projects. The minimum requirements are 1) An MS degree in computer science or related fields, 2) Strong background on Pattern Recognition & 3D Visual data analysis, and 3) Efficient programming skills in C++ and Matlab. Interested person should contact me directly through email.