Associate Professor, Computer Science
Dongxiao Zhu is currently an Associate Professor at Department of Computer Science, Wayne State University. He received the B.S. from Shandong University (1996), the M.S. from Peking University (1999) and the Ph.D. from University of Michigan (2006). Dongxiao Zhu's recent research interests are in Machine Learning and Applications in health informatics, natural language processing, medical imaging, recommender systems, cybersecurity, and other data science domains with emphasis on S & P, adversarial robustness, explainability and fairness. Dr. Zhu is the Director of Wayne AI Research Initiative and the Director of Trustworthy AI Lab at Wayne State University. He has published over 80 peer-reviewed publications and served on program committees (SPC/PC) of flagship AI/Machine Learning conferences (NuerIPS, ICML, AAAI, IJCAI, ACL, EMNLP, AMIA, MICCAI) and of premier biomedical informatics journals (Bioinformatics, Nucleic Acids Research, TCBB, Scientific Reports, BMC Genomics, Plos One and Frontiers in Genetics). Dr. Zhu's research has been supported by NIH, NSF and private agencies and he has served on multiple NIH and NSF grant review panels. Dr. Zhu has advised numerous students at undergraduate, graduate and postdoctoral levels and his teaching interest lies in programming language, data structures and algorithms, machine learning and data science.
Ph.D 2006, University of Michigan, Ann Arbor
C++ Programming; Data Structures; Image Processing; Bioinformatics; Design and Analysis of Algorithms; Data Mining; Machine Learning; Deep Learning
Machine Learning and Applications to Health Informatics, Natural Language Processing, Biomedical Imaging and other Data Science domains.
National Science Foundation (CNS 2043611)
Title: SCC-CIVIC-PG Track A: Leveraging AI-assist Microtransit to Ameliorate Spatiotemporal Mismatch between Housing and Employment.
Total amount: $49,898
PI: Dongxiao Zhu (CS), Co-PI's: Marco Brocanelli (CS), Daniel Grosu (CS), Tierra Bills (CE)
National Institute of Health (R61HD105610)
Title: Severity Predictors Integrating salivary Transcriptomics and proteomics with Multi neural network Intelligence in SARS-CoV2 infection in Children (SPITS MISC)
Budget: 01/01/2021 – 12/31/2022
Total amount: $1,433,469
PI's: Dongxiao Zhu (WSU), Usha Sethuraman (Michigan Children Hospital, contact) and Steve Hicks (Penn State Medicine)
Henry Ford Health Science Center
Titile: Uncertainty in Segmentation of 3D CT images of Prostate Cancer Patients.
Budget: 07/01/2020 - 06/30/2021
Total amount: $35,000
PI: Dongxiao Zhu (CS)
I am looking for collaborations in leveraging AI and Machine Learning to solve problems in diverse data-rich domains, which inludes but not limited to: EHR, Health & Wellness, Life Science, Medical Imaging, Natural Language Processing, Cybersecurity, Mobility, and Transportation research domains.
Recent AI and Machine Learning Original Research Publications in Top Venues
Pan, D, Li, X and Zhu, D (2021) Explaining Deep Neural Network Models with Adversarial Gradient Integration. Accepted for publication in 30th International Joint Conference on Artificial Intelligence (IJCAI-21), Montreal, Canada. Acceptance rate: 587/4,204=13.9%.
Li, X, Li, X, Pan,D and Zhu, D (2020) Improving adversarial robustness via probabilistically compact loss with logit constraints. To appear in the proceedings of Thirty-Five AAAI Conference on Artificial Intelligence (AAAI-21), virtual conference. Acceptance rate: 1,692/7,911=21.4%
Pan, D, Li, X, Li, X and Zhu, D (2020) Explainable recommendation via interpretable feature mapping and evaluating explainability. In the proceedings of 29th International Joint Conference on Artificial Intelligence (IJCAI-20), Yokohama, Japan. Acceptance rate: 592/4,717=12.6%
Li, X, Li, X, Pan,D and Zhu, D (2020) On the learning behavior of logistic and softmax losses for deep neural networks. In the proceedings of Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20), New York, USA. Acceptance rate: 1,591/7,737=20.6%.
Recent AI Application Publications in EHR, Health & Wellness, Medical Imaging, and Natural Language Processing
(EHR) Li, X, Zhu, D* and Levy, P (2020) Predicting clinical outcomes with patient stratification via deep mixture neural networks. American Medical Informatics Association (AMIA-20) Summit on Clinical Research Informatics, Houston, USA. (Best Student Paper Award, *Corresponding Autor) PubMed 32477657
(EHR) Nezhad, MZ, Sadati, N, Yang, K and Zhu, D. (2019) A deep active survival analysis approach for precision treatment recommendations: application of prostate cancer. Expert Systems with Applications. Vol. 15, 16-26.
(Health & Wellness) Wang, L. and Zhu, D. (2021). Tackling multiple ordinal regression problems: sparse and deep multi-task learning approaches. Data Mining and Knowledge Discovery (DMKD), 23 March 2021.
(Health & Wellness) Wang, L, Dong, M, Towner, E and Zhu, D (2019) Prioritization of multi-level risk factors for obesity. In the proceedings of 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM-19), 1065-1072.
(Medical Imaging) Li, X and Zhu, D (2020) COVID-MobileXpert: On-Device COVID-19 Screening using Snapshots of Chest X-Ray. To appear in the proceedings of 2020 International Conference on Bioinformatics and Biomedicine (BIBM-20).
(Medical Imaging) Li, X., Pan, D. and Zhu, D., (2021) Defending against adversarial attacks on medical imaging AI system, classification or detection? To appear in the proceedings of IEEE International Symposium on Biomedical Imaging (ISBI-21), virtual conference.
(Medical Imaging) Li, X. and Zhu, D. (2020). Robust detection of adversarial attacks on medical images. IEEE International Symposium on Biomedical Imaging (ISBI-20), Iowa City, USA.
(Medical Imaging) Li, X., Hect, J., Thompson, J. and Zhu, D. (2020). Interpreting age effects of human fetal brain from spontaneous fMRI using deep 3D convolutional neural networks. IEEE International Symposium on Biomedical Imaging (ISBI-20), Iowa City, USA.
(Medical Imaging) Manwar, R., Li, X., Mahmoodkalayeh, S., Asano, E., Zhu, D. and Avanaki, K., 2020. Deep learning protocol for improved photoacoustic brain imaging. Journal of Biophotonics, 13(10), p.e202000212.
(Natural Language Processing) Qiang, Y, Li, X and Zhu, D (2020) Toward tag-free aspect based sentiment analysis: a multiple attention network approach. in the proceedings of International Joint Conference on Neural Networks (IJCNN-20), Glasgow, Scotland, UK.
Laboratory Web Site