Get the latest news
Subscribe to receive updates from the School of Data Science.
Postdoctoral Researcher
Nazanin Moradinasab
Postdoctoral Research Associate
School of Data Science
Email: nm4wu@virginia.edu
Additional Contact Information
Office: 1919 Ivy Rd., 3 S. Ste.
Nazanin Moradinasab is a Postdoctoral Research Associate in the School of Data Science at the University of Virginia. Her research focuses on machine learning, computer vision, and multimodal models, with a strong emphasis on designing innovative approaches for situations where access to limited or insufficiently labeled data presents a challenge. In particular, Nazanin's interests include multivariate time series classification, weakly supervised learning techniques, and domain adaptation methods tailored for handling noisy and partially labeled datasets, as well as developing multimodal models to effectively integrate diverse data sources.
Before her postdoctoral appointment, Nazanin completed her Ph.D. in Systems Engineering at the University of Virginia, where she developed novel methodologies such as SupCon-TSC for multivariate time series classification and a Generalized Multi-prototype Gaussian Mixture-based model for new domain adaptation settings. Her work has been published in well-known journals and conferences, including the IEEE International Conference on Image Processing (ICIP), the Data Mining and Knowledge Discovery Journal, and the International Conference on Machine Learning and Applications. Nazanin was awarded the American Heart Association (AHA) Predoctoral Fellowship (2023–2024) as the Primary Investigator, as well as the Endowed Fellowship (2022–2023), a merit-based award recognizing her academic excellence during her Ph.D.
Nazanin holds a Ph.D. in Industrial Engineering from Tarbiat Modares University in Iran, where her research primarily focused on optimization techniques, modeling, and their applications. Her contributions have been published in prestigious journals, including the Journal of Cleaner Production (IF: 9.7), Energy (IF: 9), and Energy Sources, Part B: Economics, Planning, and Policy (IF: 3.1). She also earned her M.Sc. and B.Sc. in Industrial Engineering from K. N. Toosi University of Technology, Iran.
Education
- Ph.D. in Systems Engineering, University of Virginia
- Ph.D. in Industrial Engineering, Tarbiat Modares University, Iran
- M.Sc. in Industrial Engineering, K. N. Toosi University of Technology
- B.Sc. in Industrial Engineering, K. N. Toosi University of Technology
Selected Publications
1. Moradinasab, N., Jafarzadeh, H. and Brown, D.E., 2024, October. Gengmm: Generalized Gaussian-Mixture-Based Domain Adaptation Model for Semantic Segmentation. In 2024 IEEE International Conference on Image Processing (ICIP) (pp. 1078-1084). IEEE.
2. Moradinasab, N., Deaton, R.A., Shankman, L.S., O.K. and Brown, D.E., 2024. ProtoGMM: Multi‑prototype Gaussian Mixture‑based domain adaptation model for semantic segmentation. International Conference on Machine Learning and Applications (ICMLA). (Accepted)
3. Moradinasab, N., Sharma, S., Bar-Yoseph, R., Radom-Aizik, S., C. Bilchick, K., M. Cooper, D., Weltman, A. and Brown, D.E., 2024. Universal representation learning for multivariate time series using the instance-level and cluster-level supervised contrastive learning. Data Mining and Knowledge Discovery, pp.1-27.
4. Moradinasab, N., Deaton, R.A., Shankman, L.S., Owens, G.K. and Brown, D.E., 2023, October. Label-efficient Contrastive Learning-based model for nuclei detection and classification in 3D Cardiovascular Immunofluorescent Images. In Workshop on Medical Image Learning with Limited and Noisy Data (pp. 24-34). Cham: Springer Nature Switzerland.
5. McBee, P., Moradinasab, N., Brown, D.E. and Syed, S., 2023. Pre-training Segmentation Models for Histopathology. In Medical Imaging with Deep Learning, short paper track.
6. Moradinasab, N., Sharma, Y., Shankman, L.S., Owens, G.K. and Brown, D.E., 2022, December. Weakly Supervised Deep Instance Nuclei Detection using Points Annotation in 3D Cardiovascular Immunofluorescent Images. In Machine Learning for Healthcare Conference (pp. 565-584). PMLR.
7. Sali, R., Moradinasab, N., Guleria, S., Ehsan, L., Fernandes, P., Shah, T.U., Syed, S. and Brown, D.E., 2020. Deep learning for whole-slide tissue histopathology classification: A comparative study in the identification of dysplastic and non-dysplastic Barrett’s esophagus. Journal of Personalized Medicine, 10(4), p.141.
8. Bar‐Yoseph, R., Radom‐Aizik, S., Coronato, N., Moradinasab, N., Barstow, T.J., Stehli, A., Brown, D. and Cooper, D.M., 2022. Heart rate and gas exchange dynamic responses to multiple brief exercise bouts (MBEB) in early‐and late‐pubertal boys and girls. Physiological reports, 10(15), p.e15397.
9. Annapareddy, N., Fallin, K., Folks, R., Jarrard, W., Durieux, M., Moradinasab, N., Naik, B., Sengupta, S., Ndaribitse, C. and Brown, D., 2022, April. Handwritten text and digit classification on rwandan perioperative flowsheets via yolov5. In 2022 systems and information engineering design symposium (SIEDS) (pp. 270-275). IEEE.