Ms. Jingyi Gao | Probabilistic Modeling | Best Researcher Award

University of Virginia | United States

Author Profile

Academic and Research Profile of Jingyi Gao

Early Academic Pursuits

Jingyi Gao’s academic foundation is marked by a strong interdisciplinary focus, combining mathematics, computer science, and economics during her undergraduate studies at the University of California, San Diego. She pursued dual degrees-a Bachelor of Science in Mathematics-Computer Science and a Bachelor of Arts in Economics-demonstrating both technical and analytical versatility. Building on this, she earned a Master of Science in Applied Mathematics and Statistics from Johns Hopkins University, where she graduated with a GPA of 3.9/4.0. Currently, she is pursuing a Ph.D. in Systems and Information Engineering at the University of Virginia, with a research concentration in time series prediction, Bayesian probabilistic modeling, and federated learning.

Professional Endeavors

Gao has gained extensive teaching and mentoring experience across prestigious institutions. At the University of Virginia, she has served as a Teaching Assistant for multiple graduate and undergraduate courses, guiding more than a thousand students in areas such as data mining, AI, and big data systems. She has also contributed as a peer mentor for the Data Justice Academy, fostering diversity in data science research. Beyond academia, her professional journey includes research internships at the University of Pittsburgh and Tencent, where she applied machine learning techniques to healthcare stress detection and cloud infrastructure optimization. Her roles highlight both academic excellence and industry-relevant impact.

Contributions and Research Focus

Jingyi Gao’s research contributions lie at the intersection of machine learning, statistical modeling, and human-centered applications. She has worked on federated learning frameworks to enhance privacy in distributed systems, developed adaptive time series models for real-time prediction, and applied deep latent variable models in ergonomics and healthcare monitoring. Her publications span high-impact venues, including work accepted in Pattern Recognition and presented at IEEE conferences. Her efforts in behavioral modeling, stress detection, and multimodal sensor data analysis underscore her commitment to advancing computational methods for practical societal challenges.

Impact and Influence

Through her teaching, mentorship, and publications, Gao has influenced both academic communities and applied research domains. By mentoring underrepresented groups in data science, she has contributed to inclusive research culture. Her innovative approaches in federated learning and human behavior modeling provide scalable solutions for industries like healthcare, occupational health, and cloud services. Her conference presentations at IEEE CASE, ICMLA, and INFORMS further reflect her growing influence in the global research community.

Academic Citations

Although early in her career, Gao’s scholarly work has begun to attract attention, with multiple preprints available on arXiv and accepted publications in well-recognized journals and conferences. As her ongoing Ph.D. research matures and more of her contributions are published, her academic citation count and impact are expected to expand significantly.

Legacy and Future Contributions

Jingyi Gao’s trajectory suggests a promising future as a leader in data science and applied machine learning. With a foundation that bridges theory and practice, she is well-positioned to make lasting contributions in federated learning, real-time predictive modeling, and socially responsible AI applications. Her future work is likely to leave a meaningful legacy in shaping privacy-preserving, adaptive, and human-centered machine learning systems that address pressing global challenges.

Conclusion

In summary, Jingyi Gao exemplifies the qualities of a rising researcher who blends academic rigor, teaching excellence, and innovative research applications. Her interdisciplinary training, impactful publications, and commitment to mentorship signal a strong potential to become a thought leader in her field. With her ongoing contributions and dedication, Gao is poised to significantly advance both the academic and practical dimensions of data-driven science.

Notable Publications

“Gait-Based Hand Load Estimation via Deep Latent Variable Models with Auxiliary Information"

Author: J Gao, S Lim, S Chung
Journal: arXiv preprint arXiv
Year: 2025

"Federated automatic latent variable selection in multi-output gaussian processes"

Author: J Gao, S Chung‏
Journal: arXiv preprint arXiv
Year: 2025

"Modeling Regularity and Predictability in Human Behavior from Multidimensional Sensing Signals and Personal Characteristics"

Author: J Gao, R Yan, A Doryab
Journal: International Conference on Machine Learning and Applications
Year: 2023

"Machine learning to summarize and provide context for sleep and eating schedules"

Author: T Chen, Y Chen, J Gao, P Gao, JH Moon, J Ren, R Zhu, S Song, JM Clark
Journal: bioRxiv
Year: 2021

Dr. Toktam Dehghani | Prediction models for medicine | Best Researcher Award

Assistant Professor, at Mashhad University of Medical Sciences, Iran📖

Dr. Toktam Dehghani is a skilled educator and researcher specializing in medical informatics and bioinformatics. With a Ph.D. in Computer Engineering, she has extensive experience in applying artificial intelligence and data mining techniques to various fields of healthcare, particularly in diagnostics and predictive modeling. Dr. Dehghani is deeply involved in cutting-edge research on genetic disorders, cancer detection, and AI-based health technology. She has developed several AI-driven platforms and decision support systems that are shaping the future of personalized medicine and healthcare

Profile

Scopus Profile

Google Scholar Profile

Education Background🎓

Dr. Toktam Dehghani holds a Ph.D. in Computer Science from the University of Manchester, UK, where she specialized in artificial intelligence and its applications in medical data analysis. Prior to her doctoral studies, she earned her Master’s degree in Bioinformatics from the University of Tehran, Iran. During her academic journey, she gained expertise in bioinformatics, medical data analysis, and the application of machine learning techniques to healthcare problems. Dr. Dehghani’s academic background reflects her strong foundation in both computer science and biomedical research, equipping her with a unique interdisciplinary perspective for solving complex health-related challenges through innovative technologies.

Professional Experience🌱

Dr. Toktam Dehghani is an Assistant Professor at the Medical Informatics Department of Mashhad University of Medical Sciences. She lectures postgraduate students in Artificial Intelligence (AI), Medical Software Development, and Bioinformatics. With over a decade of experience in academia, she has also served as a lecturer at Ferdowsi University of Mashhad and Toos Higher Education Institute, where she taught courses in Artificial Intelligence, Data Mining, Bioinformatics, and Advanced Algorithms to undergraduate and postgraduate students. Dr. Dehghani is also the Manager of the Health Technology Incubator at SMARTDX Co., leading the development of AI-based platforms for diagnosing genetic disorders and cancers

Research Interests🔬

Dr. Dehghani’s research interests lie at the intersection of Machine Learning, Bioinformatics, and Medical Informatics. She is particularly focused on the application of AI and data mining techniques to solve complex problems in genetic disorders, cancer diagnosis, and healthcare decision support systems. Her recent research includes predictive models for medical student performance, cardiovascular event prediction, pulmonary thromboembolism diagnosis, and machine learning for genetic data analysis. She has also worked extensively on protein structure prediction and the application of deep learning in bioinformatics.

Author Metrics

Dr. Toktam Dehghani has established herself as a prominent author in the field of computer science and bioinformatics. With over 20 peer-reviewed publications, her work has been cited more than 300 times, highlighting her significant contribution to the academic community. She maintains an h-index of 10, demonstrating her consistent impact on the field. Her research articles have been published in reputable journals such as Bioinformatics, Journal of Medical Systems, and IEEE Transactions on Biomedical Engineering, covering topics like artificial intelligence, machine learning applications in healthcare, and bioinformatics. Dr. Dehghani is recognized for her expertise in utilizing computational methods to address complex biological and medical challenges.

Publications Top Notes 📄

1. Deep Learning on Ultrasound Images of Thyroid Nodules

Authors: Y Sharifi, MA Bakhshali, T Dehghani, M DanaiAshgzari, M Sargolzaei, et al.
Journal: Biocybernetics and Biomedical Engineering
Volume: 44
Year: 2021
Summary: This study investigates the application of deep learning techniques on ultrasound images to aid in the detection and diagnosis of thyroid nodules, enhancing diagnostic accuracy.

2. Efficient Semi-Partitioning and Rate-Monotonic Scheduling Hard Real-Time Tasks on Multi-Core Systems

Authors: M Naghibzadeh, P Neamatollahi, R Ramezani, A Rezaeian, T Dehghani
Conference: 8th IEEE International Symposium on Industrial Embedded Systems (SIES)
Year: 2013
Summary: This paper addresses the problem of scheduling real-time tasks on multi-core systems, focusing on an efficient semi-partitioning method and rate-monotonic scheduling for hard real-time tasks.

3. A Comparative Study of Explainable Ensemble Learning and Logistic Regression for Predicting In-Hospital Mortality in the Emergency Department

Authors: Z Rahmatinejad, T Dehghani, B Hoseini, F Rahmatinejad, A Lotfata, et al.
Journal: Scientific Reports
Volume: 14(1)
Article Number: 3406
Year: 2024
Summary: This paper compares the performance of ensemble learning models with logistic regression for predicting in-hospital mortality, with a focus on the explainability of the models in clinical settings.

4. BetaProbe: A Probability-Based Method for Predicting Beta Sheet Topology Using Integer Programming

Authors: M Eghdami, T Dehghani, M Naghibzadeh
Conference: 5th International Conference on Computer and Knowledge Engineering
Year: 2015
Summary: BetaProbe presents a method for predicting the beta-sheet topology of proteins, utilizing integer programming for more accurate computational predictions in bioinformatics.

5. Enhancement of Protein β-Sheet Topology Prediction Using Maximum Weight Disjoint Path Cover

Authors: T Dehghani, M Naghibzadeh, J Sadri
Journal: IEEE/ACM Transactions on Computational Biology and Bioinformatics
Volume: 16(6)
Year: 2018
Summary: This work improves the prediction of β-sheet topology in proteins by using a maximum weight disjoint path cover, contributing to advancements in protein structure prediction.

Conclusion

Dr. Toktam Dehghani is a highly deserving candidate for the Best Researcher Award due to her innovative research in AI, bioinformatics, and healthcare. Her contributions to personalized medicine and AI-driven diagnostic systems have the potential to revolutionize healthcare practices, especially in the areas of genetic disorders and cancer. While there are areas for improvement, such as enhancing clinical integration and expanding the scope of her AI models, her dedication to advancing healthcare through technology positions her as a leader in the field. Dr. Dehghani’s ongoing contributions to both academia and industry ensure that her impact will continue to grow, making her an exemplary choice for this prestigious award.