Juhua Hu

Juhua Hu, Ph.D.

Assistant Professor

Computer Science and Systems
School of Engineering and Technology
University of Washington | Tacoma

Director

Center for Data Science

Contact

Box 358426, 1900 Commerce Street
Tacoma, WA 98402-3100
Office: MDS / 203A
Phone: +1 253-692-4625
Email: juhuah [at] uw [dot] edu

Biography [CV][My LinkedIn] [My Google Scholar Citations] [My DBLP]

Juhua Hu is currently an Assistant Professor of Computer Science and Systems in the School of Engineering and Technology at the University of Washington Tacoma and the Director of Center for Data Science. She obtained her Ph.D. degree in Computer Science from School of Computing Science, Simon Fraser University in December 2017, under the supervision of Dr. Jian Pei. Juhua received her B.Sc. and M.Sc. degrees in Computer Science from Nanjing University in June 2009 and June 2012, respectively. As a master student, Juhua joined the LAMDA group and worked with Dr. Yuan Jiang and Dr. Zhi-Hua Zhou.

News

Dec. 2023: Our paper "Dual-disentangled Deep Multiple Clustering" got accepted by SDM'24.
Oct. 2023: Our paper "NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients" got accepted by BigData'23.
Sep. 2023: Our paper "Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP" got accepted by NeurIPS'23.
Aug. 2023: Our paper "Dictionary-Guided Text Recognition for Smart Street Parking" got accepted by BMVC'23.
Jul. 2023: Our paper "Improved Visual Fine-tuning with Natural Language Supervision" got accepted by ICCV'23.
Mar. 2022: Our paper "Unsupervised Visual Representation Learning by Online Constrained K-Means" got accepted by CVPR'22.
Dec. 2021: Our paper "Improved Knowledge Distillation via Full Kernel Matrix Transfer" got accepted by SDM'22.
July 2021: Our paper "Weakly Supervised Representation Learning with Coarse Labels" got accepted by ICCV'21.
May 2021: Juhua received NSF CRII Award.
July 2020: My undergraduate student Tucker R. Stewart receives Outstanding Undergraduate Research Award.
Feb. 2020: Our paper "Hierarchically robust representation learning" got accepted by CVPR'20.
Jan. 2020: My undergraduate student Tucker R. Stewart is awarded the Mary Gates Research Scholarship.
July 2019: Our paper "SoftTriple loss: Deep metric learning without triplet sampling" got accepted by ICCV'19.
Sept. 2018: Juhua joined UW Tacoma as an Assistant Professor.
Jun. 2018: Our paper "Exact and consistent interpretation for piecewise linear neural networks: A closed form solution" got accepted by KDD'18.
Dec. 2017: Juhua successfully defended her thesis "Subspace Clustering Methods for Understandable Information Organization".
July 2017: Our survey paper "Subspace multi-clustering: A review" got accepted by KAIS.
Oct. 2016: Our extended version of ICDM'15 paper "Finding multiple stable clusterings" got accepted by KAIS.
July 2016: Computing Science Graduate Student Story: Juhua Hu.

Research Interests

Juhua's primary research interest is in the areas of machine learning, data mining, and data science. She is especially interested in deep representation learning, deep model interpretation and compression, time series analysis, and explainable and fair ML, where the applications span over Computer Vision, Healthcare, Cybersecurity, Human Computer Interaction, and Smart City.

Project - Rare Event Prediction in Time Series

Abstract
Predicting rare events within a time series is a critical task in many real-world applications. Taking the healthcare industry as an example, it would be very useful to predict an influx in the number of patients that would overwhelm a hospital beyond its capacity. Without such capability, it could have negative consequences in the hospital's ability to adequate health care. Rare event prediction in time series is a challenging problem due to the non-linear nature of rare events, the inability to capture their key information in the systematic components of the temporal data, and the data imbalance between rare and normal events. This project will result in a framework to address these challenges. With such a prediction framework, steps can be taken to ensure the affected population's readiness for such rare events. For instance, the application of the resulting technology will significantly improve readiness in the healthcare care industry. Furthermore, the resulting technology can be applied to other areas of societal interest. This project studies the nature of rare events in time series and addresses the above-mentioned challenges with three technical aims. First, it is well known that sequence models such as recurrent neural networks can be used to capture both the temporal and non-linear nature of the data. Nevertheless, they have not been well studied for the problem of rare event prediction in time series. One goal of this project is to thoroughly study if sequence models can capture both the temporal and non-linear nature of the rare events to facilitate the prediction. Second, the key information of rare events can be hidden by the seasonal fluctuations in the time series. Another goal of this project is to study if time series decomposition that separates the seasonality can help the prediction of rare events. Finally, in terms of the data imbalance problem, traditional prediction models often treat normal and rare events equivalently, which can be harmful for the rare event prediction. This project will develop a new method based on the properties of rare events to emphasize their importance. Moreover, filters can be specifically designed to extract rare events better to reduce the effect from large amount of normal data. Both strategies have not been well studied for the rare event prediction in time series, which will be the third goal of this project.
Publications
  • T. Stewart [PhD], K. Stern, G. O'Keefe, A. Teredesai, and J. Hu. NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients. In: Proceedings of the IEEE International Conference on Big Data (BigData'23), Sorrento, Italy, 2023, pp.1843-1852. [Pre-Print PDF]
  • K. Ewig [MSc], X. Lin [MSc], T. Stewart [PhD], K. Stern, G. O'Keefe, A. Teredesai, and J. Hu. Multi-Subset Approach to Early Sepsis Prediction. To appear in: Proceedings of the 9th International Conference on Health Informatics and Medical Systems (HIMS'23), Las Vegas, NV, 2023. [Pre-Print PDF]
  • A. Teredesai, S. Huang [MSc], T. Stewart [PhD], J. Hu, A. Thakker [High School], K. Stern, and G. O'Keefe. Sub-Sequence Graph Representation Learning on High Variability Data for Dynamic Risk Prediction in Critical Care. In: Proceedings of the IEEE International Conference on Big Data (BigData'22), Osaka, Japan, 2022, pp.2082-2092. [Pre-Print PDF]
  • T. Stewart [PhD], B. Yu, A. Nascimento, and J. Hu. Enhancing Peak Network Traffic Prediction via Time-series Decomposition. arXiv preprint arXiv:2303.13529, 2023.
  • B. Yu, G. Graciani [MSc], A. Nascimento, and J. Hu. Cost-adaptive Neural Networks for Peak Volume Prediction with EMM Filtering. In: Proceedings of the IEEE International Conference on Big Data (BigData'19), Los Angeles, CA, 2019, pp.4208-4213. [Pre-Print PDF]
    • Activities
  • M. Binjolkar [MSc], Talk at 2023 SET/Center for Data Science Research Seminar: Data Augmentation Towards Class Imbalance in EHR: A Sepsis Case Study.
  • R. Kumar [MSc], Poster at 2023 SET Research Showcase: Enhanced Finger Detection in sEMG Using Computer Vision.
  • L. Preuett [MSc], Poster at 2022 SET Research Showcase: Enhanced Finger Movement Detection Using sEMG by Data Augmentation.
  • H. Thakur [MSc], Talk at 2022 SET/Center for Data Science Research Seminar: Early Prediction of Sepsis Onset in Trauma Patients: An Interpretable CNN Approach.
    • Acknowledgement
    nsf UWMed advata infoblox

    Selected Publications

    Journal Articles
    J. Yao, E. Liu, M. Rashid, and J. Hu. AugDMC: Data Augmentation Guided Deep Multiple Clustering. Procedia Computer Science, 222 (2023): 571-580. DOI: 10.1016/j.procs.2023.08.195. [Online PDF][Code][Datasets]
    J. Hu and J. Pei. Subspace multi-clustering: A review. Knowledge and Information Systems (KAIS), 2018, 56(2): 257-284. DOI: 10.1007/s10115-017-1110-9. [Online PDF]
    J. Hu, Q. Qian, J. Pei, R. Jin and S. Zhu. Finding multiple stable clusterings (An extended version of ICDM 2015). Knowledge and Information Systems (KAIS), 2017, 51(3): 991-1021. DOI: 10.1007/s10115-016-0998-9. [Online PDF][Code]("Bests of ICDM 2015")
    J. Hu, D.-C. Zhan, X. Wu, Y. Jiang and Z.-H. Zhou. Pairwised specific distance learning from physical linkages. ACM Transactions on Knowledge Discovery from Data (TKDD), 2015, 9(3): Article 20. [Pre-Print PDF]
    J. Hu, Y. Jiang and Z.-H. Zhou. A co-training method based on teaching-learning model. Journal of Computer Research and Development (in Chinese with English abstract), 2013, 50(11): 2262-2268. [PDF] (This paper won the Best Student Paper Award at 2012 National Conference on Agent Theory and Applications, Changchun, China)
    Conference Papers
    J. Yao and J. Hu. Dual-disentangled Deep Multiple Clustering. To appear in: Proceedings of the SIAM International Conference on Data Mining (SDM'24), Houston, TX, 2024. [Pre-Print PDF][Code][Datasets]
    T. Stewart, K. Stern, G. O'Keefe, A. Teredesai, and J. Hu. NPRL: Nightly Profile Representation Learning for Early Sepsis Onset Prediction in ICU Trauma Patients. In: Proceedings of the IEEE International Conference on Big Data (BigData'23), Sorrento, Italy, 2023, pp.1843-1852. [Pre-Print PDF]
    Q. Qian, Y. Xu, and J. Hu. Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP. To appear in: Proceedings of the 37th Conference on Neural Information Processing Systems (NeurIPS'23), New Orleans, LA, 2023.[Pre-Print PDF][Code]
    D. Zhong, J. Li, W. Cheng, and J. Hu. Dictionary-Guided Text Recognition for Smart Street Parking. In: Proceedings of the 34th British Machine Vision Conference (BMVC'23), Aberdeen, UK, 2023.
    J. Wang, Y. Xu, J. Hu, M. Yan, J. Sang, Q. Qian. Improved Visual Fine-tuning with Natural Language Supervision. In: Proceedings of the International Conference on Computer Vision (ICCV'23), Paris, France, 2023, pp.11865-11875. [Pre-Print PDF] [Code]
    S. Seyed Monir, J. Hu, B. Tribelhorn, and H. E. Dillon. Enhanced chaotic transition prediction using hierarchical clustering for the Lorenz System. In: ASME International Mechanical Engineering Congress and Exposition, vol. 87677, p. V010T11A065. American Society of Mechanical Engineers, 2023.
    K. Ewig, X. Lin, T. Stewart, K. Stern, G. O'Keefe, A. Teredesai, and J. Hu. Multi-Subset Approach to Early Sepsis Prediction. To appear in: Proceedings of the 9th International Conference on Health Informatics and Medical Systems (HIMS'23), Las Vegas, NV, 2023. [Pre-Print PDF]
    A. Teredesai, S. Huang, T. Stewart, J. Hu, A. Thakker, K. Stern, and G. O'Keefe. Sub-Sequence Graph Representation Learning on High Variability Data for Dynamic Risk Prediction in Critical Care. In: Proceedings of the IEEE International Conference on Big Data (BigData'22), Osaka, Japan, 2022, pp.2082-2092. [Pre-Print PDF]
    Q. Qian, Y. Xu, J. Hu, H. Li, and R. Jin. Unsupervised Visual Representation Learning by Online Constrained K-Means. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'22, acceptance rate: 2,067/8,161=25.3%), New Orleans, LA, 2022, pp.16640-16649. [Pre-Print PDF] [Code]
    Q. Qian, H. Li, and J. Hu. Improved knowledge distillation via full kernel matrix transfer. In: Proceedings of the SIAM International Conference on Data Mining (SDM'22, acceptance rate: 83/298=27.8%), Virtual, 2022, pp.612-620. [Pre-Print PDF][Code] (SIAM Early Career Travel Award)
    Y. Xu, Q. Qian, H. Li, R. Jin, and J. Hu. Weakly supervised representation learning with coarse labels. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV'21, acceptance rate: 1,617/6,236=25.9%), Virtual, 2021, pp.10593-10601. [Pre-Print PDF][Code]
    C. Allen, J. Hu, V. Kumar, M. Ahmad, and A. Teredesai. Interpretable phenotyping for electronic health records. In: Proceedings of the IEEE International Conference on Healthcare Informatics (ICHI'21), Victoria, Canada, 2021, pp.161-170. [Pre-Print PDF]
    R. Zhang, S. Wang, R. Burton, M. Hoang, J. Hu, and A. Nascimento. Clustering analysis of email malware campaigns. In: Proceedings of the IEEE International Conference on Cyber Security and Resilience (CSR'21), Virtual, 2021, pp.95-102. [Pre-Print PDF]
    Q. Qian, J. Hu, and H. Li. Hierarchically robust representation learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR'20, acceptance rate: 1,470/6,656=22%), Seattle, WA, 2020, pp.7336-7344. [Pre-Print PDF] [Concepts in ImageNet]
    B. Yu, G. Graciani, A. Nascimento, and J. Hu. Cost-adaptive neural networks for peak volume prediction with EMM filtering. In: Proceedings of the IEEE International Conference on Big Data (BigData'19), Los Angeles, CA, 2019, pp.4208-4213. [Pre-Print PDF]
    Q. Qian, L. Shang, B. Sun, J. Hu, H. Li, and R. Jin. SoftTriple loss: Deep metric learning without triplet sampling. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV'19, acceptance rate: 1,077/4,303=25%), Seoul, Korea, 2019, pp.6450-6458. [Pre-Print PDF][Code]
    L. Chu, X. Hu, J. Hu, L. Wang, and J. Pei. Exact and consistent interpretation for piecewise linear neural networks: A closed form solution. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'18, acceptance rate: 107/983=10.9%), London, UK, 2018, pp.1244-1253. [Pre-Print PDF]
    J. Hu, Q. Qian, J. Pei, R. Jin and S. Zhu. Finding multiple stable clusterings. In: Proceedings of the 15th IEEE International Conference on Data Mining (ICDM'15, acceptance rate: 68/810=8.4%), Atlantic City, NJ, 2015, pp.171-180. [Pre-Print PDF][Slides][Fruit Data] (Invited to KAIS SI on "Bests of ICDM 2015", Student Travel Award)
    Q. Qian, J. Hu, R. Jin, J. Pei and S. Zhu. Distance metric learning using dropout: A structured regularization approach. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'14, acceptance rate: 151/1,036=14.6%), New York, NY, 2014, pp.323-332. [Pre-Print PDF]
    J. Hu, J. Pei and J. Tang. How can I index my thousands of photos effectively and automatically? An unsupervised feature selection approach. In: Proceedings of the 14th SIAM International Conference on Data Mining (SDM'14, acceptance rate: 60/389=15.4%), Philadelphia, PA, 2014, pp.136-144. [Pre-Print PDF][Poster] (Student Travel Award)
    Y.-F. Li, J. Hu, Y. Jiang and Z.-H. Zhou. Towards discovering what patterns trigger what labels. In: Proceedings of the 26th AAAI Conference on Artificial Intelligence (AAAI'12, acceptance rate: 294/1,129=26%), Toronto, Canada, 2012, pp.1012-1018. [Pre-Print PDF] [Code]
    Newsletters
    J. Li, P. Samrith, N. Guobadia, J. Hu and W. Cheng. Automatic street parking sign reading. IEEE IOT-AHSN TC Newsletter, 1(14): 3-4, 2021. [Online PDF]
    M. Fotouhi, G. Jowkar, T. Wang, J. Hu, P. Arabshahi and W. Cheng. EMG sensor based finger movement detection. IEEE IOT-AHSN TC Newsletter, 1(14): 11-12, 2021. [Online PDF]
    Workshops
    H. Chau, Y. Jin, J. Li, J. Hu and W. Cheng. Real-time street parking sign detection and recognition. In: IJCAI-ECAI 2022 AI4AD (Artificial Intelligence for Autonomous Driving) Workshop, Vienna, Austria, 2022. [Online PDF]
    Tutorials
    M. Ahmad, C. Eckert, C. Allen, V. Kumar, J. Hu, and A. Teredesai. Fairness in Healthcare AI. In: The 9th IEEE International Conference on Healthcare Informatics (ICHI'21), Victoria, Canada, 2021, pp.554-555.
    M. Ahmad, C. Eckert, C. Allen, J. Hu, V. Kumar, and A. Teredesai. Fairness in Healthcare Machine Learning: A Practical Guide. In: The 25th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'21), Delhi, India, 2021. [Presentation Slides]
    Pre-prints
    T. Stewart, B. Yu, A. Nascimento, and J. Hu. Enhancing peak network traffic prediction via time-series decomposition. arXiv preprint arXiv:2303.13529, 2023.
    Ph.D. Thesis
    J. Hu. Subspace Clustering Methods for Understandable Information Organization. School of Computing Science, Simon Fraser University, Canada, December 2017. [PDF]

    Teaching

    Instructor, TCSS 422 [Computer Operating Systems], Spring 2019, Winter, Spring & Autumn 2020, Winter 2021, Winter, Spring & Autumn 2022, Winter 2023, Autumn 2023, University of Washington | Tacoma.
    Instructor, TCSS 551 [Big Data Analytics], Autumn 2018, Spring 2019, Winter & Spring 2020, Spring & Autumn 2021, Autumn 2022, Autumn 2023, University of Washington | Tacoma.
    Instructor, CMPT 454 [Advanced Database Systems], Fall 2017, Simon Fraser University (Burnaby).
    TA, CMPT 454, Spring 2017, Simon Fraser University (Surrey).
    TA, CMPT 454, Summer 2016, Simon Fraser University (Burnaby).
    Part-time Instructor, CMPT 354 [Database Systems], Fall 2015, Simon Fraser University (Burnaby).
    Instructor, CMPT 354 [Database Systems], Fall 2014, Simon Fraser University (Surrey).
    TA, CMPT 354, Fall 2013, Simon Fraser University (Burnaby).
    TA, Theory of Compiling, Spring 2010, Nanjing University.

    Students

    Current
    Tucker Stewart, PhD 2020
    Nicole Guobadia, PhD 2021
    Yin Jin, PhD 2022
    Jiawei Yao, PhD 2023
    Deyang Zhong, PhD 2023
    Carla Peterson, PhD 2023
    Past
    Richard Franklin, Thesis, M.Sc. 2023
    Deyang Zhong, Thesis published at BMVC'23, M.Sc. 2023, now Ph.D. student at UW Tacoma
    Larry Preuett, Thesis, M.Sc. 2022, now at Zetec and Ph.D. student at UW Tacoma
    Kevin Ewig, Thesis published at HIMS'23, M.Sc. 2022, now at LEG-TECH
    Yin Jin, Thesis accepted by IJCAI'22 AI4AD (Artificial Intelligence for Autonomous Driving) Workshop, M.Sc. 2021, now Ph.D. student at UW Tacoma
    Christine Allen, Thesis (co-supervisor), Thesis published at ICHI'21, M.Sc. 2020, now at KenSci
    Ghazaleh Jowkar, Thesis (co-supervisor), M.Sc. 2020, now at Oracle
    Zhongyu Jiang, Thesis (co-supervisor), M.Sc. 2019, now Ph.D. student at UW Seattle
    Mayuree Binjolkar, Capstone, M.Sc. 2023, now Ph.D. student at UW Seattle
    Raj Kumar, Capstone, M.Sc. 2023
    Xiangwen (Shellen) Lin, Independent Study & Capstone published at HIMS'23, M.Sc. 2022
    Sankalp Rathore, Independent Study & Capstone, M.Sc. 2022, now at Beyond Limits
    Brad Luong, Capstone, M.Sc. 2022, now at Boeing
    Himanshu Thakur, Capstone, M.Sc. 2022, now at Amazon
    Maham Rashid, Capstone published at Procedia Computer Science, M.Sc. 2022, now at Accenture
    Yixian Lin, Independent Study & Capstone, M.Sc. 2021
    Enbei Liu, Independent Study & Capstone published at Procedia Computer Science, M.Sc. 2021, now at YBB Technology Inc.
    Yiming Gan, Capstone, M.Sc. 2021, now at KenSci
    Ziqing Ying, Capstone, M.Sc. 2020, now at Amazon
    Amandeep Puri, Capstone, M.Sc. 2020, now at Washington State Patrol
    Giovanna S. Graciani, Capstone published at BigData'19, M.Sc. 2019, now at Intel
    Tongjue Wang, Independent Study published at IEEE IOT-AHSN TC Newsletter, M.Sc. 2019, now at Amazon
    Victor Chau, Thesis accepted by IJCAI'22 AI4AD (Artificial Intelligence for Autonomous Driving) Workshop, B.Sc. 2021, Graduated with CSS Honors
    Firn Tieanklin, Thesis, B.Sc. 2021, Graduated with CSS Honors, now Ph.D. student at UW Seattle
    Egor Maksimenka, Thesis, B.Sc. 2021, Graduated with CSS Honors, now at Adobe
    Tucker Stewart, Thesis, B.Sc. 2020, Graduated with CSS Honors, now Ph.D. student at UW Tacoma
    Jack Lin, Directed Research, B.Sc. 2021
    Nicole Guobadia, Directed Research published at IEEE IOT-AHSN TC Newsletter, B.Sc. 2020, now Ph.D. student at UW Tacoma
    Privacy | Terms Last updated in Feb 2024 by Juhua Hu.