Prof. Zinan Chen

Shenzhen University, China

Abstract

Data visualization is an important field for discovering hidden patterns in datasets. Among the available techniques, kernel density visualization (KDV) has become a widely adopted method for domain experts, including criminologists, transportation specialists, and epidemiologists, to analyze location data. Representative applications include crime hotspot detection, traffic accident hotspot detection, and disease outbreak detection. Given its broad applicability, KDV is supported by numerous scientific computing packages, such as scikit-learn and SciPy; visualization packages, such as deck.gl and seaborn; and geographic information systems, such as QGIS and ArcGIS.

However, KDV is computationally expensive and does not scale well to large datasets or high-resolution visualizations. Moreover, to thoroughly understand their data, domain experts need to perform exploratory operations, such as zooming and panning, and apply advanced analytical techniques that require computing multiple KDVs. Consequently, existing off-the-shelf software packages often cannot support KDV efficiently, or even feasibly, in big data settings.

In this talk, I will first present our efficient solutions for computing KDV and its variant, spatiotemporal kernel density visualization (STKDV). I will then introduce LIBKDV, our high-performance Python library built upon these solutions. Next, I will discuss the Hong Kong and Macau COVID-19 hotspot maps powered by LIBKDV. Finally, I will outline potential directions for future research and software development.

Biography

Zinan Chen is a Distinguished Professor in the College of Computer Science and Software Engineering at Shenzhen University. He is a recipient of the National Science Fund for Excellent Young Scientists (Overseas) and a Senior Member of IEEE. He received his Ph.D. from The Hong Kong Polytechnic University in March 2019. From September 2018 to August 2020, he worked as a Research Assistant in the Department of Computer Science at The University of Hong Kong. He subsequently served as a Research Assistant Professor at Hong Kong Baptist University from September 2020 to August 2023.

His research interests include data science, spatiotemporal intelligence, spatiotemporal data management and analytics, and large-scale data visualization. He has published nearly 60 papers in leading international conferences and journals, including SIGMOD, VLDB, ICDE, SIGKDD, NeurIPS, IEEE TKDE, and IEEE TIP. His work received a Research Track Honorable Mention Award at ACM SIGKDD 2026.

Prof. Chen has led three projects funded by the National Natural Science Foundation of China (NSFC): “Efficient Algorithms for Kernel Density Estimation,” supported by the Young Scientists Fund; “Efficient Algorithms for Road Network Analytics,” supported by the General Program; and “Large-Scale Spatiotemporal Data Analytics,” supported by the National Science Fund for Excellent Young Scientists (Overseas).

His conference reviewing service includes VLDB (Demo Track, 2022–2024; Research Track, 2025–2027), ICDE (2022 and 2024–2027), EDBT 2023, ACM Multimedia 2026 (Research and Dataset Tracks), IJCAI 2020, SSDBM 2024, DASFAA (2021–2024), and WISE (2019–2024). He received an Outstanding Reviewer Award at ICDE 2024.

He also reviews for leading international journals, including The VLDB Journal, IEEE Transactions on Knowledge and Data Engineering, ACM Transactions on Knowledge Discovery from Data, Artificial Intelligence, IEEE Transactions on Computers, World Wide Web, IEEE Transactions on Network Science and Engineering, Pattern Recognition, Data & Knowledge Engineering, Journal of Computer Science and Technology, and The Journal of Supercomputing. His professional service further includes appointments as Proceedings Chair for MDM (2021–2027) and Big Data Cup Challenge Chair for IEEE Big Data 2025.