To support intelligent transportation for smart city, we plan to study a systematic and comprehensive framework to tackle cutting-edge research problems in many aspects, including transportation data collection and data fusion by spatial crowdsourcing techniques, new deep-learning models for transportation problems, and real-time advanced spatial query processing. In our preliminary studies, we have published our work on renowned venues, including SIGMOD, VLDB, CIKM, TKDE, VLDB J. etc.
In this area, we study how to utilize crowdsourcing techniques for traffic sensing and traffic data collection. Our preliminary study has focused on top-k ranking through crowdsourced pairwise comparisons. This directly connects to traffic sensing through mobile users when traffic measurement are general inaccurate and multi-sources. We have proposed a cost-aware auto-tune crowdsourcing algorithm that effectively save human power but can still yield accurate answers. By incorporating our techniques with diversified transportation data sources, we can retrieve and determine traffic conditions at low cost. The related work have been published in SIGMOD, VLDB, etc.
Deep Learning based Transportation Data Processing
Classic transportation models are not designed for handling rich information, which has become an obstacle for advanced spatio-temporal query processing in modern applications. In this study, we attempt to propose a complex traffic model which not only captures spatio-temporal information but also makes use of heterogenous sources. To achieve this goal, we study and design cutting-edge solutions in the area of data indexing, data mining, and machine learning. The related results have been published in IJCAI, SIGIR, TIST, SIGMOD, ICDE, CIKM, GeoInformatica, etc.
Spatio-temporal query processing
We aim at providing efficient and effective processing schemes for advanced spatio-temporal query for a wide range of modern spatial application. Advanced spatio-temporal query comes with intractable complexity which prohibits real-time computation. To tackle this problem, we devise online indexing algorithms that can well utilized the topological information in transportation network to guarantee effective index to support efficient exact and / or approximate query. Related results have been published in VLDB, TKDE, GeoInformatica, etc.
 T. N. Chan, M. L. Yiu, and L. H. U, KARL: Fast Kernel Aggregation Queries, Proceedings of the 35th IEEE International Conference on Data Engineering (ICDE), to appear, 2019.
 Siyuan Wu, Leong Hou U, Sourav S. Bhowmick, Wolfgang Gatterbauer: PISTIS: A Conflict of Interest Declaration and Detection System for Peer Review Management. SIGMOD Conference 2018: 1713-1716.
 Leong Hou U, Junjie Zhang, Kyriakos Mouratidis, Ye Li: Continuous Top-k Monitoring on Document Streams. IEEE Trans. Knowl. Data Eng. 29(5): 991-1003 (2017)
 Li, Ye, U Hou LeongHou, Man Lung Yiu and Ngai Meng Kou. “An Experimental Study on Hub Labeling based Shortest Path Algorithms.” PVLDB 11 (2017): 445-457.
 Yan Li, Ngai Meng Kou, Hao Wang, Leong Hou U, Zhiguo Gong: A Confidence-Aware Top-k Query Processing Toolkit on Crowdsourcing. PVLDB 10(12): 1909-1912 (2017).
 Yiyang Yang, Zhiguo Gong, Qing Li, Leong Hou U, Ruichu Cai, Zhifeng Hao: A Robust Noise Resistant Algorithm for POI Identification from Flickr Data.
 Ngai Meng Kou, Yan Li, Hao Wang, Leong Hou U, Zhiguo Gong: Crowdsourced Top-k Queries by Confidence-Aware Pairwise Judgments. SIGMOD Conference 2017: 1415-1430.
 Ngai Meng Kou, Leong Hou U, Nikos Mamoulis, Yuhong Li, Ye Li, and Zhiguo Gong: A Topicbased Reviewer Assignment System. In Proceedings of VLDB2015
 Ngai Meng Kou, Leong Hou U, Nikos Mamoulis, and Zhiguo Gong: Weighted Coverage based Reviewer Assignment. In Proceedings of SIGMOD2015.
 Bailong Liao, Leong Hou U, Man Lung Yiu, Zhiguo Gong: Beyond Millisecond Latency kNN Search on Commodity Machine. IEEE Trans. Knowl. Data Eng. 27(10): 2618-2631 (2015)
 Ngai Meng Kou, Leong Hou U, Yiyang Yang, and Zhiguo Gong: Travel Topic Analysis: A Mutually Reinforcing Method for Geo-tagged Photos, Geoinformatica, to appear.
 Yiyang Yang, Zhiguo Gong, Leong Hou U: Identifying Points of Interest using heterogenous Features. ACM TIST (TIST) 5(4):68 (2014).
 Yiyang Yang, Zhiguo Gong, and Leong Hou U. Identifying points of interest by self-tuning clustering. In SIGIR, 2011.
 Siyuan Wu, Leong Hou U, Sourav S. Bhowmick, Wolfgang Gatterbauer: Conflict of Interest Declaration and Detection System in Heterogeneous Networks. CIKM 2017: 2383-2386.