Dr. Deng was awarded a PhD degree in computer science at The University of Queensland (UQ) in 2007 with focus on data and knowledge engineering. He also hold a Master degree in Information and Communication Technology in 2001 and a Bachelor degree in Electrical Engineering in 1994. He had been an acting lecturer and course convener in the School of Information Technology and Electrical Engineering at UQ during 2008-2012, and the co-supervisor of one PhD student. He had been a postdoctoral research fellow at CSIRO ICT center in 2007. He had been an ARC Australian Postdoctoral Fellow working during 2010-2012. He had been a researcher in Huawei Noah Ark’s Research Lab, Hong Kong from June 2013. The Noah’s Ark Lab conducts state-of-the-art research in data mining and artificial intelligence by exploring theories and building intelligent systems.
More information on Dr Deng's research interests and publications can be found on his personal website.
- COSC1114 Operating System Principles
- 2015 PhD Project (one scholarship, please contact me if you are interested)
The smart city are also known as ubiquitous city, intelligent cities, virtual cities, digital cities, knowledge cities which are all perspectives on the idea that ICT is central to the operation of the future city, even though it has been recognized the use of ICT alone does not make cities smart - other dimensions include cultural and natural amenities, people and skills, knowledge precincts and governance. Many cities in Asian, Europe, and America such as Hong Kong, Amsterdam and Osaka currently have smart city projects. Robust urban computing requires the combination of a huge amount of static knowledge about the city (i.e. urban, social and cultural knowledge) with an even much larger set of dynamic data (originating in real time from heterogeneous and multiple sources). The most dominant dynamic data perhaps are the trajectories of massive humans and vehicles in the city. In the last decade, trajectory-data-intensive urban computing has attracted much attention from ICT researchers and industrial practitioners to address problems, combined with other city information, in urban planning, city transport, social applications, environment, urban energy consumption, economy, public safety and security.
However, urban computing on trajectory data is still in its early stage. First, the concept of smart city encompasses so many aspects of complex city life such that new urban computing problems continuously emerge, for example, the recharge station positioning for electrical vehicles. Second, most exiting urban computing solutions explore single-source data (e.g., using taxi trajectory data only); as a consequence, the robustness of solution is largely constrained by the limited information of the single-source data (e.g., taxi trajectory data has nothing related to the population using public transport systems). In the progress towards smart city, the information about different facets in the same urban space, unknown previously, becomes more and more available, for example, the trajectories of bus/subway passengers using smartcard ticketing system devices, the trajectories of cell phone users, the trajectories of buses, and the trajectories of social media check-ins. While heterogeneous trajectory data provide unprecedented rich information to enable robust solutions of urban computing problems, it introduces enormous technical challenges in order to settle heterogeneity.
Aim 1: Develop a heterogeneous data management system which comprises a distributed data storage and management layer and data access layer.
Aim 2: The comprehensive transport patterns in hierarchical scale levels will be disclosed to enable robust traffic efficiency analysis throughout a city, to learn the impact of city events to local traffic, and to enable other urban computing tasks investigated in this project.
Aim 3: The study provides insight to the characteristics of regions and social communities in the city which helps better facility planning, social interaction, and collaboration of local communities for mutual benefits.
- Masters Project
- Huang, G.,Deng, K.,Xie, Z.,He, J. (2020). Intelligent pseudo-location recommendation for protecting personal location privacy In: Concurrency Computation, 32, 1 - 11
- Li, J.,Cai, T.,Deng, K.,Wang, X.,Sellis, T.,Xia, F. (2020). Community-diversified influence maximization in social networks In: Information Systems, 92, 1 - 12
- Huang, G.,Deng, K.,He, J. (2020). Cognitive Traffic Anomaly Prediction from GPS Trajectories Using Visible Outlier Indexes and Meshed Spatiotemporal Neighborhoods In: Cognitive Computation, 12, 967 - 978
- Deng, K.,Li, Y.,Zeng, J.,Yuan, M.,Luo, J.,Yu, J. (2019). User Preference Analysis for Most Frequent Peer/Dominator In: IEEE Transactions on Knowledge and Data Engineering, 31, 1412 - 1425
- Tian, Q.,Li, J.,Chen, L.,Deng, K.,Li, R.,Reynolds, M.,Liu, C. (2019). Evidence-driven dubious decision making in online shopping In: World Wide Web, 22, 2883 - 2899
- Huang, G.,Deng, K.,Ren, Y.,Li, J. (2019). Root Cause Analysis of Traffic Anomalies Using Uneven Diffusion Model In: IEEE Access, 7, 16206 - 16216
- Cai, B.,Huang, G.,Xiang, Y.,He, J.,Huang, G.,Deng, K.,Zhou, X. (2018). Clustering of multiple density peaks In: Proceedings of the 22nd Pacific-Asia Conference on Knowledge Discovery and Data Mining, Switzerland, 3-6 June 2018
- Xie, Q.,Pang, C.,Zhou, X.,Zhang, X.,Deng, K. (2018). Error-Bounded Approximation of Data Stream: Methods and Theories In: Learning from Data Streams in Evolving Environments, Springer, Cham, Switzerland
- Rumi, S.,Deng, K.,Salim, F. (2018). Crime event prediction with dynamic features In: EPJ Data Science, 7, 1 - 27
- Rumi, S.,Deng, K.,Salim, F. (2018). Theft prediction with individual risk factor of visitors In: Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems, Seattle, United States, 06-09 November 2018
4 PhD Completions8 PhD Current Supervisions and 1 Masters by Research Current Supervisions
- Personalised Online Learning Analytics by Exploring Multilayer Graph Data (Administered by Deakin University). Funded by: ARC Linkage via Other University from (2019 to 2021)
- Effective and Efficient Query Processing over Dynamic Social Networks (Administered by Swinburne University of Technology). Funded by: ARC Discovery Projects 2016 from (2016 to 2019)