Focusing on the important supporting role of big data in the process of urban intelligence, the research group integrate intelligent technologies for mining the value of big data in developing a smart city. One of the key research areas is to investigate learning and representation algorithms by combining knowledge graph and big data; propose joint models by integrating structural information and big data, so as to more effectively describe the linkage among the inner and outer entities of knowledge graph; automatically fill in the missing information of knowledge graph with deep modeling; propose multi-labeled relation extraction algorithms by attention-based capsule networks; explore multi-source sensing and fusion of urban big data; conduct urban big data mining and analysis with transfer learning and federated learning.
With the widespread adoption of could computing platforms, data encryption has to be conducted prior to the various data processing tasks. This new trend of data processing makes the research on encrypted-domain signal processing more and more popular. By jointly considering the data encryption and compression, we pr [...]
Spatio-Temporal data analytics: Spatio-Temporal data, generated by either GPS-embedded equipment (such as iPhones) or manual inputs from users, contains large amount of noise, which makes the quality of the data analysis significantly low in many applications. To solve the problem, we propose a reinforcement learning [...]
Urban big data and wisdom perception system Urban environments are highly heterogeneous as well as environmental disturbances. Therefore, it's important to construct a novel Internet of Things framework that is able to perceive the decentralized, redundant and heterogeneous urban data in depth, and establish large-sc [...]