In Japan, Society 5.0 has been promoted by the government, which aims at integrating cyberspace and physical space to realize better and sophisticated societies, communities, industry and economy. Towards such a society, we need to acquire more information from the physical space for higher level of context recognition and understanding of real-world objects and phenomena, and consequently the number of such sensors will increase and the amount of information which they sense will also increase. Accordingly, the data analysis is conducted in remote locations (e.g. cloud servers) and the data collection cost might be a primary issue. Besides, it would not be ignorable as machine learning generally incurs significant workload at the cloud servers. In this talk, our smart sensing approaches that involve edge computing concept are introduced to show how these approaches address those issues in different smart city applications.