OCP: an OLAP-based bus crowdedness smart-perceiving mechanism for urban transportation

In this paper, we deal with the problem of similarity search about crowdedness for participatory-sensing buses urban transportation. Similarity is usually applied measuring similarities in heterogeneous information networks. However, many models implement a global setting, without taking object attributes into consideration. OCP, novel OLAP-based perception, an attribute-enriched and meta-path-based model machine learning to capture based on connectivity, visibility features. A set common attribute dimensions are defined across different types objects, which can be obtained from participatory passenger’s sensor data through deep-neural-network-based posture recognition. Accordingly, described as series node vectors dimensions. such framework, OLAP analysing multiple resolutions improving efficiency search. addition, our sources instead using vehicle GPS systems. As more collected participatory-sensing, accurate bus estimated. The experiment results further demonstrate analytical approaches.