User relationship analysis in campus based on WiFi Hotspots

With the rapid development of mobile Internet, the way users access the network becomes diverse, which provide much convenience for us to collect huge amount of users' information. In this paper, we present a model of measuring relationship between two users in campus and build a wireless data analysis system called WiCloud to verify our model. This work has several potential applications such as recommendation, advertisement targeting, and privacy protection. A novel method using decision tree model, which is usually used for decision analysis, is proposed to measure the relationship between two users in wireless network. Experiments results on real datasets validate our ideas and verify the feasibility and efficiency. Experimental results show that the accuracy of the training set is 100%, while the accuracy of the test set is 88.9%.