PROJECT TITLE :
GALLOP: Global feature fused Location Prediction for Different Check-in Scenarios - 2017
Location prediction is widely used to forecast users' next place to visit primarily based on his/her mobility logs. It's an important problem in location information processing, invaluable for surveillance, business, and personal applications. It's very difficult thanks to the sparsity problems of check-in data. An often ignored downside in recent studies is that the selection across totally different check-in eventualities, that is changing into additional urgent thanks to the increasing availability of more location check-in applications. In this paper, we have a tendency to propose a new feature fusion primarily based prediction approach, GALLOP, i.e., Global feature fused LOcation Prediction for various check-in situations. Based on the rigorously designed feature extraction ways, we tend to utilize a unique combined prediction framework. Specifically, we have a tendency to started utilize the density estimation model to profile geographical options, i.e., context info, the factorization technique to extract collaborative information, and a graph structure to extract location transition patterns of users' temporal check-in sequence, i.e., content info. An empirical study on 3 completely different check-in datasets demonstrates impressive robustness and improvement of the proposed approach.
Did you like this research project?
To get this research project Guidelines, Training and Code... Click Here