Journal Article

Mining Object Similarity for Predicting Next Locations

Meng Chen Xiaohui Yu Yang Liu

2016

Overview

Next location prediction is of great importance for many location-based applications. With the virtue of solid theoretical foundations, Markov-based approaches have gained success along this direction. In this paper, we seek to enhance the prediction performance by understanding the similarity between objects. In particular, we propose a novel method, called weighted Markov model （weighted-MM）, which exploits both the sequence of just-passed locations and the object similarity in mining the mobility patterns. To this end, we first train a Markov model for each object with its own trajectory records, and then quantify the similarities between different objects from two aspects： spatial locality similarity and trajectory similarity. Finally, we incorporate the object similarity into the Markov model by considering the similarity as the weight of the probability of reaching each possible next location, and return the top-rankings as results. We have conducted extensive experiments on a real dataset, and the results demonstrate significant improvements in prediction accuracy over existing solutions.

• Publisher: Springer US,Springer Nature B.V,School of Computer Science and Technology, Shandong University, Jinan 250101, China
• Subject: Accuracy / Artificial Intelligence / Computer Science / Computer simulation / Data Structures and Information Theory / Foundations / Grants / Information Systems Applications (incl.Internet) / Location based services / Markov analysis / Markov chains / Markov models / Mathematical models / Mining / Predictions / Regular Paper / Similarity / Software Engineering / Studies / Surveillance / Theory of Computation / Trajectories / 位置预测 / 基础 / 数据集 / 相似性挖掘 / 空间局部性 / 预测性能 / 预测精度 / 马尔可夫模型