期刊
ACM TRANSACTIONS ON INTELLIGENT SYSTEMS AND TECHNOLOGY
卷 13, 期 1, 页码 -出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/3465060
关键词
Location prediction; semantic information; data sparsity; cold-start; trajectory pattern mining
资金
- National Science Foundation of China [62072365, 61772392]
- National Key R&D Program of China [2020AAA0107100, 2020YFB1406900]
- Key Research and Development Program of Shaanxi [.2020KW-002]
- Innovation Capability Support Plan of Shaanxi [2021PT-010]
Location prediction plays an important role in many location-based services. Traditional methods solely rely on spatial-temporal trajectory data, lacking semantic knowledge and hindering our understanding of user activities. We propose ST-LSTM, a method that incorporates semantic trajectories to enhance location prediction accuracy. To address the sparsity of semantic data, we introduce a strategic filling algorithm. Additionally, we tackle the cold-start problem by establishing a virtual social network for users. Experimental results demonstrate the superiority of our method over baselines.
Location prediction has attracted much attention due to its important role in many location-based services, including taxi services, route navigation, traffic planning, and location-based advertisements. Traditional methods only use spatial-temporal trajectory data to predict where a user will go next. The divorce of semantic knowledge from the spatial-temporal one inhibits our better understanding of users' activities. Inspired by the architecture of Long Short Term Memory (LSTM), we design ST-LSTM, which draws on semantic trajectories to predict future locations. Semantic data add a new dimension to our study, increasing the accuracy of prediction. Since semantic trajectories are sparser than the spatial-temporal ones, we propose a strategic filling algorithm to solve this problem. In addition, as the prediction is based on the historical trajectories of users, the cold-start problem arises. We build a new virtual social network for users to resolve the issue. Experiments on two real-world datasets show that the performance of our method is superior to those of the baselines.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据