Predicting Future Locations with Deep Fuzzy-LSTM Network
Lists
Only you see this
Abstract
Current studies on trajectory prediction have two limitations. Spatial division approaches in most existing studies lead to sharp boundary problem of predicting methods. On the other hand, most of traditional predicting models such as Markov could only use a few latest historical locations, making long-term prediction inaccurate. To overcome these limitations,a location prediction method based on deepFuzzy-LSTM Network is proposed. The method employs a long short term memory based network to solve the long-term dependencies problem. By defining the fuzzy-based trajectory and the improved LSTM cell structure, our method solves the sharp boundary problem caused by space partition. It also considers both period and closeness of movement patterns in making prediction. We compare classical NLPMM, Naïve-LSTM and Fuzzy-LSTM methods with a cell signaling dataset consisting of the continuous trajectories of one hundred thousand city residents in 15 workdays. Results show that the proposed Fuzzy-LSTM method gets a precision of 83.98%, 6.95% higher than the NLPMM model and 4.36% higher than Naïve-LSTM model.
BibTeX
@inproceedings{li2018predicting,
author = {Mingxiao Li and Hengcai Zhang and Qiu Peiyuan and Shifen Cheng and Jie Chen and Feng Lu},
title = {{Predicting Future Locations with Deep Fuzzy-LSTM Network}},
booktitle = {SHILAP},
year = {2018},
doi = {10.11947/j.agcs.2018.20170268},
}Loading related content...