Open AccessResearch and Implementation of Key Techniques for Indoor Movement Object Trajectory Prediction
Author(s) -
Ping Zhang,
Qianqian Jiang,
Ruilin Zhang,
Bo Li
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1215/1/012020
Subject(s) - computer science , trajectory , scalability , global positioning system , signal (programming language) , key (lock) , real time computing , cluster analysis , location based service , set (abstract data type) , gps signals , object (grammar) , path (computing) , artificial intelligence , data mining , computer vision , assisted gps , telecommunications , computer network , database , computer security , physics , astronomy , programming language
With the popularity of smart mobile terminals and Wi-Fi signals, people’s demand for indoor location services has also increased. However, in the indoor space, GPS positioning is inaccurate, and the Wi-Fi signal may also have signal instability even no signal in some areas. This paper proposes a prediction method based on improved HMM model combined with historical trajectory clustering. The experimental results on UJIIndoorLoc data set show that the predicting trajectories can greatly improve the real-time performance of location services and the proposed method has great improvement in accuracy and scalability comparing with another model.