Abstract

In this work, we investigate the performance of Markov Chains with respect to modelling semantic trajectories and predicting future locations. In the first part, we examine whether and to what degree the semantic level of semantic trajectories affects the predictive performance of a spatial Markov model. It can be shown that the choice of the semantic level when describing trajectories has a significant impact on the accuracy of the models. High-level descriptions lead to better results than low-level ones. The second part introduces a multi-dimensional Markov Chain construct that considers, besides locations, additional context information, such as time, day and the users’ activity. While the respective approach is able to outperform our baseline, we could also identify some limitations. These are mainly attributed to its sensitivity towards small-sized training datasets. We attempt to overcome this issue, among others, by adding a semantic similarity analysis component to our model that takes the varying role of locations due each time to the respective purpose of visiting the particular location explicitly into consideration. To capture the aforementioned dynamics, we define an entity, which we refer to as Purpose-of-Visit-Dependent Frame (PoVDF). In the third part of this work, we describe in detail the PoVDF-based approach and we evaluate it against the multi-dimensional Markov Chain model as well as with a semantic trajectory mining and prefix tree based model. Our evaluation shows that the PoVDF-based approach outperforms its competition and lays a solid foundation for further investigation.

Highlights

  • According to recent statistics published by eMarketer [1], 242 million people in the USA are expected to use location-based services (LBS) in 2018

  • Markov model (MHMM) [10] on semantic locations coming from a location based social network (LBSN) [11]

  • It can be seen that Users 3, 5, 7 and 8 provided the least annotations

Read more

Summary

Introduction

According to recent statistics published by eMarketer [1], 242 million people in the USA are expected to use location-based services (LBS) in 2018. Up to this point and to the best of our knowledge, none of the semantic trajectory based approaches have taken the varying role and human perception of locations into account Instead, they constrain themselves to static semantic location types and inflexible associations between locations and users as described in the related work section below (Section 2). The core idea of the approach presented here lies in a dynamic and context-aware clustering of semantic locations For this purpose, we combine two different modelling techniques, a data-driven one and a knowledge-driven one, by using the semantic similarity analysis as a fusing component. For this purpose, we compare two different representation levels by mapping the available locations in our training and evaluation dataset correspondingly (e.g., burger joint to restaurant).

Related Work
Semantic Trajectories
Markov Chain Model
Evaluation
A Multi-Dimensional Markov Chain Model for Modelling Semantic Trajectories
User Study
Results
H As ea ar ia le d
Semantic Enriched Location Data and Ontology-Based Knowledge Base
PoVDSSA-Based Model Optimization Process
Result
Conclusions and Future Work
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call