Corridor Detection from Large GPS Trajectories Datasets

Claudia Cavallaro,Jordi Vitrià

doi:10.3390/app10145003

Claudia Cavallaro, Jordi Vitrià

Open Access

https://doi.org/10.3390/app10145003

Copy DOI

Journal: Applied sciences	Publication Date: Jul 21, 2020
Citations: 6	License type: CC BY 4.0

Affiliation: University of Catania, University of Barcelona

Abstract

Given the widespread use of mobile devices that track their geographical location, it has become increasingly easy to acquire information related to users’ trips in real time. This availability has triggered several studies based on user’s position, such as the analysis of flows of people in cities, and also new applications, such as route recommendation systems. Given a dataset of geographical trajectories in an urban metropolitan area, we propose a new algorithm to detect corridors. Corridors can be defined as geographical paths, with a minimum length, that are commonly traversed by a minimum number of different users. We propose an efficient strategy based on the Apriori algorithm to extract frequent trajectory patterns from the geo-spatial dataset. By discretizing the data and adapting the roles of itemsets and baskets of this algorithm to our context, we find the longest corridors formed by cells shared by a minimum number of trajectories. After that, we refine the results obtained with a subsequent filtering step, by using a Radius Neighbors Graph. To illustrate the algorithm, the GeoLife dataset is analyzed by following the proposed method. Our approach is relevant for transportation analytics because it is the base to detect lacking lines in public transportation systems and also to recommend to private users which route to take when moving from one part of the city to another on the basis of behavior of the users who provided their logs.

Highlights

The analysis of large human mobility datasets has the potential to provide many useful suggestions to public operators as well as to individual users, but in order to provide this information in a timely manner, efficient algorithms are needed.In this scenario, corridor detection has emerged as one of the key elements to make informed decisions about public transportation systems as well to recommend optimal routes to individual users
We are proposing in this paper a new approach, based on the Apriori algorithm [1], which is suitable to the use in very large datasets
Since we only considered the last level of the output of the Apriori algorithm, in this step we turned to analyze the subsets of cells that dot not appear in the last result of Apriori: the trajectories which do not participate in frequent itemsets of the longest cells

Summary

Introduction

The analysis of large human mobility datasets has the potential to provide many useful suggestions to public operators as well as to individual users, but in order to provide this information in a timely manner, efficient algorithms are needed In this scenario, corridor detection has emerged as one of the key elements to make informed decisions about public transportation systems as well to recommend optimal routes to individual users. Corridor detection has emerged as one of the key elements to make informed decisions about public transportation systems as well to recommend optimal routes to individual users In this case, the use of a brute-force algorithm is not an alternative due to its computational cost and more efficient solutions are necessary. We consider two alternating roles for items and baskets: in the first case, GPS points are represented as a set of items and trajectories as a set of baskets, but later we reverse this assignment and consider GPS points as a set of baskets and

Objectives

Methods

Results

Conclusion