An End-to-End Point of Interest (POI) Conflation Framework

Raymond Low,Zeynep Duygu Tekler,Lynette Cheah

doi:10.3390/ijgi10110779

Abstract

Point of interest (POI) data serves as a valuable source of semantic information for places of interest and has many geospatial applications in real estate, transportation, and urban planning. With the availability of different data sources, POI conflation serves as a valuable technique for enriching data quality and coverage by merging the POI data from multiple sources. This study proposes a novel end-to-end POI conflation framework consisting of six steps, starting with data procurement, schema standardisation, taxonomy mapping, POI matching, POI unification, and data verification. The feasibility of the proposed framework was demonstrated in a case study conducted in the eastern region of Singapore, where the POI data from five data sources was conflated to form a unified POI dataset. Based on the evaluation conducted, the resulting unified dataset was found to be more comprehensive and complete than any of the five POI data sources alone. Furthermore, the proposed approach for identifying POI matches between different data sources outperformed all baseline approaches with a matching accuracy of 97.6% with an average run time below 3 min when matching over 12,000 POIs to result in 8699 unique POIs, thereby demonstrating the framework’s scalability for large scale implementation in dense urban contexts.

Highlights

The ubiquitous use of mobile devices, combined with advancements in location-aware technologies, has increased our ability to capture individual mobility data at increasing geospatial-temporal resolutions, fueling research from transportation and urban sciences [1] to studies on occupancy patterns in the built environment [2]
This study proposes a novel end-to-end points of interest (POI) conflation framework that consists of six steps, starting with data procurement, schema standardisation, taxonomy mapping, POI matching, POI unification, and data verification
The feasibility of the proposed framework was demonstrated in a case study conducted in the eastern region of Singapore, where the POI data from five data sources was conflated to form a unified POI dataset

Summary

Introduction

The ubiquitous use of mobile devices, combined with advancements in location-aware technologies, has increased our ability to capture individual mobility data at increasing geospatial-temporal resolutions, fueling research from transportation and urban sciences [1] to studies on occupancy patterns in the built environment [2]. A potential application of this capability includes the identification of points of interest (POI) by analysing users’ mobility data to identify specific locations of interest that are regularly visited by the same user or by a large number of distinct users throughout the day [3,4]. Other than passively analysing the users’ mobility data, a more active data collection approach involves crowdsourcing, where a community of volunteers are asked to provide semantic information about a recently visited location to assemble and maintain a high-resolution geospatial database [5]. With the continual changes in POI data over time due to business renewals and urban development, these valuable sources of geospatial data continue to remain relevant with many potential application areas in various fields.

Results

Discussion

Conclusion