Smart City Gnosys
Smart city article details
| Title | A Gis Based Spatiotemporal Modelling Approach For Cycling Risk Mapping Using Crowd-Sourced Sensor Data |
|---|---|
| ID_Doc | 1953 |
| Authors | Feizizadeh B.; Omarzadeh D. |
| Year | 2025 |
| Published | Annals of GIS, 31, 2 |
| DOI | http://dx.doi.org/10.1080/19475683.2025.2453550 |
| Abstract | The major objective of this study is to apply integrated data-driven methods to estimate cyclist risk and discomfort in Berlin based on the OpenSenseMap dataset. The proposed approach makes use of crowd-sourced sensor data collected during cycling (speed, bike vibration, distance to other objects), spatial statistics and multi-criteria decision analysis to provide a continuous estimation of cycling discomfort and risk in the traffic network. We employed cycling traffic volume and route discomfort estimation techniques to determine the spatiotemporal patterns of cycling traffic volume and discomfort levels. Accordingly, a GIS-based multiple criteria analysis approach was applied to map areas with high cycling traffic volume based on the condition of the cycling lanes, environmental, road traffic, land use and sociodemographic characteristics. The results show that the central area of Berlin has a high cycling traffic volume as well as a high level of discomfort. In this context, we found a significant spatial correlation between the cycling traffic volume and discomfort with the land use characteristics such as commercial or residential areas, motor vehicle traffic volume and sociodemographic characteristics in Berlin. Furthermore, results revealed a correlation between intensive traffic volume and commercial zones, schools and university areas. As we identified high-risk cycling directions and their autocorrelation with relevant indicators, the obtained results from this study will support decision-makers and authorities in recognizing the high-risk cycling areas and optimizing the risk areas, which accordingly increase the cycling safety and wellbeing of citizens. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group, on behalf of Nanjing Normal University. |
| Author Keywords | crowd-sourced sensor data; Cycling risk analysis; OpenSenseMap data; spatiotemporal analysis |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
27990  | 0.894 | Brito B.; Costa D.G.; Silva I. | Geospatial Risk Assessment Of Cyclist Accidents In Urban Areas: A K-Means Clustering Approach | 2024 IEEE 22nd Mediterranean Electrotechnical Conference, MELECON 2024 (2024) |
| 23768 | 0.865 | Ferreira J.M.; Costa D.G. | Enhancing Cycling Safety In Smart Cities: A Data-Driven Embedded Risk Alert System | Smart Cities, 7, 4 (2024) |
| 57738 | 0.858 | Oliveira F.; Costa D.G. | Toward Sustainable Cycling: Modelling And Visualization Issues Of Cycle Paths For Iot-Based Sensing | 2021 IEEE Globecom Workshops, GC Wkshps 2021 - Proceedings (2021) |
| 37229 | 0.855 | Ferreira J.M.; Bittencourt J.C.N.; Costa D.G. | Mobialert: A Data-Driven Embedded System Approach To Enhance Safety For Cyclists | 2024 IEEE Smart Cities Futures Summit, SCFC 2024 (2024) |
| 9519 | 0.85 | Cuong D.V.; Ngo V.M.; Cappellari P.; Roantree M. | Analyzing Shared Bike Usage Through Graph-Based Spatio-Temporal Modeling | IEEE Open Journal of Intelligent Transportation Systems, 5 (2024) |