A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Analysis on spatiotemporal urban mobility based on online car-hailing data
Abstract As an emerging travel mode, online car-hailing plays an increasingly important role in people's daily travel. Car-hailing data provide a new source to study human mobility in urban areas. This study focuses on identifying the distribution of regions with high travel intensity and the correlation between travel intensity and points of interest (POIs), based on the online car-hailing data collected in Chengdu, China. Firstly, the whole city area was divided into 16,100 uniform blocks and the number of pick-up and drop-off activities in each block was counted. Then, all POIs were categorized into 13 types and the number of different types of POIs in each block was counted. On this basis, the grade of travel intensity and POIs density in each block was identified according to the number of travel activities and POIs respectively. Finally, the correlation between the travel intensity and the POIs density was explored with ordered logistic regression. Experiment results showed that regions with high travel intensity are mainly distributed within the Second Ring Road, while those in the suburbs of city are usually the large transportation hubs, such as airports and train stations. Different types of POIs have different impacts on the online car-hailing travel intensity, and the density of traffic facilities has the greatest impact, including pick-up and drop-off, followed by density of scenic spot. The densities of service facilities and sports facility have an impact on the intensity of pick-up, while the impact on the intensity of drop-off is not significant. The density of company has no significant impact on the intensity of neither pick-up nor drop-off. These findings can contribute to a better understanding of online car-hailing travel activities and their relation with the urban space, and can provide useful information for urban planning and location-based services.
Analysis on spatiotemporal urban mobility based on online car-hailing data
Abstract As an emerging travel mode, online car-hailing plays an increasingly important role in people's daily travel. Car-hailing data provide a new source to study human mobility in urban areas. This study focuses on identifying the distribution of regions with high travel intensity and the correlation between travel intensity and points of interest (POIs), based on the online car-hailing data collected in Chengdu, China. Firstly, the whole city area was divided into 16,100 uniform blocks and the number of pick-up and drop-off activities in each block was counted. Then, all POIs were categorized into 13 types and the number of different types of POIs in each block was counted. On this basis, the grade of travel intensity and POIs density in each block was identified according to the number of travel activities and POIs respectively. Finally, the correlation between the travel intensity and the POIs density was explored with ordered logistic regression. Experiment results showed that regions with high travel intensity are mainly distributed within the Second Ring Road, while those in the suburbs of city are usually the large transportation hubs, such as airports and train stations. Different types of POIs have different impacts on the online car-hailing travel intensity, and the density of traffic facilities has the greatest impact, including pick-up and drop-off, followed by density of scenic spot. The densities of service facilities and sports facility have an impact on the intensity of pick-up, while the impact on the intensity of drop-off is not significant. The density of company has no significant impact on the intensity of neither pick-up nor drop-off. These findings can contribute to a better understanding of online car-hailing travel activities and their relation with the urban space, and can provide useful information for urban planning and location-based services.
Analysis on spatiotemporal urban mobility based on online car-hailing data
Zhang, Bin (author) / Chen, Shuyan (author) / Ma, Yongfeng (author) / Li, Tiezhu (author) / Tang, Kun (author)
2019-10-15
Article (Journal)
Electronic Resource
English
Spatiotemporal Prediction of Urban Online Car-Hailing Travel Demand Based on Transformer Network
| DOAJ | 2022
Identification of Urban Jobs–Housing Sites Based on Online Car-Hailing Data
| DOAJ | 2023
Self-Attention ConvLSTM for Spatiotemporal Forecasting of Short-Term Online Car-Hailing Demand
| DOAJ | 2022