| 1. |
- Jia, Ruo, 1993, et al.
(författare)
-
A spatio-temporal deep learning model for short-term bike-sharing demand prediction
- 2023
-
Ingår i: Electronic Research Archive. - : American Institute of Mathematical Sciences (AIMS). - 2688-1594. ; 31:2, s. 1031-1047
-
Tidskriftsartikel (refereegranskat)abstract
- Bike-sharing systems are widely operated in many cities as green transportation means to solve the last mile problem and reduce traffic congestion. One of the critical challenges in operating high-quality bike-sharing systems is rebalancing bike stations from being full or empty. However, the complex characteristics of spatiotemporal dependency on usage demand may lead to difficulties for traditional statistical models in dealing with this complex relationship. To address this issue, we propose a graph-based neural network model to learn the representation of bike-sharing demand spatial-temporal graph. The model has the ability to use graph-structured data and takes both spatial -and temporal aspects into consideration. A case study about bike-sharing systems in Nanjing, a large city in China, is conducted based on the proposed method. The results show that the algorithm can predict short-term bike demand with relatively high accuracy and low computing time. The predicted errors for the hourly station level usage demand prediction are often within 20 bikes. The results provide helpful tools for short-term usage demand prediction of bike-sharing systems and other similar shared mobility systems.
|
|
| 2. |
- Zhang, Zhe, et al.
(författare)
-
How do travel characteristics of ridesplitting affect its benefits in emission reduction? evidence from Chengdu
- 2023
-
Ingår i: Transportation Research Part D: Transport and Environment. - 1361-9209. ; 123
-
Tidskriftsartikel (refereegranskat)abstract
- Ridesplitting, a shared mobility service, has the potential to reduce traffic-related air pollution. This study evaluates the impacts of ridesplitting on reducing different types of emissions and investigate how travel characteristics of ridesplitting affect emission reduction based on a ridesourcing dataset in Chengdu, China. First, this study quantifies the influence of ridesplitting on emissions reduction compared to single ride (i.e., non-ridesplitting) for each trip. The results indicate that a ridesplitting trip averagely reduce CO2, CO, NOx, and HC emissions by 34.52%, 5.98%, 33.10%, and 13.42%, respectively. Subsequently, using explainable machine learning, we quantitatively analyze how the travel characteristics of ridesplitting affect emission reduction at two levels. At the trip level, shared travel distance, shared travel time, delay, and detour are important factors for emission reduction. At the grid level, the number of orders that match co-riders within the same spatial community is more important than the total number of orders.
|
|
| 3. |
- Parishwad, Omkar, 1987, et al.
(författare)
-
Prospects of the Activity-Based Modelling Approach: A Review of Sweden’s Transport Model- SAMPERS
- 2023
-
Ingår i: Smart Innovation, Systems and Technologies. - : Springer. - 2190-3026 .- 2190-3018. - 9789819932832 ; 356, s. 139-148
-
Konferensbidrag (refereegranskat)abstract
- The rapid changes in global development scenarios, such as technological advancements, lifestyle decisions and climate change, call for updated transport models to test micro-level policy decisions. This paper explores the advances in activity-based transport modelling in simulating travel demand in urban scenarios, focusing on Sweden’s National Transport model. Sampers is used for impact analysis, investment calculations for traffic simulations, transport policy implementation evaluations, and accessibility and impact analysis of extensive changes in land use and transport systems in cities and regions of Sweden. This research systematically compares individual components, sub-models, and algorithms and discusses integrations with cutting-edge agent-based models. Furthermore, recent research and projects for Sampers are investigated, highlighting its advantages over current models, potential gaps and limitations, and long-term development prospects. The study concludes by cross-referencing Sampers’ global developments and regional needs to assess its long-term development prospects.
|
|
| 4. |
- Qiu, Chen, et al.
(författare)
-
A Network-Wide Traffic Speed Estimation Model with Gaussian Process Inference
- 2023
-
Ingår i: Smart Innovation, Systems and Technologies. - 2190-3026 .- 2190-3018. ; 356, s. 221-228
-
Konferensbidrag (refereegranskat)abstract
- Accurate urban road traffic speed analysis and prediction are important for the application of intelligent transportation systems. However, the limited and inefficient traffic state monitoring infrastructure installed on urban roads makes it difficult to monitor the traffic state of an entire network. Moreover, the complex characteristics of urban road networks may lead to difficulties for traditional statistical and traffic flow models in dealing with this type of complex relationship. Therefore, this study proposes a network-wide traffic speed estimation model with full spatial and temporal coverage and selects floating vehicle trajectory data in an actual road network for experiments. The results show that the proposed model can accurately estimate the full spatiotemporal traffic state of a traffic network with only partial data input. This method can be effectively applied to urban road state estimation and can provide a scientific basis for traffic management departments to formulate congestion mitigation strategies.
|
|
| 5. |
- Wang, Shuli, 1996, et al.
(författare)
-
Multivariate Sequence Clustering for Driving Preference Classification Based on Wide-Range Trajectory Data
- 2023
-
Ingår i: Smart Innovation, Systems and Technologies. - 2190-3026 .- 2190-3018. ; 356, s. 45-54
-
Konferensbidrag (refereegranskat)abstract
- Accurate driving preferences classification is a crucial component for autonomous connected vehicles in making more safety and more efficient driving decisions. Most existing studies identify drivers’ driving preferences based on the historical data of the individual vehicle, and the selected variables are limited to the mechanical motion of the vehicle, which seldomly takes the influence of road traffic conditions and surrounding vehicles into account. This study proposes a driving preferences classification method by multivariate sequence clustering algorithm based on wide-range trajectory data. Based on the specific range of road sections, the selected variables for each trajectory are converted from the time domain to the space domain separately, to capture the dynamic changes of the features along the road area. Multivariate time series clustering combining a weighted Dynamic Time Warping (WDTW) and the k-medoids algorithm is used to classify driving preferences into different levels, and a popular internal evaluation metric is employed to determine the optimal cluster result. This study also investigates the heterogeneity of driving behaviors at different driving preference levels. The results show that the proposed method could better recognize drivers’ internal driving preferences.
|
|
