Jiatao Chen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiatao Chen has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
- Ming Cai
School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China
4 shared publications - Chen Xiong
Guangdong Provincial Key Laboratory of Intelligent Transportation System, School of Intelligent Systems Engineering, Shenzhen Campus of Sun Yat-sen University, Shenzhen 518107, China
1 shared publication Delong Zeng
Sun Yat-sen University, Guangdong Provincial Key Laboratory of Intelligent Transportation System, Guangzhou, China
1 shared publication- Junshu He
School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China
1 shared publication - Shuqi Zhong
School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen 518107, China
1 shared publication - Wan Wei
Bioinformatics Institute (BII), Agency for Science, Technology and Research (A*STAR), 30 Biopolis Street, 138671 Singapore
1 shared publication
Latest Publications
- Open Access
- 5 December 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (23) , 3843
A Transport Mode Detection Framework Based on Mobile Phone Signaling Data Combined with Bus GPS Data
Transport mode is one of the important travel characteristics for citizens, which is crucial to the planning and management of urban transportation. With the natural advantages of large sample sizes and a wide coverage of people, more and more researchers adopt mobile phone signaling data (MSD) to detect transport modes. However, due to their low positioning accuracy and temporally irregular nature, identifying transport modes with similar spatiotemporal features, such as the bus and car modes, is particularly challenging. We propose a transport detection framework using MSD combined with bus GPS data to distinguish between the car and bus modes. First, a trajectory matching algorithm is proposed to obtain the most probable bus that mobile phone users may take. Then, more features are mined to improve the accuracy of transport mode detection with different classification models. Furthermore, for signaling trajectories identified as the bus mode, more bus travel information is recognized, including the boarding and alighting station and timestamp. Finally, we built a ground truth dataset and compared the recognition accuracies under different features and classification models. The result shows that the transport mode detection accuracies of the proposed framework with the GBDT, XGBoost, and LightGBM algorithms are all higher than 94%.
- 5 December 2024
- Published by MDPI AG in Mathematics
- Vol. 12 (23) , 3843
Open AccessA Transport Mode Detection Framework Based on Mobile Phone Signaling Data Combined with Bus GPS Data
Transport mode is one of the important travel characteristics for citizens, which is crucial to the planning and management of urban transportation. With the natural advantages of large sample sizes and a wide coverage of people, more and more researchers adopt mobile phone signaling data (MSD) to detect transport modes. However, due to their low positioning accuracy and temporally irregular nature, identifying transport modes with similar spatiotemporal features, such as the bus and car modes, is particularly challenging. We propose a transport detection framework using MSD combined with bus GPS data to distinguish between the car and bus modes. First, a trajectory matching algorithm is proposed to obtain the most probable bus that mobile phone users may take. Then, more features are mined to improve the accuracy of transport mode detection with different classification models. Furthermore, for signaling trajectories identified as the bus mode, more bus travel information is recognized, including the boarding and alighting station and timestamp. Finally, we built a ground truth dataset and compared the recognition accuracies under different features and classification models. The result shows that the transport mode detection accuracies of the proposed framework with the GBDT, XGBoost, and LightGBM algorithms are all higher than 94%.
- Open Access
- 30 June 2023
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2023 (1) , 1-16
A Privacy-Preserving and Edge-Collaborating Architecture for Personalized Mobility
Driven by technologies and demands, the modern transportation system has developed from intelligent transportation systems (ITS) to autonomous transportation systems (ATS) to resolve intertwined demands and supplies with few human interventions. In ATS, personal mobility service (PMS) is the service that can sense real-time traffic conditions comprehensively, learn travelers’ preferences accurately, recommend multimodal travel options appropriately, and provide service responses timely to elevate the level of personalization and intelligence in smart mobility services. Since current PMS widely employs centralized approaches (CPMS) to process massive sensitive data from individuals and support diverse edge devices, resulting in high pressure in privacy protection and performance balancing, this paper presents a federated PMS (FPMS) and its design architecture in logical and physical views by adopting federated learning to provide multimodal, dynamic, and personalized travel options with system-saving safety and efficiency guaranteed. Moreover, through an extensive evaluation, the performances of CPMS and FPMS are compared to reveal the merits of FPMS in reducing costs and latency.
- 30 June 2023
- Published by Wiley in Journal of Advanced Transportation
- Vol. 2023 (1) , 1-16
Open AccessA Privacy-Preserving and Edge-Collaborating Architecture for Personalized Mobility
Driven by technologies and demands, the modern transportation system has developed from intelligent transportation systems (ITS) to autonomous transportation systems (ATS) to resolve intertwined demands and supplies with few human interventions. In ATS, personal mobility service (PMS) is the service that can sense real-time traffic conditions comprehensively, learn travelers’ preferences accurately, recommend multimodal travel options appropriately, and provide service responses timely to elevate the level of personalization and intelligence in smart mobility services. Since current PMS widely employs centralized approaches (CPMS) to process massive sensitive data from individuals and support diverse edge devices, resulting in high pressure in privacy protection and performance balancing, this paper presents a federated PMS (FPMS) and its design architecture in logical and physical views by adopting federated learning to provide multimodal, dynamic, and personalized travel options with system-saving safety and efficiency guaranteed. Moreover, through an extensive evaluation, the performances of CPMS and FPMS are compared to reveal the merits of FPMS in reducing costs and latency.
- 10 February 2023
- Published by Springer Nature in Transportation
- Vol. 51 (4) , 1433-1465
Inferring alighting bus stops from smart card data combined with cellular signaling data
- 10 February 2023
- Published by Springer Nature in Transportation
- Vol. 51 (4) , 1433-1465
Inferring alighting bus stops from smart card data combined with cellular signaling data
- Open Access
- 1 June 2020
- Published by Elsevier in Results in Physics
- Vol. 17, 103048
Fast high-precision displacement measurement system based on fringe image analysis techniques
- 1 June 2020
- Published by Elsevier in Results in Physics
- Vol. 17, 103048
Open AccessFast high-precision displacement measurement system based on fringe image analysis techniques