Abstract
Urban swarming transportation (UST) is a type of road transportation where multiple types of vehicles such as cars, buses, trucks, motorcycles, and bicycles, as well as pedestrians are allowed and mixed together on the roads. Predicting the traffic jam speed under UST is very different and difficult from the single road network traffic prediction which has been commonly studied in the intelligent traffic system (ITS) research. In this research, the road network wide (RNW) traffic prediction which predicts traffic jam speeds of multiple roads at once by utilizing citizens’ mobile GPS sensor records is proposed to better predict traffic jam under UST. In order to conduct the RNW traffic prediction, a specific data preprocessing is needed to convert traffic data into an image representing spatial-temporal relationships among RNW. In addition, a revised capsule network (CapsNet), named OCapsNet, which utilizes nonlinearity functions in the first two convolution layers and the modified dynamic routing to optimize the performance of CapsNet, is proposed. The experiments were conducted using real-world urban road traffic data of Jakarta to evaluate the performance. The results show that OCapsNet has better performance than Convolution Neural Network (CNN) and original CapsNet with better accuracy and precision.
Highlights
The term “smart city” has been defined by IBM [1] to indicate a smart city that utilizes information and communication technology to analyze and integrate the data into core systems for running the city
We proposed capsule network (CapsNet)-based traffic jam prediction as a comparable to Convolution Neural Network (CNN)-based predictive model to deal with the road network wide (RNW) condition which is the complex road network and spatial-temporal traffic road characteristics under Urban swarming transportation (UST); We improved the performance of CapsNet by utilizing nonlinearity function in the convolution layer of CapsNet to modify dynamic routing on the two-capsule layer of the original CapsNet
We aim to propose a traffic jam prediction model that is based on the following considerations: (1) traffic data recorded by mobile sensors such as global positioning system (GPS) were used, instead of using fixed detectors on the road, (2) spatial-temporal characteristics of data were used as input image, (3) RNW
Summary
The term “smart city” has been defined by IBM [1] to indicate a smart city that utilizes information and communication technology to analyze and integrate the data into core systems for running the city. The key enabler of the smart city depends on the connected devices and how the collected data, generated through the Internet of Things (IoT) sensors [2], is used. A large amount of data collected from speed sensors or surveillance camera systems have been used to monitor traffic conditions on roads in an intelligence traffic system (ITS) domain. The most common detection technologies are loop detector, road-side cameras, and on-board equipment [3]. Yisheng, et al utilized California’s freeway traffic detector station data to predict traffic flow [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
