Construction of Regional Intelligent Transportation System in Smart City Road Network via 5G Network
Author:
- 14 February 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-9
Abstract
This purpose of the research is to explore the construction status and prediction performance of intelligent transportation systems in the road network of smart cities based on 5G (5th Generation Mobile Communication Technology) network, and further intellectualize the smart city. Aiming at the diversity and complexity of regional traffic influencing factors of road network in the construction of smart city, this research carries out resource real-time load balancing scheduling from the perspective of 5G heterogeneous network. Meanwhile, CNN (convolutional neural network) in the introduced deep learning algorithm is improved, and finally an intelligent traffic prediction model is constructed based on 5G load balancing and AlexNet network. The model is simulated and its performance is analyzed. The results show that the algorithm proposed is compared with LSTM (Long Short-Term Memory), CNN, RNN (Recurrent Neural Network), VGGNet (Visual Geometry Group Network), and BN (Bayesian network) models regarding Accuracy, Precision, Recall, and F1. It is found that the road network prediction accuracy of the algorithm proposed is 94.05%, which is at least 4.29% higher than that of the model algorithm proposed by other scholars. The analysis of network data transmission synchronization performance suggests that there are obvious performance improvements in access delay, access collision rate, reliability, and network throughput. Among them, the packet loss rate is lower than 0.1, the access collision rate is basically stable at about 0, the access time is stable at about 75ms, and the sending throughput is basically maintained at about 1, which is significantly better than the performance of other algorithms. Therefore, the intelligent transportation system can achieve better data transmission performance under the premise of ensuring high prediction performance, with prominent instantaneity, which can provide experimental basis for the intelligent development of transportation in smart cities.Keywords
Funding Information
- Chinese Academy of Science Technology for Development CASTED
- College Scientific Research Project of China University of Political Science Law (20ZFG63001)
This publication has 38 references indexed in Scilit:
- Data-Driven Deep Learning for Automatic Modulation Recognition in Cognitive RadiosIEEE Transactions on Vehicular Technology, 2019
- A Sample Update-Based Convolutional Neural Network Framework for Object Detection in Large-Area Remote Sensing ImagesIEEE Geoscience and Remote Sensing Letters, 2019
- Efficient image encryption and compression based on a VAE generative modelJournal of Real-Time Image Processing, 2018
- Deep learning methods in transportation domain: a reviewIET Intelligent Transport Systems, 2018
- Government affairs service platform for smart cityFuture Generation Computer Systems, 2018
- An enhanced framework for multimedia data: Green transmission and portrayal for smart traffic systemComputers and Electrical Engineering, 2018
- Cryptanalyzing and Improving a Novel Color Image Encryption Algorithm Using RT-Enhanced Chaotic Tent MapsIEEE Access, 2018
- sdnMAC: A Software-Defined Network Inspired MAC Protocol for Cooperative Safety in VANETsIEEE Transactions on Intelligent Transportation Systems, 2018
- An Efficient Deep Learning Model to Predict Cloud Workload for Industry InformaticsIEEE Transactions on Industrial Informatics, 2018
- Deep Learning-Based Socio-Demographic Information Identification From Smart Meter DataIEEE Transactions on Smart Grid, 2018