Miao Yu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Miao Yu has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
- Hao Zhang
Business School, China University of Political Science and Law, Beijing, China
3 shared publications - Jian Fu
Business School, China University of Political Science and Law, Beijing, China
3 shared publications - Jiaqi Li
Management School, Xiamen University, Xiamen, China
2 shared publications - Shuling Kang
Business School, China University of Political Science and Law, Beijing, China
2 shared publications - Chunshan Du
Business School, China University of Political Science and Law, Beijing 100088, China
1 shared publication Dingyi Yao
Business School, China University of Political Science and Law, Beijing 100088, China
1 shared publication
Latest Publications
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 17244-17254
The Intelligent Traffic Safety System Based on 6G Technology and Random Forest Algorithm
The main objective of this study is to explore and evaluate the application potential of combining Sixth Generation (6G) technology and random forest (RF) algorithm in the intelligent traffic safety system. This study designs and implements an intelligent traffic safety system using the RF algorithm and 6G technology, to improve the traffic conditions’ real-time monitoring and prediction ability. The advantages of 6G technology in real-time data transmission and efficient data processing. Moreover, the application of the RF algorithm in traffic congestion and accident prediction is discussed. The value of these techniques in improving prediction accuracy, system stability, and safety performance is analyzed. Extensive experimental tests are carried out in multiple traffic scenarios by constructing modules such as data collection and preprocessing, model training and optimization, real-time data processing, and system integration and display. In the experimental test, two main scenarios of traffic congestion warning and accident prediction are designed. The results reveal that in the traffic congestion warning scenario, under the condition that the traffic flow is 1800-2000 vehicles/hour and the average speed is 45-55 km/h, the prediction accuracy reaches 96%, the recall is 99%, and the F1 score is 97%. In the traffic accident prediction scenario, the system’s prediction accuracy, recall, and F1 score are 92%, 95%, and 93% when the traffic flow is 1200-1400 vehicles/hour on rainy days. The results of this study provide practical technical solutions for smart city traffic management and explore the prospect of future intelligent transportation system development, thus offering a theoretical and empirical basis for research and practice in related fields.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 17244-17254
The Intelligent Traffic Safety System Based on 6G Technology and Random Forest Algorithm
The main objective of this study is to explore and evaluate the application potential of combining Sixth Generation (6G) technology and random forest (RF) algorithm in the intelligent traffic safety system. This study designs and implements an intelligent traffic safety system using the RF algorithm and 6G technology, to improve the traffic conditions’ real-time monitoring and prediction ability. The advantages of 6G technology in real-time data transmission and efficient data processing. Moreover, the application of the RF algorithm in traffic congestion and accident prediction is discussed. The value of these techniques in improving prediction accuracy, system stability, and safety performance is analyzed. Extensive experimental tests are carried out in multiple traffic scenarios by constructing modules such as data collection and preprocessing, model training and optimization, real-time data processing, and system integration and display. In the experimental test, two main scenarios of traffic congestion warning and accident prediction are designed. The results reveal that in the traffic congestion warning scenario, under the condition that the traffic flow is 1800-2000 vehicles/hour and the average speed is 45-55 km/h, the prediction accuracy reaches 96%, the recall is 99%, and the F1 score is 97%. In the traffic accident prediction scenario, the system’s prediction accuracy, recall, and F1 score are 92%, 95%, and 93% when the traffic flow is 1200-1400 vehicles/hour on rainy days. The results of this study provide practical technical solutions for smart city traffic management and explore the prospect of future intelligent transportation system development, thus offering a theoretical and empirical basis for research and practice in related fields.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 17269-17279
The Application of 6G Technology and Back Propagation Neural Network in the Smart Public Transport System
To clarify the applications of the sixth-generation (6G) mobile communication technology and neural networks in the smart public transport system, firstly, this system’s overall framework is constructed. 6G technology is integrated into this framework to enable real-time collection and updating of bus information data, supporting intelligent services, enhancing overall efficiency, service quality, and user experience of public transport. Secondly, a vehicle travel time prediction model based on Back Propagation Neural Network (BPNN) is established. Furthermore, addressing the shortcomings of BPNN, genetic algorithm (GA) is employed to optimize the connection weights and thresholds of BPNN, thereby improving its performance. Finally, a real-time scheduling scheme for smart public transport is designed based on 6G technology and BPNN, and the model and system performance are verified through experiments. The results indicate that the mean relative error, mean absolute error, and root mean square error between predicted and actual values of the model before optimization were 48.61%, 51.77, and 0.863 respectively. After optimization, these metrics improved significantly to 10.54%, 19.07, and 0.152, demonstrating a notable enhancement in prediction accuracy compared to before optimization. Meanwhile, user satisfaction with the smart public transport system gradually increased, from 75% in March to 92% in November. This indicates that user satisfaction with the proposed system has gradually improved over time. Therefore, the research results provide a theoretical basis and robust technical support for the smart public transport system’s construction and promote the intelligent and modern development of public transport services.
- 18 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 26 (10) , 17269-17279
The Application of 6G Technology and Back Propagation Neural Network in the Smart Public Transport System
To clarify the applications of the sixth-generation (6G) mobile communication technology and neural networks in the smart public transport system, firstly, this system’s overall framework is constructed. 6G technology is integrated into this framework to enable real-time collection and updating of bus information data, supporting intelligent services, enhancing overall efficiency, service quality, and user experience of public transport. Secondly, a vehicle travel time prediction model based on Back Propagation Neural Network (BPNN) is established. Furthermore, addressing the shortcomings of BPNN, genetic algorithm (GA) is employed to optimize the connection weights and thresholds of BPNN, thereby improving its performance. Finally, a real-time scheduling scheme for smart public transport is designed based on 6G technology and BPNN, and the model and system performance are verified through experiments. The results indicate that the mean relative error, mean absolute error, and root mean square error between predicted and actual values of the model before optimization were 48.61%, 51.77, and 0.863 respectively. After optimization, these metrics improved significantly to 10.54%, 19.07, and 0.152, demonstrating a notable enhancement in prediction accuracy compared to before optimization. Meanwhile, user satisfaction with the smart public transport system gradually increased, from 75% in March to 92% in November. This indicates that user satisfaction with the proposed system has gradually improved over time. Therefore, the research results provide a theoretical basis and robust technical support for the smart public transport system’s construction and promote the intelligent and modern development of public transport services.
- 11 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (4) , 3577-3588
Internet-of-Things-Based Low-Carbon Distribution Route Optimization for Logistics
This study addresses the optimization of cold chain logistics distribution routes by proposing a low-carbon distribution route optimization model based on the Internet of Things (IoT) technology. Using IoT technology to monitor key data, such as temperature, humidity, and vehicle location along cold chain logistics distribution routes, the study dynamically optimizes the distribution process. Incorporating principles of low-carbon distribution, the model considers factors, such as fuel consumption, vehicle emissions, and transport efficiency to minimize carbon emissions and ensure environmentally friendly logistics operations. A genetic algorithm is employed as a path optimization tool, iteratively evolving toward optimal or near-optimal distribution routes, effectively reducing carbon emissions. The introduction of IoT technology extends route optimization beyond traditional cost and time considerations to include environmental impact and sustainability, reflecting the logistics industry’s commitment to green and low-carbon development. Actual distribution data from a cold chain logistics company in a specific city are collected and divided into training and test sets for model training and validation. The model is validated and analyzed through simulations and experiments under different scenarios. Experimental results demonstrate that the optimized distribution routes reduce total travel distance by an average of 10.2%, total energy consumption by 12.5%, and total carbon emissions by 12.8%. Additionally, the temperature fluctuation range is reduced by an average of 13.3%. The genetic algorithm employed in the study converges within 350 generations across all scenarios, with an average convergence time of 45 s. Hence, this study provides an effective solution for optimizing cold chain logistics distribution routes, offering significant practical value.
- 11 September 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (4) , 3577-3588
Internet-of-Things-Based Low-Carbon Distribution Route Optimization for Logistics
This study addresses the optimization of cold chain logistics distribution routes by proposing a low-carbon distribution route optimization model based on the Internet of Things (IoT) technology. Using IoT technology to monitor key data, such as temperature, humidity, and vehicle location along cold chain logistics distribution routes, the study dynamically optimizes the distribution process. Incorporating principles of low-carbon distribution, the model considers factors, such as fuel consumption, vehicle emissions, and transport efficiency to minimize carbon emissions and ensure environmentally friendly logistics operations. A genetic algorithm is employed as a path optimization tool, iteratively evolving toward optimal or near-optimal distribution routes, effectively reducing carbon emissions. The introduction of IoT technology extends route optimization beyond traditional cost and time considerations to include environmental impact and sustainability, reflecting the logistics industry’s commitment to green and low-carbon development. Actual distribution data from a cold chain logistics company in a specific city are collected and divided into training and test sets for model training and validation. The model is validated and analyzed through simulations and experiments under different scenarios. Experimental results demonstrate that the optimized distribution routes reduce total travel distance by an average of 10.2%, total energy consumption by 12.5%, and total carbon emissions by 12.8%. Additionally, the temperature fluctuation range is reduced by an average of 13.3%. The genetic algorithm employed in the study converges within 350 generations across all scenarios, with an average convergence time of 45 s. Hence, this study provides an effective solution for optimizing cold chain logistics distribution routes, offering significant practical value.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (4) , 3502-3511
Cold Chain Logistics Supervision of Agricultural Products Supported Using Internet of Things Technology
With the acceleration of globalization and urbanization processes, cold chain logistics (CCL) for agricultural products plays a pivotal role in modern agricultural supply chains. This study aims to explore methods to enhance the efficiency and quality of agricultural product CCL supervision through the use of Internet of Things (IoT) technology. Addressing challenges, such as real-time data acquisition difficulties, information asymmetry, and data security concerns in the agricultural CCL sector, this research develops an IoT-based agricultural CCL supervision system. This system innovatively integrates three components: 1) a real-time data collection module; 2) a temperature and humidity regulation module; and 3) a logistics information privacy protection module. The latter employs an anonymous authentication based on blockchain to bolster the security and confidentiality of logistics information. The system model is simulated and evaluated by MATLAB. Results demonstrate that the proposed system exhibits optimal computational efficiency, maintaining a computational overhead of approximately 0.10 s, which is lower than other algorithms exceeding 0.13 s. In terms of operational efficiency, with 250 consensus nodes, the consensus throughput remains consistently above 90 bps, while central processing unit utilization does not exceed 20%. Regarding data transmission security, the average delivery rate of the model exceeds 80.48%, and the average leakage rate remains below 5.72% for a data volume of 10 Mb, underscoring robust network data security transmission performance. Therefore, the system model developed in this study significantly enhances the real-time accuracy and security of agricultural product CCL supervision, presenting a pioneering technical solution essential for advancing the efficiency and quality of the supply chain.
- 1 July 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 12 (4) , 3502-3511
Cold Chain Logistics Supervision of Agricultural Products Supported Using Internet of Things Technology
With the acceleration of globalization and urbanization processes, cold chain logistics (CCL) for agricultural products plays a pivotal role in modern agricultural supply chains. This study aims to explore methods to enhance the efficiency and quality of agricultural product CCL supervision through the use of Internet of Things (IoT) technology. Addressing challenges, such as real-time data acquisition difficulties, information asymmetry, and data security concerns in the agricultural CCL sector, this research develops an IoT-based agricultural CCL supervision system. This system innovatively integrates three components: 1) a real-time data collection module; 2) a temperature and humidity regulation module; and 3) a logistics information privacy protection module. The latter employs an anonymous authentication based on blockchain to bolster the security and confidentiality of logistics information. The system model is simulated and evaluated by MATLAB. Results demonstrate that the proposed system exhibits optimal computational efficiency, maintaining a computational overhead of approximately 0.10 s, which is lower than other algorithms exceeding 0.13 s. In terms of operational efficiency, with 250 consensus nodes, the consensus throughput remains consistently above 90 bps, while central processing unit utilization does not exceed 20%. Regarding data transmission security, the average delivery rate of the model exceeds 80.48%, and the average leakage rate remains below 5.72% for a data volume of 10 Mb, underscoring robust network data security transmission performance. Therefore, the system model developed in this study significantly enhances the real-time accuracy and security of agricultural product CCL supervision, presenting a pioneering technical solution essential for advancing the efficiency and quality of the supply chain.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-9
Communication Security Analysis of Intelligent Transportation System Using 5G Internet of Things From the Perspective of Big Data
The transportation system has entered the era of 5G intelligent Internet of things (IoT), which can realize the comprehensive monitoring, perception, and intelligent decision-making of people, vehicles, roads, and the environment. The purpose is to solve the problems in the communication security of intelligent transportation system (ITS) and improve the vulnerability of traditional distributed architecture. The security issues of the Internet of vehicles (IoV) in 5G environment are analyzed from the perspective of big data. An access control mechanism based on risk prediction is proposed aiming at the problems existing in the node access control process. A Wasserstein Distance-based Combined Generative Adversarial Network (WCGAN) is proposed. It modifies the loss function to solve the gradient disappearance problem, and a combination of multiple generators is designed to solve the pattern collapse. The simulation experiment is carried out on the dataset of the intrusion detection evaluation project. The WCGAN model has the smallest prediction error than the other models regarding the node packet transmission rate. Its loss value is close to 0 after 10 iterations, while the loss value of the BP neural network (BPNN) is about 0.28. The prediction accuracy of the WCGAN model can reach 86.3% when the training set is 5000, which is much higher than that of BPNN (77.8%). The reason is that the WCGAN model increases the number of generators according to GAN, which improves the low accuracy caused by pattern collapse. The IoT-based ITS can implement corresponding strategies according to the prediction results and control the access rights of nodes, thus ensuring the security of information resources effectively. The research content reduces the communication delay under ensuring the integrity and confidentiality of information in the process of data transmission, and provides a reference for ensuring the safe communication of IoV.
- 23 March 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-9
Communication Security Analysis of Intelligent Transportation System Using 5G Internet of Things From the Perspective of Big Data
The transportation system has entered the era of 5G intelligent Internet of things (IoT), which can realize the comprehensive monitoring, perception, and intelligent decision-making of people, vehicles, roads, and the environment. The purpose is to solve the problems in the communication security of intelligent transportation system (ITS) and improve the vulnerability of traditional distributed architecture. The security issues of the Internet of vehicles (IoV) in 5G environment are analyzed from the perspective of big data. An access control mechanism based on risk prediction is proposed aiming at the problems existing in the node access control process. A Wasserstein Distance-based Combined Generative Adversarial Network (WCGAN) is proposed. It modifies the loss function to solve the gradient disappearance problem, and a combination of multiple generators is designed to solve the pattern collapse. The simulation experiment is carried out on the dataset of the intrusion detection evaluation project. The WCGAN model has the smallest prediction error than the other models regarding the node packet transmission rate. Its loss value is close to 0 after 10 iterations, while the loss value of the BP neural network (BPNN) is about 0.28. The prediction accuracy of the WCGAN model can reach 86.3% when the training set is 5000, which is much higher than that of BPNN (77.8%). The reason is that the WCGAN model increases the number of generators according to GAN, which improves the low accuracy caused by pattern collapse. The IoT-based ITS can implement corresponding strategies according to the prediction results and control the access rights of nodes, thus ensuring the security of information resources effectively. The research content reduces the communication delay under ensuring the integrity and confidentiality of information in the process of data transmission, and provides a reference for ensuring the safe communication of IoV.
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-9
Construction of Regional Intelligent Transportation System in Smart City Road Network via 5G Network
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.
- 14 February 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. PP (15249050) , 1-9
Construction of Regional Intelligent Transportation System in Smart City Road Network via 5G Network
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.
- 6 February 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (9) , 6185-6200
SALSTM: An improved LSTM algorithm for predicting the competitiveness of export products
- 6 February 2022
- Published by Wiley in International Journal of Intelligent Systems
- Vol. 37 (9) , 6185-6200
SALSTM: An improved LSTM algorithm for predicting the competitiveness of export products
- Open Access
- 1 January 2019
- Published by American Institute of Mathematical Sciences (AIMS) in Discrete and Continuous Dynamical Systems - S
- Vol. 12 (4&5) , 979-987
A solution of TSP based on the ant colony algorithm improved by particle swarm optimization
TSP is a classic problem in the field of logistics, and ant colony algorithm is an important way to solve the problem. However, the ant colony algorithm has some shortcomings in practical application. In this paper, the ant colony algorithm is improved by particle swarm optimization algorithm, and the ant colony algorithm is obtained by giving the ant colony a certain ''particle property''. Finally, an example is given to demonstrate the effectiveness of the improved ant colony algorithm.
- 1 January 2019
- Published by American Institute of Mathematical Sciences (AIMS) in Discrete and Continuous Dynamical Systems - S
- Vol. 12 (4&5) , 979-987
Open AccessA solution of TSP based on the ant colony algorithm improved by particle swarm optimization
TSP is a classic problem in the field of logistics, and ant colony algorithm is an important way to solve the problem. However, the ant colony algorithm has some shortcomings in practical application. In this paper, the ant colony algorithm is improved by particle swarm optimization algorithm, and the ant colony algorithm is obtained by giving the ant colony a certain ''particle property''. Finally, an example is given to demonstrate the effectiveness of the improved ant colony algorithm.
- 30 January 2016
- Published by Atlantis Press SARL
- p. 573-579
Research on the Application of Internet Financial Integration in China Ping An (Group)
- 30 January 2016
- Published by Atlantis Press SARL
- p. 573-579
Research on the Application of Internet Financial Integration in China Ping An (Group)