Analysing the Smart Loaded Traffic Square System for Emergency Vehicles via the Use of a Deep Learning Model
Keywords:
Emergency Vehicles, Smart Loaded Traffic Square System, VGG16, VGG19, ResNet101, ResNet152Abstract
In the realm of urban traffic management, particularly within densely populated traffic squares, ensuring the swift and unimpeded passage of emergency vehicles (EVs) presents a significant challenge. This study introduces a comprehensive Smart Loaded Traffic Square System (SLTSS) that leverages advanced deep learning models to optimize traffic flow for EVs amidst heavy congestion. Through an empirical analysis encompassing various convolutional neural network architectures, including AlexNet, VGG16, VGG19, ResNet 50, ResNet 101, and a proposed custom ResNet152 model, this paper evaluates the effectiveness of these models in classifying EVs from other vehicles within a traffic square setting. The methodology adopted for this study involves a step-wise approach, starting with data cleaning to ensure high-quality, noise-free images for model training. Following segmentation and feature extraction processes, each model was trained and tested on a dataset comprising images of diverse vehicles within urban traffic scenarios. The performance of each model was meticulously assessed based on accuracy, precision, recall, and F1-score metrics, providing a holistic view of their classification capabilities. Results from this study underscore the pronounced impact of model complexity on classification performance. The foundational AlexNet model established a baseline with an accuracy of 85%, precision of 83%, and an F1-score of 82.5%. Subsequent models exhibited incremental improvements, with VGG16 and VGG19 models reaching accuracies up to 90% and 89%, respectively. However, it was the ResNet series that demonstrated significant advancements, with ResNet 50 achieving a 92% accuracy, ResNet 101 further elevating this to 93%, and the proposed ResNet152 model topping the charts with a remarkable 94% accuracy, alongside commensurate improvements in precision, recall, and F1-scores. The comparative analysis vividly illustrates the correlation between the depth and sophistication of the neural network architecture and its ability to accurately classify EVs in complex urban traffic scenarios. The proposed ResNet152 model, in particular, showcased superior performance with a 94% precision, 95% recall, and a 94% F1-score, underlining the potential of deep architectures in enhancing the operational efficiency of emergency responses within loaded traffic environments.
Downloads
References
Humayun, Mamoona, Maram Fahhad Almufareh, and Noor Zaman Jhanjhi. "Autonomous traffic system for emergency vehicles." Electronics 11, no. 4 (2022): 510.
Cafiso, Salvatore, Alessandro Di Graziano, Tullio Giuffrè, Giuseppina Pappalardo, and Alessandro Severino. "Managed Lane as Strategy for Traffic Flow and Safety: A Case Study of Catania Ring Road." Sustainability 14, no. 5 (2022): 2915.
Pashayev, Elgun. "Area-wide Traffic Calming in Inner-city Area of Dresden." PhD diss., Westsächsische Hochschule Zwickau, 2023.
Hughes, Jonathan E., Daniel Kaffine, and Leah Kaffine. "Decline in traffic congestion increased crash severity in the wake of COVID-19." Transportation research record 2677, no. 4 (2023): 892-903.
González-Aliste, Pablo, Iván Derpich, and Mario López. "Reducing urban traffic congestion via charging price." Sustainability 15, no. 3 (2023): 2086.
Fahs, Walid, Fadlallah Chbib, Abbas Rammal, Rida Khatoun, Ali El Attar, Issam Zaytoun, and Joel Hachem. "Traffic Congestion Prediction Based on Multivariate Modelling and Neural Networks Regressions." Procedia Computer Science 220 (2023): 202-209.
Xie, Derong, Sihao Chen, Haotong Duan, Xinwei Li, Caotong Luo, Yuxuan Ji, and Huiming Duan. "A novel grey prediction model based on tensor higher-order singular value decomposition and its application in short-term traffic flow." Engineering Applications of Artificial Intelligence 126 (2023): 107068.
Yang, Bo, Hua Zhang, Mengxin Du, Anna Wang, and Kai Xiong. "Urban traffic congestion alleviation system based on millimeter wave radar and improved probabilistic neural network." IET Radar, Sonar & Navigation (2023).
Haboury, Nathan, Mo Kordzanganeh, Sebastian Schmitt, Ayush Joshi, Igor Tokarev, Lukas Abdallah, Andrii Kurkin, Basil Kyriacou, and Alexey Melnikov. "A supervised hybrid quantum machine learning solution to the emergency escape routing problem." arXiv preprint arXiv:2307.15682 (2023).
Srivastava, Sandesh Kumar, Anshul Singh, Ruqaiya Khanam, Prashant Johri, Arya Siddhartha Gupta, and Gaurav Kumar. "Smart Traffic Control for Emergency Vehicles Using the Internet of Things and Image Processing." Trends and Advancements of Image Processing and Its Applications (2022): 53-73.
Xing, Xue, and Xiaoyu Li. "Recommendation of urban vehicle driving routes under traffic congestion: A traffic congestion regulation method considering road network equilibrium." Computers and Electrical Engineering 110 (2023): 108863.
Jutury, Dheeraj, Neetesh Kumar, Anuj Sachan, Yash Daultani, and Naveen Dhakad. "Adaptive neuro-fuzzy enabled multi-mode traffic light control system for urban transport network." Applied Intelligence 53, no. 6 (2023): 7132-7153.
Li, Xiang, Jiao Gui, and Jiaming Liu. "Data-driven traffic congestion patterns analysis: A case of Beijing." Journal of Ambient Intelligence and Humanized Computing 14, no. 7 (2023): 9035-9048.
Singh, Shyam Pratap, Arshad Ali Khan, Riad Souissi, and Syed Adnan Yusuf. "Leveraging Neo4j and deep learning for traffic congestion simulation & optimization." arXiv preprint arXiv:2304.00192 (2023).
Fahs, Walid, Fadlallah Chbib, Abbas Rammal, Rida Khatoun, Ali El Attar, Issam Zaytoun, and Joel Hachem. "Traffic Congestion Prediction Based on Multivariate Modelling and Neural Networks Regressions." Procedia Computer Science 220 (2023): 202-209.
Moumen, Idriss, Jaafar Abouchabaka, and Najat Rafalia. "Adaptive traffic lights based on traffic flow prediction using machine learning models." International Journal of Electrical and Computer Engineering (IJECE) 13, no. 5 (2023): 5813-5823.
Gamel, Samah A., Esraa Hassan, Nora El-Rashidy, and Fatma M. Talaat. "Exploring the effects of pandemics on transportation through correlations and deep learning techniques." Multimedia tools and applications 83, no. 3 (2024): 7295-7316.
Li, Jiaqi, Xiaoyuan Xu, Zheng Yan, Han Wang, Mohammad Shahidehpour, and Yue Chen. "Coordinated Optimization of Emergency Response Resources in Transportation-Power Distribution Networks under Extreme Events." IEEE Transactions on Smart Grid (2023).
Latif, Rana Muhammad Amir, Muhammad Jamil, Jinliao He, and Muhammad Farhan. "A Novel Authentication and Communication Protocol for Urban Traffic Monitoring in VANETs Based on Cluster Management." Systems 11, no. 7 (2023): 322.
Agarwal, Piyush, Sachin Sharma, and Priya Matta. "Federated Learning in Intelligent Traffic Management System." In 2023 Winter Summit on Smart Computing and Networks (WiSSCoN), pp. 1-6. IEEE, 2023.
Wang, Hao, Yun Yuan, Xianfeng Terry Yang, Tian Zhao, and Yang Liu. "Deep Q learning-based traffic signal control algorithms: Model development and evaluation with field data." Journal of Intelligent Transportation Systems 27, no. 3 (2023): 314-334.
Obayya, Marwa, Fahd N. Al-Wesabi, Rana Alabdan, Majdi Khalid, Mohammed Assiri, Mohamed Ibrahim Alsaid, Azza Elneil Osman, and Amani A. Alneil. "Artificial Intelligence for Traffic Prediction and Estimation in Intelligent Cyber-Physical Transportation Systems." IEEE Transactions on Consumer Electronics (2023).
Husnain, Ghassan, Shahzad Anwar, and Fahim Shahzad. "An Enhanced AI-Enabled Routing Optimization Algorithm for Internet of Vehicles (IoV)." Wireless Personal Communications 130, no. 4 (2023): 2623-2643.
Seong, Kijin, Junfeng Jiao, and Akhil Mandalapu. "Effects of urban environmental factors on heat-related emergency medical services (EMS) response time." Applied Geography 155 (2023): 102956.
Liu, Jun, Xing Fu, Alexander Hainen, Chenxuan Yang, Leon Villavicencio, and William J. Horrey. "Evaluating the impacts of vehicle-mounted Variable Message Signs on passing vehicles: implications for protecting roadside incident and service personnel." Journal of Intelligent Transportation Systems (2023): 1-21.
Vlachogiannis, Dimitris M., Hua Wei, Scott Moura, and Jane Macfarlane. "HumanLight: Incentivizing Ridesharing via Human-centric Deep Reinforcement Learning in Traffic Signal Control." arXiv preprint arXiv:2304.03697 (2023).
Dodia, Ayush, Sumit Kumar, Ruchi Rani, Sanjeev Kumar Pippal, and Pramoda Meduri. "EVATL: A novel framework for emergency vehicle communication with adaptive traffic lights for smart cities." IET Smart Cities 5, no. 4 (2023): 254-268.
Sumi, L.; Ranga, V. Intelligent traffic management system for prioritizing emergency vehicles in a smart city. Int. J. Eng. 2018, 31, 278–283.
Nellore, K.; Hancke, G.P. Traffic management for emergency vehicle priority based on visual sensing. Sensors 2016, 16, 1892.
González, C.L.; Pulido, J.J.; Alberola, J.M.; Julian, V.; Niño, L.F. Autonomous Distributed Intersection Management for Emergency Vehicles at Intersections. In Practical Applications of Agents and Multi-Agent Systems; Springer: Berlin/Heidelberg, Germany, 2021
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
