Attention Mechanism-Based Convolutional Model for Collaborative Control of Traffic Signals at Multiple Intersections
Downloads
The necessity for collaborative traffic signal control optimisation is growing in importance as intelligent transportation technology continues to advance. The study started a related application investigation to successfully raise the degree of cooperative control of traffic lights at several crossings. Based on an in-depth analysis of the traffic scenarios at multiple intersections, the study clarified the key points for optimising the collaborative control of traffic signals. Subsequently, an attention convolution model was introduced to capture the dynamic information changes of key spatial regions and data in the traffic scene through a spatial and temporal attention mechanism. The average vehicle travel time under model control was tested to be 12.4% and 23.3% shorter than the other two methods, respectively. The ablation experiments showed that the model reduced the passing time by about 9.5% and 6.7%. Moreover, the attention is mainly focused on the nodes closer to the location, and the model is more spatially interpretable. The results illustrate that the designed collaborative control of traffic signals at multiple intersections method based on the convolutional model with attention mechanism can enhance the flexibility of traffic management on the basis of improving the efficiency of collaborative control. This offers compelling evidence in favour of building a more clever and effective cooperative traffic signal control system at several crossings.
Downloads
Guo MH, et al. Attention mechanisms in computer vision: A survey. Comput Vis Media. 2022;8(3):331-368. DOI: 10.1007/s41095-022-0271-y.
Pei Y, et al. FCN-attention: A deep learning UWB NLOS/LOS classification algorithm using fully convolution neural network with self-attention mechanism. Geo-Spatial Inf Sci. 2024;27(4):1162-1181. DOI: 10.1080/10095020.2023.2178334.
Lu E, Hu X. Image super-resolution via channel attention and spatial attention. Appl Intell. 2022;52(2):2260-2268. DOI: 10.1007/s10489-021-02464-6.
Bhosle K, Musande V. Evaluation of deep learning CNN model for recognition of devanagari digit. Artif Intell Appl. 2023;1(2):114-118. DOI: 10.47852/bonviewAIA3202441.
Preethi P, Mamatha HR. Region-based convolutional neural network for segmenting text in epigraphical images. Artif Intell Appl. 2023;1(2):119-127. DOI: 10.47852/bonviewAIA2202293.
Zhao Q, et al. HyperAttentionDTI: Improving drug-protein interaction prediction by sequence-based deep learning with attention mechanism. Bioinformatics. 2022;38(3):655-662. DOI: 10.1093/bioinformatics/btab715.
Cheng Z, et al. IIFDTI: predicting drug-target interactions through interactive and independent features based on attention mechanism. Bioinformatics. 2022;38(17):4153-4161. DOI: 10.1093/bioinformatics/btac485.
Muruganantham P, Balakrishnan SM. Attention aware deep learning model for wireless capsule endoscopy lesion classification and localization. J Med Biol Eng. 2022;42(2):157-168. DOI: 10.1007/s40846-022-00686-8.
Tomar I, Sreedevi I, Pandey N. State-of-art review of traffic light synchronization for intelligent vehicles: current status, challenges, and emerging trends. Electronic. 2022;11(3):465. DOI: 10.3390/electronics11030465.
Gholamhosseinian A, Seitz J. Acomprehensive survey on cooperative intersection management for heterogeneous connected vehicles. IEEE Access. 2022;10:7937-7972. DOI: 10.1109/ACCESS.2022.3142450.
Miletić M, et al. A review of reinforcement learning applications in adaptive traffic signal control. IET Intell Transp Syst. 2022;16(10):1269-1285. DOI: 10.1049/itr2.12208.
Dewi C, et al. Synthetic data generation using DCGAN for improved traffic sign recognition. Neural Comput Appl. 2022;34(24):21465-21480. DOI: 10.1007/s00521-021-05982-z.
LiuC, Ke L. Cloud assisted internet of things intelligent transportation system and the traffic control system in the smart city. J Control Decis. 2023;10(2):174-187. DOI: 10.1080/23307706.2021.2024460.
Soydaner D. Attention mechanism in neural networks: where it comes and where it goes. Neural Comput Appl. 2022;34(16):13371-13385. DOI: 10.1007/s00521-022-07366-3.
Lin S, Zeng Y, Gong Y. Learning of time-frequency attention mechanism for automatic modulation recognition. IEEE Wirel Commun Lett. 2022;11(4):707-711. DOI: 10.1109/LWC.2022.3140828.
Ramaswamy SL, Chinnappan J. RecogNet-LSTM + CNN: a hybrid network with attention mechanism for aspect categorization and sentiment classification. J Intell Inform Syst. 2022;58(2):379-404. DOI: 10.1007/s10844-021-00692-3.
Kavianpour P, et al. A CNN-BiLSTM model with attention mechanism for earthquake prediction. J Supercomput. 2023;79(17):19194-19226. DOI: 10.1007/s11227-023-05369-y.
Alirezazadeh P, Schirrmann M, Stolzenburg F. Improving deep learning-based plant disease classification with attention mechanism. GesundePflanzen. 2023;75(1):49-59. DOI: 10.1007/s10343-022-00796-y.
Babbar S, Bedi J. Real-time traffic, accident, and potholes detection by deep learning techniques: a modern approach for traffic management. Neural Comput Appl. 2023;35(26):19465-19479. DOI: 10.1007/s00521-023-08767-8.
Gupta H, Verma OP. Monitoring and surveillance of urban road traffic using low altitude drone images: a deep learning approach. Multimed Tools Appl. 2022;81(14):19683-19703. DOI: 10.1007/s11042-021-11146-x.
Kamal H, et al. Digital-twin-based deep reinforcement learning approach for adaptive traffic signal control. IEEE Internet Things J. 2024;11(12):21946-21953. DOI: 10.1109/JIOT.2024.3377600.
Wang M, et al. UniTSA: A universal reinforcement learning framework for V2X traffic signal control. IEEE Trans Veh Technol. 2024;73(10):14354-14369. DOI: 10.1109/JIOT.2025.3586315.
Kumar R, Sharma NVK, Chaurasiya VK. Adaptive traffic light control using deep reinforcement learning technique. Multimed Tools Appl. 2024;83(5):13851-13872. DOI: 10.1007/s11042-023-16112-3.
Li W, et al. LSTM-TCN: dissolved oxygen prediction in aquaculture, based on combined model of long short-term memory network and temporal convolutional network. Environ Sci Pollut Res. 2022;29(26):39545-39556. DOI: 10.1007/s11356-022-18954-8.
Fan J, et al. Parallel spatio-temporal attention-based TCN for multivariate time series prediction. Neural Comput Appl. 2023;35(18):13109-13118. DOI: 10.1007/s00521-021-05958-z.
Huan H, et al. A text classification method based on a convolutional and bidirectional long short-term memory model. Connect Sci. 2022;34(1):2108-2124. DOI: 10.1080/09540091.2022.2098926.
Zhang D, et al. An efficient lightweight convolutional neural network for industrial surface defect detection. Artif Intell Rev. 2023;56(9):10651-10677. DOI: 10.1007/s10462-023-10438-y.
Gou C, Zhou Y, Li D. Driver attention prediction based on convolution and transformers. J Supercomput. 2022;78(6):8268-8284. DOI: 10.1007/s11227-021-04151-2.
Gupta D, Sharma A. A two-stage attention augmented fully convolutional network-based dynamic video summarization. Multimedia Syst. 2023;29(6):3685-3701. DOI: 10.1007/s00530-023-01154-2.
Zhang H, et al. Attention-based feature fusion generative adversarial network for yarn-dyed fabric defect detection. Text Res J. 2023;93(5-6):1178-1195. DOI: 10.1177/00405175221129654.
Hu X, et al. Attention-based conv-LSTM and Bi-LSTM networks for large-scale traffic speed prediction. J Supercomput. 2022;78(10):12686-12709. DOI: 10.1007/s11227-022-04386-7.
Li Z, et al. Fusion attention mechanism bidirectional LSTM for short-term traffic flow prediction. J Intell Transp Syst. 2024;28(4):511-524. DOI: 10.1080/15472450.2022.2142049.
Zohourianshahzadi Z, Kalita JK. Neural attention for image captioning: review of outstanding methods. Artif Intell Rev. 2022;55(5):3833-3862. DOI: 10.1007/s10462-021-10092-2.
Copyright (c) 2026 Junlin Zhang, Shiliang Zhang, Jun Qiao, Jianping Xu, Hao Xiang
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
