{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T16:01:50Z","timestamp":1784476910705,"version":"3.55.0"},"reference-count":30,"publisher":"Fuji Technology Press Ltd.","issue":"4","funder":[{"DOI":"10.13039\/501100016342","name":"Nanjing Vocational Institute of Transport Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100016342","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Jiangsu Transportation Science and Technology","award":["JG2521"],"award-info":[{"award-number":["JG2521"]}]},{"name":"Jiangsu Transportation Science and Technology","award":["JZ2408"],"award-info":[{"award-number":["JZ2408"]}]},{"name":"Jiangsu Transportation Science and Technology","award":["JT2024YB070"],"award-info":[{"award-number":["JT2024YB070"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JACIII","J. Adv. Comput. Intell. Intell. Inform."],"published-print":{"date-parts":[[2026,7,20]]},"abstract":"<jats:p>With the development of the economy, urban traffic congestion has become increasingly serious, causing a series of problems such as safety and environmental pollution. To address the challenge of urban traffic congestion problems, traffic signal configuration optimization based on time-varying traffic states and real-time performance is an important direction with practical engineering significance. In this study, we design a traffic signal controller that learns online without requiring a traffic model. A model-free action-dependent adaptive dynamic programming (ADP) that employs two neural networks (an action network and a critic network) to approximate the Hamilton\u2013Jacobi\u2013Bellman equation is employed to provide self-learning optimization ability with varying traffic states. The proposed controller employs a neuro-fuzzy system that functions as an action network to generate control decisions utilizing expertise and mitigates the stochastic exploration inefficiency inherent in conventional ADP. ADP provides reinforcement signals that indicate a reward or punishment for the neuro-fuzzy system to guide it in adjusting its parameters. Subsequently, actions associated with lower cumulative delay are reinforced. The proposed traffic signal controller can reduce the blindness of learning by using experience and the inaccuracy of the traffic model. An artificial bee colony algorithm was employed to train the ADP to meet the real-time requirement for traffic signal control. The controller can adapt to fluctuating traffic states by training continuously, and achieves a smaller average delay in the long run. The simulation results demonstrate that proposed controller achieves a reduced delay through supervised learning with an accelerated training speed.<\/jats:p>","DOI":"10.20965\/jaciii.2026.p1044","type":"journal-article","created":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T15:02:07Z","timestamp":1784473327000},"page":"1044-1055","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Dynamic Model-Free Neuro-Fuzzy System for Traffic Signal Control"],"prefix":"10.20965","volume":"30","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-2397-0921","authenticated-orcid":true,"given":"Tao","family":"Li","sequence":"first","affiliation":[{"name":"Nanjing Vocational Institute of Transport Technology, No.629 Longmian Avenue, Jiangning, Nanjing, Jiangsu 211188, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7153-7997","authenticated-orcid":true,"given":"Dianwei","family":"Qian","sequence":"additional","affiliation":[{"name":"School of Cntrol and Computer, North China Electric Power University, No.2 Beinong Road, Changping District, Beijing 102206, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlan","family":"Guo","sequence":"additional","affiliation":[{"name":"Nanjing Vocational Institute of Transport Technology, No.629 Longmian Avenue, Jiangning, Nanjing, Jiangsu 211188, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"8550","published-online":{"date-parts":[[2026,7,20]]},"reference":[{"key":"key-10.20965\/jaciii.2026.p1044-1","doi-asserted-by":"crossref","unstructured":"H. Wei, G. Zheng, V. Gayah, and Z. Li, \u201cRecent advances in reinforcement learning for traffic signal control: A survey of models and evaluation,\u201d ACM SIGKDD Explorations Newsletter, Vol.22, No.2, pp. 12-18, 2021. https:\/\/doi.org\/10.1145\/3447556.3447565","DOI":"10.1145\/3447556.3447565"},{"key":"key-10.20965\/jaciii.2026.p1044-2","doi-asserted-by":"crossref","unstructured":"B. Xu, Y. Wang, Z. Wang, H. Jia, and Z. Lu, \u201cHierarchically and cooperatively learning traffic signal control,\u201d Proc. of the AAAI Conf. on Artificial Intelligence, Vol.35, No.1, pp. 669-677, 2021. https:\/\/doi.org\/10.1609\/aaai.v35i1.16147","DOI":"10.1609\/aaai.v35i1.16147"},{"key":"key-10.20965\/jaciii.2026.p1044-3","doi-asserted-by":"crossref","unstructured":"Y. Tang, X. Dai, and Y. Lv, \u201cLarge language model-assisted arterial traffic signal control,\u201d IEEE J. of Radio Frequency Identification, Vol.8, pp. 322-326, 2024. https:\/\/doi.org\/10.1109\/jrfid.2024.3384289","DOI":"10.1109\/JRFID.2024.3384289"},{"key":"key-10.20965\/jaciii.2026.p1044-4","doi-asserted-by":"crossref","unstructured":"W. Wei and M. Wang, \u201cResearch on traffic signal control based on intelligence techniques,\u201d Proc. of the 2003 IEEE Int. Conf. on Intelligent Transportation Systems, Vol.1, pp. 892-896, 2003. https:\/\/doi.org\/10.1109\/itsc.2003.1252078","DOI":"10.1109\/ITSC.2003.1252078"},{"key":"key-10.20965\/jaciii.2026.p1044-5","doi-asserted-by":"crossref","unstructured":"L. Huang and X. Qu, \u201cImproving traffic signal control operations using proximal policy optimization,\u201d IET Intelligent Transport Systems, Vol.17, No.3, pp. 592-605, 2023. https:\/\/doi.org\/10.1049\/itr2.12286","DOI":"10.1049\/itr2.12286"},{"key":"key-10.20965\/jaciii.2026.p1044-6","doi-asserted-by":"crossref","unstructured":"C.-Y. Jiang, X.-M. Hu, and W.-N. Chen, \u201cAn urban traffic signal control system based on traffic flow prediction,\u201d 2021 13th Int. Conf. on Advanced Computational Intelligence, pp. 259-265, 2021. https:\/\/doi.org\/10.1109\/icaci52617.2021.9435905","DOI":"10.1109\/ICACI52617.2021.9435905"},{"key":"key-10.20965\/jaciii.2026.p1044-7","doi-asserted-by":"crossref","unstructured":"F. C. Wang, \u201cDesign and implementation of intelligent traffic signal light control system based on LoRa technology,\u201d Applied and Computational Engineering, Vol.117, pp. 107-113, 2025. https:\/\/doi.org\/10.54254\/2755-2721\/2025.20314","DOI":"10.54254\/2755-2721\/2025.20314"},{"key":"key-10.20965\/jaciii.2026.p1044-8","doi-asserted-by":"crossref","unstructured":"Y. Zhang et al., \u201cAn occupancy-based adaptive signal control for a congested signalized intersection in the low CV penetration environment,\u201d J. of Advanced Transportation, Vol.2022, Article No.4745879, 2022. https:\/\/doi.org\/10.1155\/2022\/4745879","DOI":"10.1155\/2022\/4745879"},{"key":"key-10.20965\/jaciii.2026.p1044-9","doi-asserted-by":"crossref","unstructured":"W. Wei, Y. Zhang, J. B. Mbede, Z. Zhang, and J. Song, \u201cTraffic signal control using fuzzy logic and MOGA,\u201d 2001 IEEE Int. Conf. on Systems, Man and Cybernetics, e-Systems and e-Man for Cybernetics in Cyberspace, Vol.2, pp. 1335-1340, 2001. https:\/\/doi.org\/10.1109\/ICSMC.2001.973106","DOI":"10.1109\/ICSMC.2001.973106"},{"key":"key-10.20965\/jaciii.2026.p1044-10","doi-asserted-by":"crossref","unstructured":"Y. Wu, \u201cEnhancing urban traffic flow through fuzzy logic-based signal light control optimization,\u201d Int. J. of e-Collaboration, Vol.20, No.1, 2024. https:\/\/doi.org\/10.4018\/ijec.358746","DOI":"10.4018\/IJeC.358746"},{"key":"key-10.20965\/jaciii.2026.p1044-11","doi-asserted-by":"crossref","unstructured":"B. A. Khan and N. S. Lai, \u201cAn advanced fuzzy logic based traffic controller,\u201d Int. J. of Innovation in the Digital Economy, Vol.5, No.1, pp. 31-40, 2014. https:\/\/doi.org\/10.4018\/ijide.2014010103","DOI":"10.4018\/ijide.2014010103"},{"key":"key-10.20965\/jaciii.2026.p1044-12","doi-asserted-by":"crossref","unstructured":"T. Meepokgit and S. Wisayataksin, \u201cTraffic signal control with state-optimizing deep reinforcement learning and fuzzy logic,\u201d Applied Sciences, Vol.14, No.17, Article No.7908, 2024. https:\/\/doi.org\/10.3390\/app14177908","DOI":"10.3390\/app14177908"},{"key":"key-10.20965\/jaciii.2026.p1044-13","doi-asserted-by":"crossref","unstructured":"E. Bingham, \u201cReinforcement learning in neurofuzzy traffic signal control,\u201d European J. of Operational Research, Vol.131, No.2, pp. 232-241, 2001. https:\/\/doi.org\/10.1016\/s0377-2217(00)00123-5","DOI":"10.1016\/S0377-2217(00)00123-5"},{"key":"key-10.20965\/jaciii.2026.p1044-14","doi-asserted-by":"crossref","unstructured":"M. C. Choy, D. Srinivasan, and R. L. Cheu, \u201cCooperative, hybrid agent architecture for real-time traffic signal control,\u201d IEEE Trans. on Systems, Man, and Cybernetics \u2013 Part A: Systems and Humans, Vol.33, No.5, pp. 597-607, 2003. https:\/\/doi.org\/10.1109\/tsmca.2003.817394","DOI":"10.1109\/TSMCA.2003.817394"},{"key":"key-10.20965\/jaciii.2026.p1044-15","doi-asserted-by":"crossref","unstructured":"\u00d6. N. Kenger and E. \u00d6zceylan, \u201cFuzzy min\u2013max neural networks: A bibliometric and social network analysis,\u201d Neural Computing and Applications, Vol.35, No.7, pp. 5081-5111, 2023. https:\/\/doi.org\/10.1007\/s00521-023-08267-9","DOI":"10.1007\/s00521-023-08267-9"},{"key":"key-10.20965\/jaciii.2026.p1044-16","doi-asserted-by":"crossref","unstructured":"C. Wang, X. Lv, M. Shao, Y. Qian, and Y. Zhang, \u201cA novel fuzzy hierarchical fusion attention convolution neural network for medical image super-resolution reconstruction,\u201d Information Sciences, Vol.622, pp. 424-436, 2023. https:\/\/doi.org\/10.1016\/j.ins.2022.11.140","DOI":"10.1016\/j.ins.2022.11.140"},{"key":"key-10.20965\/jaciii.2026.p1044-17","doi-asserted-by":"crossref","unstructured":"J. Dai et al., \u201cA fuzzy adaptive zeroing neural network model with event-triggered control for time-varying matrix inversion,\u201d IEEE Trans. on Fuzzy Systems, Vol.31, No.11, pp. 3974-3983, 2023. https:\/\/doi.org\/10.1109\/tfuzz.2023.3272653","DOI":"10.1109\/TFUZZ.2023.3272653"},{"key":"key-10.20965\/jaciii.2026.p1044-18","doi-asserted-by":"crossref","unstructured":"H. Zhao, C. Dong, J. Cao, and Q. Chen, \u201cA survey on deep reinforcement learning approaches for traffic signal control,\u201d Engineering Applications of Artificial Intelligence, Vol.133, Part A, Article No.108100, 2024. https:\/\/doi.org\/10.1016\/j.engappai.2024.108100","DOI":"10.1016\/j.engappai.2024.108100"},{"key":"key-10.20965\/jaciii.2026.p1044-19","doi-asserted-by":"crossref","unstructured":"X. Du et al., \u201cFELight: Fairness-aware traffic signal control via sample-efficient reinforcement learning,\u201d IEEE Trans. on Knowledge and Data Engineering, Vol.36, No.9, pp. 4678-4692, 2024. https:\/\/doi.org\/10.1109\/TKDE.2024.3376745","DOI":"10.1109\/TKDE.2024.3376745"},{"key":"key-10.20965\/jaciii.2026.p1044-20","doi-asserted-by":"crossref","unstructured":"H. Jiang et al., \u201cA general scenario-agnostic reinforcement learning for traffic signal control,\u201d IEEE Trans. on Intelligent Transportation Systems, Vol.25, No.9, pp. 11330-11344, 2024. https:\/\/doi.org\/10.1109\/tits.2024.3377106","DOI":"10.1109\/TITS.2024.3377106"},{"key":"key-10.20965\/jaciii.2026.p1044-21","doi-asserted-by":"crossref","unstructured":"L. Kuang, J. Zheng, K. Li, and H. Gao, \u201cIntelligent traffic signal control based on reinforcement learning with state reduction for smart cities,\u201d ACM Trans. on Internet Technology, Vol.21, No.4, Article No.102, 2021. https:\/\/doi.org\/10.1145\/3418682","DOI":"10.1145\/3418682"},{"key":"key-10.20965\/jaciii.2026.p1044-22","doi-asserted-by":"crossref","unstructured":"M. Raeis and A. Leon-Garcia, \u201cA deep reinforcement learning approach for fair traffic signal control,\u201d arXiv:2107.10146, 2021. https:\/\/doi.org\/10.48550\/arXiv.2107.10146","DOI":"10.1109\/ITSC48978.2021.9564847"},{"key":"key-10.20965\/jaciii.2026.p1044-23","doi-asserted-by":"crossref","unstructured":"Z. Zhao, K. Wang, Y. Wang, and X. Liang, \u201cEnhancing traffic signal control with composite deep intelligence,\u201d Expert Systems with Applications, Vol.244, Article No.123020, 2024. https:\/\/doi.org\/10.1016\/j.eswa.2023.123020","DOI":"10.1016\/j.eswa.2023.123020"},{"key":"key-10.20965\/jaciii.2026.p1044-24","doi-asserted-by":"crossref","unstructured":"A. R. M. Jamil, K. K. Ganguly, and N. Nower, \u201cAdaptive traffic signal control system using composite reward architecture based deep reinforcement learning,\u201d IET Intelligent Transport Systems, Vol.14, No.14, pp. 2030-2041, 2020. https:\/\/doi.org\/10.1049\/iet-its.2020.0443","DOI":"10.1049\/iet-its.2020.0443"},{"key":"key-10.20965\/jaciii.2026.p1044-25","doi-asserted-by":"crossref","unstructured":"H. Kamal, W. Y\u00e1nez, S. Hassan, and D. Sobhy, \u201cDigital-twin-based deep reinforcement learning approach for adaptive traffic signal control,\u201d IEEE Internet of Things J., Vol.11, No.12, pp. 21946-21953, 2024. https:\/\/doi.org\/10.1109\/jiot.2024.3377600","DOI":"10.1109\/JIOT.2024.3377600"},{"key":"key-10.20965\/jaciii.2026.p1044-26","unstructured":"P. J. Werbos, \u201cApproximate dynamic programming for real-time control and neural modeling,\u201d D. A. White and D. A. Sofge (Eds.), \u201cHandbook of Intelligent Control: Neural, Fuzzy, and Adaptive Approaches,\u201d pp. 493-525, Van Nostrand Reinhold, 1992."},{"key":"key-10.20965\/jaciii.2026.p1044-27","doi-asserted-by":"crossref","unstructured":"D. Wang, N. Gao, D. Liu, J. Li, and F. L. Lewis, \u201cRecent progress in reinforcement learning and adaptive dynamic programming for advanced control applications,\u201d IEEE\/CAA J. of Automatica Sinica, Vol.11, No.1, pp. 18-36, 2024. https:\/\/doi.org\/10.1109\/JAS.2023.123843","DOI":"10.1109\/JAS.2023.123843"},{"key":"key-10.20965\/jaciii.2026.p1044-28","doi-asserted-by":"crossref","unstructured":"C. Cai, \u201cAn approximate dynamic programming strategy for responsive traffic signal control,\u201d 2007 IEEE Int. Symp. on Approximate Dynamic Programming and Reinforcement Learning, pp. 303-310, 2007. https:\/\/doi.org\/10.1109\/ADPRL.2007.368203","DOI":"10.1109\/ADPRL.2007.368203"},{"key":"key-10.20965\/jaciii.2026.p1044-29","doi-asserted-by":"crossref","unstructured":"T. Li, D. Zhao, and J. Yi, \u201cApplication of ADP to intersection signal control,\u201d Proc. of the 4th Int. Symp. on Neutral Networks, Part 1, pp. 374-379, 2007. https:\/\/doi.org\/10.1007\/978-3-540-72383-7_44","DOI":"10.1007\/978-3-540-72383-7_44"},{"key":"key-10.20965\/jaciii.2026.p1044-30","unstructured":"D. Karaboga, \u201cAn idea based on honey bee swarm for numerical optimization,\u201d Technical Report-TR 06, Erciyes University, 2005."}],"container-title":["Journal of Advanced Computational Intelligence and Intelligent Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.fujipress.jp\/main\/wp-content\/themes\/Fujipress\/hyosetsu.php?ppno=jacii003000040009","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,19]],"date-time":"2026-07-19T15:02:39Z","timestamp":1784473359000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.fujipress.jp\/jaciii\/jc\/jacii003000041044"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,20]]},"references-count":30,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,7,20]]},"published-print":{"date-parts":[[2026,7,20]]}},"URL":"https:\/\/doi.org\/10.20965\/jaciii.2026.p1044","relation":{},"ISSN":["1883-8014","1343-0130"],"issn-type":[{"value":"1883-8014","type":"electronic"},{"value":"1343-0130","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7,20]]}}}