This paper presents a novel Multi-DL Fuzzy Approach aimed at performing image recognition in the development of a real-time traffic alert system, addressing the problem of traffic congestion and related incidents. Traditional monitoring by road operators predominantly relies on fixed location cameras, yielding limited and sometimes ambiguous information. This study proposes leveraging Twitter (now known as ‘X’) as a more comprehensive data source alongside employing fuzzy techniques with Deep Learning (DL) neural networks such as CNN, VGG16, and Xception to analyze and classify traffic images. The innovative integration of these technologies augments the precision in categorizing varying traffic conditions, namely fluid and dense traffic, accidents and fires. Thus, this proposal mitigates the ambiguities prevalent in traffic image interpretation, and reduces the dependency on static data sources. The proposed models showed improved results by combining information from the DL models, elevating accuracy from 84% in crisp classification to 90% utilizing fuzzy information.
AlbalateD.Bel-PinanaP., The effects of public private partnerships on road safety outcomes, Accident Analysis & Prevention128 (2019), 53–64. doi:10.1016/j.aap.2019.03.015.
2.
AyoraV.HoritaF.KamienskiC., Social networks as real-time data distribution platforms for smart cities, in: Proceedings of the 10th Latin America Networking Conference, ACM, São Paulo, Brazil, 2018, pp. 2–9. ISBN 978-1-4503-5922-1. doi:10.1145/3277103.3277123.
3.
Berners-LeeT.HendlerJ.LassilaO., The semantic web, Scientific american284(5) (2001), 34–43. doi:10.1038/scientificamerican0501-34.
4.
ChengZ.PangM.-S.PavlouP.A., Mitigating traffic congestion: The role of intelligent transportation systems, Information Systems Research31(3) (2020), 653–674. doi:10.1287/isre.2019.0894.
5.
CholletF., Xception: Deep learning with depthwise separable convolutions, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 1251–1258.
6.
CuiH.YuanG.LiuN.XuM.SongH., Convolutional neural network for recognizing highway traffic congestion, Journal of Intelligent Transportation Systems24(3) (2020), 279–289. doi:10.1080/15472450.2020.1742121.
7.
DhruvP.NaskarS., Image classification using convolutional neural network (CNN) and recurrent neural network (RNN): A review, Machine learning and information processing (2020), 367–381. doi:10.1007/978-981-15-1884-3_34.
8.
DoranD.SeverinK.GokhaleS.DagninoA., Social media enabled human sensing for smart cities, AI Communications29(1) (2016), 57–75. doi:10.3233/AIC-150683.
9.
GanaieM.A.HuM.MalikA.TanveerM.SuganthanP., Ensemble deep learning: A review, Engineering Applications of Artificial Intelligence115 (2022), 105151. doi:10.1016/j.engappai.2022.105151.
10.
GaoY.LiJ.XuZ.LiuZ.ZhaoX.ChenJ., A novel image-based convolutional neural network approach for traffic congestion estimation, Expert Systems with Applications180 (2021), 115037. doi:10.1016/j.eswa.2021.115037.
11.
IbrahimD., An overview of soft computing, Procedia Computer Science102 (2016), 34–38. doi:10.1016/j.procs.2016.09.366.
12.
IkiriwatteA.PereraD.SamarakoonS.DissanayakeD.RupasignheP., Traffic density estimation and traffic control using convolutional neural network, in: 2019 International Conference on Advancements in Computing (ICAC), IEEE, 2019, pp. 323–328. doi:10.1109/ICAC49085.2019.9103369.
13.
JainN.K.SainiR.MittalP., A review on traffic monitoring system techniques, Soft Computing: Theories and Applications (2019), 569–577.
14.
KangQ.DingX., Urban management image classification approach based on deep learning, Journal of ambient intelligence and smart environments13(5) (2021), 347–360. doi:10.3233/AIS-210609.
15.
KlirG.YuanB., Fuzzy Sets and Fuzzy Logic, Vol. 4, Prentice hall, New Jersey, 1995.
16.
KumarM.SinghA., Probabilistic data structures in smart city: Survey, applications, challenges, and research directions, Journal of Ambient Intelligence and Smart Environments (2022), 1–56.
17.
KurniawanJ.SyahraS.G.DewaC.K.et al., Traffic congestion detection: Learning from CCTV monitoring images using convolutional neural network, Procedia computer science144 (2018), 291–297. doi:10.1016/j.procs.2018.10.530.
18.
LinC.-J.JhangJ.-Y., Intelligent traffic-monitoring system based on YOLO and convolutional fuzzy neural networks, IEEE Access10 (2022), 14120–14133. doi:10.1109/ACCESS.2022.3147866.
19.
MuñozA.Martínez-EspañaR.Guerrero-ContrerasG.Balderas-DíazS.Bueno-CrespoA., A real-time traffic alert system based on image recognition: A case of study in Spain, in: 2023 19th International Conference on Intelligent Environments (IE), 2023, pp. 1–7. doi:10.1109/IE57519.2023.10179106.
20.
RuspiniE.H., A new approach to clustering, Information and control15(1) (1969), 22–32. doi:10.1016/S0019-9958(69)90591-9.
21.
SauraJ.R.Palacios-MarquésD.Ribeiro-SorianoD., Using data mining techniques to explore security issues in smart living environments in Twitter, Computer Communications179 (2021), 285–295. doi:10.1016/j.comcom.2021.08.021.
22.
SimonyanK.ZissermanA., Very deep convolutional networks for large-scale image recognition, 2014, arXiv preprint arXiv:1409.1556.
23.
TalaatF.M.ZainEldinH., An improved fire detection approach based on YOLO-v8 for smart cities, Neural Computing and Applications (2023), 1–16.
24.
WangP.LiL.JinY.WangG., Detection of unwanted traffic congestion based on existing surveillance system using in freeway via a CNN-architecture trafficnet, in: 2018 13th IEEE Conference on Industrial Electronics and Applications (ICIEA), IEEE, 2018, pp. 1134–1139. doi:10.1109/ICIEA.2018.8397881.
25.
WangQ.ZhengJ.XuH.XuB.ChenR., Roadside magnetic sensor system for vehicle detection in urban environments, IEEE Transactions on Intelligent Transportation Systems19(5) (2017), 1365–1374. doi:10.1109/TITS.2017.2723908.
26.
XuC.MaoY., An improved traffic congestion monitoring system based on federated learning, Information11(7) (2020), 365. doi:10.3390/info11070365.
ZhuY.YanW.Q., Traffic sign recognition based on deep learning, Multimedia Tools and Applications81(13) (2022), 17779–17791. doi:10.1007/s11042-022-12163-0.
29.
ZhuoY.WangP.SunJ.JinY., Traffic congestion detection based on the image classification with CNN, in: Advances in Guidance, Navigation and Control, Springer, 2022, pp. 4569–4580. doi:10.1007/978-981-15-8155-7_378.
