Smart City Gnosys
Smart city article details
| Title | Iot-Based Intelligent Traffic Management System Using Hybrid Ann-Svm Prediction Model For Smart Cities |
|---|---|
| ID_Doc | 33980 |
| Authors | Dogra A.K.; Kaur J. |
| Year | 2024 |
| Published | Optoelectronics, Instrumentation and Data Processing, 60, 5 |
| DOI | http://dx.doi.org/10.3103/S875669902470078X |
| Abstract | Abstract: Intelligent Transportation Systems (ITSs) can be used to inform and motivate users to make wise decisions about their daily travel routes and method of transportation while reaching more sustainable social and transportation authority goals. However, in reality, it is difficult for an ITS to support multidimensional travel goals and enable personalized, context-driven incentive generation. This is due to the fact that an ITS must deal with the issue of diverse travellers having varying travel preferences and restrictions for route and modality in the face of dynamically changing traffic conditions. In this designed model, the roadside security camera images are gathered and preprocessed using image resizing and greyscale conversion techniques to reduce the complexity of the model and resize the total amount of pixels into 256 256. With the help of the GLRLM technique, features from the segmented images are obtained in order to train the classifier for predicting the density of the traffic. These preprocessed images are divided into segments based on a threshold for separating the cars on the road. Using a hybrid ANN-SVM classification technique, which divides density levels into low, medium, and high categories, these chosen features are trained. The I2I communication is used to adjust the timing of the traffic lights at the junction based on the various density levels, and the also uploaded density levels to the cloud for alerting the vehicles based on the I2V communication. Simulation analysis showed that proposed model attains performance value of 96.2 accuracy, 94.3 precision, 94.3 recall, 3.8 mean square error (MSE), 97.1 specificity, 97.1 negative predictive value (NPV), 2.9 false positive rate (FPR), 5.7 false negative rate (FNR), 2.9 false omission rate (FOR) and 5.7 false discovery rate (FDR). These evaluated values are contrasted with those obtained using established methods like -nearest neighbours (KNN), gradient boosting, and random forest (RF). As a result, the IoT-based intelligent traffic management system for smart cities that uses a hybrid ANN-SVM prediction model outperforms the conventional model. © Allerton Press, Inc. 2024. |
| Author Keywords | GLRLM; greyscale conversion; hybrid ANN-SVM; image resizing; intelligent traffic management; threshold |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
32646  | 0.89 | Limkar S.; Ashok W.V.; Shende P.; Wagh K.; Wagh S.K.; Kumar A. | Intelligent Transportation System Using Vehicular Networks In The Internet Of Vehicles For Smart Cities | Journal of Electrical Systems, 19, 2 (2023) |
| 8520 | 0.884 | Shamitha C.; Radhika S.; Malathy K.; Ranjith S.; Sasirekha N. | An Intelligent Iot Enabled Traffic Queue Handling System Using Machine Learning Algorithm | Proceedings of the 2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022 (2022) |
| 19433 | 0.883 | Al-Jawahry H.M. | Developing An Intelligent Traffic Management System For Smart Cities Through The Integration Of Machine Learning And Iot Technologies | Lecture Notes in Networks and Systems, 1306 LNNS (2025) |
| 6910 | 0.881 | Dankan Gowda V.; Yogi K.S.; Srinivas I.V.; Kumar B.K.; Srinivas D.; Sudhakar Reddy N. | Ai And Machine Learning For Intelligent Traffic Management In Iot-Connected Cities | 2024 Asian Conference on Intelligent Technologies, ACOIT 2024 (2024) |
| 30638 | 0.88 | Sabeer S.; Ali S.S.; Siddiqua A.; Anjum A. | Implementing Ml And Iot-Based Predictive Traffic-Management Systems For Smart Cities | 2024 2nd International Conference Computational and Characterization Techniques in Engineering and Sciences, IC3TES 2024 (2024) |
| 5762 | 0.88 | Prakash J.; Murali L.; Manikandan N.; Nagaprasad N.; Ramaswamy K. | A Vehicular Network Based Intelligent Transport System For Smart Cities Using Machine Learning Algorithms | Scientific Reports, 14, 1 (2024) |
| 35967 | 0.878 | Yuan T.; Da Rocha Neto W.; Rothenberg C.E.; Obraczka K.; Barakat C.; Turletti T. | Machine Learning For Next-Generation Intelligent Transportation Systems: A Survey | Transactions on Emerging Telecommunications Technologies, 33, 4 (2022) |
| 29829 | 0.878 | Alsolami B.; Mehmood R.; Albeshri A. | Hybrid Statistical And Machine Learning Methods For Road Traffic Prediction: A Review And Tutorial | EAI/Springer Innovations in Communication and Computing (2020) |
| 24035 | 0.874 | Naveed S.A.; Farooq U.; Raza M.A.; Rehman Z.U.; Saleem M.; Ghazal T.M. | Enhancing Traffic Flow And Congestion Management In Smart Cities Utilizing Svm-Based Linear Regression Approach | International Journal of Advanced and Applied Sciences, 11, 10 (2024) |
| 18553 | 0.874 | Lilhore U.K.; Imoize A.L.; Li C.-T.; Simaiya S.; Pani S.K.; Goyal N.; Kumar A.; Lee C.-C. | Design And Implementation Of An Ml And Iot Based Adaptive Traffic-Management System For Smart Cities | Sensors, 22, 8 (2022) |