This study explores cloud-based data mining algorithm integration in elevating smart city infrastructure management and decision support systems. Specifically, the authors focus on optimizing traffic management through the analysis of real-time traffic sensor data. Timestamped history records of vehicle count, traffic speed, density, weather condition, accidents, and traffic signals were utilized. Machine learning models such as Support Vector Machine, K-Nearest Neighbors, Decision Trees, and Random Forest were trained and tested. The analysis indicated SVM to be the most effective instrument, resulting in an accuracy of 98.98%. The model was also instrumental in reducing vehicle count by 16.7%, traffic density by 25%, and traffic speed was increased by 50%. KNN’s overall accuracy experience was 94.5%, and the model was shown to be highly optimized for various forever traffic conditions. However, the overall impact on traffic speed and density was not as significant compared to the previously-discussed model. DT and RF demonstrated respective accuracies of 92.3% and 91.2%, offering varying levels of decision interpretation and ensemble learning opportunities. As a result, the study indicates that machine learning can play a critical role in improving urban traffic management via traffic congestion prediction and minimization, resulting in improved traffic flow, overall trip time reduction, and general urban mobility management. T.
Integrating Cloud-based Data Mining Algorithms for Smart City Infrastructure Management and Decision Support Systems
24.09.2024
582960 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Smart city traffic safety management decision support system
Europäisches Patentamt | 2022
|British Library Conference Proceedings | 2006
|Integrating Remote Sensing Data in Decision Support Systems for Transportation Asset Management
Transportation Research Record | 2018
|