TRAFFIC ACCIDENT DETECTION IN SMART CITY TRANSPORTATION USING AN ENSEMBLE DEEP LEARNING FRAMEWORK
DOI: 
SHARE THIS ARTICLE
DOWNLOAD ARTICLE
REVIEW REPORT
CITE THIS ARTICLE
In the era of smart cities, intelligent transportation systems (ITS) are pivotal for ensuring efficient, safe, and sustainable urban mobility. One of the critical challenges in ITS is the timely and accurate detection of traffic accidents, which directly impacts emergency response, traffic management, and public safety. This study presents a hybrid deep learning ensemble approach that integrates classical machine learning algorithms—Support Vector Machine (SVM), K-Nearest Neighbours (KNN), and Random Forest (RF)—to enhance the accuracy and robustness of traffic accident detection. The proposed method leverages high-dimensional traffic data including vehicle speed, GPS coordinates, traffic density, and time-series patterns captured from IoT sensors and surveillance systems. A feature extraction phase powered by deep learning techniques, such as autoencoders or convolutional layers, reduces noise and enhances the representational quality of input data. Subsequently, individual classifiers (SVM, KNN, and RF) are trained on the processed features and their outputs are combined using a weighted ensemble strategy to form the final prediction.
Keywords
Article Information
Article Metrics
HOW TO CITE
Copy
KUMAR, I. K. (2026). Traffic Accident Detection in Smart City Transportation Using an Ensemble Deep Learning Framework. International Journal of Science, Strategic Management and Technology, 02(6). https://doi.org/10.55041/ijsmt.v2i6.119
KUMAR, I. "Traffic Accident Detection in Smart City Transportation Using an Ensemble Deep Learning Framework." International Journal of Science, Strategic Management and Technology, vol. 02, no. 6, 2026, pp. . doi:https://doi.org/10.55041/ijsmt.v2i6.119.
KUMAR, I. "Traffic Accident Detection in Smart City Transportation Using an Ensemble Deep Learning Framework." International Journal of Science, Strategic Management and Technology 02, no. 6 (2026). https://doi.org/https://doi.org/10.55041/ijsmt.v2i6.119.
References
2.Srivastava AN, Zane-Ulman B. (2005). Discovering recurring anomalies in text reports regarding complex space systems. In Aerospace Conference, IEEE. IEEE 3853-3862.
3.Ghazizadeh M, McDonald AD, Lee JD. (2014). Text mining to decipher free-response consume complaints: Insights from the nhtsa vehicle owner’s complaintdatabase.Human Factors 56(6):1189-1203.http://dx.doi.org/10.1504/IJFCM.2017.089439.
4.Chen ZY, Chen CC. (2015). Identifying the stances of topic persons using a model-based expectationmaximization method. J. Inf. Sci. Eng 31(2): 573-595. http://dx.doi.org/10.1504/IJASM.2015.068609.
[5] Williams T, Betak J, Findley B. (2016). Text mining analysis of railroad accident investigation reports. In 2016 Joint Rail Conference. American Society of Mechanical Engineers V001T06A009-V001T06A009. http://dx.doi.org/10.14299/ijser.2013.01.
[6] Suganya, E. and S. Vijayarani. “Analysis of road accidents in India using data mining classification algorithms.” 2017 International Conference on Inventive Computing and Informatics (ICICI) (2017):1122-1126. [7] Sarkar S, Pateshwari V, Maiti J. (2017). Predictive model for incident occurrences in steel plant in India. In ICCCNT 2017, IEEE, pp. 1-5.http://dx.doi.org/10.14299/ijser.2013.01.
Ethics and Compliance
Indexed In
Similar Articles
Previous Article
