The study of data science involves working with massive volumes of data and state-of-the-art instruments and techniques to find patterns in the data, obtain relevant information, and make business decisions. It is a difficult undertaking to analyze vast volumes of multidimensional road traffic data in order to find anomalies. When dealing with enormous volumes of traffic data in various formats, computational data science (CDS) should be employed. The objective of the CDS approach was to identify patterns in the traffic data that could impact traffic effectiveness. By using data science to detect data anomalies to a greater extent with contemporary artificial intelligence techniques like deep learning (DL), traffic congestion and vehicle lineups are lessened. The primary benefit of the CDS strategy is that it helps identify reasons for data anomalies early on, thereby preventing long-term traffic congestion. Additionally, CDS showed outcomes that were improving in a variety of road traffic circumstances.
Road Traffic Anomalies Detection Using Deep Learning Algorithm and Computational Data Science
Smart Innovation, Systems and Technologies
International Conference on Business Intelligence and Data Analytics ; 2024 ; Bangalore, India April 05, 2024 - April 06, 2024
25.02.2025
13 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Detection of road traffic anomalies based on computational data science
Springer Verlag | 2022
|Detection of road traffic anomalies based on computational data science
DOAJ | 2022
|Road traffic accident risk prediction deep learning algorithm
Europäisches Patentamt | 2022
|