A Computational Data Science Based Detection of Road Traffic Anomalies

An essential component of an Intelligent Transportation System (ITS) is anomaly detection. There is an increasing need for the identification of unusual occurrences in the traffic network due to the yearly growth in vehicle usage and the continual improvement of the traffic networking. Traffic anomaly detection provides sufficient decision-supporting information for road network operators, users, and other stakeholders. It is difficult to find anomalies in large-scale multivariate road traffic data. By bridging the gap between automated and manual traffic analysis methods, visual analytics helps increase process transparency. New rapid and effective processing tools and methodologies are required to swiftly extract and analyze data from the enormous volume of data. Data science approaches can be used to research and pinpoint various kinds of severe attacks and anomalies. Hence, Computational Data Science based detection of road traffic Anomalies is presented in this analysis. Thecomputational data science techniques (CDS) are needed to manage vast volumes of traffic data in a wide range of forms. Finding abnormalities in traffic data that impact traffic efficiency produced the development of computational data science.The primary advantage of the CDS approach is the early identification of data anomaly sources to avoid traffic congestion over a long-term.