Traffic Signal Data for Emergency Vehicles using C-Means and SVM Classification

Traffic related troubles include not just traffic jamming due to increase in vehicular density, but also complexity for passage of emergency vehicles, violation of rules such as red signal jumps, vehicle breakdowns and accidents causing blockage of roads and loss of lives. Nowadays lot of people losing their lives due to delay of emergency vehicle service. By providing ambulance service timely and accurate can reduce the deaths. By avoiding the unnecessary time delay near traffic jams during an emergency situation. Clustering is a machine learning procedure that includes the gathering of targeted information which is a strategy for unsubstantiated learning and is a typical procedure for factual information investigation utilized in numerous fields. Fuzzy C-means logic is a technique for clustering which enables one bit of information to have a place with two or more clustering. The proposed Fuzzy C-Means (FCM) algorithm technique is often utilized calculation, to inspect the different types of information with the frequent data sets. The Support Vector Machine (SVM) classification method is obviously used classification model which classifies the data entirely however the size is in a common manner. In this paper, a set of datasets is implanted and the experimental clustering report is verified with the frequent parameters such as overlapping, data partitioning, high dimensional data and irrelevant data clustering. On comparing with existing clustering processes, this proposed approach shows the high efficiency than other clustering models with approximate effective results on the association rules.