C-means clustering and deep-neuro-fuzzy classification for road weight measurement in traffic management system

Abstract

Intelligent traffic management system (ITMS) is used to improve traffic flow by integrating information from different data repositories and online sensors, detecting incidents, and taking actions on traffic routing, and thus helps to reduce both fuel consumption and associated emission of green house gases. Collecting and modeling tremendous amount of continuous data from all road segments is a complex task. Data mining techniques are involved to shape the unstructured data to a structural formulation and make easier decision system for ITMS problems. In addition, making analytical decision on optimum route planning requires real-time road segment weight calculation from continuous data, in different time domains, for every day in a year. Dynamic road weights are calculated or upgraded using different environmental, road and vehicle-related decision attributes. Road segment weight decision is complicated due to the decision overlapping between the attribute clusters. Classification technique is required to provide accurate data modeling without any chaos overlapping scenario. Deep-neuro-fuzzy classification can help to improve the performance of the classification as well as remove the weight overlapping burdens. Thus, in this paper we are proposing a python-based compact model with c-means clustering and deep-neuro-fuzzy classification for road weight measurement in ITMS.