Improving Infrastructure for Transportation Systems Using Clustering

摘要

Transportation systems are called the lifeline of any urban area. Major transportation systems includes cars, taxis, buses, trams etc., which carries most of the local transport in a city. This work encourages the more use of public transport over private vehicles so as to save environment, energy and resources by suggesting improvement in infrastructure of bus services. Experimental work on data collected from city of New York is presented in this work. This data collected from taxis is used to analyze the presence of traffic in the area. Temporal data segmentation with respect to different time zones is performed considering the dynamic patterns of urban traffic. Next, popular data mining techniques of clustering are applied on this segmented data to form clusters for each time zone so as to identify areas of high traffic. Further, another data set of bus stops is used to identify places with no bus stops and high traffic congestions. Henceforth new bus stops are suggested on places with high traffic density and no bus stops. Thus, a comparative study over baseline is done to recommend places that require bus stops.