Traffic Data Collection and Visualization Tool for Knowledge Discovery Using Google Maps

Introduction

Traffic jams have become a serious issue in many cities in the world as it affects people’s daily life, fuel consumption, time, and air pollution. It has a significant impact on economic productivity and the environment in urban areas. City-wide traffic modeling, visualization, analysis, and prediction can be used to assist transportation planners to make better decisions about improving traffic jams and also help dwellers to make better decisions. Thus, traffic flow management and analysis have become essential for both individuals to better manage daily routes, and for transportation, planners to optimally schedule road infrastructure maintenance and development tasks (Jiber et al., 2018). As a result, it is needed to have traffic data collection and apply effective methods to process and analyze the collected data to extract meaningful information. Traffic conditions can be improved by improving infrastructure also; however, it is expensive, and without proper traffic management, it cannot be a standalone solution to the problem (Hossan and Nower 2020). Proper traffic data analysis and visualization can provide an appropriate guideline to manage road traffic even as it suggests which infrastructure needs improvement. Therefore, the analysis of traffic data to extract the nature of the traffic stream is one of the most important requirements of traffic management systems.

To improve traffic conditions and to manage transportation systems more effectively, various techniques have been adopted to collect traffic data from various sources, such as stationary sensor/camera-based methods (monitoring from traffic sensors or optical devices), air/space-borne methods (monitoring from airplanes or satellites), and floating-car based methods (monitoring from floating/probe cars), etc. However, the above-mentioned methods have a lot of limitations such as they are costly and require maintenance. Moreover, stationary sensor/camera-based methods can only measure traffic data at fixed positions. To get the traffic information of the whole transportation network, a large number of detectors are needed, as a result, the system can be very expensive. Air/space-borne methods can monitor traffic conditions over large areas, but the data are available only when the air/space-borne detectors are flying over the monitored areas. Thus, the implementation of traffic monitoring systems requires a considerable amount of investment in equipment and qualified personnel to process the data (Lima and Campos 2017). However, many cities in the world suffer a huge traffic jam but there is no traffic monitoring infrastructure such as stationary sensors or detection mechanisms available.

In this context, a geographic information system (GIS) can be utilized which is designed to capture, store, manipulate and manage all types of traffic data (Ciepłuch et al., 2010). It is experimentally shown that the traffic data gathered from the web sources can be considered as a reliable data source that does not require a high level of accuracy (Lima and Campos 2017). Different GIS systems, such as Google map, Bing map, Open Street Maps offer huge amounts of geographic data, for example, street map, aerial/satellite imagery, geocoding, searches, routing functionality, and traffic jam, etc. This traffic information can act as a preferential source of information where monitoring infrastructure is not available. However, traffic information gathered from a web application requires a paid Application Program Interface (API) of these services which is not free of cost.