Satidchoke Phosaard

Perception-Based Road Traffic Congestion Classification Using Neural Networks and Decision Tree

In this study, we investigated an alternative technique to automatically classify road traffic congestion with travelers’ opinions. The method utilized an intelligent traffic camera system orchestrated with an interactive web survey system to collect the traffic conditions and travelers’ opinions. A large numbers of human perceptions were used to train the artificial neural network (ANN) model and the decision tree (J48) model that classify velocity and traffic flow into three congestion levels: light, heavy, and jam. The both model was then compared to the Occupancy Ratio (OR) technique, currently in service in the Bangkok Metropolitan Administration (BMA). The accuracy of ANN was more than accuracy of the J48. The evaluation indicated that our ANN model could determine the traffic congestion levels 12.15% more accurately than the existing system. The methodology, though conceived for use in Bangkok, is a general Intelligent Transportation System (ITS) practice that can be applied to any part of the world.

Classification of Road Traffic Congestion Levels from Vehicle’s Moving Patterns: A Comparison Between Artificial Neural Network and Decision Tree Algorithm

We proposed a technique to identify road traffic congestion levels from velocity of mobile sensors with high accuracy and consistent with motorists’ judgments. The data collection utilized a GPS device, a webcam, and an opinion survey. Human perceptions were used to rate the traffic congestion levels into three levels: light, heavy, and jam. We successfully extracted vehicle’s moving patterns using a sliding windows technique. Then the moving patterns were fed into ANN and J48 algorithms. The comparison between two learning algorithms yielded that the J48 model shown the best result which achieved accuracy as high as 91.29%. By implementing the model on the existing traffic report systems, the reports will cover on comprehensive areas. The proposed method can be applied to any parts of the world.

X3DOM virtual reality book store

Virtual reality commer1ce (VR-commerce) is a potential candidate for a wide adoption of the next wave of the e-commerce platform, since its advantages and novel shopping experience derived from the VR interface. Currently, platform dependence and downloading and installing a huge virtual world before cruising into the VR-store are examples among many cumbersome shoppers facing in using such platform. WebGL is a front runner for implementing this kind of innovative shopping experience, which just enters its matured phase. This study is the first implementation of a full-scale virtual reality store by X3D. It focused on the technical feasibility aspects of implementing a virtual reality book store by the X3D and WebGL standard.

A multimedia-based and time-sensitive interactive web survey for road user opinion on traffic condition

Web Survey has increased in popularity because of its convenience, ease of use, low cost, and quickness in knowing the result of a survey in real time. Web survey is widely used to gather user opinions on various purposes. However, most such systems are plain-text, and sometimes with a few graphical images. This paper presents an innovative Multimedia-Based and Time-Sensitive Interactive (MTI) Web Survey to collect user opinions on the traffic condition. Open source development tools and emerging web technologies, such as PHP and AJAX, are used in implementing the system to achieve event-sensitive user opinions. This MTI web survey, though presented and illustrated by using road user opinion on traffic condition data, is a general technique that can be applied to any time-sensitive data collection. The usability testing on MTI web survey was also conducted to gain insights on usage issues and the results are discussed.