Various recent intelligent transport system projects are promoting vehicle safety and efficient vehicular traffic control all over the world. One of ITS applications is a system that solves road traffic problems by using vehicular communications technology. Inter-vehicle communication (IVC) is the communications technology for vehicles to exchange moving vehicle information by wireless networks without any base stations. The Vehicular Ad-hoc Network (VANET) is expected to provide new applications for passengers of vehicles by enabling vehicles to communicate with each other via IVC as well as with roadside base stations via roadside-to-vehicle communications. However, when each vehicle transmits its own information to neighboring vehicles, the amount of information being transmitted increases significantly. To solve this problem, we present a novel real-time recognition method for vehicular traffic congestion via VANET with IVC. Vehicles collect the original GPS information of other vehicles by communicating with each other, and they create content that may be useful for drivers by analyzing that original information. The proposed method can reduce the information amount and deliver the analyzed contents to other vehicles efficiently. Computer simulation results show that the proposed method provides real-time information of vehicular accidents and traffic congestion to distant vehicles accurately.

Many people have suffered and died due to a lot of large-scale disasters such as earthquake, fire, and terrorism, etc. In disasters where most evacuators become panic, two things are necessary for their immediate evacuation. The first is to estimate the location of the disaster occurrence. The second is to construct an evacuation support system that searches for safe and efficient evacuation routes. In this paper, we propose Emergency Rescue Urgent Communication -- Evacuation Support System (EUC-ESS) based on Mobile Ad-hoc networks (MANET) composed of many mobile terminals. Using experiments and computer simulations, we show that this system would support evacuators in determining appropriate routes for survivors.

Many people have faced mortal risks due to sudden disasters such as earthquakes, fires, and terrorisms, etc. In disasters where most people become panic, it is important to grasp disaster positions immediately and to find out some appropriate evacuation routes. We previously proposed the specific evacuation support system named as Emergency Rescue Evacuation Support System (ERESS). ERESS is based on Mobile Ad-hoc network (MANET) and aims to reduce the number of victims in panic-type disasters. This system consists of mobile terminals with advanced disaster recognition algorithm and various sensors such as acceleration, angular velocity and earth magnetism. However, the former ERESS did not have the clear criteria to detect the disaster outbreak. In this paper, we propose a new disaster recognition algorithm by Support Vector Machine (SVM) which is a kind of machine learning. In this method, an ERESS mobile terminal learns the behaviors of its holder by SVM. The SVM acquires the decision boundary based on the sensing data of the terminal holder, and it is judged whether to be the emergency. We show the validity of the proposed method by panic-type experiments.