Decision trees and production rules, which are among the methods used in knowledge discovery and data mining, are applied to investigate drivers’ route choice behavior. These methods have an advantage over artificial neural networks, another data mining method often used in analysis of travel behavior: they facilitate determination of the relationships between the explanatory variables and the choice. Specifically, the C4.5 algorithm, which produces a decision tree and a set of production rules from the tree, is applied here. Two surveys were carried out to collect data on drivers’ route choice behavior between two alternative routes on expressway networks. The two data sets include the expected minimum, maximum, and average travel times along each alternative route, as indicated by the respondent as well as his or her sociodemographic attributes. The results of the analyses suggest that different expected travel times influence route choice in different cases and that a maximum or average travel time determines route choice in some cases regardless of other attributes. The results of a comparison analysis between the C4.5 algorithm and discrete choice models indicate the superior ability offered by the former in representing drivers’ route choice.

No abstract

In order to health monitoring the state of largescale infrastructures, image acquisition by autonomous flight drone is efficient for stable angle and high quality image. Supervised learning requires a great deal of dataset consisting images and annotation labels. It takes long time to accumulate images including damaged region of interest (ROI). In recent years, unsupervised deep learning approach such as generative adversarial network (GAN) for anomaly detection algorithms have progressed. When a damaged image is a generator input, it tends to reverse from the damaged state to the health-like state image. Using the distance of distribution between the real damaged image and the generated reverse aging health-like image, it is possible to detect the concrete damage automatically from unsupervised learning. This paper proposes an anomaly detection method using unpaired image-to-image translation mapping from damaged image to reverse aging fake like health condition. Actually, we apply our method to field studies, and we examine the usefulness for health monitoring concrete damages.