Kôiti Hasida

TL;DR: A new method to infer users' longterm properties from their respective location histories is proposed and a machine learning approach is taken to automatically classify users into different categories for each user property.

TL;DR: This paper describes MIKE, an automatic commentary system for the game of soccer that interprets this domain with six soccer analysis modules that run concurrently within a role-sharing framework and discusses how to control the interaction between them.

TL;DR: This paper proposes a new approach to automatically obtain a social network, especially a collaboration network of researchers, of a community from the Web, by analyzing the retrieved documents and assigning edge labels to represent classes of relations such as co-author, same laboratory, same project, or same conference.

TL;DR: The proposed method is based on the (auto-)correlation matrix of Fourier transform features, naturally containing the correlations between the frequencies as well as the ordinary power spectrum for each frequency, and outperformed the other methods in the experiment on gait identification.

TL;DR: In this paper, the authors present a model incorporating the findings of recent research, which suggests repatriate adjustment and turnover intentions are related to the following key factors: employee expectations upon repatriation, employee perceptions of organizational repatriation support practices, and employee perception of the appropriateness of both job content upon return and the availability of external career opportunities based on the employee's new found expertise.