Shin-ichi Matsuda
Nanzan University
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Shin-ichi Matsuda.
Archive | 1998
Isao Yoshimura; Mitsu Yoshimura; Shin-ichi Matsuda
The task of signature verification is to judge whether the writer of a signature is truly the declared person or not, by referring to a previously provided signature database. The verification is completed when the observed dissimilarity between the questioned signature and a set of signatures, which were previously written by the declared person and included in the database, is less than a given threshold. This paper proved, through a verification experiment using a signature database supplied by CADIX Co. Ltd., that the use of multiple representatives, which represent respective clusters constructed by a clustering procedure, is effective. According to the experiment, the resulting error rate decreased from about 6% to about 1% on average by increasing the number of representatives from one to three.
Communications in Statistics-theory and Methods | 2018
Taka-aki Shiraishi; Shin-ichi Matsuda
ABSTRACT We consider multiple comparison test procedures among treatment effects in a randomized block design. We propose closed testing procedures based on maximum values of some two-sample t test statistics and based on F test statistics. It is shown that the proposed procedures are more powerful than single-step procedures and the REGW (Ryan/Einot–Gabriel/Welsch)-type tests. Next, we consider the randomized block design under simple ordered restrictions of treatment effects. We propose closed testing procedures based on maximum values of two-sample one-sided t test statistics and based on Batholomew’s statistics for all pairwise comparisons of treatment effects. Although single-step multiple comparison procedures are utilized in general, the power of these procedures is low for a large number of groups. The closed testing procedures stated in the present article are more powerful than the single-step procedures. Simulation studies are performed under the null hypothesis and some alternative hypotheses. In this studies, the proposed procedures show a good performance.
Japanese Journal of Applied Statistics | 1990
Shin-ichi Matsuda; Yasushi Nagata
Japanese journal of biometrics | 2008
Shin-ichi Matsuda
Japanese Journal of Applied Statistics | 2006
Takanori Tanase; Shin-ichi Matsuda
Japanese Journal of Applied Statistics | 1990
Shin-ichi Matsuda; Takashi Fujimaoto; Isao Yoshimura
Japanese journal of biometrics | 2016
Taka-aki Shiraishi; Shin-ichi Matsuda
Japanese journal of biometrics | 2016
Taka-aki Shiraishi; Shin-ichi Matsuda
kansei Engineering International | 2006
Ken Nishina; Shinji Niwa; Shin-ichi Matsuda
Japanese Journal of Applied Statistics | 1994
Shin-ichi Matsuda