Katsuhiko Takabayashi

Learn More
This paper proposes a novel decision tree for a data set with time-series attributes. Our time-series tree has a value (i.e. a time sequence) of a time-series attribute in its internal node, and splits examples based on dis-similarity between a pair of time sequences. Our method selects, for a split test, a time sequence which exists in data by exhaustive(More)
The hepatitis temporal database collected at Chiba university hospital between 1982--2001 was recently given to challenge the KDD research. The database is large where each patient corresponds to 983 tests represented as sequences of irregular timestamp points with different lengths. This paper presents a temporal abstraction approach to mining knowledge(More)
In this paper, we apply our PrototypeLines to Chronic Hepatitis Data and demonstrate the results so that domain experts can inspect them closely. PrototypeLines represents a method which visualizes irregular multi-dimensional time-series data as a sequence of probabilistic prototypes. It displays summarized information based on a proba-bilistic mixture(More)
A machine learning technique called Graph-Based Induction (GBI) efficiently extracts typical patterns from graph-structured data by stepwise pair expansion (pairwise chunking). It is very efficient because of its greedy search. Meanwhile, a decision tree is an effective means of data classification from which rules that are easy to understand can be(More)
More than 10 years ago Haux et al. tried to answer the question how health care provision will look like in the year 2013. A follow-up workshop was held in Braunschweig, Germany, for 2 days in May, 2013, with 20 invited international experts in biomedical and health informatics. Among other things it had the objectives to discuss the suggested goals and(More)
OBJECTIVES The prevalence of electronic medical record in Japan varies according to the size of the hospital which is 62.5% in major hospitals, 21.7% in medium, 9.1% in small size hospitals, and 16.5% in clinics. The complete paperless system is very limited, though some major hospitals are aiming at this system. Several regional network systems which(More)
Health care and information technology in health care is advancing at tremendous speed. We analysed whether the prognoses by Haux et al. - first presented in 2000 and published in 2002 [1] - have been fulfilled in 2013 and which might be the reasons for match or mismatch. Twenty international experts in biomedical and health informatics met in May 2013 in a(More)