Ikki Ohmukai

<p>This paper describes a new challenge for addressing knowledge graph completion held in Japan, 2018. Deep learning techniques have opened a new vista of Artificial Intelligence and promoted applying the AI-related systems to a wide variety of so...

<p>As a research theme becomes more complicated, the range of knowledge necessary for research spreads wider. The collaborative research by multiple researchers is known to be effective for doing complicated research. Existing methods on research ...

We describe a procedure for constructing a website for publishing open data by focusing on the case of Open DATA METI, a website of the Ministry of Economy, Trade, and Industry. We developed two sites for publishing open data: a data catalog site ...

Web API is useful solution for the various needs of scholarly information services. In CiNii, a qualitative difference is not established between the service and Web API so that third parties can utilize data of CiNii. This paper describes the sys...

Currently, news contents are based on traditional taxonomy with hierarchical structure. Meanwhile, social bookmarks have a flat structure called folksonomy which has less difficulty to get news rather than taxonomy. However, bookmark tags depends ...

This paper proposes a new crossover method for distributed genetic algorithms(DGA). DGA with multiple Subpopulations provides better solutions than conventional GA with a single population, and the proposed method including the hybridization cross...

Here in this paper, we discuss how to build up a recommendation system for PDA, using a domain ontology and individual preference. The domain ontology comes from a commercial directory service. Individual preference comes from positioning data and...

In this research, we propose a system called ActionLog which supports authoring and sharing Weblog contents for the purposes of support on reviewing and support on communicating in academic conferences. ActionLog collects users' actions from other...

Recently, tags of social bookmark services are used as metadata of web pages. In this case, meta data are desirable to be written in words which are related with contents of web pages. In our research, we focus marking which users underline or hig...

E-commerce sites improve their sales by presenting products that match users' preferences using recommendation methods. A user's preference may change during the shopping. In this paper, this change is called a "preference shift". However, convent...

E-commerce sites improve their sales by presenting products that match users' preferences using recommendation methods. A user's preference may change during the shopping. In this paper, this change is called a "preference shift". However, convent...

Extracting a user's preference model and its transition on e-commerce sites improves their sales by presenting products that match the user's preference and marketing based on product choices of users. A method to obtain a user's preference model ...

This paper describes design process of metadata in CiNii, which is an academic information service provided by National Institute of Informatics. We develop its bibliographic metadata based on several web standards such as OpenSearch and RDF. We a...

Linked Open Data (LOD) is the concept that realizes developing database resources as commons by generating machine readable data linked each other on the web with distributed activities. LOD enables trial of supply public services, which used to b...

"Open data" attracts attention as part of the information disclosure by governments and public institutions. Although the spread of the open data movement in Japan is behind as compared with the Western countries, quality and quantity of data are ...