Toshitaka Maki

A New Multiple Label Propagation Algorithm for Linked Open Data

In recent years, Linked Open Data (LOD) has been attracting attention in the world since the LOD have features such as semantic web and ontology. Also, applications using the LOD have been increasing year after year in Japan and in all over the world. However, there are a problem that most of existing LOD are not linked with other LOD. Therefore, original features of the LOD have been lost. In this study, we propose a new Multiple Label Propagation algorithm for linking each other the existing LOD to bring out the original features by semi-supervised learning. This algorithm predicts semantic labels of individual data of the LOD using an assumption that adjacent nodes belong to a same or similar class. Therefore, the algorithm has new formula to consider semantic distance. Thereby, the algorithm is possible to extend links between neighborhood nodes (data). In addition, the algorithm is possible to correspond multi-label data. The results of experiments showed that the algorithm can give the label prediction values representing semantic distances, and can be processed much faster than a conventional algorithm.

Link prediction of LOD by multiple label propagation algorithm considering semantic distance

This paper presents link prediction of Linked Open Data (LOD) by Multiple Label Propagation Algorithm (MLPA). The current LOD do not have enough links. Therefore, the LOD have not been able to exert so much semantic characteristics. In order to solve this problem, we proposed the MLPA considering semantic distance. The MLPA can expand potential links of each data contained in the LOD. The experimental result of the MLPA shows the good performance and the validity of this algorithm is confirmed.

Design and Characteristics of Two-Dimensional Color Code Editor with Dotted Images

In recent years, QR code is widely used in the accessing to the Internet by cellular phones. As this code is a set symbol of simply black and white dots, it is very simple and insipid. In order to improve this weakness, a color two-dimensional color code editor with dotted images has been developed. This paper presents the design method and reading characteristics of the code editor. The experimental results show good performances of the decoding characteristics by the existing QR decoder and the effectiveness of the editor is also confirmed.

Resource Propagation Algorithm to Reinforce Knowledge Base in Linked Data

Linked Data are data of directed graph with labels to describe based on Resource Description Framework (RDF), and can create a knowledge base by linking each resource on the Web. However, a large amount of Linked Data does not have enough links since resources defined at Internationalized Resource Identifier (IRI) data type are scanty. Therefore, this paper presents that Resource Propagation Algorithm predicts links between resources in Linked Data based on semantic distance, and reinforces the knowledge base. The algorithm was confirmed that it was able to generate semantic links between the resources considering predicate dictionary.

Metadata Complement Method by Linked Open Data for Literature Search

In the current papers of the academic society, there are often cases where the literature metadata such as keywords or abstracts are insufficient. In this paper, we propose a new literature retrieval support system that complements the data using the open data and facilitates the search when the relational literature metadata are missing or insufficient using Linked Open Data (LOD). The missing keywords are estimated from the existing titles and abstracts of the literature by extracting the semantic information of the papers. We constructed a prototype of new literature search support system using IEICE Knowledge Discovery System (I-Scover) and confirmed that as a result of experiments using this support system, search accuracy and search time were also improved.

Beacon-based tourist information system to identify visiting trends of tourists

In this study, we propose a system that provides tourist information and obtains trends of visiting tourists using beacons and cloud service. As part of our research, we are working on the promotion of local area tourism in cooperation with a local community. A low energy Bluetooth device is used as a beacon to transmit a universally unique identifier. In addition, beacons are placed at sightseeing spots and tourist facilities. Our proposed system comprises two application programs; one is a client-side application program that provides area-specific tourist information corresponding to the detected beacon. The other is a server-side application to record time and location information of the detected beacons. In this paper, we describe the scheme of our system, and present the results of experiments conducted using the prototype system in the local tourist area. In addition, we discuss an open platform for information collection services using beacons.

A New Laboratory Assignment Support System for Undergraduate Students

University students of science and engineering have to study in laboratories for graduation. Therefore, they are necessary to select the laboratories at a time when they become the 4th-grade. However, there are some problems in laboratory assignment. For example, there is a specialized mismatch problem of the students and the laboratories. In this study, we proposed a new laboratory assignment support system to solve their problems using two databases of syllabuses and graduation papers. The proposed system has an algorithm to extracts technical terms from syllabuses selected by a student user, and calculates similarity as four specialized fields using typical keywords of the laboratories. We developed a prototype based on the proposed system, and conducted an evaluation by a questionnaire survey. As a result, the prototype showed that it is able to solve the laboratory assignment problems.

Research field analysis using linked data of I-Scover

This paper presents the research field analysis method using the Linked Data of I-Scover [1]. I-Scover is the article retrieval system of the Institute of Electronics, Information and Communication Engineers (IEICE). This system manages the article metadata by Linked Data format. The research field analysis of the articles is important, and the effective article classification is desired for faceted navigation. The simulation results of the proposed analysis method show the good performance and the validity of this method is confirmed.

Tourism Local Community System Using LOD

This paper presents a new tourism local community system based on the LOD (Linked Open Data). In this study, the tourism-related data are converted into the RDF (Resource Description Framework) data and stored as LOD database in the local community system. N-triple data are generated by parsing the texts and connected to other related terms. Therefore, the relationship could be realized close to the ontology. The prototype system is constructed and the validity of the proposed system is confirmed by the experiments.

Adaptive Keyword Extraction System for the Hierarchical Category Search

As the Big Data is handled in the modern Internet, it needs various efficient search methods to retrieve the required information in the flood of information. In this paper, we propose a new Hierarchical Search Interface by Self-Organizing search method with a smartphone. The users can search the objective terms by pushing buttons for each adaptive hierarchical categories without any input of keyword. We describe the experimental results and the effectiveness of the proposed system is confirmed by the prototype simulation.