loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Affiliation

Mitsubishi Electric Corporation, Japan
Context (please use complete words only)
Field
Sort by

6 Papers

Reliable Image Matching using Binarized Gradient Features Obtained with Multi-flash Camera

Topics: Object and Face Recognition; Object Detection and Localization; Vision for Robotics

Authors: Yasunori Sakuramoto 1 , Yuichi Kanematsu 1 , Shuichi Akizuki 1 , Manabu Hashimoto 1 , Kiyotaka Watanabe 2 and Makito Seki 2

Affiliations: 1 Chukyo University, Japan , 2 Mitsubishi Electric Corporation, Japan

Digital Object Identifier: 10.5220/0005267902600264

Proceedings of VISAPP 2015/VISIGRAPP, ISBN: 978-989-758-090-1

Collapse Button Quick Abstract
In this paper, we propose an object detection method using features describing information about a concavoconvex shape of an object that are obtained by using a small camera that controls the illumination direction. A feature image containing information about the shape of the object is generated by integrating images obtained by turning on, one by one, light emitting diodes (LEDs) annularly arranged around the camera. Our method can reliably detect a texture-less object by using this feature image in the matching process. Experiments using 200 actual images confirmed that the method achieves a 97.5% recognition success rate and a 4.62 sec processing time.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Applications

Robotics

Software Engineering
Pattern Recognition

Bayesian Networks for Matcher Composition in Automatic Schema Matching

Topics: Coupling and Integrating Heterogeneous Data Sources; Organisational Issues on Systems Integration

Authors: Daniel Nikovski 1 , Alan Esenther 1 , Xiang Ye 1 , Mitsuteru Shiba 2 and Shigenobu Takayama 2

Affiliations: 1 Mitsubishi Electric Research Laboratories, United States , 2 Mitsubishi Electric Corporation, Japan

Digital Object Identifier: 10.5220/0004001500480055

Proceedings of ICEIS 2012, ISBN: 978-989-8565-10-5

Collapse Button Quick Abstract
We propose a method for accurate combining of evidence supplied by multiple individual matchers regarding whether two data schema elements match (refer to the same object or concept), or not, in the field of automatic schema matching. The method uses a Bayesian network to model correctly the statistical correlations between the similarity values produced by individual matchers that use the same or similar information, in order to avoid overconfidence in match probability estimates and improve the accuracy of matching. Experimental results under several testing protocols suggest that the matching accuracy of the Bayesian composite matcher can significantly exceed that of the individual component matchers.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Coupling and Integrating Heterogeneous Data Sources

Enterprise Information Systems

Organisational Issues on Systems Integration
Databases and Information Systems Integration

MICROWAVE WPT TECHNOLOGY DEVELOPMENTS FOR SSPS APPLICATION

Authors: Takashi Saito 1 , Yoshiharu Fuse 1 , Shoichiro Mihara 1 , Shuji Nakamura 1 , Koichi Ijichi 1 , Yukihiro Homma 2 , Takuro Sasaki 2 , Eiichiro Fujiwara 3 , Yuichiro Ozawa 3 and Teruo Fujiwara 3

Affiliations: 1 Japan Space Systems(J-spacesystems), Japan , 2 Mitsubishi Electric Corporation (MELCO), Japan , 3 IHI Aerospace Co., Ltd. (IA), Japan

Digital Object Identifier: 10.5220/0005413600350043

Proceedings of ICTRS 2012, ISBN: 978-989-8565-28-0

Collapse Button Quick Abstract
Japan Space Systems(J-spacesystems), formerly known as Institute for Unmanned Space Experiment Free Flyer (USEF), has been studying Space Solar Power System as future electricity alternative energy source. Since 2009, J-spacesystems started new research and development project of the Microwave Ground Wireless Power Transmission under a support of Ministry of Economy, Trade and Industry. This project includes the study for highly-efficient and thin structured phased array antenna, and the study for highlyefficient rectenna element. Also this project plans to demonstrate ground wireless power transmission as a previous stage to the next space proof of SSPS. In this paper, outline and progress of this project are introduced.

SEMI-SUPERVISED INFORMATION EXTRACTION FROM VARIABLE-LENGTHWEB-PAGE LISTS

Topics: Coupling and Integrating Heterogeneous Data Sources; Legacy Systems; Web Databases

Authors: Daniel Nikovski 1 , Alan Esenther 1 and Akihiro Baba 2

Affiliations: 1 Mitsubishi Electric Research Laboratories, United States , 2 Mitsubishi Electric Corporation, Japan

Digital Object Identifier: 10.5220/0001858402610266

Proceedings of ICEIS 2009, ISBN: 978-989-8111-84-5

Collapse Button Quick Abstract
We propose two methods for constructing automated programs for extraction of information from a class of web pages that are very common and of high practical significance — variable-length lists of records with identical structure. Whereas most existing methods would require multiple example instances of the target web page in order to be able to construct extraction rules, our algorithms require only a single example instance. The first method analyzes the document object model (DOM) tree of the web page to identify repeatable structure that includes all of the specified data fields of interest. The second method provides an interactive way of discovering the list node of the DOMtree by visualizing the correspondence between portions of XPath expressions and visual elements in the web page. Both methods construct extraction rules in the form of XPath expressions, facilitating ease of deployment and integration with other information systems.
Collapse Button Related Ontology Subjects/Areas/Topics (5)
Coupling and Integrating Heterogeneous Data Sources

Enterprise Information Systems

Web Databases
Databases and Information Systems Integration

Legacy Systems

TERM KNOWLEDGE ACQUISITION USING THE STRUCTURE OF HEADLINE SENTENCESFROM INFORMATION EQUIPMENTS OPERATING MANUALS

Topics: Knowledge Acquisition; Natural Language Processing

Authors: Makoto Imamura 1 , Yasuhiro Takayama 1 , Masanori Akiyoshi 2 and Norihisa Komoda 2

Affiliations: 1 Information Technology R&D Center, Mitsubishi Electric Corporation, Japan , 2 Graduate School of Information Science and Technology, Osaka University, Japan

Digital Object Identifier: 10.5220/0001875803010308

Proceedings of ICSOFT 2008, ISBN: 978-989-8111-51-7

Collapse Button Quick Abstract
This paper proposes a method for automatically extracting term knowledge such as case relations and IS-A relations between words in the headline sentences of operating manuals for information equipments. The proposed method acquires term knowledge by the following iterative processing: the case relation extraction using correspondence relations between surface cases and deep cases; the case and IS-A relation extraction using compound word structures; the IS-A relation extraction using correspondence between the case structures in the hierarchical headline sentences. The distinctive feature of our method is to extract new case relations and IS-A relations by comparison and matching the case relations extracting from the super and sub headline sentences using the headline hierarchy. We have confirmed that the proposed method has achieved 92.4% recall and 96.8% precision for extracting case relations, and 93.9% recall and 89.9% precision for extracting IS-A relations from an operating manual of a car navigation system.
Collapse Button Related Ontology Subjects/Areas/Topics (8)
Applications

Knowledge Engineering and Ontology Development

Pattern Recognition

Artificial Intelligence

Knowledge-Based Systems

Symbolic Systems
Knowledge Acquisition

Natural Language Processing

A DOCUMENT RULES DESCRIPTION LANGUAGE BASED ON FEATURE LOGIC FOR XML DOCUMENT EXCHANGE

Topic: XML and Domain Mark-up Languages

Authors: Makoto Imamura 1 , Yasuhiro Takayama 1 , Yasuhiro Okada 1 and Norihisa Komoda 2

Affiliations: 1 Mitsubishi Electric Corporation, Japan , 2 Osaka University, Japan

Digital Object Identifier: 10.5220/0002111800710077

Proceedings of ICE-B 2007/ICETE, ISBN: 978-989-8111-11-1

Collapse Button Quick Abstract
We propose a minimum Document Rules Description Language DRDL for XML validation and translation in web-based document exchange. DRDL has small syntax and simple semantics so that it can ease to reuse document rules. Furthermore, DRDL can describe mapping constraints from XML tree structure to table structure for web input-form generation. The technical feature of DRDL is to extend and reinterpret a Feature Logic, which has been used for representing linguistic knowledge, in order to allow existential and universal quantifiers over list-value to cope with XML. DRDL has already been applied to real systems such as elevator design support, Web-EDI, government-to-business and facility management.
Collapse Button Related Ontology Subjects/Areas/Topics (4)
Communication and Software Technologies and Architectures

Enterprise Information Systems

XML and Domain Mark-up Languages
e-Business

Topic(s):

Filter listed results, by

Publication date

From:
To:
Author
Locate Author in list below
Data pager
Data pager
123
 Page 1 of 3, items 1 to 10 of 27.
Add Author(s) to filter:
Conference

- Science and Technology Publications, Lda.
RESOURCES

Proceedings

Papers

Authors

Ontology

CONTACTS

Science and Technology Publications, Lda
Avenida de S. Francisco Xavier, Lote 7 Cv. C,
2900-616 Setúbal, Portugal.

Phone: +351 265 520 185 (National fixed network call)
Fax: +351 265 520 186
Email: info@scitepress.org

EXTERNAL LINKS

PRIMORIS

INSTICC

SCITEVENTS

CROSSREF

PROCEEDINGS SUBMITTED FOR INDEXATION BY:

dblp

Ei Compendex

SCOPUS

Semantic Scholar

Google Scholar

Microsoft Academic