DocumentCode
2455952
Title
Novel Approach for Test Methods Automatic Selection in Product Reliability: Improved Method for Acquiring Part-Whole Relation
Author
Ohmori, Nobuyuki ; Mori, Tatsunori
Author_Institution
´´Grad. Sch. of Environ. & Inf. Sci., Yokohama Nat. Univ., Yokohama, Japan
fYear
2010
fDate
12-14 Dec. 2010
Firstpage
834
Lastpage
839
Abstract
In the product development process, test planning can be a time-consuming task, in particular, the test methods for product reliability are usually selected manually because many documents must be referred to when selecting suitable test methods. To make this process more efficient, we have been researched methods to support test planning. In this paper a new automatic selection method for test plans is proposed. The proposed method makes use of information pertaining to cases of failure. We describe a method for searching for failure cases among products having similar attributes for a product currently under consideration. The main principle of this method consists in automated acquisition of names describing the product´s constituent components for use in the search process. Experimental results show that the proposed method delivers a greater degree of acquisition performance, precision, and recall in acquiring names of components compared with a previously proposed method.
Keywords
computer bootstrapping; process planning; product development; production engineering computing; production testing; reliability; search problems; automated acquisition; bootstrapping; product constituent components; product development process; product reliability; product testing; search process; test methods automatic selection; test planning; Context; Databases; Engines; Planning; Reliability; Standards; Testing; bootstrapping; co-occurrence; pattern; product component; product evaluation; relationship acquisition; test method;
fLanguage
English
Publisher
ieee
Conference_Titel
Machine Learning and Applications (ICMLA), 2010 Ninth International Conference on
Conference_Location
Washington, DC
Print_ISBN
978-1-4244-9211-4
Type
conf
DOI
10.1109/ICMLA.2010.129
Filename
5708952
Link To Document