Reduction Methods for Design Rationale Knowledge Model

Author(s):  
Jiaji Wang ◽  
Jihong Liu
Author(s):  
Rob H. Bracewell ◽  
Saeema Ahmed ◽  
Ken M. Wallace

This paper describes a software tool called DRed (the Design Rationale editor), that allows engineering designers to record their design rationale (DR) at the time of its generation and deliberation. DRed is one of many proposed derivatives of the venerable IBIS concept, but by contrast with other tools of this type, practicing designers appear surprisingly willing to use it. DRed allows the issues addressed, options considered, and associated arguments for and against, to be captured graphically. The software, despite still being essentially a research prototype, is already in use on high profile design projects in an international aerospace company, including the presentation of results of design work to external customers. The paper compares DRed with other IBIS-derived software tools, to explain how it addresses problems that seem to have made them unsuitable for routine use by designers. In addition to the capture and presentation of the DR itself, the set of linked DR graphs can be used to provide a map of the contents of an electronic Design Folder, containing all the documents created by an individual or team during a design project. The structure of the knowledge model instantiated in such a Design Folder is described. By reprising a design case study published at the DTM 2003 conference, concerning the design of a Mobile Arm Support (MAS), the DRed knowledge model is compared with the previously proposed Design Data Model (DDM), to show how it addresses the shortcomings identified in the DDM. Finally the methodology and results of the preliminary evaluation of the use of DRed by aerospace designers are presented.


2013 ◽  
Vol 38 (4) ◽  
pp. 465-470 ◽  
Author(s):  
Jingjie Yan ◽  
Xiaolan Wang ◽  
Weiyi Gu ◽  
LiLi Ma

Abstract Speech emotion recognition is deemed to be a meaningful and intractable issue among a number of do- mains comprising sentiment analysis, computer science, pedagogy, and so on. In this study, we investigate speech emotion recognition based on sparse partial least squares regression (SPLSR) approach in depth. We make use of the sparse partial least squares regression method to implement the feature selection and dimensionality reduction on the whole acquired speech emotion features. By the means of exploiting the SPLSR method, the component parts of those redundant and meaningless speech emotion features are lessened to zero while those serviceable and informative speech emotion features are maintained and selected to the following classification step. A number of tests on Berlin database reveal that the recogni- tion rate of the SPLSR method can reach up to 79.23% and is superior to other compared dimensionality reduction methods.


Sign in / Sign up

Export Citation Format

Share Document