Using Symbol Emergence to Discover Multi-Lingual Translations in Design

2010 ◽  
Author(s):  
Amitabha Mukerjee ◽  
Madan Mohan Dabbeeru
Keyword(s):  
Performance Measures ◽  
Computational Design ◽  
Design Knowledge ◽  
Image Schemas ◽  
Design Object ◽  
Knowledge Based ◽  
Actual Design ◽  
Image Schema ◽  
Low Dimensional ◽  
Design Scenario

Incorporating design knowledge into computational design requires “symbols” — but this term as used in knowledge-based models of design is a formal term, defined only in terms of other symbols. For most humans, symbols are [term : meaning] pairs that emerge while interacting with real designs. However, both the term and its interpretation vary considerably across design groups, particularly in today’s international cooperative design scenario. For translating symbols in design, one needs to incorporate the design context, which is since the actual design object and its characteristics form the most relevant part of the context. In this work, we consider an embodied symbols approach towards translation, where models corresponding to symbol semantics are discovered based on functional norms in a given design context. The functions are available as performance measures on a given task, and lead to low-dimensional characterizations (called image schema) that reveal inter-relations in the input space that must hold for functional validity. Some of these image schemas eventually acquire language labels and become symbols. Since different designers differ in experience and in language their symbols differ somewhat. Here we consider how independent language agents may map these low-dimensional characterizations (called chunks) to units of languages based on human commentary produced in the same context. We demonstrate how this process may work for the simple domain of insertion tasks and fits, and learn both the image schemas and the language labels in two different languages, English and Telugu.

The Birth of Symbols in Design

2009 ◽  
Author(s):  
Amitabha Mukerjee ◽  
Madan Mohan Dabbeeru
Keyword(s):  
Learning System ◽  
Locally Linear Embedding ◽  
Intermediate Step ◽  
Functional Design ◽  
Image Schemas ◽  
Wide Range ◽  
Usage Patterns ◽  
Human Usage ◽  
Low Dimensional ◽  
Design Scenario

In the widespread endeavour to standardize a vocabulary for design, the semantics for the terms, especially at the detailed levels, are often defined based on the exigencies of the implementation. In human usage, each symbol has a wide range of associations, and any attempt at definition will miss many of these, resulting in brittleness. Human flexibility in symbol usage is possible because our symbols are learned from a vast experience of the world. Here we propose the very first steps towards a process by which CAD systems may acquire symbols is by learning usage patterns or image schemas grounded on experience. Subsequently, more abstract symbols may be derived based on these grounded symbols, which thereby retain the flexibility inherent in a learning system. In many design tasks, the “good designs” lie along regions that can be mapped to lower dimensional surfaces or manifolds, owing to latent interdependencies between the variables. These low-dimensional structures (sometimes called chunks) may constitute the intermediate step between the raw experience and the eventual symbol that arises after these patterns become stabilized through communication. In a multi-functional design scenario, we use a locally linear embedding (LLE) to discover these manifolds, which are compact descriptions for the space of “good designs”. We illustrate the approach with a simple 2-parameter latch-and-bolt design, and with a 8-parameter universal motor.

A Novel Application of Gamification for Collecting High-Level Design Information

2015 ◽  
Author(s):  
Hyunmin Cheong ◽  
Wei Li ◽  
Francesco Iorio
Keyword(s):  
User Study ◽  
Design Knowledge ◽  
Cad Systems ◽  
Design Information ◽  
Knowledge Based ◽  
Game Mechanics ◽  
Abstract Level ◽  
Level Problem ◽  
Level Design ◽  
High Level

This paper presents a novel application of gamification for collecting high-level design descriptions of objects. High-level design descriptions entail not only superficial characteristics of an object, but also function, behavior, and requirement information of the object. Such information is difficult to obtain with traditional data mining techniques. For acquisition of high-level design information, we investigated a multiplayer game, “Who is the Pretender?” in an offline context. Through a user study, we demonstrate that the game offers a more fun, enjoyable, and engaging experience for providing descriptions of objects than simply asking people to list them. We also show that the game elicits more high-level, problem-oriented requirement descriptions and less low-level, solution-oriented structure descriptions due to the unique game mechanics that encourage players to describe objects at an abstract level. Finally, we present how crowdsourcing can be used to generate game content that facilitates the gameplay. Our work contributes towards acquiring high-level design knowledge that is essential for developing knowledge-based CAD systems.

scholarly journals The Path to Neutralization: Image Schemas and Prefixed Motion Verbs

2007 ◽  
Vol 10 ◽  
pp. 61 ◽  
Author(s):  
Tore Nesset
Keyword(s):  
Motion Verbs ◽  
Image Schemas ◽  
Principled Explanation ◽  
Image Schema

This paper investigates the path image schema in Russian motion verbs. It is argued that this image schema provides a principled explanation why Russian has a contrast between unidirectional and non-directional unprefixed motion verbs, but no such contrast for prefixed verbs.

BDS: A Knowledge-Based Bumper Design System

1997 ◽  
Author(s):  
Beverly J. Becker ◽  
Gregory A. Kaepp
Keyword(s):  
Software Design ◽  
Product Performance ◽  
Design System ◽  
Design Knowledge ◽  
Performance Requirement ◽  
Knowledge Based ◽  
Design Engineers ◽  
Design Alternatives ◽  
Design Requirements ◽  
Knowledge Based Engineering

Abstract A knowledge-based Bumper Design System (BDS) has been developed which automatically generates optimized conceptual bumper beams which meet manufacturing and product performance requirement. The BDS has captured and refined the corporate design knowledge of the product design engineer, the CAD designer, the CAE analyst and manufacturer. The BDS enables the bumper design engineers to evaluate multiple design alternatives quickly and early in the design process. It also automates repetitive bumper analysis tasks. The purpose of the paper is to describe the BDS. A description of the Knowledge Based Engineering (KBE) methodology used to create the BDS is given, as well as an overview of bumper designs and design requirements. An overview of the BDS software design, user interface, and a sample run are also presented.

HCS: Designing a Balanced Scorecard in a Knowledge-Based Firm

2001 ◽  
Vol 16 (4) ◽  
pp. 569-601 ◽  
Author(s):  
Chris Moore ◽  
Beverly J. Rowe ◽  
Sally K. Widener
Keyword(s):  
Human Capital ◽  
Performance Measures ◽  
Measurement System ◽  
Balanced Scorecard ◽  
Systems Design ◽  
Operational Performance ◽  
Performance Measurement System ◽  
Knowledge Based ◽  
Consulting Services ◽  
Strategic Context

The purpose of this case is to enable you to design a performance measurement system using a balanced scorecard. This case is based on factual issues and decisions faced by the real-world managers and employees of Holloway Consulting Services (HCS) (names and dollar amounts have been changed). HCS is a service firm that provides its customers with managed business solutions, i.e., integrating outsourcing options with systems design and support. Currently, HCS collects several financial and operational performance measures; however, Sharon Holloway, owner of HCS, is concerned that these measures are not adequate for a firm that competes using intangible assets, especially human capital. Therefore, she plans to implement a balanced scorecard in which performance measures are linked to the firm's strategy. This case provides you with the opportunity to develop a balanced scorecard that incorporates both traditional and nontraditional performance measures within the strategic context of a knowledge-based firm.

A Knowledge-Based Approach for the Automated Design of Robotic/Human Manufacturing Workcells in Hazardous Environments

2013 ◽  
Author(s):  
Joshua M. Williams ◽  
Mitch W. Pryor
Keyword(s):  
Manufacturing Systems ◽  
National Laboratory ◽  
Computational Design ◽  
Los Alamos National Laboratory ◽  
Knowledge Based ◽  
Design Engineers ◽  
Hazardous Environments ◽  
Interdisciplinary Knowledge ◽  
High Level ◽  
System Designs

The design of manufacturing systems in hazardous environments is complex, requiring interdisciplinary knowledge to determine which components and operators (human or robotic) are feasible. When conceptualizing designs, some options may be overlooked or unknowingly infeasible due to the design engineers’ lack of knowledge in a particular field or ineffective communication of requirements between disciplines. Computational design tools can help alleviate many of the problems encountered in this design task. We create a knowledge-based system (KBS) utilizing CLIPS to automate the synthesis of conceptual manufacturing system designs in radioactive environments. The KBS takes a high-level functional description of a process and uses FBS modeling to generate multiple designs with generic components retrieved from a database and low-level manufacturing task sequences. Using this approach, many options are explored and operator task compatibility is directly addressed. The KBS is applied to the design of glovebox processing systems at Los Alamos National Laboratory (LANL).

Study on the Organization Model for the Design Process Modular of Complex Mechanical Product

2012 ◽  
Vol 538-541 ◽  
pp. 2990-2994
Author(s):  
Jun Zheng
Keyword(s):  
Product Design ◽  
Design Process ◽  
Directed Acyclic Graph ◽  
Semantic Relations ◽  
Design Knowledge ◽  
Modular Approach ◽  
Organization Model ◽  
Acyclic Graph ◽  
Knowledge Based ◽  
Special Collections

In order to provide knowledge service more efficiently for complex mechanical product design, a knowledge organization model for complex mechanical product design knowledge based on the process modular approach was proposed. First, a general form, the knowledge instance, would be used to represent all forms of the knowledge for complex mechanical product design; then, based on the contents and features of the knowledge instances and the semantic relations in the domain ontology, the special collections of the knowledge instances which have related features would be composed to knowledge modules, and knowledge modules would be organized as a DAG(directed acyclic graph). The complex mechanical product design knowledge could be efficiently and completely queried based-on semantic according to the logical relationships expressed in the DAG.

Sign in / Sign up

Export Citation Format

Share Document