The potential of machine learning techniques for expert systems

Reich, Yoram; Fenves, Steven J.

doi:10.1017/s0890060400001219

Cited by 13 publications

(3 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although one can give a precise formal definition, others can always find intuitive examples that fall outside the specified boundaries and counterexamples that fall within them. However, many definitions have been given before and some of them are reviewed in [Reich and Fenves, 1989]. Among the previous definitions, the author believes that the definition .given by Lanley [1996] is the broadest and the most accurate:…”

Section: Previewmentioning

confidence: 99%

Equation Discovery in Databases from Engineering

Roddis¹,

Zhang²

2000

Computing in Civil and Building Engineering (2000)

View full text Add to dashboard Cite

As the quantity of electronically generated engineering data grows rapidly, building computer systems to analyze data automatically and intelligently becomes increasingly important to engineers. The overall process of extracting useable knowledge from electronically stored data is called knowledge discovery in databases. The part of the process where patterns are extracted or models are built is referred to as data mining. This dissertation proposes a data mining method that combines machine learning and regression to help engineers in acquiring knowledge which is preferably expressed as equations. A learning algorithm based on the method has been implemented in the computer system EDDE (Equation Discovery in Databases from Engineering). In addition, to obtain useful models that are understandable to engineers, knowledge specific to the particular problem area is incorporated into EDDE to guide the discovery process. The role of this domain knowledge is investigated. The system EDDE is extensively tested on both synthetic data sets and actual engineering data sets. The tests on synthetic data show that EDDE has some important features, such as not being sensitive to the nwnber of variables in data sets. When compared to other methods (regression tree CART, instances based IBL, multivariate linear regression, model tree MS, neural nets, and combinations of these methods), EDDE generates a smaller size model with lower prediction error. EDDE thus swnmarizes the data more concisely and describes the data better. EDDE has been used to analyze actual data sets from civil engmeenng

show abstract

Section: Previewmentioning

confidence: 99%

Equation Discovery in Databases from Engineering

Roddis¹,

Zhang²

2000

Computing in Civil and Building Engineering (2000)

View full text Add to dashboard Cite

show abstract

“…This is in contrast to the potential that many other ML techniques offer. 76 Thus the use of ML in civil engineering is only at its infancy. Second, many previous studies contained little or no systematic testing and have had little or no follow-up work.…”

Section: State Of the Art Of Using ML In Civil Engineeringmentioning

confidence: 99%

Machine Learning Techniques for Civil Engineering Problems

Reich

1997

Computer aided Civil Eng

Self Cite

138

View full text Add to dashboard Cite

The growing volume of information databases presents opportunities for advanced data analysis techniques from machine learning (ML) research. Practical applications of ML are very different from theoretical or empirical studies, involving organizational and human aspects and various other constraints. Despite the importance of applied ML, little has been discussed in the general ML literature on this topic. In order to remedy this situation, I studied practical applications of ML and developed a proposal for a seven-step process that can guide practical applications of ML in engineering. The process is illustrated by relevant applications of ML in civil engineering. This illustration shows that the potential of ML has only begun to be explored but also cautions that in order to be successful, the application process must carefully address the issues related to the seven-step process.

show abstract

“…While initial attempts at producing intelligent design systems @e.g., that of McDermott 1982!# were promising, it was quickly recognized that a major difficulty in constructing such systems lay in the acquisition and expression of the synthesis knowledge. Conventional knowledge-acquisition techniques, by which "knowledge engineers" aim to capture knowledge directly from human experts, have been found lacking when attempting to acquire experience-based heuristic knowledgẽ Berry, 1987;Hart, 1988;Gillies, 1996!. As a result, a number of authors~e.g., Michie, 1982;Lenat, 1983;Reich & Fenves, 1989! have suggested that at least some of this knowledge might be acquired automatically through the use of Machine Learning~ML!.…”

Section: Introductionmentioning

confidence: 99%

Design synthesis knowledge and inductive machine learning

Potter

Darlington

Culley

et al. 2001

AIEDAM

View full text Add to dashboard Cite

A crucial early stage in the engineering design process is the conceptual design phase, during which an initial solution design is generated. The quality of this initial design has a great bearing on the quality and success of the produced artefact. Typically, the knowledge required to perform this task is only acquired through many years of experience, and so is often at a premium. This has led to a number of attempts to automate this phase using intelligent computer systems. However, the knowledge of how to generate designs has proved difficult to acquire directly from human experts, and as a result, is often unsatisfactory in these systems. The application of inductive machine learning techniques to the acquisition of this sort of knowledge has been advocated as one approach to overcoming the difficulties surrounding its capture. Rather than acquiring the knowledge from human experts, the knowledge would be inferred automatically from a set of examples of the design process. This paper describes the authors' investigations into the general viability of this approach in the context of one particular conceptual design task, that of the design of fluid power circuits. The analysis of a series of experiments highlights a number of issues that would seem to arise regardless of the working domain or particular machine learning algorithm used. These issues, presented and discussed here, cast serious doubts upon the practicality of such an approach to knowledge acquisition, given the current state of the art.

show abstract

The potential of machine learning techniques for expert systems

Cited by 13 publications

References 44 publications

Equation Discovery in Databases from Engineering

Equation Discovery in Databases from Engineering

Machine Learning Techniques for Civil Engineering Problems

Design synthesis knowledge and inductive machine learning

Contact Info

Product

Resources

About