Towards integrating rule-based expert systems and neural networks

Quah, Tong-Seng; Tan, Chik How; Raman, K. S.; Srinivasan, Bobby

doi:10.1016/0167-9236(95)00016-x

Cited by 26 publications

(13 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Neural networks with their self-organisation features, are very well suited to accommodate the self-learning component of the SDSS and its potential for parallelism (Quah et al, 1996). The ability to adapt to changing circumstances and environmental factors which is unique to neural networks, together with their potential to deal with the fuzziness and bias aspects of human decision making can greatly improve the 'rigid' rule-based systems and transform the SDSS into an expert network (Quah et al, 1996). Following the neural network development approach, it might be possible, given sufficient field-based data, to include a simple cost/value analysis for the possible eco-engineering options which will further facilitate decision making process.…”

Section: Future Development Of the Sdssmentioning

confidence: 99%

A Decision Support System for the Evaluation of Eco-engineering Strategies for Slope Protection

Beek

2006

Geotech Geol Eng

View full text Add to dashboard Cite

A decision support system (DSS) has been developed to assist expert and non-expert users in the evaluation and selection of eco-engineering strategies for slope protection. This DSS combines a qualitative hazard assessment of erosion and mass movements with a detailed catalogue of eco-engineering strategies for slope protection of which the suitability is evaluated in relation to the data entered. The slope decision support system (SDSS) is a knowledge based DSS in which knowledge is stored in frames containing rules that can evaluate the available information for a project, stored as project specific information (PSI) in a data file. The advantages of such a system are that it accepts incomplete information and that the qualitative nature of the information does not instil the user with a sense of unjustified exactitude. By its multidisciplinary and progressive nature, the DSS will be of value during the initial stages of an eco-engineering project when data collection and the potential of different eco-engineering strategies are considered. The accent of the output of the DSS is on the application of ecoengineering strategies for slope protection as an environmentally-friendly solution aiding sustainable development. For its acceptance within the engineering community, the DSS needs to prove its predictive capacity. Therefore, its performance has been benchmarked against successful and unsuccessful cases of slope stabilisation using eco-engineering. The target audience and the areas of application of this DSS are reviewed and the strategies for further development in this area suggested.

show abstract

Section: Future Development Of the Sdssmentioning

confidence: 99%

A Decision Support System for the Evaluation of Eco-engineering Strategies for Slope Protection

Beek

2006

Geotech Geol Eng

View full text Add to dashboard Cite

show abstract

“…These networks can be considered as an integration between rule-based expert system and neural networks [22]. However, the advantage of these networks is that they are not necessarily static as the expert systems, but they can be trained according to the problem encountered.…”

Section: Introductionmentioning

confidence: 99%

“…Neural logic networks are powerful connectionist systems that have been applied in various domains [21,22,25,28] and by their definition can be easily interpreted in a number of expert rules. These networks can be considered as an integration between rule-based expert system and neural networks [22].…”

Section: Introductionmentioning

confidence: 99%

An evolutionary system for neural logic networks using genetic programming and indirect encoding

Tsakonas

Aggelis

Karkazis

et al. 2004

Journal of Applied Logic

View full text Add to dashboard Cite

Nowadays, intelligent connectionist systems such as artificial neural networks have been proved very powerful in a wide area of applications. Consequently, the ability to interpret their structure was always a desirable feature for experts. In this field, the neural logic networks (NLN) by their definition are able to represent complex human logic and provide knowledge discovery. However, under contemporary methodologies, the training of these networks may often result in non-comprehensible or poorly designed structures. In this work, we propose an evolutionary system that uses current advances in genetic programming that overcome these drawbacks and produces neural logic networks that can be arbitrarily connected and are easily interpretable into expert rules. To accomplish this task, we guide the genetic programming process using a context-free grammar and we encode indirectly the neural logic networks into the genetic programming individuals. We test the proposed system in two problems of medical diagnosis. Our results are examined both in terms of the solution interpretability that can lead in knowledge discovery, and in terms of the achieved accuracy. We draw conclusions about the effectiveness of the system and we propose further research directions.

show abstract

“…Studies [1,3,4,5,[6][7][8][9] reveal that there are many applications for forex forecasting with BPNN, but it is hard to find a whole forecasting system based on BPNN techniques in the literature. Furthermore, most existing forecasting methods and tools do not have good interaction or flexibility, as the practitioners are required to have a thorough theory background in order to understand the methodologies and models.…”

Section: The Bpnn-based Forex Rolling Forecasting System -Bpnnfrfsmentioning

confidence: 99%

“…Decision support system (DSS) is a powerful tool which can be used to support decision makers in making strategic decisions [1]. One of their objectives is to improve management judgment by fostering understanding and insights and by allowing appropriate access to relevant information [2].…”

Section: Introductionmentioning

confidence: 99%

A Neural Network and Web-Based Decision Support System for Forex Forecasting and Trading

Lai

Wang

2004

Data Mining and Knowledge Management

View full text Add to dashboard Cite

Abstract. This study presents a neural network & web-based decision support system (DSS) for foreign exchange (forex) forecasting and trading decision, which is adaptable to the needs of financial organizations and individual investors. In this study, we integrate the back-propagation neural network (BPNN)-based forex rolling forecasting system to accurately predict the change in direction of daily exchange rates, and the Web-based forex trading decision support system to obtain forecasting data and provide some investment decision suggestions for financial practitioners. This research reveals the structure of the DSS by the description of an integrated framework, and meantime we find that the DSS is integrated, user-oriented by its implementation, and practical applications reveal that this DSS demonstrates very high forecasting accuracy and its trading recommendations are reliable.

show abstract

Towards integrating rule-based expert systems and neural networks

Cited by 26 publications

References 18 publications

A Decision Support System for the Evaluation of Eco-engineering Strategies for Slope Protection

A Decision Support System for the Evaluation of Eco-engineering Strategies for Slope Protection

An evolutionary system for neural logic networks using genetic programming and indirect encoding

A Neural Network and Web-Based Decision Support System for Forex Forecasting and Trading

Contact Info

Product

Resources

About