Showing papers in "Expert Systems With Applications in 2002"
TL;DR: A personalized recommendation methodology is suggested by which to get further effectiveness and quality of recommendations when applied to an Internet shopping mall, based on a variety of data mining techniques.
Abstract: A personalized product recommendation is an enabling mechanism to overcome information overload occurred when shopping in an Internet marketplace. Collaborative filtering has been known to be one of the most successful recommendation methods, but its application to e-commerce has exposed well-known limitations such as sparsity and scalability, which would lead to poor recommendations. This paper suggests a personalized recommendation methodology by which we are able to get further effectiveness and quality of recommendations when applied to an Internet shopping mall. The suggested methodology is based on a variety of data mining techniques such as web usage mining, decision tree induction, association rule mining and the product taxonomy. For the evaluation of the methodology, we implement a recommender system using intelligent agent and data warehousing technologies.
470 citations
TL;DR: The model depicts how companies should align the strategies with four knowledge creation modes such as socialization, externalization, combination, and internalization and found that human strategy is more likely to be effective for socialization while system strategy isMore likely toBe effective for combination.
Abstract: Knowledge has become to be considered as valuable strategic assets that can provide proprietary competitive advantages. It is more important for companies to distinguish themselves through knowledge management strategies. Without a constant creation of knowledge, a business is condemned to poor performance. However, it is still unclear how these strategies affect knowledge creation. Knowledge management strategies can be categorized as being either human or system oriented. This paper proposes a model to illustrate the link between the strategies and its creating process. The model is derived on the basis of samples from 58 Korean firms. The model depicts how companies should align the strategies with four knowledge creation modes such as socialization, externalization, combination, and internalization. It is found that human strategy is more likely to be effective for socialization while system strategy is more likely to be effective for combination. Furthermore, the survey result suggests that managers should adjust knowledge management strategies in view of the characteristics of their departments.
456 citations
TL;DR: The empirical evaluation results suggest that the proposed call-behavior-based churn-prediction technique exhibits satisfactory predictive effectiveness when more recent call details are employed for the churn prediction model construction.
Abstract: As deregulation, new technologies, and new competitors open up the mobile telecommunications industry, churn prediction and management has become of great concern to mobile service providers. A mobile service provider wishing to retain its subscribers needs to be able to predict which of them may be at-risk of changing services and will make those subscribers the focus of customer retention efforts. In response to the limitations of existing churn-prediction systems and the unavailability of customer demographics in the mobile telecommunications provider investigated, we propose, design, and experimentally evaluate a churn-prediction technique that predicts churning from subscriber contractual information and call pattern changes extracted from call details. This proposed technique is capable of identifying potential churners at the contract level for a specific prediction time-period. In addition, the proposed technique incorporates the multi-classifier class-combiner approach to address the challenge of a highly skewed class distribution between churners and non-churners. The empirical evaluation results suggest that the proposed call-behavior-based churn-prediction technique exhibits satisfactory predictive effectiveness when more recent call details are employed for the churn prediction model construction. Furthermore, the proposed technique is able to demonstrate satisfactory or reasonable predictive power within the one-month interval between model construction and churn prediction. Using a previous demographics-based churn-prediction system as a reference, the lift factors attained by our proposed technique appear largely satisfactory.
418 citations
TL;DR: The preliminary results show that rule extraction approach using GAs for bankruptcy prediction modeling is promising and is capable of extracting rules that are easy to understand for users like expert systems.
Abstract: Prediction of corporate failure using past financial data is a well-documented topic. Early studies of bankruptcy prediction used statistical techniques such as multiple discriminant analysis, logit and probit. Recently, however, numerous studies have demonstrated that artificial intelligence such as neural networks (NNs) can be an alternative methodology for classification problems to which traditional statistical methods have long been applied. Although numerous theoretical and experimental studies reported the usefulness of NNs in classification studies, there exists a major drawback in building and using the model. That is, the user cannot readily comprehend the final rules that the NN models acquire. We propose a genetic algorithms (GAs) approach in this study and illustrate how GAs can be applied to bankruptcy prediction modeling. An advantage of present approach using GAs is that it is capable of extracting rules that are easy to understand for users like expert systems. The preliminary results show that rule extraction approach using GAs for bankruptcy prediction modeling is promising.
381 citations
TL;DR: The objective of the proposed study is to explore the performance of credit scoring by integrating the backpropagation neural networks with traditional discriminant analysis approach, and the proposed hybrid approach converges much faster than the conventional neural networks model.
Abstract: Credit scoring has become a very important task as the credit industry has been experiencing double-digit growth rate during the past few decades. The artificial neural network is becoming a very popular alternative in credit scoring models due to its associated memory characteristic and generalization capability. However, the decision of network's topology, importance of potential input variables and the long training process has often long been criticized and hence limited its application in handling credit scoring problems. The objective of the proposed study is to explore the performance of credit scoring by integrating the backpropagation neural networks with traditional discriminant analysis approach. To demonstrate the inclusion of the credit scoring result from discriminant analysis would simplify the network structure and improve the credit scoring accuracy of the designed neural network model, credit scoring tasks are performed on one bank credit card data set. As the results reveal, the proposed hybrid approach converges much faster than the conventional neural networks model. Moreover, the credit scoring accuracies increase in terms of the proposed methodology and outperform traditional discriminant analysis and logistic regression approaches.
365 citations
TL;DR: An analogical reasoning structure for feature weighting using a new framework called the analytic hierarchy process (AHP)-weighted k-NN algorithm is proposed and the paper introduces AHP methodology for assigning relative importance in case indexing and retrieving.
Abstract: Case-based reasoning (CBR) is a methodology for problem solving and decision-making in complex and changing business environments. Many CBR algorithms are derivatives of the k-nearest neighbor (k-NN) method, which has a similarity function to generate classification from stored cases. Several studies have shown that k-NN performance is highly sensitive to the definition of its similarity function. Many k-NN methods have been proposed to reduce this sensitivity by using various distance functions with feature weights.
This paper proposes an analogical reasoning structure for feature weighting using a new framework called the analytic hierarchy process (AHP)-weighted k-NN algorithm. The paper also introduces AHP methodology for assigning relative importance in case indexing and retrieving. The AHP model is a methodology effective in obtaining domain knowledge from numerous experts and representing knowledge-guided indexing. The proposed AHP weighted k-NN algorithm has been shown to achieve classification accuracy higher than the pure k-NN algorithm. This approach is applied to bankruptcy prediction involves the examination of several criteria, both quantitative (financial ratios) and qualitative (non-financial variables).
284 citations
TL;DR: A data mart is constructed to reduce the size of stock data and fuzzification techniques with the grey theory is combined to develop a fuzzy grey prediction as one of predicting functions in the system to predict the possible answer immediately.
Abstract: The purpose of this paper is to predict the stock price instantly at any given time. One problem with predicting stock prices is that there may be a large or small difference in two continuous sets of data. The other problem is that the volume of stock data is so large that it affects our ability to use it. To solve these problems, we constructed a data mart to reduce the size of stock data and combined fuzzification techniques with the grey theory to develop a fuzzy grey prediction as one of predicting functions in our system to predict the possible answer immediately. To demonstrate that our system is working correctly, we used our prediction system to analyse stock data and to predict the stock price promptly at a specific time. The system can effectively help stock dealers deal with day trading.
255 citations
TL;DR: The proposed model provides a new way to model and manage teamwork processes and a reference model for coordinating the knowledge flow process with the workflow process is suggested to provide an integrated approach to model teamwork process.
Abstract: To realize effective knowledge sharing in teamwork, this paper proposes a knowledge flow model for peer-to-peer knowledge sharing and management in cooperative teams. The model consists of the concepts, rules and methods about the knowledge flow, the knowledge flow process model, and the knowledge flow engine. A reference model for coordinating the knowledge flow process with the workflow process is suggested to provide an integrated approach to model teamwork process. We also discuss the peer-to-peer knowledge-sharing paradigm in large-scale teams and propose the approach for constructing a knowledge flow network from the corresponding workflow. The proposed model provides a new way to model and manage teamwork processes.
200 citations
TL;DR: The development of ISMT and how the CBR and NN techniques are used in benchmarking suppliers during the process of new product development in Honeywell Consumer Products (Hong Kong) Limited are presented.
Abstract: A global corporation's supply chain usually consists of enterprises and manufacturers that are graphically dispersed around the world, whereby each company is involved in a wide variety of supply chain activities such as order fulfillment, international procurement, acquisition of information technology, manufacturing, and customer service. However, selecting suppliers based on accumulated experience is not both effective and scientific due to subjective judgment and lack of systematic analysis. Therefore, continuously tracking and benchmarking performance of suppliers and forming an appropriate supplier selection mechanism is one of the crucial activities in supply chain management. This paper presents an intelligent supplier management tool (ISMT) using the case-based reasoning (CBR) and neural network (NN) techniques to select and benchmark suppliers. The development of ISMT and how the CBR and NN techniques are used in benchmarking suppliers during the process of new product development in Honeywell Consumer Products (Hong Kong) Limited are presented.
164 citations
TL;DR: The model organizes knowledge in a three-dimensional knowledge space, and provides a knowledge grid operation language, KGOL, which enables people to conveniently share knowledge with each other when they work on the Internet.
Abstract: This paper proposes a knowledge grid model for sharing and managing globally distributed knowledge resources. The model organizes knowledge in a three-dimensional knowledge space, and provides a knowledge grid operation language, KGOL. Internet users can use the KGOL to create their knowledge grids, to put knowledge to them, to edit knowledge, to partially or wholly open their grids to all or some particular grids, and to get the required knowledge from the open knowledge of all the knowledge grids. The model enables people to conveniently share knowledge with each other when they work on the Internet. A software platform based on the proposed model has been implemented and used for knowledge sharing in research teams.
154 citations
TL;DR: This paper proposes a new web-mining inference amplification (WEMIA) mechanism using the inference logic of FCM, and suggests results proving the robustness of the proposed WEMIA mechanism.
Abstract: This paper is concerned with proposing the fuzzy cognitive map (FCM)-driven inference amplification mechanism in the field of web-mining. As the recent advent of the Internet, most of the modern firms are now geared towards using the web technology in their daily as well as strategic activities. The web-mining technology provides them with unprecedented ability to analyze web-log data, which are seemingly full of useful information, but often lack of important and meaningful information. This indicates the need to develop an advanced inference mechanism extracting richer implication from the web-mining results. In this sense, we propose a new web-mining inference amplification (WEMIA) mechanism using the inference logic of FCM. The association rule mining is what we adopt as the web-mining technique to prove the validity of the proposed WEMIA. The main recipe of the proposed WEMIA is the three-phased inference amplification. The first phase is to apply the association rule mining, and the second phase is to transform the association rules into FCM-driven causal knowledge bases. The third phase is dedicated to amplifying the inference by developing the causal knowledge-based inference equivalence property, which was derived from analyzing the inference mechanism of FCMs. With an illustrative web-log database, we suggest results proving the robustness of our proposed WEMIA mechanism.
TL;DR: A recognizer for two variations of the ‘bull flag’ technical charting heuristic is implemented and this recognizer is used to discover trading rules on the NYSE Composite Index.
Abstract: In this case study in knowledge engineering and data mining, we implement a recognizer for two variations of the ‘bull flag’ technical charting heuristic and use this recognizer to discover trading rules on the NYSE Composite Index. Out-of-sample results indicate that these rules are effective.
TL;DR: A genetic algorithm (GA)-based approach to enhance the case-matching process used to predict customer purchasing behavior is developed and tested with real cases provided by one worldwide insurance direct marketing company, Taiwan branch.
Abstract: Case-based reasoning (CBR) shows significant promise for improving the effectiveness of complex and unstructured decision making CBR is both a paradigm for computer-based problem-solvers and a model of human cognition However the design of appropriate case retrieval mechanisms is still challenging This paper presents a genetic algorithm (GA)-based approach to enhance the case-matching process A prototype GA–CBR system used to predict customer purchasing behavior is developed and tested with real cases provided by one worldwide insurance direct marketing company, Taiwan branch The results demonstrate better prediction accuracy over the results from the regression-based CBR system Also an optimization mechanism is integrated into the classification system to reveal those customers most likely and most unlikely customers to purchase insurance
TL;DR: Two kinds of recommender systems are presented, able to retrieve optimal products based on the customer's current preferences obtained from the iterative system–customer interactions, developed for supporting Internet commerce.
Abstract: The prosperity of electronic commerce has changed the traditional trading behaviors and more and more people are willing to conduct Internet shopping. However, the exponentially increasing information provided by the Internet enterprises causes the problem of overloaded information, and this inevitably reduces the customer's satisfaction and loyalty. One way to overcome such a problem is to build personalized recommender systems to retrieve product information that really interests the customers. For products that people may purchase relatively often, such as books and CDs, recommender systems can be built to reason about a customer's personal preferences from his purchasing history and then provide the most appropriate information services to meet his needs. On the other hand, for those commodities a general customer does not buy frequently, for example computers and home theater systems, more appropriate are the kinds of recommender systems able to retrieve optimal products based on the customer's current preferences obtained from the iterative system–customer interactions. This paper presents the above two kinds of recommender systems we have developed for supporting Internet commerce. Experimental results show the promise of our systems.
TL;DR: Experimental results are encouraging and show the usefulness of the proposed stock trading model based on chaotic analysis and piecewise nonlinear model with respect to profitability.
Abstract: Trading in stock market indices has gained unprecedented popularity in major financial markets around the world. However, the prediction of stock price index is a very difficult problem because of the complexity of the stock market data. This study proposes stock trading model based on chaotic analysis and piecewise nonlinear model. The core component of the model is composed of four phases: The first phase determines time-lag size in input variables using chaotic analysis. The second phase detects successive change-points in the stock market data and the third phase forecasts the change-point group with backpropagation neural networks (BPNs). The final phase forecasts the output with BPN. The experimental results are encouraging and show the usefulness of the proposed model with respect to profitability.
TL;DR: The proposed knowledge-based architecture investigates the mechanism of case base, heuristic base, and rule base that incorporates explicit knowledge, tacit knowledge, and procedural knowledge in support of managing knowledge and dealing with inertia.
Abstract: Knowledge is becoming much more important for individuals and organizations than before. Knowledge management (KM) has been proposed as a methodology that can manage knowledge in organizations. However, KM may also have a nature, knowledge inertia (KI), stemming from the use of routine problem solving procedures, stagnant knowledge sources, and following past experience or knowledge. It may enable or inhibit an organization's or an individual's ability on problem solving. In order to explore to what extent, this research investigates several issues. First, types of knowledge have been specified. Second, knowledge from problem solving has been classified and understood. Third, inertia from knowledge is illustrated with some cases. Fourth, circulation of knowledge types in terms of avoiding KI is described. Finally, a case study of a military training institute implementing training revolution and overcoming KI is demonstrated. The proposed knowledge-based architecture investigates the mechanism of case base, heuristic base, and rule base that incorporates explicit knowledge, tacit knowledge, and procedural knowledge in support of managing knowledge and dealing with inertia.
TL;DR: The need for a web-based expert system, the fish diagnosis process and the difficulties involved in developing the system are explained, the system structure and its components, such as database, knowledge base and image base and their functions are described.
Abstract: Fish disease diagnosis is a complicated process and requires high level of expertise. Any attempt of developing a web-based system dealing with disease diagnosis has to overcome various difficulties. This paper describes a Chinese National Funded Research Project (863 project) aiming to develop a web-based intelligent diagnosis system for fish diseases. The paper explains the need for a web-based expert system, the fish diagnosis process and the difficulties involved in developing the system. The system structure and its components, such as database, knowledge base and image base and their functions are described. The system has over 300 rules and 400 images and graphics for different types of diseases and symptoms. It can diagnose 126 types of diseases amongst nine species of primary freshwater fishes. The system has been tested and is now in pilot use by fish farmers in the North China region. Some issues on developing web-based expert systems from the experience gained from the research are discussed.
TL;DR: By using ISRMS in Honeywell Consumer Product (Hong Kong) Limited, it is found that the outsource cycle time from the searching of potential suppliers to the allocation of order is greatly reduced.
Abstract: The integration of customer relationship management (CRM) and supplier relationship management (SRM) to facilitate supply chain management in the areas of supplier selection using a help desk approach has become a promising solution for manufacturers to identify appropriate suppliers and trading partners to form a supply network on which they depend for products, services, and distribution. In this paper, an intelligent customer–supplier relationship management system (ISRMS) using the case based reasoning (CBR) technique to select potential suppliers is discussed. By using ISRMS in Honeywell Consumer Product (Hong Kong) Limited, it is found that the outsource cycle time from the searching of potential suppliers to the allocation of order is greatly reduced.
TL;DR: An expert diagnosis system is presented for interpretation of the Doppler signals of the heart valve diseases based on the pattern recognition and the test results showed that this system was effective to detect Dopplers heart sounds.
Abstract: We want to thank, the Cardiology Department of the Firat Medicine Center, Elazig, Turkey for providing the DHS signals to us. This work was supported by Firat University Research Fund. (Project No: 527).
TL;DR: This paper deals with the problem of producing a set of certain and possible rules from incomplete data sets based on rough sets and proposes a new learning algorithm, which can simultaneously derive rules from complete data sets and estimate the missing values in the learning process.
Abstract: Machine learning can extract desired knowledge from existing training examples and ease the development bottleneck in building expert systems. Most learning approaches derive rules from complete data sets. If some attribute values are unknown in a data set, it is called incomplete. Learning from incomplete data sets is usually more difficult than learning from complete data sets. In the past, the rough-set theory was widely used in dealing with data classification problems. In this paper, we deal with the problem of producing a set of certain and possible rules from incomplete data sets based on rough sets. A new learning algorithm is proposed, which can simultaneously derive rules from incomplete data sets and estimate the missing values in the learning process. Unknown values are first assumed to be any possible values and are gradually refined according to the incomplete lower and upper approximations derived from the given training examples. The examples and the approximations then interact on each other to derive certain and possible rules and to estimate appropriate unknown values. The rules derived can then serve as knowledge concerning the incomplete data set.
TL;DR: An automatic pipe-routing algorithm accommodating all major detail-design facets is presented, using pattern-match methods to provide candidate paths and a cell-generation method which satisfies geometric constraints.
Abstract: This study presents an automatic pipe-routing algorithm accommodating all major detail-design facets. First, the algorithm uses pattern-match methods to provide candidate paths. A cell-generation method is developed which satisfies geometric constraints. This makes the generation and evaluation of paths effective and efficient. Next, various non-geometric aspects, such as material costs, installation costs, and valve operability, are assessed from a fiscal point of view. Then, from a tree of combinations, the algorithm chooses an appropriate path for each pipeline from the candidate paths. Finally, a general approach toward detail design automation is suggested. The software implementation was done with Microsoft Visual Basic 6.0 and Access 2000, Heide Corporation Intent! for AutoCAD 2000, and AutoDesk AutoCAD 2000.
TL;DR: The Knowledge-Based News Miner is developed, which is designed to represent the knowledge of interest rate experts with cognitive maps, to search and retrieve news information on the Internet according to prior knowledge, and to apply the information, retrieved from news information, to a neural network model for the prediction of interest rates.
Abstract: In this paper, we investigate ways to apply news information on the Internet to the prediction of interest rates. We developed the Knowledge-Based News Miner (KBNMiner), which is designed to represent the knowledge of interest rate experts with cognitive maps (CMs), to search and retrieve news information on the Internet according to prior knowledge, and to apply the information, which is retrieved from news information, to a neural network model for the prediction of interest rates.
This paper focuses on improving the performance of data mining by using prior knowledge. Real-world interest rate prediction data is used to illustrate the performance of the KBNMiner. Our integrated approach, which utilizes CMs and neural networks, has been shown to be effective in experiments. While the 10-fold cross validation is used to test our research model, the experimental results of the paired t-test have been found to be statistically significant.
TL;DR: A prototype knowledge management system on flow and water quality is addressed to simulate human expertise during the problem solving by incorporating artificial intelligence and coupling various descriptive knowledge, procedural knowledge and reasoning knowledge involved in the coastal hydraulic and transport processes.
Abstract: Due to the complexity of the numerical simulation of flow and/or water quality, there is an increasing demand for integration of recent knowledge management, artificial intelligence technology with the conventional hydraulic algorithmic models in order to assist novice application users in selection and manipulation of various mathematical tools. In this paper, a prototype knowledge management system on flow and water quality is addressed to simulate human expertise during the problem solving by incorporating artificial intelligence and coupling various descriptive knowledge, procedural knowledge and reasoning knowledge involved in the coastal hydraulic and transport processes. The system is developed through employing Visual Rule Studio, a hybrid expert system shell, as an ActiveX Designer under Microsoft Visual Basic 6.0 environment since it combines the advantages of both production rules and object-oriented programming technology. The architecture, the development and the implementation of the prototype system are delineated in details. Based on the succinct features and conditions of a variety of flow and water quality models, three kinds of class definitions, Section and Problem as well as Question are defined and the corresponding knowledge rule sets are also established. Both forward chaining and backward chaining are used collectively during the inference process. A typical example is also presented to demonstrate the application of the prototype knowledge management system.
TL;DR: A hybrid knowledge and model system, which integrates mathematical models with knowledge rules, is presented, designed to support the whole decision process of R&D project selection and has been used in the selection of R &D projects in the National Natural Science Foundation of China.
Abstract: Decision models and knowledge rules are widely used to assist in decision-making. They are common decision support devices that should be effectively managed in decision support systems. Research and development (R&D) project selection is a complicated and knowledge intensive decision-making process where decision models and knowledge rules play an important role. This paper presents a hybrid knowledge and model system, which integrates mathematical models with knowledge rules, for R&D project selection. The system is designed to support the whole decision process of R&D project selection and has been used in the selection of R&D projects in the National Natural Science Foundation of China (NSFC).
TL;DR: Roles of ontology-related actors with respect to goals, knowledge, competencies, rights, and obligations allow to form ontology societies where specific mechanisms and processes can be installed to stabilize a steady state in the three dimensions discussed.
Abstract: Ontologies are an emerging paradigm to support declarativity, interoperability, and intelligent services in many areas, such as Agent-based Computation, Distributed Information Systems, and Expert Systems. Inspired by the definition of ‘ontology’, we discuss three dimensions of information that have fundamental impact on the usefulness of ontologies for information management: formality, stability, and sharing scope of information. We briefly sketch some techniques, which are suited to find a balance (in terms of cost-benefit ratio) in each of these dimensions when building and using ontology-based information systems. We characterize roles of ontology-related actors with respect to goals, knowledge, competencies, rights, and obligations. These roles allow to form ontology societies where specific mechanisms and processes can be installed to stabilize a steady state in the three dimensions discussed. The practical use of our approach is shown in the scenario of a distributed Organizational Memory architecture.
TL;DR: A fuzzy expert system capable to diagnose the state of a pilot-scale wastewater treatment plant, its trend and also to be able to decide the best commands to be sent to the final control elements to recover the stable operation in case of disturbances is developed.
Abstract: This paper is focused on the development of a fuzzy expert system capable to diagnose the state of a pilot-scale wastewater treatment plant, its trend and also to be able to decide the best commands to be sent to the final control elements to recover the stable operation in case of disturbances. The development of the fuzzy expert system was carried out by selecting the on-line variables to be used, building the fuzzy membership functions for each input and output variable and developing a knowledge based rules structure. Finally, the fuzzy expert system was carefully tested and adjusted by performing some experiments.
TL;DR: In this article, a declarative meta-programming approach is adopted to explicitly codify patterns in object-oriented programs, and the patterns become an active part of the software development and maintenance environment.
Abstract: In current-day software development, programmers often use programming patterns to clarify their intents and to increase the understandability of their programs. Unfortunately, most software development environments do not adequately support the declaration and use of such patterns. To explicitly codify these patterns, we adopt a declarative meta programming approach. In this approach, we reify the structure of a (object-oriented) program in terms of logic clauses. We declare programming patterns as logic rules on top of these clauses. By querying the logic system, these rules allow us to check, enforce and search for occurrences of certain patterns in the software. As such, the programming patterns become an active part of the software development and maintenance environment. (C) 2002 Elsevier Science Ltd. All rights reserved.
TL;DR: The results of this study indicated that genetic algorithms can save significant time spent on teacher assignments and are more acceptable by the teachers.
Abstract: The arrangement of courses at universities is an optimal problem to be discussed under multiple constraints. It can be divided into two parts: teacher assignments and class scheduling. This paper focused primarily on teacher assignments. Consideration was given to teacher's professional knowledge, teacher preferences, fairness of teaching overtime, school resources, and the uniqueness of the school's management. Traditional linear programming methods do not obtain satisfactory results with this complex problem. In this paper, genetic algorithm methods were used to deal with the issue of multiple constraints. As a global optimal searching method, the results of this study indicated that genetic algorithms can save significant time spent on teacher assignments and are more acceptable by the teachers.
TL;DR: The development of a prototype KBS that has the ability to assist engineers in the preliminary design of liquid retaining structures and can provide expert advice to the user in selection of design criteria, design parameters and optimum configuration based on minimum cost is presented.
Abstract: Design of liquid retaining structures involves many decisions to be made by the designer based on rules of thumb, heuristics, judgment, code of practice and previous experience. Various design parameters to be chosen include configuration, material, loading, etc. A novice engineer may face many difficulties in the design process. Recent developments in artificial intelligence and emerging field of knowledge-based system (KBS) have made widespread applications in different fields. However, no attempt has been made to apply this intelligent system to the design of liquid retaining structures. The objective of this study is, thus, to develop a KBS that has the ability to assist engineers in the preliminary design of liquid retaining structures. Moreover, it can provide expert advice to the user in selection of design criteria, design parameters and optimum configuration based on minimum cost. The development of a prototype KBS for the design of liquid retaining structures (LIQUID), using blackboard architecture with hybrid knowledge representation techniques including production rule system and object-oriented approach, is presented in this paper. An expert system shell, Visual Rule Studio, is employed to facilitate the development of this prototype system. (C) 2002 Elsevier Science Ltd. All rights reserved.
TL;DR: A new learning approach based on genetic programming to generate discriminant functions for classifying data is proposed and an adaptable incremental learning strategy and a distance-based fitness function are developed to improve the efficiency of genetic programming-based learning process.
Abstract: Classification is one of the important tasks in developing expert systems. Most of the previous approaches for classification problem are based on classification rules generated by decision trees. In this paper, we propose a new learning approach based on genetic programming to generate discriminant functions for classifying data. An adaptable incremental learning strategy and a distance-based fitness function are developed to improve the efficiency of genetic programming-based learning process. We first transform attributes of objects into fuzzy attributes and then a set of discriminant functions is generated based on the proposed learning procedure. The set of derived functions with fuzzy attributes gives high accuracy of classification and presents a linear form. Hence, the functions can be transformed into inference rules easily and we can use the rules to provide the building of rule base in an expert system.