دانلود مقاله ترجمه شده برنامه های کاربردی و روش شناسی سیستم خبره – مجله الزویر

بخشی از ترجمه:

در این مقاله با استفاده از یک بازبینی علمی/پژوهشی و همچنین دسته بندی مقالات ارائه شده بین سال های ١٩٩۵ تا ٢٠٠۴ میلادی بر اساس شاخص واژه ی کلیدی و چکیده ی مقالات، به بازبینی توسعه های صورت گرفته شده بر روی سیستم های خبره(ES) پرداخته خواهد شد، تا به چگونگی توسعه ی متدلوژی ها و کاربرد های سیستم های خبره در این دهه پی برده شود. بر مبنای ١۶۶ مقاله و ٧٨ ژورنال آکادمیک ارائه شده تا سال ٢٠۴، این مقاله با استفاده از ١١ دسته بندی، به دسته بندی متدلوژی های سیستم های خبره خواهد پرداخت: سیستم های مبتنی بر قاعده ، سیستم های مبتنی بر دانش ، شبکه های عصبی ، سیستم های خبره ی فازی(FES)، متدلوژی شیئ گرا ، استدلال مبتنی بر مورد، معماری سیستم، سیستم های عامل هوشمند، متدلوژی پایگاه داده، مدل سازی و هستی شناسی. همه ی این دسته بندی ها به همراه کاربرد آنها و پژوهش ها و دامنه های مختلفی از مسائل ارائه خواهد شد. مباحثی ارائه شده است که شامل جهت گیری های توسعه ی زیر برای متدلوژی های سیستم خبره میباشد:
• متدلوژی های سیستم خبره، تمایل به توسعه به سمت خبره بودن داشته و کاربرد های این سیستم ها را میتوان از نوع دامنه ی مسئله گرا دانست.
• پیشنهاد شده است که متدلوژی های اجتماعی متفاوتی مانند فلسفه، علم شناختی، و رفتار انسان میتواند سیستم خبره را به عنوان نوع دیگری از متدلوژی پیاده سازی کند.
• توانایی تغییر پیوسته و حفظ یافته های جدیدی را میتوان یکی از نقاط قوت متدلوژی سیستم خبره دانست.

بخشی از مقاله انگلیسی:

Abstract This paper surveys expert systems (ES) development using a literature review and classification of articles from 1995 to 2004 with a keyword index and article abstract in order to explore how ES methodologies and applications have developed during this period. Based on the scope of 166 articles from 78 academic journals (retrieved from five online database) of ES applications, this paper surveys and classifies ES methodologies using the following eleven categories: rule-based systems, knowledge-based systems, neural networks, fuzzy ESs, objectoriented methodology, case-based reasoning, system architecture, intelligent agent systems, database methodology, modeling, and ontology together with their applications for different research and problem domains. Discussion is presented, indicating the followings future development directions for ES methodologies and applications: (1) ES methodologies are tending to develop towards expertise orientation and ES applications development is a problem-oriented domain. (2) It is suggested that different social science methodologies, such as psychology, cognitive science, and human behavior could implement ES as another kind of methodology. (3) The ability to continually change and obtain new understanding is the driving power of ES methodologies, and should be the ES application of future works. q 2004 Published by Elsevier Ltd. Keywords: Expert systems; Expert system methodologies; Expert system applications; Literature survey 1. Introduction Expert systems (ES) are a branch of applied artificial intelligence (AI), and were developed by the AI community in the mid-1960s. The basic idea behind ES is simply that expertise, which is the vast body of task-specific knowledge, is transferred from a human to a computer. This knowledge is then stored in the computer and users call upon the computer for specific advice as needed. The computer can make inferences and arrive at a specific conclusion. Then like a human consultant, it gives advices and explains, if necessary, the logic behind the advice (Turban & Aronson, 2001). ES provide powerful and flexible means for obtaining solutions to a variety of problems that often cannot be dealt with by other, more traditional and orthodox methods. Thus, their use is proliferating to many sectors of our social and technological life, where their applications are proving to be critical in the process of decision support and problem solving. As a part of ES research, this paper surveys the development of ES through a literature review and classification of articles from 1995 to 2004 as a basis, exploring the ES methodologies and applications during that period. The reason for choosing this period is that the Internet was opened to general users in 1994 and this new era of information and communication technology has played important roles, not only in the field of ES, but also in the ability to collect data from online database. This literature survey started on March 2003 and it was based on a search in the keyword index and article abstract for ‘ES’ on the Elsevier SDOS, IEEE Xplore, EBSCO (electronic journal service), Ingenta, and Wiley InterScience online database, for the period from 1995 to 2004, in which 10,439 articles were updated and found on June 2004. After topic filtering, there were 166 articles from 78 journals related to the keyword ‘ES applications’, ۹۸ of which were connected to the methodology of keyword ‘ES methodology’. Based on the scope of 166 articles on ES applications, this paper surveys and classifies ES methodologies using eleven 0957-4174/$ – see front matter q 2004 Published by Elsevier Ltd. doi:10.1016/j.eswa.2004.08.003 Expert Systems with Applications xx (2004) 1–۱۱ www.elsevier.com/locate/eswa * Tel.: C886-2947-2044; fax: C886-2945-3007. E-mail address: michael@mail.tku.edu.tw. DTD 5 ARTICLE IN PRESS categories: rule-based systems, knowledge-based systems, neural networks, fuzzy ESs, object-oriented methodology, case-based reasoning (CBR), system architecture development, intelligent agent (IA) systems, modeling, ontology, and database methodology together with their applications for different research and problem domains. The rest of the paper is organized as follows. Sections 2–۱۲ present the survey results of ES methodologies and applications based on the above categories, respectively. Section 13 presents some discussion, extending to suggestions for future development of ES methodologies and applications. Finally, Section 14 contains a brief conclusion. 2. Rule-based systems and their applications A rule-based ES is defined as one, which contains information obtained from a human expert, and represents that information in the form of rules, such as IF–THEN. The rule can then be used to perform operations on data to inference in order to reach appropriate conclusion. These inferences are essentially a computer program that provides a methodology for reasoning about information in the rule base or knowledge base, and for formulating conclusions. Applications of rule-based systems on ESs are including: state transition analysis, psychiatric treatment, production planning, advisory system, teaching, electronic power planning, automobile process planning, hypergraph representation, system development, knowledge verification/ validation, alcohol production, DNA histogram interpretation, knowledge base maintenance, scheduling strategy, management fraud assessment, knowledge acquisition, knowledge representation, communication system fault diagnosis, bioseparation, material processing design, resource utilization, biochemical nanotechnology, probabilistic fault diagnosis, agriculture planning, load scheduling, apiculture, tutoring system, geoscience, and sensor control. The methodology of rule-based systems and their applications are categorized in Table 1. 3. Knowledge-based systems and their applications The most common definition of KBS is human-centered. This highlights the fact that KBS have their roots in the field of artificial intelligence (AI) and that they are attempts to understand and initiate human knowledge in computer systems (Wiig, 1994). The four main components of KBS are usually distinguished as: a knowledge base, an inference engine, a knowledge engineering tool, and a specific user interface (Dhaliwal & Benbasat, 1996). On the other hand, the term KBS includes all the organizational information technology applications that may prove helpful to manage the knowledge assets of an organization, such as ESs, rulebased systems, groupware, and database management systems (DBMS) (Laudon & Laudon, 2002). Some of these applications which are implemented by knowledge-based systems include the following: medical treatment, personal finance planning, engineering failure analysis, waste management, production management, thermal engineering, decision support, knowledge management, knowledge representation, power electronics design, framed buildings evaluation, financial analysis, chemical incident management, automatic tumor segmentation, business game, climate forecasting, agricultural management, steel composition design, strategic management, environmental protection, wastewater treatment, decision making and learning, isokinetics interpretation, chemical process controlling, therapy planning, plant process control, outage locating planning, concurrent system design, case validation, chip design, agriculture planning, power transmission protection, crop production planning, tropospheric chemistry modeling, planar robots, and urban design. The methodology of knowledge-based systems and their applications are categorized in Table 2.Some applications implemented by fuzzy ESs are such as: power load forecasting, online scheduling, chemical Table 2 Knowledge-based systems and their applications Knowledge-based systems/ applications Authors Medical treatment Alonso-Amo, Perez, Gomez, and Montes (1995) Personal finance planning Dirks, Kingston, and Haggith (1995) Engineering failure analysis Graham-Jones and Mwllor (1995) Waste management Wei and Weber (1996) Production management Dawood (1996) Thermal engineering Afgan and Carvalho (1996) Decision support Keefe and Preece (1996) Knowledge management Dutta (1997) Knowledge representation Mitra and Basu (1997) Framed buildings evaluation Lu and Simmonds (1997) Power electronics design Fezzani, Piquet, and Foch (1997) Financial analysis Matsatsinis, Doumpos, and Zopounidis (1997) Chemical incident management Finch and Lees (1997) Automatic tumor segmentation Clark et al. (1998) Business game Duan, Edwards, and Robins (1998) Climate forecasting Rodionov and Martin (1999) Agricultural management Girard and Hubert (1999) Steel composition design Manohar, Shivathaya, and Ferry (1999) Strategic management Volberda and Rutges (1999) Environmental protection Gomolka and Orlowski (2000) Wastewater treatment Baeza, Ferreira, and Laufuente (2000) Decision making and learning Mockler, Dologite, and Gartenfeld (2000) Isokinetics interpretation Alonso, Fuertes, Martinez, and Montes (2000) Chemical process controlling Barrera-Cortes, Astruc, and Tufeu (2001) Physical therapy planning Tunez, Aguila, and Marin (2001) Plant process control Acosta, Gonzalez, and Pulido (2001) Outage locating planning Liu and Schulz (2002) Concurrent system design Mills and Gomaa (2002) Case validation Knauf, Gonzalez, and Abel (2002) Chip design Bourbakis, Mogzadeh, Mertoguno, and Koutsougeras (2002) Agricultural planning Cohen and Shoshany (2002) Power transmission protection Orduna, Garces, and Handschin (2003) Crop production planning Edrees, Rafea, Fathy, and Yahia (2003) Tropospheric chemistry modeling Saunders, Pascoe, Johnson, Pilling, and Jenkin (2003) Urban design Xirogiannis, Stefanou, and Glykas (2004) Planar robots Sen, Minambres, Garrido, Almansa, and Soto (2004) Table 3 Neural networks and their applications Neural networks/applications Authors Fault diagnosis Wang, Qu, Liu, and Cheng (2004), Yang, Han, and Kim, (2004) Optimal power flow Decision making Alarm processing system Inference mechanisms Diagnostic system Machine learning Fu (1998) Power load forecasting Facility layout design Process control Knowledge learning Gold mining process design Robotic systems Parameter setting Waste treatment Biomedical application Mitigation processes control Engineering ceramics Acoustic signal diagnosing Li, Tasi, Tasi, and Chiu (2004) Crude oil distillation Liau et al. (2004) Shu-Hsien Liao / Expert Systems with Applications xx (2004) 1–۱۱ ۳ DTD 5 ARTICLE IN PRESS process fault diagnosis, ecological planning, control systems, uncertainly reasoning, knowledge integration, fault diagnosis, power system classification, fault detection, demand evaluation, wastewater treatment, machinability data selection, water supply forecast, radiography classifi- cation, on-line analytic processing, hotel selection, dryer tool integration, pooled flood frequency analysis, medical consultation system, job matching, performance indexing, computer security, gesture recognition, and medical diagnosis. The methodology of fuzzy ESs together with their applications is categorized in Table 4. 6. Object-oriented methodology and their applications Object-oriented methodology combines into one object data together with the specific procedures that operate on this data, where the object combines data and program code. Instead of passing data to procedures, programs send a message for an object to perform a procedure that is already embedded in it. Then, the same message may be sent to many different objects, but each will implement that message differently. An object’s data are encapsulated from other parts of the system, so each object is an independent software building block that can be used in many different systems without changing the program code. Some applications implemented by object-oriented methodology include the following: industry diagnosis, knowledge learning, manufacturing information network, power system maintenance, knowledge engineering, syntactic programming, and knowledge representation. The methodology of object-oriented methodology and their applications are categorized in Table 5. 7. Case-based reasoning and their applications The basic idea of CBR is to adapt solutions that were used to solve previous problems and use them to solve new problems. In CBR, descriptions of past experience of human specialists, represented as cases, are stored in a database for later retrieval when the user encounters a new case with similar parameters. The system searches for stored cases with problem characteristics similar to the new one, finds the closest fit, and applies the solutions of the old case to the new case. Successful solutions are tagged to the new case and both are stored together with the other cases in the knowledge base. Unsuccessful solutions also are appended to the case base along with explanations as to why the solutions did not work (Kolonder, 1994). Some of the applications implemented by CBR include the following: manufacturing process design, knowledge management, power system restoration training, ultrasonic inspection, medical planning, medical application, fault diagnosis, e-learning, and knowledge modeling. These CBR and their applications are categorized in Table 6. 8. Modeling and their applications Modeling methodology becomes an interdisciplinary methodology of ES in order to build formal relationships with logical model design in different knowledge/problem Table 4 Fuzzy expert systems and their applications Fuzzy expert systems/ applications Authors Power load forecasting Kim, Park, Hwang, and Kim (1995) Online scheduling Chang and Thia (1996) Chemical process fault diagnosis Ozyurt and Kandel (1996) Ecological planning Zhu, Band, Dutton, and Nimlos (1996) Power system diagnosis Cho and Park (1997) Control systems Bugarin and Barro (1998) Uncertainly reasoning Pan, DeSouza, and Kak (1998) Knowledge integration Lee, Han, Song, and Lee (1998) Fault diagnosis Lee et al. (2000) and Soliman, Rizzoni, and Kim (1999) Power system classification Dash, Mishra, Salama, and Liew (2000) Fault detection EI-Shal and Morris (2000) Demand evaluation Benson and Asgarpoor (2000) Wastewater treatment Carrasco, Rodriguez, Punal, Roca, and Lema (2004), Punal, Rodriguez, Carrasco, Roca, and Lema (2002), and Punal et al. (2001) Machinability data selection Wong and Hamouda (2002, 2003) Water supply forecast Mahabir, Hicks, and Fayek (2003) Radiography classification Liao (2003) On-line analytic processing Leung, Lau, and Kwong (2003) Hotel selection Ngai and Wat (2003) Dryer tool integration Lababidi and Baker (2003) Medical diagnosis Meesad and Yen (2003) and Sendelj and Devedzic (2004) Pooled flood frequency analysis Shu and Burn (2004) Medical consultation system Boegl, Adlassnig, Hayashi, Rothenfluh, and Leitich (2004) Job matching Drigs et al. (2004) Performance indexing Padilla-Medina and Sanchez-Marin (2004) Computer security Reznik and Dabke (2004) Gesture recognition Frantti and Kallio (2004) Table 5 Object-oriented methodology and their applications Object-oriented methodology/ applications Authors Industry diagnosis Batanov and Cheng (1995) Knowledge representation Vranes and Stanojevic (1995) Electronic power capacity planning Deb (1995) Knowledge learning Menzies (1997) Power system maintenance Kawahara, Sasaki, Kubokawa, Asahara, and Sugiyama (1998) Knowledge engineering Geymayr and Ebecken (1998) Manufacturing information network Lau, Tso, and Ho (1998) Syntactic programming Depradine (2003) 4 Shu-Hsien Liao / Expert Systems with Applications xx (2004) 1–۱۱ DTD 5 ARTICLE IN PRESS domains.