Στη διπλωματική εργασία παρουσιάζεται ένα ευφυές σύστημα αποφάσεων για τη διάγνωση και τη θεραπεία της υπέρτασης που ονομάζεται Piesys. Η δημιουργία του ευφυούς συστήματος που βασίζεται στο Piesys έγινε με τη βοήθεια δύο εργαλείων του Clips και του Fuzzytech. / In this project there is a presentation of an expert system called Piesys which is used for the diagnosis and therapy of hypertantion. The creation of the expert system became with the assistance of two expert system tools Clips and Fuzzytech.

Είναι πολύ συχνή η ανάγκη κατασκευής ωρολογίων προγραμμάτων για εκπαιδευτικούς οργανισμούς, για μέσα μαζικής μεταφοράς, για τεχνικές εταιρίες κ.α. Η κατασκευή ωρολογίων προγραμμάτων (timetabling) εντάσσεται στη γενικότερη κατηγορία προβλημάτων που είναι γνωστά ως προβλήματα χρονοδρομολόγησης (scheduling). Ένα πρόβλημα χρονοδρομολόγησης έχει γενικά σαν σκοπό να τοποθετήσει μέσα στο χρόνο ένα σύνολο από δραστηριότητες δεδομένου ενός συνόλου πόρων που αυτές οι δραστηριότητες χρειάζονται για να πραγματοποιηθούν. Ειδικά για τα σχολικά προγράμματα με τα οποία ασχολείται η παρούσα εργασία πολλές μέθοδοι και αλγόριθμοι έχουν εφαρμοστεί με στόχο την δημιουργία βέλτιστων προγραμμάτων. Παρόλα αυτά δυστυχώς η πράξη αποδεικνύεται να ανατρέπει πολλές από αυτές τις λύσεις. Έτσι η χρήση της μεθόδου των έμπειρων συστημάτων, που δεν φαίνεται να έχει χρησιμοποιηθεί ευρέως στο πρόβλημα αυτό, είναι μια υποψήφια μέθοδος για να μας δώσει πιο γενικά αποδεκτές λύσεις, που να συμβαδίζουν καλύτερα με την πραγματικότητα, αφού βασική τεχνική είναι η προσομοίωση ενός έμπειρου προγραμματιστή. Η παρούσα εργασία ασχολείται με την δημιουργία ενός έμπειρου συστήματος για την σχεδίαση εβδομαδιαίου προγράμματος μαθημάτων για το Ελληνικό Γυμνάσιο. Για την δημιουργία του έμπειρου συστήματος απευθυνθήκαμε σε ειδικούς σχεδίασης προγραμμάτων σε ελληνικά σχολεία (προγραμματιστές) οι οποίοι μας έδωσαν πλήρη περιγραφή των κανόνων και διαδικασιών που χρησιμοποιούν ώστε να εκδοθεί ωρολόγιο πρόγραμμα. Στη συνέχεια έγινε ανάλυση και εξαγωγή των στόχων και των περιορισμών του προβλήματος καθώς επίσης ορίστηκε και ο τρόπος καταχώρησης των δεδομένων. Στη συνέχεια έγινε σχεδιασμός εφαρμογής για εξαγωγή προγραμμάτων του Ελληνικού Γυμνασίου και επιλέχθηκαν οι τεχνολογίες που είναι πιο κατάλληλες για την υλοποίηση της εφαρμογής. Οι τεχνολογίες που εφαρμόσαμε ώστε να επιτευχθεί η υλοποίηση του πληροφοριακού συστήματος έκδοσης ωρολογίου προγράμματος για το Γυμνάσιο ήταν (α) το εργαλείο CLIPS (1) για την πραγμάτωση του έμπειρου συστήματος, (β) η χρήση PHP (3) και MYSQL (4) για την καταχώρηση των βασικών παραμέτρων του προγράμματος με χρήση του WEB, (γ) το εργαλείο PHLIPS (2) για την σύνδεση του CLIPS με PHP, με στόχο την εξαγωγή στο WEB των αποτελεσμάτων. Έτσι δημιουργήθηκε πληροφοριακό σύστημα όπου κάθε προγραμματιστής σχολείου μπορεί να καταχωρήσει τα στοιχεία του σχολείου, των καθηγητών, τις διαθέσιμες ώρες τους κ.α. με την ευκολία του περιβάλλοντος WEB για ένα η περισσότερα σχολεία που έχει αναλάβει. Η χρήση του WEB δίνει την ευκολία διαχείρισης του προγράμματος από οποιοδήποτε σημείο έχει πρόσβαση με το διαδίκτυο και ταυτόχρονα την χρήση γραφικού περιβάλλοντος για επίτευξη καλύτερης διαχείρισης των πληροφοριών του. Επίσης μπορεί ο χρήστης εύκολα με αλλαγή των παραμέτρων να λαμβάνει διαφορετικά αποτελέσματα και να αποφασίζει σύμφωνα με τις ανάγκες του ποια λύση θεωρεί πιο εφικτή με βάση την καθημερινή πρακτική. Η χρήση του CLIPS για επίτευξη έξυπνων έμπειρων συστημάτων και η σύνδεση μέσω του προτύπου ανάπτυξης συστημάτων PHLIPS δίνει μεγάλες δυνατότητες για τον συνδυασμό της τεχνικής νοημοσύνης με τις τεχνολογίες διαδικτύου. Η εφαρμογή δοκιμάστηκε σε αρκετά γνωστά σετ δεδομένων και πραγματικά δίνει αξιόπιστες και ανταγωνιστικές λύσεις με την καινοτομία όμως ότι είναι πιο αποδεκτές στην καθημερινή πρακτική από άλλες που δίνουν άλλες μέθοδοι τεχνικής νοημοσύνης που αναζητούν βέλτιστες λύσεις με βάση απλά ποσοτικοποιημένα κριτήρια όπως το σύνολο των κενών ορών, η καλύτερη επίτευξη των απαιτήσεων των καθηγητών κ.α. / There is a common need for the construction of timetables for educational organizations, public transportation, for construction companies, etc. The construction of timetables (timetabling problem) is part of a general category of problems known as scheduling problems. The task of a scheduling problem generally is to have a set of activities distributed through time given a set of resources which are needed in order to have these activities to be accomplished. This postgraduate thesis deals with a school timetabling problem. A variety of methods and algorithms have been implemented in order to create optimized timetables. Nevertheless, real life has shown that many of these solutions cannot be realistic. Thus the use of expert systems method, which seems not to have often used in such problems, is a good candidate to gives a more realistic and acceptable solutions, given that it tries to simulate the way an expert school timetabling maker works. This Thesis deals with the creation of an expert system that designs weekly timetables for the Greek High School. To create the expert system, we interviewed experts in designing school timetables in Greek schools, who gave us full description of the rules and procedures they use in order to construct a school timetable. Then we analyzed and extracted the objectives and constraints of the problem and we defined the method of storing the data. Then, we developed an application which produces timetables for the Greek High schools. We chose the appropriate technologies needed and were most suitable to construct the application. The technologies we have used to achieve the implementation of a computerized system for exporting timetables for the high school were, (a) the CLIPS programming tool for the creation of the expert system, (b) the PHP and MYSQL to record the key parameters of the program in a WEB environment, (c) the PHLIPS tool for the connection of CLIPS with PHP, to be able to export the results back into the WEB environment. Thus we created a computerized system where every school timetable maker can register the data concerning the school, the teachers, the available hours and dates etc. with the ease of the WEB environment for one or more schools. The potential of using the WEB environment provides the user with ease of managing the program from anywhere with access to the Internet, while using the graphical user interface for obtaining the best data management. We can easily change the parameters to obtain different results and act in accordance with our needs the most feasible solution based on daily practice. Using CLIPS to create an expert system, and the connection through the PHLIPS development standard gives great potential for the combination of artificial intelligence and internet technologies. The application was tested on several well-known data sets and really gives a reliable and competitive solutions but with the innovation, that is more acceptable in daily practice than other methods of artificial intelligence that seek optimal solutions based on simple but politicized criteria such as the total of empty hours ,to meet the requirements of teachers, etc.

A multi-level modular control scheme to realize integrated process monitoring, diagnosis and control for intelligent machining is proposed and implemented. PC-based hardware architecture to manipulate machining process cutting parameters, using a PMAC interface card as well as sensing processes performance parameters through sampling, and processing by means of DSP interface cards is presented. Controller hardware, to interface the PC-based PMAC interface card to a machining process for the direct control of speed, feed and depth of cut, is described. Sensors to directly measure on-line process performance parameters, including cutting forces, cutting sound, tool-workpiece vibration, cutting temperature and spindle current are described. The indirect measurement of performance parameter surface roughness and tool wear monitoring, through the use of NF sensor fusion modeling, is described and verified. An object based software architecture, with corresponding user interfaces (using Microsoft Visual C++ Foundation Classes and implemented C++ classes for sending motion control commands to the PMAC and receiving processed on-line sensor data from the DSP) is explained. The software structure indicates all the components necessary for integrating the monitoring, diagnosis and control scheme. C-based software code executed on the DSP for real-time sampling, filtering and FFT processing of sensor signals, is explained. Making use of experimental data and regression analysis, analytical relationships between cutting parameters (independent) and each of the performance parameters (dependent) are obtained and used to simulate the machining process. A fuzzy relation that contains values determined from statistical data (indicating the strength of connection between the independent and dependent variables) is proposed. The fuzzy relation forms the basis of a diagnostic scheme that is able to intelligently determine which independent variable to change when a machining performance parameter exceeds control limits. The intelligent diagnosis scheme is extensively tested using the machining process simulation.

Orientador: Nivaldo Lemos Coppini / Tese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Mecanica / Made available in DSpace on 2018-07-22T10:58:08Z (GMT). No. of bitstreams: 1 Costa_DalbertoDiasda_D.pdf: 7963439 bytes, checksum: ab345a526734ea426844161892948326 (MD5) Previous issue date: 1997 / Resumo: A determinação das condições de usinagem raramente tem sido contemplada como um problema de planejamento, e, portanto, integrada às outras etapas. Observa-se que essa determinação vem sendo tratada isoladamente, como um problema de pesquisa operacional (otimização de uma função objetivo) ou como uma simples consulta a um banco de dados. Em muitas situações, ela é deixada a cargo de um operador experiente. O objetivo deste trabalho foi formalizar uma metodologia para construção de uma ferramenta computacional que permita a um especialista humano gerar um sistema para enfrentar esse problema. A presente metodologia tem um caráter generalista, permitindo ao usuário obter um sistema que contenha sua experiência pessoal e seja dirigido pelo e para um determinado chão-de-fábrica. Para atingir esse objetivo empregou-se as seguintes técnicas: propagação de restrições, raciocínio baseado em casos e raciocínio qualitativo-causal. A metodologia proposta já se encontra na forma de um protótipo implementando em VISUAL-BASIC e COMMON LISP; sendo possível a construção de um Módulo Especialista para escolha das condições de corte paralelamente às outras etapas do planejamento da usinagem / Abstract: The selection of cutting conditions is an important task in the machining planning. It affects time, cost, quality and always yields undesirable side-effects as excessive tool wear and large cutting forces. However, there is a few attempt to integrate it in the automated process planning systems. Probably, because there is no theoretic models to allow theirs values to be selected. The presence of experimented personnel remains necessary to choose the initial conditions and change them when something goes wrong at the shop fIoor. The purpose ofthis research is an attempt to face this problem. A very general methodology was proposed. Constrain propagation, similarity evaluation and qualitative-causal models were the techniques employed to formalize this proposal. Constraints were used as a medium forcommunication among hierarchical levels of variables. Similarity coefficients were fundamental to retrieve past experience from a case base. The causal dependency between variables were expressed using qualitative relations, which allowed to adapted the retrieved case to satisfy the most important constraint. The current methodology - implemented using VISUAL-BASIC and COMMON LISP - permits an Expert Module to be tailored to a very specific shop fIoor and the choice of cutting variables can be made concurrently with the others planning tasks / Doutorado / Materiais e Processos de Fabricação / Doutor em Engenharia Mecânica

Firstly, this thesis reviews the literature on the application of microcomputer-based Management Information Systems (MISs) and Decision Support Systems (DSS) to Small and Medium sized Enterprises (SMEs). It is found that the hardware platform today is already sufficient for SMEs. However, information regarding successful implementation of MISs for SMEs is scarce and largely fragmented. DSS requires more focused and dedicated use of information to support managerial decision making. Unfortunately, the development of DSSs for SMEs is even more backward. Yet, there is an emerging need for SMEs today because business operations have become more sophisticated under intensified competition. With this scenario in mind, the author undertook intensive questionnaire and case surveys to find out the current development and trends for the effective applications of MISs and DSSs. In 1987, the author was awarded the Oshikawa Fellowship by Asian Productivity Organisation in Tokyo and started the present research. 446 completed questionnaire survey sheets from U.K. and Hang Kong have been received and analysed. 67 SMEs and related organisations in 6 developing/developed countries were also visited. This forms the knowledge for the development of expert systems (ES) for effective applications of MIS. The approach for DSS is based on a carefully selected business game which has most of the common business decision parameters. Intensive experiment with over 100 subjects was conducted in running the game, with an average time contribution of about 20 hours/person. The findings are again consolidated and structured into an ES. Longitudinal research was conducted in 5 representative SMEs. With the use of action learning and participation of the researcher, more in-depth firsthand information were obtained and analysed. These form part of the input to the ES as well. Both ES have been validated and further improved. The experimenters find these as keys to develop MIS/DSS for SMEs. A marketing plan is suggested to launch these two products so that they can become more easily available. Finally, recommendations are made on the effective use of the ES and for further development.

There is a growing interest in the development of computer systems that are actively involved in the tasks of the users and serve to augment the users' creativity. Cooperative computing is a major contribution to this research field. A survey of current developments in knowledge based systems led to the conclusion that there has hitherto been an absence of a formal definition of the mechanisms of cooperative computer systems based on theories of cooperation. The work in this thesis seeks to provide a full definition of cooperation derived from the behaviours of living cooperative systems. Studies on human cooperation and cooperation in the animal kingdom, established that cooperation is a dynamic behaviour; in that the interaction processes between the cooperative partners serve to facilitate the achievement of a common goal, or a set of goals that are mutually desired by the partners. Partners in cooperation are interdependent: one member's actions are contingent on another. Therefore, the underlying processes which induce and maintain cooperation were identified. These are: communication between the partners; emergence of norms and roles governing the behaviour of the cooperating members; resolution of conflicts; distributed and coordinated activities. These factors were further elucidated within the context of small problem solving groups. A model of cooperationw hich encapsulatedth esef actors was produced. From the discussionso f the advantageso f cooperationw ithin different contexts, the potential for synergy was found to be the main benefit of cooperation. The potential for achieving this synergy between a human and a computer is the main motivation for the work undertaken in this research. From the theoretical analysis of cooperation, the underlying mechanisms of a cooperative computer were successfully defined. A conceptual model of human-computer cooperation was presented. It was established that the quality of cooperation is closely associated with the nature of the task. Therefore, it is not practicable to produce a general purpose cooperative system. A specific task must be used. Creative tasks of a problem identifying and solving nature, were found to be more suitable to cooperative behaviour than others. Typical of these, and the one selected, was computer screen design. Current screen design practice was analysed, and the functional requirements and knowledge base needs of the systems were established. The underlying mechanisms of cooperation were formalised and successfully implemented within a software exemplar, named COSY. COSY exhibits the behavioural characteristics of cooperation, and utilises the knowledge of screen design to support users in the task of formatting computer screens. COSY successfully demonstrated the synergistic relationship in its cooperation with the users. It is concluded that the approach undertaken in this thesis has lead to a successful definition and implementation of the formal mechanisms of cooperation in a computer system, one which potentially enhances the innovative and creative aspects of design work.

A sample of Vancouver's zoning has been expressed as an expert system, microcomputer program, - Euclid - in order to demonstrate the feasibility of applying this tool in municipal planning, and to explore the desirability of such computer applications. Review of the literature on Expert Systems from a planning practice perspective showed that this is considered one of the more exciting and potentially useful developments emerging from Computer Science. Expert Systems are thought to be applicable to some planning tasks which are difficult to handle using the computer tools currently available yet suited to automation, however, there is in the literature very little empirical work on developing systems and testing the potential utility of expert systems in land use planning. Euclid is programmed in Turbo Prolog 2.0, a language accessible without extensive or specialized computer training. The first conclusions of the thesis are that simple but useful expert systems can be built rather quickly by planners, and that development control is a good application domain. The thesis also uncovered several weaknesses and inconsistencies which appear related to the way Zoning By-laws have been written, and suggests that the discipline of programming in logic may avoid or resolve such problems. Finally the process of developing a system is shown to be just important as the system itself: Expert systems are a way of thinking about a problem just as they are a way of solving it. / Applied Science, Faculty of / Community and Regional Planning (SCARP), School of / Graduate

In this study a Q-sort was used to measure differences in academic and public librarian attitudes toward computers, desktop publishing systems and expert systems. Fifty-two academic and sixty-two public librarians responded. The responses were sorted into groups based on the type of library and whether or not the respondent followed the stated Q-sort distribution.

This thesis addresses the problem of providing explanations for expert systems implemented in a shell that supports a hybrid knowledge representation architecture. Hybrid representations combine rules and frames and are the predominant architecture in intermediate and high-end commercial expert system shells. The main point of the thesis is that frames can be endowed with explanation capabilities on a par with rules. The point is illustrated by a partial specification for an expert system shell and sample explanations which could be generated by an expert system coded to that specification. As background information, the thesis introduces expert systems and the standard knowledge representation schemes that support them: rule-only schemes, and hybrid schemes that combine rules with frames. Explanations for expert systems are introduced in the context of rules, since rules are the only representation for which explanations are supported, either in commercial tools or in the preponderance of research. The problem addressed by the thesis, how to produce explanations for hybrid architectures, is analyzed in two dimensions. Research was surveyed in three areas for guiding principles toward solving the problem: frame logic, metalevel architectures, and reflective architectures. With the few principles that were discovered in hand, the problem is then analyzed into a small number of subproblems, mainly concerning high-level architectural decisions. The solution proposed to the problem is described in two ways. First a partial specification for expert system shell functionality is offered, which describes, first, object structures and, then, behaviors at three points in time—object compilation time, execution time, and explanation generation time. The second component of the description is a set of extended examples which illustrate explanation generation in a hypothetical expert system. The solution adopts principles of reflective architectures, storing metainformation for explanations in metaobjects which are distinct from the object-level objects they explain. The most novel contribution of the solution is a scheme for relating all the ways that objects' slot values may be computed to the goal tree construct introduced by the seminal Mycin expert system. The final chapter explores potential problems with the solution and the possibility of producing better explanations for hybrid expert system shell architectures. / Science, Faculty of / Computer Science, Department of / Graduate

An analysis of the organizational field of B.C. agriculture was conducted to explore the politics of the innovation process. Agricultural innovations in organic farming, synthetic agrichemicals and biogenetic engineering were studied at the individual, organizational and interorganizational levels. Research questions regarding the innovation decision—making process, innovation championship, organizational politics, organization theory and interorganizational networks were explored. A total of 137 persons (organic and conventional farmers, BCMAFF employees, farm organization employees) were interviewed in this research study. Data was collected via semi—structured interviews, questionnaires, and analysis of publications to investigate a total of 28 research questions. Similarities and differences between organic and conventional farmers in respect to their socioeconomic characteristics, motivations, actions and environmentalist beliefs were identified. Organic farmers basis for their innovation adoption decisions was found to be largely informed by their environmentalist philosophy whereas the primary motivating factor for conventional farmers was economic rather than ideological. Case studies of 33 farm organizations (20 conventional and 13 organic) were conducted. Organizational fields were found to be defined not only in terms of products, services and geographic location but also in terms of ideology. Within the conventional agriculture organizational field there was a high degree of homogeneity in organizational structures and decision making processes as well as close collaboration with government policy makers. Within the organic agriculture organizational field there was homogeneity in production practices, but heterogeneity in organizational structures, goals and decision making processes based on the radicalness of the environmentalist philosophy of an organization’s membership. The formation and operation of interorganizational networks in each organizational field confirmed previous findings of the critical problems in overorganized and underorganized networks. A longitudinal analysis of organizational politics in the organic agriculture organizational field revealed that institutionalization processes engender political contests among competing interests. The successful championship of an innovative government regulatory system was attributed to the early use of a wide variety of collaborative and competitive political games. Opponents’ efforts to neutralize champions’ escalation of commitment during the later stages of the innovation development process proved to be ineffective. / Business, Sauder School of / Graduate