expert systems dudychr go ovefivff[1].pptx

f8dgxg2b25 38 views 23 slides Sep 25, 2024
Slide 1
Slide 1 of 23
Slide 1
1
Slide 2
2
Slide 3
3
Slide 4
4
Slide 5
5
Slide 6
6
Slide 7
7
Slide 8
8
Slide 9
9
Slide 10
10
Slide 11
11
Slide 12
12
Slide 13
13
Slide 14
14
Slide 15
15
Slide 16
16
Slide 17
17
Slide 18
18
Slide 19
19
Slide 20
20
Slide 21
21
Slide 22
22
Slide 23
23

About This Presentation

Expert system a branch of artificial intelligence is one of the new waves of technology that have influenced the services of the library. The concept of expert system developed from the subject domain of artificial intelligence (AI) requires a departure from conventional practices and programming te...


Slide Content

Khushi rohilla Expert systems in libraries KHUSHI ROHILLA M-22

Contents Introduction Definitions of expert systems Characteristics of expert systems Need for expert systems Components of expert systems Application in libraries Features of expert system Limitations of expert systems Conclusion References 2

introduction Expert system a branch of artificial intelligence is one of the new waves of technology that have influenced the services of the library. The concept of expert system developed from the subject domain of artificial intelligence (AI) requires a departure from conventional practices and programming techniques. “Expert systems in libraries are computer-based systems that mimic the decision-making abilities of a human expert in a specific domain, using a knowledge base and inference engine to provide expert-level advice, support, and solutions to library users and staff, with the goal of improving the quality, accuracy, and efficiency of library services and operations”. It stores and interprets the experience and knowledge of human expert by using computer technology. Edward Albert Feigenbaum has defined an expert system as “an intelligent computer programmes that uses knowledge and inference procedure to solve problems that are difficult enough to require significant human expertise for their solutions” In simpler terms: "Expert systems in libraries are computer programs that think like a librarian, providing expert advice and answers to users and staff, making library services more accurate, efficient, and user-friendly."

Cambridge international dictionary of E nglish defines an expert system as a computer system which asks questions and gives answers that have been thought of by a human expert. According to H arrod’s librarians glossary . An expert system is a computer system which embodies certain decision-making processes relating to a particular subject; such as system comprises of five parts – a knowledge base, an inference machine, an explanation program, a knowledge refining program, and a natural language processor. According to K ashyap(1999), an expert system makes the knowledge of experts available to others in situations where they require expert knowledge , or support of knowledge of experts available to others in situations where they require expert knowledge, or support of knowledgeable people or professionals engaged in development and application in a well-defined area. Expert systems are a recent product of artificial intelligence. In simple term, an expert system stores large amount of data and disseminate it in a systematic way as required by the users . Subaveerapandiyan , A. (2023). 4 Definitions of expert system:

Characteristics of expert system: 5 Expert system in Artificial intelligence offers the highest level of expertise. It provides efficient and accurate solution to imaginative problem. An expert system has adequate response time. The total time must be less than the time taken by a human expert to get the most accurate solution for the same problem. An expert system interacts in a very reasonable period of time with the user. It is always reliable and does not make much mistake. Expert system has to link with meta knowledge that means it is known about themselves with own knowledge limitations and abilities. Due to implementation of meta knowledge, it makes more interactive and simple for several data representations. Capable of handling challenging decisions and problems: An expert system is capable of handling challenging decision, problems and delivering solution. Gladness , K. (2023).

Need for expert system: 6 Expert systems can answer questions and solve problems much faster than the human expert. Due to the capabilities of computers of processing a huge number of complex operations in a guide & accurate way, expert systems can provide both fast and reliable answers in situation where the human experts cannot. Expert system can be used to perform monotonous operations and other that are boring or uncomfortable to humans. Substantial savings can be achieved from using expert system. Human get tired from physical or mental workload, expert system cannot. Human have limited working memory and unable to process complex, large amount data. • Humans lie, hide and die. He may also retire or transferred from his job while the expert system is also available. • Expert system does not forget or never make mistake in calculation. Murthy , S. S. ( 20 17).

Components of expert system User interface Interference engine Knowledge base 7

User interface is the component which enables the user to communicate with the expert system. Most expert systems are interactive; they need users to input information about a particular situation before they can offer advice. Most of the existing user interfaces of expert systems are menu driven, accepting single words or short phrases from the human user. A few have natural language capabilities. The expert system aims to assist or advise the non-expert users, but it will be consulted only if it helps the users to perform that task more easily. Thus, expert systems must meet all the requirements of good interface design. ( e- gyankosh,n.d .) User interface:

Interference engine: interference engine stands between the user and the knowledge base. It performs two major tasks: first, it examines existing facts and rules, and adds new facts when possible; second, it decides the order in which inferences are made. In doing so, the inference engine conducts the conclusion with the user. The inference strategies used in expert systems are: Modusponens Reasoning about uncertainty Resolution Engine part of the system means it is used to drive around amongst the various inferences it might make. This means it allows to pursue reasoning strategies or control strategies as they are sometimes called, to decide what operators to apply at each stage of the search.

The most common control strategies used in expert systems are forward chaining , backward chaining and bi-directional . Broadly speaking, forward chaining involves reasoning from data to hypotheses, while backward chaining attempts to find data to prove, or disapprove, a hypothesis. Pure forward chaining leads to unfocused questioning in a dialogue mode system, whereas pure backward chaining tends to be rather relentless in its goal-directed questioning. Most successful expert systems use bi-directional reasoning method. Asemi , A., Ko, A. And nowkarizi , M. (2021), Interference engine ( contd …1)

Knowledge base: The knowledge base is a vital component of an expert system. It embodies the expert knowledge the system needs to do the tasks it is designed to carry out during its everyday processing. Different types of knowledge may need to be incorporated: Knowledge about the problem domain. Knowledge about objects in the problem domain. Facts specific to the problem domain. The factual information held by the system is data about the domain which do not vary whatever particular circumstances are considered. ( Asemi , A., Ko, A. and Nowkarizi , M. (2021),)

Knowledge base (CONTD..1) These data are stored in a conventional data base. During system processing, data specific to the set of conditions being considered at a particular time are held in the 'working memory' and are usually discarded at the end of the session Of more interest is the human expert knowledge which relates to the problem domain or to the objects of the domain. This knowledge cannot be stored in a conventional data base, but it has to be represented by a formalism that is suitable for the kind of manipulation required by the tasks that the system is performing. ( Asemi , A., Ko, A. and Nowkarizi , M. (2021)

Components of expert system ( contd …) 13

Application in Libraries 14

Application in Libraries (contd..1) Administration :- Library administration must deal with complex problems on a day-to-day basis. Problems with budgeting, staff, and planning are just a few of the difficulties they face every day. During budget cuts, the administrator must determine what items to cut and by how much. Should staff be reduced? Should serials be cancelled? Will there be any money to buy books or equipment? An expert system could be helpful in assisting the administrator in making these decisions. One could develop a system composed of the heuristics (rules-of-thumb) that librarians use to make these decisions . Staff management :- Staff management in hiring, promoting and placement of the staff, an expert system might be useful. By using criteria such as qualifications required for the job and experience, an expert system could be used to assist in the hiring process. An expert system could be developed to determine which staff members should receive raises, disciplined, or dismissal. Planning:- A n expert system using information from patterns and material usage could help plan for remodeling or new facilities. The system would help the administrator to determine where the circulation desk should be located, where the copy machine should be placed, and where the OPAC terminals would get the most use. Gladness , K. (2023). 15

Application in Libraries (contd..2) Technical Services:- More efforts have been in developing expert system applications for technical services. The focus of research efforts are witnessed in the areas of cataloguing, collection development. Cataloguing :- Expert systems have been developed to create MARC record6 and to apply some of the rules in AACR-2 for cataloguing. Roy chang7 developed a cataloguing expert system based on the rules in AACR-2. He determined that its usefulness was limited because the system had no means of interpreting the rules. In this opinion 'cataloguing problems today are too widespread For employing an expert system’. Classification:- Classification is also a difficult area for an expert system. While there are guides to determine classification numbers and subject headings, there are no strict rules available, and the relationship between objects and classes are often ambiguous. Research is progressing in the development of systems for assigning subject headings and class numbers. Collection Development:- There are only two possible responses when one considers new materials for acquisition or old materials for discarding; yes or no. With only two possible responses, it is easier to develop an $expert system. There has been at least one successful attempt at building expert system for collection development at Applied Physics library. Reference Service:- Expert systems would be useful for assisting patrons in locating materials and information. Expert systems may prompt the user for the type of information needed and display materials that may contain it. Gladness, K. (2023).

6.) F eatures of Expert system: (1.) Experts can be freed from routine tasks and made available for more exciting, creative and demanding work. (2.) Expertise can be pooled when more than one expert contributes to the system development. The pooling exercise can assist in the refinement of the procedures and help to make them more consistent. (3.) Knowledge can be safeguarded, developed and distributed. Enormous sums of money are spent on training individuals, yet all their knowledge and expertise is lost when they die or leave the company. Expert systems offer a way of capturing this expertise and knowledge and at the same time making it available to other people. (4.) Expertise can be available. Since expert systems provide explanations for advice given they can be used 24 hours a day without the presence of the expert. (5.)Expert systems can be used for training purposes. The- problem-solving and explanation capabilities of expert systems are particularly useful in training. Situations. Training can also be distributed throughout a company and done on an individual basis at times suited to the employee . Subaveerapandiyan , A. (2023).

Features of Expert system (CONTD...1) 18 (6.) Expert systems can provide a standardized approach to problem solving. (7.) The development of an expert system offers the expert with an opportunity to critically assess and improve his problem-solving behavior. (8.) The performance of non-experts can be improved over a period of time and they may eventually even reach expert status. (9.) In many situations, expert systems can provide solutions to problems far more quickly than a human expert. (10.) Expert systems have the potential for saving companies a vast amount of money, thus increasing profits. Subaveerapandiyan , A. (2023).

The expert systems are often created utilizing the software development Methodology called prototyping. The objective of the software prototype is to validate proposed designs by constructing a low-cost system that has enough functionality to test out major designs decisions. The prototyping allows developer to fairly quickly create one or more systems that approximate the final system. However, there is no any guarantee that software techniques utilized in the small-scale prototype will work in the large-scale production system. This can lead to a false sense of accomplishments. In most libraries, expert systems are prototypes, not production systems. ( Murthy, S. S. (2017). 19 Limitations of expert system:

Limitations of expert system ( contd …1) It is evident that no technology is entirely perfect to offer easy and complete solution. Also, the level and caliber of effort that must be expended to create an expert system is directly related to the power and complexity of that system. The more intelligent the system is the greater the effort that must be expended to create it and also the greater the degree of expertise that is needed to do so. Larger systems are not only expensive but also require a significant amount of development time and computer resources. There is also the need for skilled personnel combined with expensive developed tools. ( Murthy, S. S. (2017). 20

CONCLUSION The usefulness of expert systems in library and information systems will depend on increasing power and efficiency of hardware and software. To be able to offer expert system services to their clients, libraries will have to be involved in the following areas: A. Development of prototype 'systems. B. Development of knowledge representation schemes. C. Experimentation with knowledge-based indexing, abstracting, and classification. D. Experimentation with specialized development environments for specific domains of knowledge. As knowledge based expert systems become more acceptable in the library community, libraries will begin to develop, purchase and maintain interactive knowledge-based expert systems for their clients. 21

References Subaveerapandiyan , A. (2023). Application of Artificial Intelligence (AI) In Libraries and Its Impact on Library Operations Review. Library Philosophy and Practice, , 1-19. Gladness, K. (2023). Constraints Facing African Academic Libraries in Applying Electronic Security Systems to Protect Library Materials. International Journal of Librarianship, 8(1), 31-48.   https://egyankosh.ac.in/bitstream/123456789/10553/1/Unit-1.pdf Asemi , A., Ko, A. and Nowkarizi , M. (2021), "Intelligent libraries: a review on expert systems, artificial intelligence, and robot", Library Hi Tech, Vol. 39 No. 2, pp. 412-434. https://doi.org/10.1108/LHT-02-2020-0038 Murthy, S. S. ( 20 17). Expert systems for library and information services. DESIDOC Bulletin of Information Technology

23