International Higher Diploma in Computer Studies Knowledge Based System The marks given in brackets are indicative of the weight given to each part of the question. Answer FOUR questions out of SIX. Time: TWO hours and 10 minutes reading time Reference materials are NOT allowed. Question 1 a) Outline the characteristics of Knowledge-Based Systems. b) c) Simulate human reasoning about a problem domain rather than simulating the domain Reason using representations of human knowledge Solve problems using heuristics or rules of thumb - not guaranteed to succeed Able to explain and justify solutions/advice in order to convince user that reasoning is valid. List and explain the different types of KBS Applications. [4 Marks] [12 Marks] Interpretation - take observations and infer descriptions e.g. natural language understanding Prediction - recognise situations and infer likely consequences e.g. weather forecasting Diagnosis - observe symptoms and infer causes of those symptoms e.g. medicine, mechanical design - given a set of constraints develop configurations which satisfy those constraints e.g. computer system design Planning - specifying actions e.g. robot movement, project planning etc. Monitoring - compare current observations with expected observations and both indicate discrepancies and suggest corrective action e.g. patient monitoring Instruction - assist the learning process e.g. recognise errors in student programs and suggest alternatives Control - adaptively govern the overall control of various control systems e.g. power plants, chemical plants. List four benefits of Knowledge-Based Systems. [4 Marks] Knowledge base systems capture and distribute knowledge Knowledge base systems are dependable Knowledge base systems have been proven Knowledge base systems are accurate and consistent Knowledge base systems are profitable d) What is the definition for ontologies? [5 Marks] Ontology provides an explicit conceptualization (i.e., meta information) that describes the semantics of the data. They have a function similar to a database schema. Some differences are: A language for defining ontologies is syntactically and semantically richer than common approaches for databases. An ontology must be a shared and consensual terminology because it is used for information sharing and exchange. An ontology provides a domain theory and not the structure of a data container. IHDCS/KBS/0611 Page 1 of 9 Question 2 Write short notes on each of the following: a) Knowledge Engineering Knowledge engineering is the study of how to collect, organize, and express this experiential knowledge. It is through the knowledge engineering process that a knowledge base is created. The major elements of the knowledge engineering process can include one or more of the following: Knowledge Acquisition Spatial Data Manipulation Environmental Setting Development Knowledge Encoding (Business Process and Rule Development) Report and Map Configuration b) Knowledge Acquisition It translate human knowledge in current, written, conceptual and abstract representations into computer representations. It is also the process of eliciting expertise in an application area. Knowledge Acquisition is the first stage of the knowledge engineering process. It is where a manual tool such as interviewing is used to actually extract the knowledge from a person with expertise in the problem domain. c) Knowledge Representation The third phase in E/KBS development is knowledge representation. The major objective in this phase is to take the acquired knowledge and translate it into machine-readable form. Knowledge Representation refers to the formalism, both syntax and semantics, used to store knowledge in an architecture. This can be done in many ways as follows: Declarative. Knowledge is stored as a set of statements about the world. These statements are static but can be added to, deleted or modified. Procedural. Knowledge is stored as a set of procedures which can themselves determine when they should be executed. Their execution is the intelligent behavior that was expected in the situation. Symbolic. The storage of the knowledge utilizes symbols in order to represent objects of the outside world or sets of perceptions about the outside world. SubSymbolic. The knowledge is stored without the use of symbols. This typically means the architecture uses direct mapping from the inputs to outputs. Uniform Representation. The knowledge base chooses one method for representing the knowledge (e.g. frames, semantic nets etc) and uses it exclusively. Non-Uniform Representation. Many different representation methods are used. d) Knowledge Management Knowledge Management is the collection of processes that govern the creation, dissemination, and utilization of knowledge. In one form or another, knowledge management has been around for a very long time. Practitioners have included philosophers, priests, teachers, politicians, scribes, Liberians, etc. IHDCS/KBS/0611 Page 2 of 9 Knowledge management is not a, "a technology thing" or a, "computer thing" If we accept the premise that knowledge management is concerned with the entire process of discovery and creation of knowledge, dissemination of knowledge, and the utilization of knowledge then we are strongly driven to accept that knowledge management is much more than a "technology thing" and that elements of it exist in each of our jobs. e) Knowledge Elicitation [5 x 5 Marks] The most important branch of knowledge acquisition is knowledge elicitation - obtaining knowledge from a human expert (or human experts) for use in an expert system. Knowledge elicitation is difficult. This is the principle reason why expert systems have not become more widespread - the knowledge elicitation bottleneck. The knowledge elicitation (and analysis) task involves: Finding at least one expert in the domain who: o is willing to provide his/her knowledge; o has the time to provide his/her knowledge; o is able to provide his/her knowledge. Repeated interviews with the expert(s), plus task analysis, concept sorting, etc, etc.. Knowledge structuring: converting the raw data (taken from the expert) into intermediate representations, prior to building a working system. This will improve the knowledge engineer's understanding of the subject; This provides easily-accessible knowledge for future KEs to work from (knowledge archiving). Building a model of the knowledge derived from the expert, for the expert to criticise. From then on, the development proceeds by stepwise refinement. Question 3 a) Describe the different stages of knowledge acquisition. [10 Marks] 1) Identification Here the problem is identified, and the purpose of the Artificial Intelligence application to be built is. It also involves identifying the number of participants involved and the resources that are available for the system. Basically the Knowledge Engineer will become familiar with the situation and the main characteristics of the problem. 2) Conceptualization Decisions have to be made on certain issues that would affect he overall structure of the system for example what information is needed and how will it be represented in the Knowledge Base, how will certain knowledge be extracted etc. 3) Formalization The knowledge is extracted from the experts and the knowledge has to be represented into the Knowledge Base. This shows that the Knowledge Acquisition and the Knowledge Representation is carried out together in this stage. The acquisition methodology used will IHDCS/KBS/0611 Page 3 of 9 depend on the way the knowledge is organised and represented. For example the methodology Rule Based system would mean representing the knowledge in terms of rules. 4) Implementation The knowledge is actually programmed into the computer by developing an expert system prototype. Also the knowledge is checked to make changes or use alternative methods. 5) Testing The system is tested by using examples which will validate the rules used and also the results are shown to the expert to see if they are satisfied. What is “Case Based Reasoning”? Describe the four steps in CBR methods. [15 Marks] b) CBR is a deceptively simple problem solving paradigm that involves matching your current problem against problems that you have solved successfully in the past. The process can be augmented by adapting solutions so they more closely match your current problem. In case-based reasoning (CBR) systems expertise is embodied in a library of past cases, rather than being encoded in classical rules. Each case typically contains a description of the problem, plus a solution and/or the outcome. The knowledge and reasoning process used by an expert to solve the problem is not recorded, but is implicit in the solution. Methods of CBR Exemplar-based reasoning - CBR is seen as a task of classifying a new case into a given set of classes which consists of previously experienced (prototypical) cases. The classes represent the set of possible solutions, and it is therefore not possible to modify a solution. This method is useful for weak theory domains. Instance-based reasoning - A highly syntactic specialization of Exemplar-based reasoning without domain knowledge. Memory-based reasoning - The collection of cases is seen as a large memory, and reasoning consists of accessing and searching the memory. Case-based reasoning - Typical CBR systems have some richness of information, and a certain complexity in its internal organization. It is able to modify, or adapt a retrieved solution when it is used to solve a problem with another context than described in the case. Analogy-based reasoning - Methods that are able to solve problems by using experience from a different domain. IHDCS/KBS/0611 Page 4 of 9 Question 4 a) Describe the major components of a DSS strategic plan. b) [10 Marks] Current Environment Analysis: Here the parameters defined by the existing business model are documented. In the "current environment analysis" phase, an inventory of all reporting aspects is taken. The inventory must include data sources, data production and information accessibility. Business Needs Analysis: The "business needs" analysis is conducted to determine the required information deliverables. A comparison is then made to determine if those needs are being met. Additionally, this phase attempts to document the specific areas where requirement gaps exist. In this phase, the strategy foundation is determined. The business needs analysis phase should be isolated into short-term and long-term categories that contain similar objectives. Action Planning: The action planning phase reviews the gaps identified in the "needs" analysis and determines specific action plans to address them. Additionally, plans are developed to meet the long-term DSS goals of the institution. Once the real issues are understood, the issues are prioritized and alternatives are evaluated. The actions for feasibility and fit within the plan's foundation are then discussed. Once the strategy is agreed upon, key actions to implement the strategy should be evaluated. These actions should not be abstract but real, action-oriented, specific ideas. If possible, return on investment, net present value, or payback period analysis of the proposed actions should be developed. A detailed project plan should be constructed and tracked to ensure the action plans are successful. Implementation: The implementation phase is dedicated to placing the action plans into production. Review and Strategy Monitoring: The DSS strategy team determines a plan review frequency. The plan review meetings should be frequent enough to react to changes in the market and to significant gaps between the business needs and the current environment. The review meetings should recycle through the strategy plans starting with the Gap Analysis stage continuing through the Implementation phase. Describe the process by which decision support systems are developed. [10 Marks] Strategy There are many different ways of developing DSS, each suited to different conditions. These options include quick-hit development of a few specific DSS, phased development of a related series of specific DSS, and development of a full-service DSS generator. The quick-hit approach essentially involves scanning the organization to find easy, rapid development opportunities characterized by willing users, a well-understood problem, and readily apparent fruitful approaches using information technology – in short, low-risk, high=payoff development. The problem with this approach is that development tends to be unplanned, and ad hoc. Different DSS are developed, with no sharing of capabilities or experience. The specific DSS constructed have no general capabilities and may not be adaptable to future problems, forcing total redesign in the near term. IHDCS/KBS/0611 Page 5 of 9 Analysis The purpose of systems analysis in DSS construction is to identify a problem and a set of capabilities that users consider helpful in arriving at decisions about that problem. c) How do you understand Decision Support Systems? [5 Marks] Decision-support systems are interactive computer-based tools used since the 1960s by decisionmakers to help answer questions, solve problems and support or refute conclusions. A decision support system (DSS) is a computer program application that analyzes business data and presents it so that users can make business decisions more easily. It is an "informational application" (in distinction to an "operational application" that collects the data in the course of normal business operation). Question 5 a) Describe the characteristics of expert systems. [10 Marks] Heuristics Expert systems are considered as a branch of AI because the method of problem solving is predominantly based on heuristics. This contrasts very much with the conventional programming paradigm that uses algorithms to solve problems. Representing knowledge using rules As we have already seen, expert systems differ from conventional programming in that they process knowledge rather than data or information. This knowledge is frequently represented in a computer in the form of rules; they store the 'rules of thumb ‘that guide the human expert. The inference engine The real forte of expert systems is their capacity to make inferences or the drawing of conclusions from premises. This is precisely what makes an expert system intelligent. Explanation facilities The ability to explain their reasoning processes are another key feature of expert systems. Such explanation facilities provide the user with a means of understanding the system behaviour. b) Discuss the advantages and disadvantages of using expert systems. [10 Marks] Advantages of Expert Systems Permanence - Expert systems do not forget, but human experts may IHDCS/KBS/0611 Page 6 of 9 Reproducibility - Many copies of an expert system can be made, but training new human experts is time-consuming and expensive If there is a maze of rules (e.g. tax and auditing), then the expert system can "unravel" the maze Efficiency - can increase throughput and decrease personnel costs. Although expert systems are expensive to build and maintain, they are inexpensive to operate. Development and maintenance costs can be spread over many users. The overall cost can be quite reasonable when compared to expensive and scarce human experts. Cost savings: Wages - (elimination of a room full of clerks) Other costs - (minimize loan loss) Consistency - With expert systems similar transactions handled in the same way. The system will make comparable recommendations for like situations. Humans are influenced by recency effects (most recent information having a disproportionate impact on judgment) primacy effects (early information dominates the judgment). Documentation - An expert system can provide permanent documentation of the decision process Completeness - An expert system can review all the transactions, a human expert can only review a sample Timeliness - Fraud and/or errors can be prevented. Information is available sooner for decision making Breadth - The knowledge of multiple human experts can be combined to give a system more breadth that a single person is likely to achieve Reduce risk of doing business Consistency of decision making Documentation Achieve Expertise Entry barriers - Expert systems can help a firm create entry barriers for potential competitors Differentiation - In some cases, an expert system can differentiate a product or can be related to the focus of the firm. Computer programs are best in those situations where there is a structure that is noted as previously existing or can be elicited. Disadvantages of Rule-Based Expert Systems Common sense - In addition to a great deal of technical knowledge, human experts have common sense. It is not yet known how to give expert systems common sense. Creativity - Human experts can respond creatively to unusual situations, expert systems cannot. Learning - Human experts automatically adapt to changing environments; expert systems must be explicitly updated. Case-based reasoning and neural networks are methods that can incorporate learning. Sensory Experience - Human experts have available to them a wide range of sensory experience; expert systems are currently dependent on symbolic input. Degradation - Expert systems are not good at recognizing when no answer exists or when the problem is outside their area of expertise. c) List the different methods of CBR. Methods of CBR [5 Marks] Exemplar-based reasoning - CBR is seen as a task of classifying a new case into a given set of classes which consists of previously experienced (prototypical) cases. The classes represent the set of possible solutions, and it is therefore not possible to modify a solution. This method is useful for weak theory domains. Instance-based reasoning - A highly syntactic specialization of Exemplar-based reasoning without domain knowledge. IHDCS/KBS/0611 Page 7 of 9 Memory-based reasoning - The collection of cases is seen as a large memory, and reasoning consists of accessing and searching the memory. Case-based reasoning - Typical CBR systems have some richness of information, and a certain complexity in its internal organization. It is able to modify, or adapt a retrieved solution when it is used to solve a problem with another context than described in the case. Analogy-based reasoning - Methods that are able to solve problems by using experience from a different domain. Question 6 a) Describe the key areas which should be examined in evaluating Groupware. [10 Marks] Administration You should examine the ease of installation and management of the system across multiple servers. The system must allow remote administration from anywhere on the network. The system should share user and group information among its modules to allow the administrator to make changes and implement security easily. Messaging Standard client e-mail features including text-formatting capabilities, delivery options, attachment support, and user-configurable views are essential. On the server, you expect a single message store, support for multiple directories, and robust routing features. Collaboration It is important to consider discussion groups, rating the ease of posting and editing messages as well as attaching documents. Rate the ability to collapse threads for easy navigation and readability, and require a visual indication of which messages have been read and those that are unread. Scheduling Look for scheduling features for users, groups, and resources that provide time-conflict resolution, free-time searches, and creation of recurring events. Applications development Evaluate the tools for customizing groupware environments for made-to-order applications. Products that include forms designing and scripting tools are preferable. Developers need the ability to access the groupware data stores as well as access external database formats easily. b) Differentiate between verification, validation and evaluation of expert systems. [10 Marks] Verification of an expert system, or any computer system for that matter, is the task of determining that the system is built according to its specifications. Issues raise includes: Does the design reflect the requirements? Are all of the issues contained in the requirements addressed in the design? Does the detailed design reflect the design goals? Does the code accurately reflect the detailed design? Is the code correct with respect to the language syntax? IHDCS/KBS/0611 Page 8 of 9 Validation is the process of determining that the system actually fulfills the purpose for which it was intended. Issues raise include: How well do inferences made compare with knowledge and heuristics of experts in the field? How well do inferences made compare with historic (known) data? What fraction of pertinent empirical observations can be simulated by the system? What fraction of model predictions are empirically correct? What fraction of the system parameters does the model attempt to mimic? Evaluation reflects the acceptance of the system by the end users and its performance in the field. In other words: c) Verify to show the system is built right. Validate to show the right system was built. Evaluate to show the usefulness of the system. Give the definition of Groupware. [5 Marks] Groupware is sometimes seen as a contraction of group working software. Essentially it is networked computer software that lets different people coordinate their work activities. Originally applied almost exclusively to computer conferencing (where users add their own 'conversational' notes to topics of shared interest), the term has been extended to apply to other areas like workflow software and desk-top videoconferencing. Groupware packages are diverse in the functions they offer. Most include a shared database where team members can work on common documents and hold electronic discussions. Some include group schedulers, calendars and/or e-mail. IHDCS/KBS/0611 Page 9 of 9