Introduction to knowledge-based systems

Introduction to knowledge-based systemsDr. Zahoor TanoliXahoor@gmail.com1Course Objectives2To set a research focus, learning about practical problems, research challenges

And

To come up with a version of a research paper, depending on your interest, you can work on more than one papers General InformationDiscussion / mailing listCIIT-Attock-KBS-Fall15Discussions, queries, announcements, , everything!

Course ScheduleLecturesMonday: 5:00 to 8:00 PMAssignments20%Multiple assignmentsQuizzes / Project10%Random quizzes throughout semester Practical projects by each individual20%Final exam50%

Grading PolicyRelative marking: grades are given according to the class standing of a studentGrading will follow the bell shaped curve, as much as possibleAverage marks of the class will be approx centered around grade BApprox 10% of the top students will get grade AAssignmentsIts your responsibility to regularly check the course Googlegroup for important notificationsAssignments will usually contain three parts:Questions on course topicsQuestions on research papersProgramming and model buildingSubmission date given with each assignLate assignment is not acceptedPlagiarism will not be toleratedAcademic HonestyYour work in this class must be your ownFor the first infraction, all involved students will receive 0 marksIf they are found to have collaborated excessively or to have cheatede.g. by copying or sharing answers during an assignment, project or examinationFurther infractions will result in failure in the course

Overview of the courseThis course is about knowledge-based systemsexpert systemsknowledge systems. - three different terms which mean more or less the same thing.One could also say that it is about applied artificial intelligence.2KBSs & KnowledgeWhat is a knowledge-based system?A system which is built around a knowledge base. i.e. a collection of knowledge, taken from a human, and stored in such a way that the system can reason with it.What is knowledge?Knowledge is the sort of information that people use to solve problems. 3KnowledgeKnowledge includes:facts, concepts, procedures, models, heuristics, examples.Knowledge may be:specific or generalexact or fuzzyprocedural or declarative4Expert systemsWhat is an expert system?A particular kind of knowledge-based systemOne in which the knowledge, stored in the knowledge base, has been taken from an expert in some particular field.Therefore, an expert system can, to a certain extent, act as a substitute for the expert from whom the knowledge was taken.5Artificial intelligenceWhat is Artificial Intelligence?Artificial Intelligence (AI) is concerned with exploring such aspects of human (and other animal) mental activity as:understanding creativityperception problem-solvingconsciousness using languageintelligenceby simulating them using computers. 6It is therefore closely connected with such social sciences as:psychologylinguisticsphilosophy7Applied artificial intelligenceWhat is applied AI?Applied AI is concerned with producing software which is intelligentIt is intelligent in that it is based on what we know about human reasoning and other mental abilitiesWe are therefore talking about a branch of advanced computing - computer technology - rather than social science8Knowledge engineeringThe term knowledge engineering is often used to mean the process of designingbuildinginstallingan expert system or other knowledge-based system.Some authors use the term to mean just the knowledge acquisition phase.9ExpertsAn expert is an experienced practitioner in his/her particular field. More than that, he/she is a highly effective problem-solver and decision-taker in that field.Experts have three qualities:They make good decisionsThey make those decisions quicklyThey are able to cope with a wide range of problems.10As a result, they are valuable, highly-paid, and tend to be overworked.11Experts and expert systemsNote that:The task that an expert system performs will generally be regarded as difficult.An expert system almost always operates in a rather narrow field of knowledge. The field of knowledge is called the knowledge domain of the system.There are many fields where expert systems can usefully be built.There are many fields where they cant.12Experts and expert systemsNote also that an expert can usuallyexplainand justifyhis/her decisions.13Reasons for building an E.S.One might build an expert system for any or all of the following reasons:To archive an experts knowledge, to insure against the day when he/she leaves, or retires, or dies.To disseminate his/her knowledge, so that it is available in more (possibly many more) places than the location of the expert.To ensure uniformity of advice/decisions. As a basis for training other specialists.14Advantages of expert systemsPut another way, E.S. have the following advantages over human experts:The knowledge is permanentThe knowledge is easily replicatedThe knowledge is represented explicitly, and can be evaluatedThe system is consistent - whereas human practitioners have bad days, computers dont.Once built, running costs are low15Disadvantages of expert systemsDeveloping an expert system usually costs a great deal of time & moneyHistorically, there has been a high failure rate in E.S. projectsThe project may well fail during development - most likely during the knowledge acquisition phase.The development may succeed, but the organisation may fail to accept and use the finished system. 16Disadvantages of expert systemsA human expert can update his/her knowledge in the light of Common sense Knowledge derived from other domain Contacts with other experts. An expert system cant.

17Application areas of KBSIndustrial Control and MonitoringFault DiagnosisRobotics Image ProcessingMachine & Computer VisionMedical & Diagnostic SystemsFinancial & Stock Market Monitoring and PredictionSpeech Processing and SynthesisNatural Language ProcessingEnvironmental MonitoringHigh Voltage SystemsEngine Control and Vehicle ApplicationsIntelligent Signal Processing

Choosing a KBS and ES projectBecause of cost, and the danger of failure, it is important that KBS and E.S. projects are carefully chosen.18Choosing a KBS and ES projectThe expense must be justified, in the light of the possible benefits.E.S. technology must be appropriatethe right kind of expertise is involvedit isnt a problem which conventional programming could do better.Management, and the participants, must support the project fully.18The phone call testA rather simpler approach to answering the question which domains are worth building into an expert system?Any problem that can be and frequently is solved by your in-house expert in a 10-30 minute phone call can be automated as an expert system.Prof.Morris Firebaugh22Possible KBS and ES - case historiesFor discussion. The following seven problem areas may, or may not, be suitable for building knowledge base and developing an expert systems.23Possible KBS and ES - case historiesA certain third world country has a large population, very few trained doctors, and insufficient resources to train many more. It is proposed to provide paramedics, who can be trained relatively cheaply and easily, with medical kits and portable PCs, each PC to be loaded with KBS and ES that can advise on the diagnosis and treatment of a variety of common diseases.24Possible KBS and ES- case historiesThe housing department in capital is overworked, although the staff turnover is quite low. Much of the work the staff do involves interviewing clients, and there is a clear pattern of questioning (which varies to a limited degree, depending on the circumstances of the client). It is proposed to build KBS, which will direct the questioning process.25Possible KBS and ES - case historiesA firm of perfume importers relies heavily on its chief perfume expert, who is skilled at selecting perfume that are destined to be popular, on the basis of their smell and long lastingness. She is soon to retire Proposed to build KBS that will enable any of several junior perfume specialists to do their job26Possible KBS and ES- case historiesAn education authority has a severe shortage of primary school teachers. It is proposed that KB should be built which can facilitate to do the job of teaching English and arithmetic to five year old children27Possible KBS and ES - case historiesA software company proposes to build an expert system which can perform book-keeping for small commercial concerns.28Possible KBS and ES- case historiesA large manufacturer of diesel electric locomotives has problems in providing enough maintenance personnel who are sufficiently skilled to locate faults in these (highly complex) locomotives They propose to build knowledge base and ES which can perform fault location on such a machine29Possible KBS and ES- case historiesA mineral exploitation company wishes to extend its operations, which involveSearching for undiscovered deposits of valuable metal ores. Shortage of trained geologists Build a knowledge base using geological sites Come to a conclusion about how likely it is that there is a worthwhile mineral deposit there30Future Research ProjectsAgent-Based Models to Support Pandemic PlanningThe goal of this research is to build agent-based models of infectious diseases spread, based on key cohorts and data from previous epidemics. Informed by census data on population profiles and area densities,The models need to be calibrated and refined to support policy planning, in terms of vaccination and social distancing measures.

Contextualized web browsingModern web browsers are able to predict surf targets, and various web annotation tools augment the presentation of web pages with a second layer of information (e.g., notes, ratings or discussions about content on that page). No efficient and comprehensive approach to the automated discovery of context information exists yet. Such context information includes (but is not restricted to) background knowledge (e.g., from Wikipedia or online databases), information about provenance, history and follow-ups of information on the respective page (e.g., news articles). In this student project, a framework for the automated or semi-automated (interactive) discovery and presentation of context information using state-of-the-art machine learning / data mining and linked data technologies should be developed and implementedNew Methods for Probabilistic Anomaly Detection in Real Time

There is an increasing need to analyze multiple streams of data in real time. The goal of this work is to develop new techniques and tools to respond to this need. This project will focus on the task of detecting anomalies/outliers in data in real time. This has applications in medicine, chemistry, engineering and many other disciplines.

Social Media Analysis and ToolsThe advent of Social Media sites offers many new sources of data to analyses and use in novel ways. We have now available a vast amount of information about people, brands and corporations what they say and what is said about themwho they connect to and who connects with them how they respond to events and become authorities on events Wars, sport, elections, floods can all be viewed through the lenses of social media activity.In particular, sentiment analysis techniques can be applied to analyze the influence and reach of brands and people. This analysis will most likely involve the following steps: gathering data from a social media forum (e.g. Twitter) categorizing and clustering the data based on features and on sentiment and identifying trends in the data.