Knowledge Engineering

Knowledge Elicitation: Process of Acquiring Knowledge

2009-08-06T20:33:00.000-07:00

Knowledge Elicitation is the process of acquiring knowledge about a specific domain. A conceptual model of the domain knowledge is created at the end of the knowledge elicitation process. It is one of the most important and a crucial task of the development of an expert system since it directly has an impact on the overall quality of the system. Knowledge elicitation is also often viewed as the bottleneck in the development of expert systems or knowledge based systems. It is difficult and time consuming activity.

The knowledge is elicited chiefly from experts in the field and data/ information available from published literature. There are various known knowledge elicitation techniques available. The choice of technique to be used in the knowledge elicitation process depends on the nature of the situation within which the knowledge is elicited, the domain knowledge and availability of experts.

The knowledge elicitation process gets tricky as the vast amount of information is often kept inside the heads of domain experts. This makes the entire process complicated as the domain experts may not be willing to disclose the information, due to worries of being sidelined or becoming less important or getting redundant. In certain domains, the domain experts may not even be aware of the tacit knowledge and implicit conceptual models they come to use over many years of experience.

Some of the techniques used in the knowledge elicitation process are as follows:

Documentation Analysis: It is used for orientation and preparation. Documentation is perhaps the most common source of information, as it is often readily available. It helps knowledge engineers to conceptualize unfamiliar content and identify critical concepts in the domain. Documentation should not be the solitary source of information, but it normally supplements other sources of information.

Interviews: Interviews are the oldest and most common tool used for data collection. An interview can be structured or unstructured. Unstructured interviews normally carried out at the early stages of the knowledge elicitation/ modelling process. The structured interviews help to refine the knowledge acquired

Observation: There are two types of observation techniques, obtrusive and unobtrusive observation. In unobtrusive observation, the observer does not interact with the expert in action. The intention is to observe how a task is being performed usually, without disturbing or interfering in any way. The advantage with unobtrusive observation is that the person will carry out the tasks in a typical manner without any interference. Unobtrusive observation may not always be suitable as certain tasks require interaction to understand the reasoning behind certain steps in the process. In obtrusive observation, the observer gets the person to verbalize his thoughts as the task is being performed.

Questionnaires

Protocol analysis

Laddering

Repertory Grid Technique

Card Sorting

Three Card Trick

Twenty Questions Technique

Concept maps and Process maps

Privacy Policy of Knowledge Engineering Blog

2009-04-09T02:01:00.000-07:00

We use third-party advertising companies, like Google, to serve advertisements when you visit our website/ blog. These companies may use information (but not your name, address, email address, or telephone number) about your visits to this and other websites in order to provide advertisements about goods and services of interest to you.

Please take note of the following:

1. Google, as a third party vendor, uses cookies to serve advertisements on this site.

2. Google's use of the DART cookie enables it to serve advertisements to users based on their visits to this site and other sites on the Internet.

3. Users may opt out of the use of the DART cookie by visiting the Google ad and content network privacy policy.

Thanks for your understanding. We hope the information provided in this blog is useful.

What is Optimization?

2008-09-21T22:20:00.000-07:00

Optimization is the process of finding the best solution (optimal solution) for a given problem. It is generally misunderstood that optimization is synonymous to maximization. The truth is that optimization may represent either maximization or minimization depending upon the type of problem at hand.

For example, the problem of finding a solution that provides the maximum profit for a given set of resources and constraints is a maximization problem. The same problem could be modeled as a minimization problem to find a solution that provides the minimum cost for a given set of resources and constraints.

Optimization can be of two types:

Global optimization and

Local optimization

The global optimum is always unique whereas the local optimum could change for every run of the optimization process depending on the initial solution set. While global optimum is desirable, in some cases, it may not be possible to find the global optimum or to verify whether a given solution is the global optimum. Global optimization also requires more computational power.

Even though various optimization techniques exist, the best technique depends on the type of problem, the domain and the business requirements. The following are some of the well known optimization techniques:

Linear Programming

Integer Programming

Mixed-Integer Programming

Constraint Programming

Genetic Algorithms

Simulated Annealing

Hopfield Neural Network

What is Image Thinning?

2008-05-19T15:47:00.000-07:00

Image thinning is the process of reducing the width of a digitised pattern to just a single pixel so that the topological properties are preserved. The output of thinning is called Skeleton. A skeleton provides an abstraction of the global shape of the object. A skeleton normally requires less storage space compared to the original pattern while it preserves the essential structural information of the pattern.

Neural networks has been successfully applied to image thinning problems and pattern recognition applications like Optical Character Recognition (OCR) and medical imaging applications.

Constraints in Genetic Algorithms (GA)

2008-04-28T01:54:00.000-07:00

Most of the real-world optimization problems have constraints. Constraints limit the feasible portion of the search space. Constraints are of two types, hard constraints and soft constraints. Hard constraints are constraints that have to be met at any cost, irrespective of the objective function. Soft constraints are more flexible. A minor violation of the soft constraints may be acceptable if it provides a significant gain in the fitness value. If the soft constraints are not met, then certain level of penalty will be imposed.

Different approaches are used to handle constraints in Genetic Algorithms, some of which are explained below:

Remove infeasible solutions: In this approach, infeasible solutions are simply thrown away. This approach has an advantage that there will be no infeasible solutions in the population. Many seem to believe that penalty functions should be harsh so that Genetic Algorithms will avoid the forbidden spaces. The foundation of Genetic Algorithms theory, however, suggests that Genetic Algorithms optimize by combining partial information from the population. Therefore, this approach can result in valuable information being lost as infeasible solutions may still contain fit schema. Another disadvantage is that the algorithm spends much time in evaluation and rejection of infeasible solutions, especially in highly constrained problems.

Repair infeasible solutions: In this approach, the algorithm converts a solution that violates hard constraints into one that does not. This method replaces infeasible solutions with their repaired equivalent. The disadvantage is that the repair strategies have to be problem specific.

Penalize infeasible solutions: Penalty function methods have been the most popular approach in Genetic Algorithms, because of their simplicity and ease of implementation. In this approach, the algorithm transforms constrained optimization into unconstrained optimization. Depending on the problem and the importance of the constraint, the penalty function can be uniform, polynomial, exponential or stepped. The advantage of this approach is that it can consider infeasible solutions. However, the most difficult aspect of the penalty function approach is to find appropriate penalty parameters needed to guide the search towards the constrained optimum.

Selection in Genetic Algorithms

2008-01-18T20:51:00.000-08:00

We had seen the basic Genetic Algorithms operations in the previous post. In this post, let us see, in detail, how the selection or reproduction operator works.

Selection is the procedure by which candidate solutions are determined for recombination to generate offsprings for the next generation. The chance that a particular candidate solution or string will be selected is based on the string's fitness value.

There are many types of selection operators. For example, a selection operator always selects the fittest individuals and discards the remaining solutions. Depending on the domain, many variants of the selection operators are being used. It is difficult to determine which is better.

The most common selection method used in Genetic Algorithms is the Roulette Wheel Method, which selects the strings statistically based on their relative fitness value, calculated from a fitness function. At the time of offspring creation, a simple spin of the roulette wheel yields the lucky candidate. In Roulette Wheel, highly fit candidate solutions get more chances of being selected for the next generation.

We will see the Roulette Wheel method of selection, in detail, later on.

Basic Genetic Algorithms Operations

2008-01-17T20:53:00.000-08:00

As we had seen earlier, Genetic Algorithms (GA) have a solid basis in genetics and evolutionary biological systems. There are basically two kinds of operations in Genetic Algorithms, that are discussed below.

Genetic Operation: The genetic operation mimics the process of heredity of genes to produce new offsprings in each generation.

Evolution Operation: The evolution operation mimics the process of biological evolution to create the next population from generation to generation.

The Genetic operations include crossover and mutation operators while the evolution operation includes the selection or reproduction operation. We will see these three Genetic Algorithms operators in detail in the next post.

Genetic Algorithms: The Iterative Loop

2008-01-16T00:07:00.000-08:00

Genetic Algorithms iteratively generate new solutions from current set of solutions and replace some or all of the existing population with the newly created members. The iteration of the Genetic Algorithms is explained below:

An initial population of strings is created randomly.

Measure the goodness/ strength of each individual in the population.

Select individuals in the parent pool for the creation of next generation.

New individuals (Offsprings) are created by performing crossover and/ or mutation on the selected individuals.

The new population is tested to see if it satisfies the stopping criteria. If it satisfies, stop the loop; otherwise the next genetic algorithms iteration is performed.

When Should You Use Genetic Algorithms (GA)?

2008-01-15T20:28:00.000-08:00

Genetic Algorithms (GA) are more suitable for the following problems:

Domain knowledge is not sufficient enough to narrow the search space. Genetic Algorithms has overcome the main drawback of expert systems, providing rules.

Problems where the traditional search methods fail.

The search space is vast, complex and poorly understood. Genetic Algorithms are proven to provide robust search in complex search spaces.

What are Genetic Algorithms?

2008-01-14T05:23:00.001-08:00

Genetic Algorithms are search algorithms that exploit the idea of the survival of the fittest. Genetic Algorithms derive their name since it is modeled after genetics and evolution. Genetic Algorithms have been proven to be robust, flexible and efficient in vast complex spaces.

Artificial Intelligence Techniques

2008-01-08T21:48:00.000-08:00

Artificial Intelligence techniques aim at developing intelligent machines, especially smart computer programs. Artificial Intelligence would impart the machines/ programs the capability to mimic human intelligence. The objective of Artificial Intelligence is to make the machines/ programs to keep learning, react to the environment and take decisions on its own without the intervention of humans. The ultimate goal of Artificial Intelligence is to make computer programs to find solutions to problems as well as humans do.

The following are some of the techniques that fall under the category of Artificial Intelligence:

Case Based Reasoning
Rule Based Reasoning
Genetic Algorithms
Fuzzy Systems
Artificial Neural Networks
Intelligent Agents

We will see, in detail, about each of the Artificial Intelligence techniques in our future posts.

CBR Applications

2008-01-04T00:46:00.000-08:00

The following are some applications where Case-Based Reasoning (CBR) has been used:

Fault Diagnosis
Medical Diagnosis
Credit Card Risk Assessment
Design of bridges
Customer Service Hotline
Helpdesk
Troubleshooting Applications

When Should You Use Case Based Reasoning (CBR)?

2008-01-02T20:23:00.000-08:00

Case Based Reasoning (CBR) is more suitable for the following problems:

The problem domain is complex and not amenable to complete mathematical modeling.

An explicit model is extremely difficult to elicit and represent with rules.

Historical data exists within the organization.

The domain experts have considerable difficulty in writing down the decision rules. But, they are comfortable in providing well-proven heuristics and experiences, to incorporate into the case base as cases. They have little difficulty in recalling concrete cases, which they have encountered in the past.

The domain is such that it needs reasoning for the system's solutions.

Case Based Reasoning (CBR) vs Artificial Neural Networks (ANN)

2008-01-01T21:33:00.000-08:00

The main similarity between Artificial Neural Networks (ANN) and Case Based Reasoning (CBR) is that both do not need an explicit model. Both CBR and ANN techniques do not have to go through the knowledge-acquisition bottleneck. ANN is essentially a data mining technique, which can work directly from the data.

But, the main criticism against ANN is that it works as a “Black Box”, so they suffer from a lack of transparency. Validity of the systems decision cannot be judged because of the nature of the inner workings, the output of the network is a function of weighted vectors that depends on the network's architecture and the learning mode used. So, it becomes very difficult to use ANN for diagnosis applications, as most of the diagnosis needs an explanation for the result obtained.

ANN are not suitable when background domain knowledge has to be taken into account, whereas in CBR domain knowledge can be incorporated in the form of knowledge-guided clustering. Neural networks cannot cope with complex structures and in order to perform well the coverage of the domain has to be exhaustive during the "learning" phase. CBR does not need an exhaustive coverage of the domain, as cases can be added to the case-base incrementally.

Case Based Reasoning (CBR) vs Rule Based Reasoning (RBR)

2007-12-23T20:19:00.000-08:00

Rule Based Reaoning (RBR) requires us to elicit an explicit model of the domain. As we all know and have experienced, knowledge acquisition has a set of associated problems. In contrast, Case Based Reasoning (CBR) does not require an explicit model. Cases that identify the significant features are gathered and added to the case base during development and after deployment. This is easier than creating an explicit model, as it is possible to develop case bases without passing through the knowledge-acquisition bottleneck.

Domain experts would have accumulated knowledge over the years through experience. It would be a blunder mistake if we do not use them to our advantage. But the difficulty lies in getting the experts to list down the decision rules which they use. It is a Herculean task to comprehensively recall all the tacit rules which they have come to adopt. However, they usually have little difficulty in recalling concrete cases, which they have encountered in practice. Thus, their mental set appears to be oriented towards a Case Based Reasoning approach.

Developing a CBR system is much faster and easier than constructing a rule-based equivalent. Case bases do not have to be complete when they are deployed for use, as even non-computer experts can add cases to the existing structure.

Maintenance with a Rule Based System may be a nightmare. If the rules are not written clearly, it would lead to many sleepless nights of debugging. Maintenance with Case Based Systems are much easier and straightforward.

When rules are added or deleted from a rule-based system, the system has to be checked for conflicting rules and redundant rules. An addition or deletion of a case from the case base does not any further checking or debugging. But it have to be noted that while it does not affect the system’s functioning, it may have an impact on the outcome of the system.

Problem Approach in CBR

2007-12-22T20:35:00.000-08:00

In an earlier post, we saw what exactly is Case-Based Reasoning (CBR). Here, we are going to see how CBR approaches a problem.

CBR revolves around case base, a database of past cases, that typically contains cases with problem description, possible causes and solutions. Don't confuse yourself with case base and database. They are similar, but not the same. Database works on crisp data and exact solution match, whereas CBR is based on fuzzy match. CBR has the ability to learn and improve, whereas databases do not.

In CBR, a new problem is solved by finding a similar past case, and reusing it in the new problem situation. Note the word similar. CBR would give a solution even if you don't get an exact match. If you accept the solution, then it goes into the case base as another case. If the solution is not accepted, it gives CBR a learning step.

The following four steps summarize how a problem is solved in CBR:

Search for the most similar case (or cases) comparing the present case to the past cases in the case base
Retrieve and Use the case to solve the current problem
Revise and adapt the propose solution if necessary
Save the solution as part of a new case

Do ants leave there saliva?

2007-12-21T07:18:00.000-08:00

This post is mainly to try out a SEO (Search Engine Optimization) technique from Vic at Blogger Unleashed. Vic's new blog was indexed and ranked number one for the term "Do ants scratch there ass?". The same technique was used by Grizz in his post to be ranked number one for the term "Do ants scatch there ass?"

Now, it is my turn to try out the term "Do ants leave there saliva?" You could have noticed the spelling mistakes, but just ignore them. They were intentionally made. I am doing this understanding only half the technique. But, who cares? If I can get the indexing by Google, then it will be a lot better for this blog.

Just ignore this post if you are looking for any tips on Artificial Intelligence or Knowledge Engineering. I will be coming out with posts on the topics related to Artificial Intelligence/ Knowledge Engineering soon.

What is Case Based Reasoning?

2007-12-20T20:20:00.000-08:00

Case-Based Reasoning (CBR) is a problem solving model that is fundamentally different from other major Artificial Intelligence (AI) techniques.

CBR does not rely solely on the general knowledge of a problem domain. CBR is able to make use of the specific knowledge of previously experienced concrete problem situations. These previous situations are referred to as cases in CBR.

CBR uses an incremental approach to sustained learning, since a new experience is retained each time a problem has been solved, making it available for future problems.

In the next post, we will see how to solve problems using CBR.

A blog on Artificial Intelligence

2007-12-19T20:12:00.000-08:00

This is my new blog. Here, I am going to share with you my knowledge on topics like Artificial Intelligence, Knowledge Engineering, Neural Networks, Case Based Reasoning, Intelligent Agents, Rule Based Reasoning, Fuzzy Systems, Genetic Algorithms and other related topics.

I am still in the process of setting up this blog. When the tweaking of the layout is complete, I will start posting the discussions. Until then, good bye.