0% found this document useful (0 votes)
91 views4 pages

Part-A Q1. How The Knowledge Is Acquired To Make A New Expert System? Ans

The document discusses knowledge acquisition techniques for developing expert systems, including protocol generation, analysis, and more. It also discusses issues with knowledge acquisition such as tacit knowledge being hard for experts to describe. Knowledge elicitation is defined as making implicit knowledge explicit through interviews, simulations, and other methods. Sensor data capturing can help expert systems by organizing data to identify problems and take corrective action. Voice recognition software is provided as an example of an existing expert system, outlining how it works through natural language processing and its benefits for disabled students. Machine learning can impact expert systems by facilitating supervised, unsupervised, and reinforcement learning. Interview methods for knowledge acquisition are also outlined such as structured/unstructured interviews and cognitive structure analysis.

Uploaded by

aryanrajat
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
0% found this document useful (0 votes)
91 views4 pages

Part-A Q1. How The Knowledge Is Acquired To Make A New Expert System? Ans

The document discusses knowledge acquisition techniques for developing expert systems, including protocol generation, analysis, and more. It also discusses issues with knowledge acquisition such as tacit knowledge being hard for experts to describe. Knowledge elicitation is defined as making implicit knowledge explicit through interviews, simulations, and other methods. Sensor data capturing can help expert systems by organizing data to identify problems and take corrective action. Voice recognition software is provided as an example of an existing expert system, outlining how it works through natural language processing and its benefits for disabled students. Machine learning can impact expert systems by facilitating supervised, unsupervised, and reinforcement learning. Interview methods for knowledge acquisition are also outlined such as structured/unstructured interviews and cognitive structure analysis.

Uploaded by

aryanrajat
Copyright
© Attribution Non-Commercial (BY-NC)
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as DOC, PDF, TXT or read online on Scribd
You are on page 1/ 4

Part- A

Q1. How the knowledge is acquired to make a new expert system?


Ans: - The knowledge is acquired from seven techniques to make a new expert system

• Protocol generation
• Protocol analysis
• Hierarchy generation
• Sorting technique
• Limited information & Constrained-processing tasks
• Diagram based technique

Issues in Knowledge Acquisition

• Most knowledge is in the heads of experts


• Experts have vast amounts of knowledge
• Experts have a lot of tacit knowledge
o They don't know all that they know and use
o Tacit knowledge is hard (impossible) to describe
• Experts are very busy and valuable people
• Each expert doesn't know everything
• Knowledge has a "shelf life"

Q2. Why we do knowledge elicitation? Is there any use of it? Give your opinion.
Ans: - Knowledge elicitation
Making implicit (not tacit) knowledge explicit - helping experts recall, test and refine their rules-of-thumb,
heuristics and working practices. This can take the form of interviews, simulation, card sorting, concept
mapping.Knowledge Elicitation (KE) is the process of bringing out the knowledge from people's mind (both
conscious and sub-conscious) through expression, story telling or the articulation of what we know.
Expressing what is in our sub-conscious mind is very difficult but possible.Knowledge Elicitation (KE)
methods have been used to obtain the information required to solve problems. These methods can be
classified in many ways. One common way is by how directly they obtain information from the domain
expert. Direct methods involve directly questioning a domain expert on how they do their job. In order for
these methods to be successful, the domain expert has to be reasonably articulate and willing to share
information. The information has to be easily expressed by the expert, which is often difficult when tasks
frequently performed often become 'automatic.' Indirect methods are used in order to obtain information that
can not be easily expressed directly.

KE Methods by Interaction Type

• Interviewing
• Case Study
• Protocols
• Critiquing
• Role Playing
• Simulation
• Prototyping
• Teachback
• Observation
• Goal Related
• List Related
• Construct Elicitation
• Sorting
• Laddering
• 20 Questions
• Document Analysis

Q3. How sensor data capturing is helpful in making an expert system?


Ans:-

Agent Data Sensor

Environment

Capturing, organizing, and processing sensor data into usable and timely information can help your
company analyze and track key performance metrics through your entire system, identify problems early
on, take immediate corrective action and save money.

Part-B

Q4. Describe the working of any one existing expert system.


Ans:-

Voice Recognition Software for Disabled Students


How does Voice Recognition Software Work

Voice recognition software uses a type of artificial intelligence technology called natural language
processing, or NLP. NLP stores a vast database of information, and compares input to that information in
order find a corresponding piece of data.

In order to recognize human speech, the program has to have a variety of different pronunciations on file for
each word. As each word is spoken, the program compares it to all of the similar words on file, and chooses
the best match.

Voice-to-Text Software

Voice-to-text software can help a disabled student with a variety of school-related tasks. In the classroom
and at home, using speech recognition software is helpful for these students.

• Taking notes: Students with dyslexia, vision impairments, or motor control issues often have trouble
with note-taking. This places them at a disadvantage for homework, tests, or even classroom
participation. Voice-to-text software translates the teacher's lecture into notes for the student,
eliminating the problem.
• Written coursework: These same students can use the voice recognition software to answer
homework questions, take tests, or compose essays.

Voice-to-Sign Language Software

In addition to voice-to-text translation, natural language processing algorithms are now able to translate the
spoken word into both text and visual sign language. The iCommunicator program, for example, is
essentially a real-time translation program for anyone with hearing impairments.

Using this type of software, the hearing impaired can communicate with anyone, even when a sign-language
interpreter is not available. The software translates the spoken word into sign language and text, and then
translates the user's typed response into a computer-generated voice.

Benefits of AI Technology for Disabled Students

The use of natural language processing allows voice recognition technology to translate human speech into
text, sign language or even another spoken language. This gives disabled students the same opportunities as
the other students, and increases effective communications in the classroom.

Q5. What impact can machine learning technologies have on expert system?
Ans:-

Machine learning is a method of automated knowledge creation or refinement of knowledge through


computer program.

Learning works in two main ways:

1. Supervised
2. Unsupervised
3. Reinforcement learning

Supervised learning has an objective function that is a dependent variable and uses historical data also
known as training data to learn the rules that classify a set of independent variables into the class of the
dependent variable.

Unsupervised learning discovers the implicit relationships between a collection of data and evolves the
rules that describe the changes of behavior in the variables that seem to have the greatest causal impact
on other variables.

In reinforcement learning, external trainer will provide the training in form of signals on the basis of
which system operates.

Q6. What is the process of interview? Give proper examples of various methods of
interviewing?
Ans:-

Process of interview consists of asking questions from domain expert and how they perform the task. It can
be structured, unstructured, and semi- structured. Success of interview depends on the questions asked &
knowledge of expert in that domain.

Interviewing methods are:

 Interviewing – structured, semi- structured, unstructured. It is a direct method in which procedures


are followed.
 Interruption analysis - it uses problem solving strategies.
 Cognitive structure analysis – it have content of knowledge structure & it is representational format
of experts’ knowledge.
 Tutorial interview – whatever expert is taught is asked in an interview.
 Questionnaire – sequence of questions or tasks are given which will cause & effect relationships.
 ACT-based representation of knowledge – it is combination of methods & it includes production
rules describing goal relationship.

You might also like