CODEWITHSUNDEEP
setlogicfuzzy-logicfuzzy-comparison
kevinh
kevinh

Reputation: 59

Fuzzy logic - Computing membership function given term set

I am a student studying for a Fuzzy Logic exam, and I have been working my way through the questions about fuzzy sets. However I have just came across an exam question that I do not understand how to do from the lecturer's notes, and was wondering if someone could help me get started:

This is the part of the question I am stuck on:

Subjects of both sexes whose ages ranged from 6 to 72 were asked to class the height of both men and women using the term set of heights: "very very short, very short, short, tall, very tall, very very tall"

        |                      height in centimetres                                   |
Gender  | very very short | very short |   short  | tall  | very tall | very very tall |
--------|-----------------|------------|----------|-------|-----------|----------------|
Male    |        138.7    |   143.1    |   156.8  | 179.4 |    189.5  | 197.7          |     
Female  |        134.8    |   143.0    |   149.2  | 172.9 |    181.4  | 190.9          |

Q) Using the table above, compute the membership function for the set SHORT for the perception of MALE and FEMALE heights.

My thoughts on it:

I have done the other fuzzy set questions from previous exam papers but none are in a form like this.

Usually we are given a universe of discourse (eg animals in the animal kingdom) and are asked to figure out the fuzzy set based on information supplied (eg: penguins are 80% birds), none of the other questions ask about computing the membership function.

I presume it might look like something like slide 83 in the lecture notes, but I'm not sure: https://www.cs.tcd.ie/Khurshid.Ahmad/Teaching/Lectures_on_Fuzzy_Logic/CS4001_FuzzySets_Systems_Properties_Lect_2.pdf

Can anyone help me? Thanks very much.

Upvotes: 0

Views: 523

Answers (1)

palun
palun

Reputation: 38

I suspect the lecturer didn't really mean 'compute' but rather 'construct'. Provided you have no restrictions regarding the type of membership function, you can just use a simple triangular one. For 'short male' you would then have a maximum (1.0) at 156.8 and minima (0.0) at 143.1 and 179.4.

Upvotes: 1

Related Questions