CISC-467*Fuzzy Logic
Fall 2019 |
 |
Announcements
Return to menu
Assignment
| Date | Text |
| 20191018 |
Assignment |
Return to menu
Personnel
| Instructor |
Dr. Robin W. Dawes |
 |
| Goodwin 537 |
||
| dawes
AT cs DOT queensu DOT ca |
||
| http://sites.cs.queensu.ca/dawes/ |
||
| 533-6061 (but speaking to me in
person is a much better idea) |
||
| Office Hours: TBA |
| TAs |
Name |
Email |
Office Hours |
Picture |
Return to menu
Course Information
| Calendar
Description |
History of fuzzy theory; fundamental concepts of fuzzy theory: sets, relations, and logic operators. Approximate reasoning, fuzzy inference, possibility theory. Separation from probability. Fuzzy control systems. Fuzzy pattern recognition. Advanced topics may include fuzzy expert systems, financial systems, graph theory, optimization. |
| Suggested Texts |
There is no required text for this course. Here are some suggestions: Fuzzy Logic - Yen and Langari Free PDF texts: Bede - Mathematics of Fuzzy Sets and Fuzzy Logic Chen and Pham - Introduction to Fuzzy Sets, Fuzzy Logic and Fuzzy Control Systems |
| Syllabus |
Introduction (2 weeks)
Fuzzy Logical Operators (1 week)
Fuzzy Inference Systems (2 weeks)
Fuzzy Control Systems (2 weeks)
Fuzzy Implication (1 week)
Applications and Advanced Topics in Fuzzy Logic (4 weeks)
|
| Marking Scheme |
Contributions to
shared knowledge base: 10% Homework: 10% Midterm test: 15% Presentation on advanced topic: 20% Implementation project: 20% Term Paper: 25% |
Return to menu
Schedule
| Class
Schedule |
Monday 1:30 - 2:20 Wednesday 12:30 - 1:20 Friday 11:30 - 12:20 |
All classes are in Jeffery 234 |
||
| Test
Schedule |
Date |
Locations |
Material |
Solutions |
| Midterm |
Wednesday October 30, 12:30 - 1:20 |
Jeffery 234 |
||
Return to menu
Course Plan and Record
Return to menu
Demo Programs
| Date | Description | Source |
| General note:
several of these python source files have .py3 as their
extension. This is because I have set up my IDE to use this
extension to distinguish between Python 2 and Python 3 files.
For obscure reasons, some of the extensions are .py even though all
the programs are written in Python 3. You may want to change
all the extensions to .py |
||
| The Mamdani model for Fuzzy Rule Based Inference systems. This contains class definitions for Clauses, Rules, Rule_Sets, and Piecewise_Functions. A variety of t-norms and s-norms are provided. Rules can be resolved using clipping or scaling. Rule_Sets are defuzzified using the Centre of Mass method. |
Python
3 source code |
|
| Mamdani System for controlling the
depth of water in a tank |
Python
3 source code |
|
| The Sugeno model for Fuzzy Rule Based Inference systems. This is a very simple version of the Sugeno model: all Rule consequents are constants (as opposed to the full Sugeno model in which consequents can be linear combinations of the input variables). |
Python
3 source code |
|
| Sugeno System for controlling the depth of water in a tank - this
is a work in progress! |
Python
3 source code |
|
| T-norm side-by-side comparison, and s-norm side-by-side
comparison. Each of 7 popular t-norms is shown as a matrix of t(x,y) values, with (0,0) in the bottom left corner and (1,1) in the top right. Shades of grey are used to represent the t(x,y) values, with black representing 0 and white representing 1. On the second display screen (reached by clicking anywhere in the image) the corresponding s-norms are displayed. |
Python 3 source code | |
| Implication side-by-side comparison. 11 popular implication operators are shown in the same manner as the t-norms and s-norms in the demo just above |
Python 3 source code | |
| Modus Ponens An implication operator lets us create a relation between a fuzzy set A and a fuzzy set B. the operator satisfies the Modus Ponens criterion if the result of composing A with the A_Implies_B relation is B. This depends on the t-norm and s-norm used to resolve the composition. This demo runs through several well-known implication operators and combines each with a collection of t-norm/s-norm pairs. From the results it is possible to see which combinations satisfy the Modus Ponens criterion. |
Python 3 source code |
Return to menu
Practice Problems
Return to menu
Recommended Readings
| Source |
Section |
Comments |
| Learning
(Your
First Job) |
All |
Essential reading for all students |
| Computer Science For Fun | Any | purely recreational |
Fuzzy Readings
Here is a small collection of tutorials, interesting papers, index pages etc. on fuzzy theory. I have not read all of these (yet). Some may be different versions of the same document, found on different sites and not yet weeded out. Some of these links may no longer connect to documents.
You are encouraged to recommend new links to add to this page.
Return to menu
Sample Test
| |
Return to menu
Sample of Term Papers, etc.
| Sample Term Papers | Sample 1 Sample 2 Sample 3 Sample 4 |
| Sample Implementations | Sample 1 Sample 2 |
| Sample Presentations | Sample 1 Sample 2 |
Return to menu
Academic Integrity in CISC 467
Students are responsible for familiarizing themselves with the regulations concerning academic integrity and for ensuring that their actions conform to the principles of academic integrity. Information on academic integrity is available in the Arts and Science Calendar (see Academic Regulation 1 on the Arts and Science website).
Departures from academic integrity include plagiarism, use of
unauthorized materials, facilitation, forgery and falsification, and are
antithetical to the development of an academic community at Queen's. Given
the seriousness of these matters, actions which contravene the regulation
on academic integrity carry sanctions that include but are not
limited to
- a warning
- loss of grades on an assignment or test
- failure of a course
- requirement to withdraw from the university
Any violation of Academic Integrity in CISC-467 will result in a
grade of 0 on the work involved, and a maximum final grade of 60 in the
course. Repeated violations will result in a final grade of 0.
The preceding text on academic integrity is based on a document written by Prof. Margaret Lamb and is used here with her permission.
Return to menu
557 Goodwin Hall
Queen's University
Kingston, Ontario, Canada
K7L 2N8
Phone: (613) 533-6050
Fax: (613) 533-6513
