How many rules we need?
3 views (last 30 days)
Show older comments
Hello, How can determine how many rules and fuzzy sets we need in our fuzzy system? Is by increasing the rules and fuzzy sets, the system would be better? How can we determine how many rules and fuzzy sets we need actually for better results? Thanks
0 Comments
Answers (1)
Walter Roberson
on 31 May 2016
2 Comments
Walter Roberson
on 31 May 2016
For the best accuracy, you should have one rule for each possible combination of inputs. For example, if you have two inputs, each of which are floating point numbers in the range 1 (included) to 2 (excluded), then for the best accuracy you should have (2^53)^2 = 2^106 rules. 2^53 is the number of different representable floating point numbers between 1 (included) and 2 (excluded).
See Also
Categories
Find more on Fuzzy Inference System Modeling in Help Center and File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!