As far as I know, it is not necessary to have all the inputs and outputs in a rule. For example, in your system a rule can have only 2 inputs which are along with at least one output. This can be applied in the Matlab fuzzy logic toolbox as well.

Hope it could help you.

Hi Nabila Hamdaoui, as mentioned Mahdieh, it is unnecessary to involve all inputs and outputs. But the following should give you the illustration of number of rules required for a 6-input fuzzy system:

If you are using the grid partitioning technique to generate the rules, you will have 64 (26) rules for each input with 2 MFs, or 729 (36) rules for each input with 3 MFs.

If you have the "gameplay" data, you can reduce the number of rules substantially by using the subtractive clustering technique.

If you have the experts to define the number of MFs and the rules, then the number of rules can be arbitrarily large or arbitrarily small. It depends!

I agree with Mahdieh. It is not necessary to include all inputs and outputs in a rule. You need at least one input and at least one output to create a rule.

For maximum number of rules possible, it is dependent on the number of membership functions of the inputs and outputs. The minimum number of rule(s) required to produce an output is one. And that would most likely result in an output of zero for some input conditions except that lone rule covers the entire range of input data.

Thank you very much for your responses. They are very helpful.

In your problem you have 4 outputs. Then you can partition the problem in 4 1-output sub-problems, each sub-problem referring to 1 player-type and you may construct the individual fuzzy-models separately. How many inputs should have a fuzzy model? It should have all significant inputs for recognizing a particular player type. Thus, it is possible that inputs in each player-model will be different. It is also possible that single rules will have different sets of inputs. But the model as a whole should be satisfactorily precise.

Hi is not imperative include all inputs and outputs. Exists models that are updated in the training phase.

you can model the system with a few rules such as mentioned in:

o Montes Dorantes P.N., Mexicano Santoyo A, Méndez G.M. (2018). Modeling Type-1 Singleton Fuzzy Logic Systems using statistical parameters in foundry temperature control application. Smart and Sustainable Manufacturing systems ASTM. 2(1), pp. 180-203. DOI: 10.1520/SSMS20180031

o Montes Dorantes P, Jiménez Gómez M., Mexicano Santoyo A., Mendez G.M. (2017). Fuzzy look-up table for knowledge management and decision making.

Educational Alternatives 15, pp. 181-191.

o Montes Dorantes P.N., Jiménez Gómez M.A, Mexicano Santoyo A., Méndez G.M. (2017). Measurement's noise, filtered by a type-1 neuro-fuzzy technique in quality assurance. International Journal of advanced Manufacturing technology (IJAMT, Springer), 92(1), pp. 755-763. DOI: 10.1007/s00170-017-0151-2. ISSN 02683768

o P. N. M. Dorantes and G. M. Méndez. (2016). Type-2 Fuzzy Logic Systems for Temperature Evaluation in Ladle Furnace. IEEE LATIN AMERICA TRANSACTIONS. IEEE LATIN AMERICA TRANSACTIONS, 14(8), pp. 3914-3920. DOI: 10.1109/TLA.2016.7786380. ISSN 15480992

o P. N. M. Dorantes and G. M. Méndez. (2015). Non-iterative Radial Basis Function Neural Networks to Quality Control via Image Processing, IEEE LATIN AMERICA TRANSACTIONS, 13(10), pp. 3457-3451. DOI: 10.1109/TLA.2015.7387253. ISSN 15480992

o Montes Dorantes P.N., Jiménez Gómez M.A, Méndez G.M. , Nieto González J.P., de la Rosa Elizondo J. (2015). One step models for soft computing techniques. Industrial application to image processing in quality assurance process. International Journal of advanced Manufacturing technology (IJAMT, Springer), 81(5), pp.771-778. DOI: 10.1007/s00170-015-7101-7

o P.N. M. Dorantes, J. P. N. González and G. M. Méndez. (2014). Fault Detection Systems via a Novel Hybrid Methodology for Fuzzy Logic Systems Based on Individual Base Inference and Statistical Process Control. IEEE LATIN AMERICA TRANSACTIONS, 12(4), pp. 706-712. DOI: 10.1109/TLA.2014.6868873. ISSN15480992

o Montes Dorantes P. N., Nieto González J.P., Praga-Alejo R., Guajardo Cosio K.L., Méndez G.M. (2014). Sistema inteligente para procesamiento de imágenes en control de calidad basado en el modelo difuso singleton tipo 1. Research in Computing Science 74, pp. 117-130.

Regards

Pascual.

Thank you very much @Pascual for all those references