Using the sugeno indistinct implication algorithm for identifying emotions based on the information on the motor units

In order to proceed from the determined through the facial image motor units conjunction to the basic emotion it is required to teach the algorithms of referring the image to express one of the basic emotions with definite intensity — so called classifiers. The article considers the implementation of the MATLAB classifiers by means of the Sugeno indistinct implication using the MATLAB FuzzyLogicToolbox. The application of the MATLAB FuzzyLogicToolbox has certain specific features that determinate the need for prediction. The article examines the algorithm of constructing the fuzzy logic system, the specification of a triangular shape membership function, the rules development and the defuzzification methods. We provide examples of the MATLAB FuzzyLogicToolbox graphic interface.

References

[1] Boyko A.A., Pilipenko M.N., Spiridonov I.N. Opredelenie dvigatel’nykh edinits po videoizobrazheniyu protsessa psikhologicheskogo testirovaniya po metodike R.B. Kettela [Action units detection using video of psychological testing according to R.B. Cattell]. Fizika i radioelektronika v meditsine i ekologii (FREME’2016). Dokl. XII mezhd. nauch. konf. s nauchnoy molodezhnoy sessiey [Physics and radioelectronics in medicine and ecology (FREME’2016). Proc. XII Int. Conf. with Youth Session]. Vladimir, VlGU publ., 2016, pp. 42–46.

[2] Pilipenko M.N., Latysheva E.Yu., Boyko A.A., Spiridonov I.N. Research of algorithms for action units’ automatic detection using facial image. Biotekhnosfera, 2016, no. 6(48), pp. 8–12.

[3] Zadeh L.A. Fuzzy sets. Information and Control, vol. 8, 1965, pp. 338–353.

[4] Zadeh L.A. The concept of a linguistic variable and its application to approximate reasoning. Information Sciences, vol. 9, 1975, pp. 43–80.

[5] Zadeh L.A. The concept of a linguistic variable and its application to approximate reasoning. ERL, 1973, 171 p. (Russ. ed.: Ponyatie lingvisticheskoy peremennoy i ego primenenie k prinyatiyu priblizhennykh resheniy). Moscow, Mir publ., 1976, 167 p.

[6] Zadeh L.A. Fuzzy logic. Computer, vol. 21, no. 4, 1988, pp. 83–93.

[7] Kosko B. Fuzzy systems as universal approximators. IEEE Transactions on Computers, 1994, vol. 43, no. 11, pp. 1329–1333.

[8] Leonenkov A.V. Nechetkoe modelirovanie v srede MATLAB i fuzzyTECH [Fuzzy modeling in MATLAB and fuzzyTECH]. Sankt-Petersburg, BKhV-Peterburg publ., 2003, 719 p.

[9] Kruglov V.V., Dli M.I. Intellektual’nye informatsionnye sistemy: komp’yuternaya podderzhka sistem nechetkoy logiki i nechetkogo vyvoda [Intelligent information systems: computer support of fuzzy logic systems and fuzzy entering]. Moscow, Fizmatlit publ., 2002, 227 p.

[10] Sugeno M. Fuzzy measures and fuzzy integrals: a survey. In: Fuzzy automata and decision processes. North-Holland, 1977, pp. 89–102.

[11] Takagi T., Sugeno M. Fuzzy identification of systems and its applications to modeling and control. IEEE Transactions on Systems, Man and Cybernetics, vol. 15, no. 1, 1985, pp. 116–132.

[12] Rutkovskaya D., Pilin’skiy M., Rutkovskiy L. Neyronnye seti, geneticheskie algoritmy i nechetkie sistemy [Neural networks, genetic algorithms and fuzzy systems]. Moscow, Goryachaya liniya — Telekom publ., 2006, 452 p.