The development of advanced network simulators for air transport by using fuzzy models and noise-resistant coding

The article analyzes foreign experience and concludes that one of the ways to improve the efficiency of aviation security in the Russian Federation is to use modern network training complexes. A new approach to the assessment of the competence of the aviation security screeners was proposed and tested, that allows to take into account the parameters of the oculomotor activity and heart rate variability of the aviation security screeners being tested, different from the existing approaches using fuzzy classification models. The eye-tracking technology and the device of psychophysiological testing UPFT-1/30 "Psychophysiologist" were used as instruments of psychophysiological monitoring. The basics of automatic generation of fuzzy models such as Sugeno and Mamdani from experimental data are presented. Experimental studies were conducted on the basis of the Ulyanovsk Civil Aviation Institute. The results of the comparison of the generated models showed that the Sugeno model trained with the use of ANFIS-algorithm is more accurate than the Mamdani model and the linear regression model identifies the dependence being studied, according to the competence of aviation security screeners. As a criterion of quality of models on training and test data the average square error is used. The actual problem of choosing an effective concept of noise-resistant coding in the telecommunication component of advanced training complexes is substantiated. The ways of solving the important problem of increasing the reliability of actual digital data in network training complexes based on the use of noise-resistant coding are described. A model of permutation decoder of non-binary redundant code based on lexicographic cognitive map is presented. This model of redundant code decoder uses methods of cognitive data processing in the implementation of the procedure of permutation decoding to effectively protect remote control commands from the influence of destructive factors on the control process