The problem of improving the reliability of cryptographic data protection in neural network systems with flexible configuration is considered. To ensure the possibility of encrypting/decrypting messages it is proposed to use combinatorial optimization methods for the tasks of forming encoded sequences with improved quality indicators for correcting ability, noise immunity, and autocorrelation properties.
Noise immunity is one of the essential characteristics of modern wireless data reception/transmission systems. In wireless systems such as Wi-Fi, HiperLan, or Bluetooth, the signal is propagated by electromagnetic oscillations in the environment. However, unlike wiring systems, these oscillations are unprotected from external influences. Noise immunity is one of the essential characteristics of modern wireless data reception/transmission systems.
Comparative analysis of the effectiveness of monolithic and cyclic noise protective codes built on "Ideal Ring Bundles" (IRBs) as the common theoretical basis for synthesis, researches and application of the codes for improving technical indexes of coding systems with respect to performance, reliability, transformation speed, and security has been realized. IRBs are cyclic sequences of positive integers, which form perfect partitions of a finite interval of integers. Sums of connected IRB elements enumerate the natural integers set exactly R-times.
The method of synthesis of noise-resistant barker-like code sequences with the use of ideal ring bundles has been improved. The method for fast finding of such noise-like noise-resistant code sequences, which are able to find and correct errors in accordance with the length of the obtained code sequence, has been improved. An algorithm is implemented to quickly find such noise-resistant barker-like code sequences that are able to find and correct errors in accordance with the length of the obtained code sequence.