E. S. Sazonov

Learn More
In this paper we propose a novel swallowing sound recognition technique based on the limited receptive area (LIRA) neural classifier and timefrequency decomposition. Time-frequency decomposition methods commonly used in sound recognition increase dimensionality of the signal and require steps of feature selection and extraction. Quite often feature(More)
 The paper presents a hybrid system controller, incorporating a neural and an LQG controller. The neural controller has been optimized by genetic algorithms directly on the inverted pendulum system. The failure-free optimization process stipulated a relatively small region of the asymptotic stability of the neural controller, which is concentrated around(More)
The paper presents a method for failure-free genetic algorithm optimization of a system controller. Genetic algorithms present a powerful tool that facilitates producing near-optimal system controllers. Applied to such methods of computational intelligence as neural networks or fuzzy logic, these methods are capable of combining the non-linear mapping(More)
Non-destructive testing (NDT) is an important area of research, dealing with diagnostic and monitoring the health of structures and structural components and preventing catastrophic failures. One of the recently developed NDT techniques is the method of strain energy mode shapes that allows the determination of changes in structural integrity from changes(More)
An effective technique for extracting an audio input from a composite signal that contains a nonstationary noise-corrupted periodic disturbance is presented. The proposed technique cancels the periodic disturbance using a synthesized signal whose parameters are adjusted adaptively. A combination of a generalized phase-locked loop (PLL) and an adaptive least(More)
Spoken words recognition provides applications like spoken commands recognitions in robotics command, speech based number dialing for phones and mobiles, etc. It also provides applications in railway and banking areas. This work aims at designing of optimal Multilayer Perceptron Neural Network (MLP NN) based classifiers for speaker dependent spoken digits(More)
  • 1