This paper compares two approaches for detecting and analyzing acoustic microwaves in piezoelectric materials, specifically in Lithium Niobate (LiNbO3) substrates. The first method focuses on modeling the propagation of acoustic microwaves in piezoelectric structures, utilizing an interdigital transducer (IDT) to excite the electroelastic waves. This method investigates various wave types, such as secondary surface waves, leaky waves, bulk waves, and skimming bulk waves, and applies wavelet transform for efficient detection. Two wavelet functions—Mexican-hat and Morlet—are compared based on their ability to detect acoustic wave singularities, with an emphasis on their efficiency in processing microwave signals. The second method introduces a machine learning approach using support vector machines (SVM) to detect ultrasonic pulses and identify previously undetectable waves. By classifying real and imaginary parts of the coefficient attenuation and acoustic velocity, this method provides more accurate values and facilitates the modeling of ultrasonic pulse propagation. While the wavelet-based approach focuses on signal processing for wave detection, the SVM-based method excels in detecting complex wave patterns that traditional methods may overlook, offering higher precision in ultrasonic pulse modeling and the realization of acoustic microwave devices.

In this paper, the leaky acoustic microwaves (LAW) in a piezoelectric substrate (Lithium Niobate LiNbO3 Cut Y-X) were studied. The main method for this research was classification using a probabilistic neural network (PNN).The originality of this method is in the accurate values it provides. In our case, this technique was helpful in identifying undetectable waves, which are difficult to identify by classical methods. Moreover, all the values of the real part and the imaginary part of the coefficient attenuation with the acoustic velocity were classified in order to build a model from which we could easily note the Leaky waves. Accurate values of the coefficient attenuation and acoustic velocity for Leaky waves were obtained. Hence, in this study, the focus was on the interesting modeling and realization of acoustic microwave devices (radiating structures) based on the propagation of acoustic microwaves

Feed for word neural networks (FFNN) have attracted a great attention, in digital communication area. Especially they are investigated as nonlinear equalizers at the receiver, to mitigate channel distortions and additive noise. The major drawback of the FFNN is their extensive training. We present a new approach to enhance their training efficiency by adapting the activation function. Adapting procedure for activation function extensively increases the flexibility and the nonlinear approximation capability of FFNN. Consequently, the learning process presents better performances, offers more flexibility and enhances nonlinear capability of NN structure thus the final state kept away from undesired saturation regions. The effectiveness of the proposed method is demonstrated through different challenging channel models, it performs quite well for nonlinear channels which are severe and hard to equalize. The performance is measured throughout, convergence properties, minimum bit error achieved. The proposed algorithm was found to converge rapidly, and accomplish the minimum steady state value. All simulation shows that the proposed method improves significantly the training efficiency of FFNN based equalizer compared to the standard training one.

In this paper, we propose a new method for Bulk waves detection of an acoustic microwave signal during the propagation of acoustic microwaves in a piezoelectric substrate (Lithium Niobate LiNbO₃). We have used the classification by probabilistic neural network (PNN) as a means of numerical analysis in which we classify all the values of the real part and the imaginary part of the coefficient attenuation with the acoustic velocity in order to build a model from which we note the Bulk waves easily. These singularities inform us of presence of Bulk waves in piezoelectric materials.

The Removal of noise and restoration of signals has been one of the most interesting researches in the field of signal processing in the past few year. In this paper, we have tested various deconvolution algorithms proposed in literature, using denoised signal (by wavelets techniques in our case) instead of measured one which is the real signal degraded by measurement procedure. It is very difficult to compare algorithms because the results obtained depend heavily on signal quality (signal-to-noise ratio, sampling), and on algorithm parameters and optimizations. Which criteria should be used to compare signals? Our algorithm which based on Tikhonov-Miller regularization and a model of solution, is a iterative algorithm, gives best results without artifacts and oscillations related to noise, and achieves higher-quality denoising and a high restoration ratio for noisy signal than the existing methods.