Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: chirp transform

Sortuj według:

Ogranicz wyniki do:

PCG signal classification using a hybrid multi round transfer learning classifier

Ismail Shahid, Ismail Basit

Biocybernetics and Biomedical Engineering

2023

Vol. 43, no. 1

313--334

Diagnosis of cardiovascular diseases using Phonocardiography(PCG) is a challenging task as signal itself is cyclo-stationary. It has spectral contents which are overlapped by multiple sources having similar spectral contents but acting as noise. Moreover, length variation in the signals and sampling using different equipment also make analysis of these signal a testing task. In this research, authors have introduced a hybrid technique to counter the variations just mentioned. Our technique is composed of high resolution spectrum generation, conversion of spectral contents to Spectrogram and multi round training. Use of fixed length spectral contents makes system independent of signal length. By using Spectrogram, the deep features can be extracted from spectrum which are used as an input to Pre-trained networks (PTNs). Finally, transfer learning is applied with multiple rounds of training. The introduced methodology is validated using multiple datasets having different PCG signals, sampling frequency, signals length and signal quality. From the reported results, it is evident that Chirplet Z transform (CZT) based Spectrogram can be utilized for mutlticlass classification. If CZT based Spectrograms are passed through multi rounds of training, then accuracy can be further increased. The reported results are accurate to 99% in the case of testing for best case scenarios and even in worst case, the results dont fall below 85%. However, an important observation is that they are consistent across the experimental protocols. The computational cost associated with the introduced technique is low which makes it suitable for hardware implementation.

Przetwarzanie sygnałów radarowych w mikroskali czasowej

Pieniężny A., Fornalik J.

Biuletyn Wojskowej Akademii Technicznej

2007

Vol. 56, nr sp.2

341-351

Pojęcie mikroskali czasowej sygnału wynika z natury szybkiej zmienności jego struktury częstotliwościowo-czasowej. Zmienność ta, jako cecha współczesnego kanału radiowego funkcjonującego w sensie obecności urządzeń nadawczo-odbiorczych w przestrzeni propagacji sygnałów, implikuje istotne trudności we właściwej ocenie parametrów sygnału. Pomiar tych parametrów nie napotyka na trudności w przypadkach gdy czas przebywania sygnału w systemie pomiarowym jest relatywnie duży. Natomiast pewna klasa sygnałów, do której należą również sygnały współczesnych radarów, charakteryzuje się zarówno krótkim czasem trwania, jak i małą powtarzalnością w czasie. Zapewnienie wysokiej skuteczności pomiarów oraz przetwarzania ich wyników w warunkach silnych ograniczeń czasowych determinuje konieczność dysponowania odpowiedniej klasy urządzeniem pomiarowym. W artykule przedstawiono problem przetwarzania realnych sygnałów radarowych z zastosowaniem analizatora kompresyjnego, w tym w warunkach jednoczesnego ich występowania.

Basically, the process of radar signals recognition is based on signal time parameters measurement and deinterleaving. The following time parameters are defined as primary parameters: TOA-time of arrival, PW-pulse width, A-amplitude, RF-radio-frequency (carrier frequency) FMOP-frequency modulation on a pulse. Time parameters are associated with DOA-direction of arrival. For each pulse, the specific description, socalled, pulse descriptor word (PDW), containing primary parameters is created. On the basis of PDW, the process of deinterleaving is performed. Signal spectrum (FMOP) is a very good descriptor of a radar signal. This results in a particular interest in several applications to determine it by the use of specialized measurement equipment. The most popular and obvious method, based on modern technology, is to use a digitizing technique and subsequently, the algorithm of fast Fourier transform. Such an approach of signal spectrum evaluation is relatively easy when a signal is not limited in time. The same problem becomes extremely difficult task when short pulsed radar signals are discussed. Facing with that problem, the paper presents a wideband signals compression principle using dispersive delay lines (DDL) made with surface acoustic wave (SAW) technology, to measure instantaneous spectrum of short pulsed radar signals. Basic theory of the problem is described and experimental results are presented.