Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "time-frequency analysis" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 26
Tytuł:
The synchrosqueezing method in bearing estimation of stationary signals for passive sonar with towed array
Autorzy:
Czarnecki, K.
Leśniak, W.
Powiązania:
https://bibliotekanauki.pl/articles/332264.pdf
Data publikacji:
2015
Wydawca:
Polskie Towarzystwo Akustyczne
Tematy:
reassignment method
time-frequency analysis
direction of arrival
Opis:
In this paper a novel method of the bearing estimation in a passive sonar system with a towed array is introduced. The classical approach of the bearing estimation based on the spatial spectrum is extended by using the synchrosqeezing method that is a part of the reassignment method introduced by Kodera et al. The usage of this method leads to the precise bearing estimation. The proposed method requires a relatively small amount of computation, because of possibility of using the FFT algorithm. Moreover, method immunity against AWGN is tested for a selected sonar array having regard to the direction of arrival and the signal frequency.
Źródło:
Hydroacoustics; 2015, 18; 41-46
1642-1817
Pojawia się w:
Hydroacoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Deep learning-based CNC milling tool wear stage estimation with multi-signal analysis
Autorzy:
Karabacak, Yunus Emre
Powiązania:
https://bibliotekanauki.pl/articles/27312777.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
wear stage estimation
milling
convolutional neural network
time-frequency analysis
Opis:
CNC milling machines are frequently used in the manufacturing of mechanical parts in the industry. One of the most important components of milling machines is the cutting tool. Monitoring the cutting tool wear is important for the reliability, continuity, and quality of production. Monitoring the tool and detecting the stage of wear are difficult processes. In this work, the convolutional neural network (CNN), which is a deep learning method in which the features are extracted by an inner process, was performed to detect the wear stages of the milling tool. These stages that define the total lifespan of the tool are known as initial wear (IW), steady-state wear (SSW), and accelerated wear (AW). Short Time Fourier Transform (STFT) was applied to signals, and signal spectrograms were used to train CNN models with different complex architectures. Vibration signals, acoustic emission signals, and motor current signals from The Nasa Ames Milling Dataset were used to obtain the spectrograms. Pre-trained CNNs (GoogleNet, AlexNet, ResNet-50, and EfficientNet-B0) detected the tool wear stage with varying accuracies. It has been seen that the time duration of model training increases as the size of the dataset grows and the network architecture becomes more complex. The recommended method has also been tested on the 2010 PHM Data Challenge Dataset. CNN shows promise for condition monitoring of milling operations and detecting tool wear stage.
Źródło:
Eksploatacja i Niezawodność; 2023, 25, 3; art. no. 168082
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
The Defect Detection in Ceramic Materials Based on Time-Frequency Analysis by Using the Method of Impulse Noise
Autorzy:
Akinci, T. C.
Powiązania:
https://bibliotekanauki.pl/articles/177471.pdf
Data publikacji:
2011
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
impulse noise
time-frequency analysis
defect detection in ceramic materials
Opis:
In this study, it was achieved by using the method of impulse noise to detect internal or surface cracks that can occur in the production of ceramic plates. Ceramic materials are often used in the industry, especially as kitchenware and in areas such as the construction sector. Many different methods are used in the quality assurance processes of ceramic materials. In this study, the impact noise method was examined. This method is a test technique that was not used in applications. The method is presented as an examination technique based on whether there is a deformation on the material according to the sound coming from it as a result of a plastic bit hammer impact on the ceramic material. The application of the study was performed on plates made of ceramic materials. Here, it was made with the same type of model plates manufactured from the same material. The noise that would occur as a result of the impact applied on a point determined on the materials to be tested has been examined by the method of time-frequency analysis. The method applied gives pretty good results for distinguishing ceramic plates in good condition from those which are cracked.
Źródło:
Archives of Acoustics; 2011, 36, 1; 77-85
0137-5075
Pojawia się w:
Archives of Acoustics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Time–frequency Analysis of the EMG Digital Signals
Autorzy:
Kuniszyk-Jóźkowiak, W.
Jaszczuk, J.
Sacewicz, T.
Codello, I.
Powiązania:
https://bibliotekanauki.pl/articles/106250.pdf
Data publikacji:
2012
Wydawca:
Uniwersytet Marii Curie-Skłodowskiej. Wydawnictwo Uniwersytetu Marii Curie-Skłodowskiej
Tematy:
time-frequency analysis
EMG signal
Fast Fourier Transform
predictive analytics
wavelet analysis
Opis:
In the article comparison of time-frequency spectra of EMG signals obtained by the following methods: Fast Fourier Transform, predictive analysis and wavelet analysis is presented. The EMG spectra of biceps and triceps while an adult man was flexing his arm were analysed. The advantages of the predictive analysis were shown as far as averaging of the spectra and determining the main maxima are concerned. The Continuous Wavelet Transform method was applied, which allows for the proper distribution of the scales, aiming at an accurate analysis and localisation of frequency maxima as well as the identification of impulses which are characteristic of such signals (bursts) in the scale of time. The modified Morlet wavelet was suggested as the mother wavelet. The wavelet analysis allows for the examination of the changes in the frequency spectrum in particular stages of the muscle contraction. Predictive analysis may also be very useful while smoothing and averaging the EMG signal spectrum in time.
Źródło:
Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica; 2012, 12, 2; 20-25
1732-1360
2083-3628
Pojawia się w:
Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Inter-harmonic parameter identification method based on transform with local maximum spectrum
Autorzy:
Sun, Lin
Song, Jing
Jin, Yan
Powiązania:
https://bibliotekanauki.pl/articles/2042793.pdf
Data publikacji:
2022
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
inter-harmonic
parameter identification
power system
synchrosqueezed transform
time-frequency analysis
Opis:
In order to improve the detection accuracy of harmonics/inter-harmonics in power systems, a new method of harmonic/inter-harmonic detection based on synchrosqueezed transform and the Hilbert operator based on local spectrum maximum is proposed. Firstly, the spectrum of inter-harmonic signals is obtained through short-time Fourier transform, and the local maximum value of the spectrum in the frequency direction is detected. Then, based on the maximum frequency of the spectrum, a new frequency redistribution operator and synchronous extraction operator are constructed. It combines the operators with ridge detection for the decomposition of harmonic/inter-harmonic signals, so as to obtain a series of intrinsic mode function (IMF) components. Finally, the instantaneous amplitude and frequency of the IMF components is obtained by using the Hilbert operator. Meanwhile, according to the instantaneous frequency mutation point in the spectrum, the starting and ending time of transient harmonics/inter-harmonics is located accurately. Based on a low signal-to-noise ratio (SNR), the wavelet packet method (WP), Hilbert Marginal Spectrum method (HMS), synchrosqueezing wavelet transform method (SST), the Hybrid SST method (HSST), enhanced empirical wavelet transform (EEWT) and the proposed method are used to identify the harmonic/inter-harmonic parameters, respectively. The experimental results show that the proposed LMSST method can effectively separate the steady-state and transient harmonic/inter-harmonic signals, and has higher detection accuracy and better noise robustness.
Źródło:
Archives of Electrical Engineering; 2022, 71, 1; 189-209
1427-4221
2300-2506
Pojawia się w:
Archives of Electrical Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Time-frequency Representation -enhanced Transfer Learning for Tool Condition Monitoring during milling of Inconel 718
Autorzy:
Zhou, Yuqing
Sun, Wei
Ye, Canyang
Peng, Bihui
Fang, Xu
Lin, Canyu
Wang, Gonghai
Kumar, Anil
Sun, Weifang
Powiązania:
https://bibliotekanauki.pl/articles/24200823.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
tool condition monitoring
time-frequency analysis
Markov Transition Field
transfer learning
Opis:
Accurate tool condition monitoring (TCM) is important for the development and upgrading of the manufacturing industry. Recently, machine-learning (ML) models have been widely used in the field of TCM with many favorable results. Nevertheless, in the actual industrial scenario, only a few samples are available for model training due to the cost of experiments, which significantly affects the performance of ML models. A time-series dimension expansion and transfer learning (TL) method is developed to boost the performance of TCM for small samples. First, a time-frequency Markov transition field (TFMTF) is proposed to encode the cutting force signal in the cutting process to two-dimensional images. Then, a modified TL network is established to learn and classify tool conditions under small samples. The performance of the proposed TFMTF-TL method is demonstrated by the benchmark PHM 2010 TCM dataset. The results show the proposed method effectively obtains superior classification accuracies for small samples and outperforms other four benchmark methods.
Źródło:
Eksploatacja i Niezawodność; 2023, 25, 2; art. no. 165926
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Electrochemical grinding of titanium-containing materials
Autorzy:
Przystupa, K.
Litak, G.
Powiązania:
https://bibliotekanauki.pl/articles/102219.pdf
Data publikacji:
2017
Wydawca:
Stowarzyszenie Inżynierów i Techników Mechaników Polskich
Tematy:
hybrid processes
electrochemical grinding (ECG)
micro short-circuit
time-frequency analysis
Opis:
The paper focuses on machining difficult-to-cut materials where a significant component is titanium. The paper discusses a complex process of electrochemical grinding (ECG). A practical example was given by discussing the results of ECG. Selected difficult-to-cut materials, along with their typical ECG properties, were compared. In addition, the paper discusses the phenomenon of micro short-circuits constituting a form of an interference characteristic for the process. The results presented in the paper refer to the phenomenon of a micro short-circuits, i.e. the case when a rapid and uncontrolled electrical discharge occurs in the machining zone. The paper presents examples of recorded micro short-circuits and attempts a time-frequency analysis regarding the occurrence of the disturbance. To reveal the dynamics of the ECG process we applied wavelet analysis.
Źródło:
Advances in Science and Technology. Research Journal; 2017, 11, 4; 183-188
2299-8624
Pojawia się w:
Advances in Science and Technology. Research Journal
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Generative modelling of vibration signals in machine maintenance
Autorzy:
Puchalski, Andrzej Adam
Komorska, Iwona
Powiązania:
https://bibliotekanauki.pl/articles/28086927.pdf
Data publikacji:
2023
Wydawca:
Polska Akademia Nauk. Polskie Naukowo-Techniczne Towarzystwo Eksploatacyjne PAN
Tematy:
time-frequency analysis
condition monitoring
anomalies detection
deep generative models
variational autoencoder
data distribution
Opis:
The exponential development of technologies for the acquisition, collection, and processing of data from real-world objects is creating new perspectives in the field of machine maintenance. The Industrial Internet of Things is the source of a huge collection of measurement data. The performance of classification or regression algorithms needs to take into account the random nature of the process being modelled and any incomplete observability, especially in terms of failure states. The article highlights the practical possibilities of using generative artificial intelligence and deep machine learning systems to create synthetic measurement observations in monitoring the vibrations of rotating machinery to improve unbalanced databases. Variational AutoencoderVAE generative models with latent variables in the form of high-level input features of time-frequency spectra were studied. The mapping and generation algorithm was optimised and its effectiveness was tested in the practical solution of the task of diagnosing the three operating states of a demonstration gearbox.
Źródło:
Eksploatacja i Niezawodność; 2023, 25, 4; art. no. 173488
1507-2711
Pojawia się w:
Eksploatacja i Niezawodność
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
An uncertainty principle related to the Poisson summation formula
Autorzy:
Gröchenig, K.
Powiązania:
https://bibliotekanauki.pl/articles/1221102.pdf
Data publikacji:
1996
Wydawca:
Polska Akademia Nauk. Instytut Matematyczny PAN
Tematy:
uncertainty principle
Poisson summation formula
unimodular polynomial
modulation space
time-frequency analysis
phase space
Opis:
We prove a class of uncertainty principles of the form $∥S_{g}f∥_{1} ≤ C(∥x^{a}f∥_{p} + ∥ω^{b}f̂∥_{q})$, where $S_{g}f$ is the short time Fourier transform of f. We obtain a characterization of the range of parameters a,b,p,q for which such an uncertainty principle holds. Counter-examples are constructed using Gabor expansions and unimodular polynomials. These uncertainty principles relate the decay of f and f̂ to their behaviour in phase space. Two applications are given: (a) If such an inequality holds, then the Poisson summation formula is valid with absolute convergence of both sums. (b) The validity of an uncertainty principle implies sufficient conditions on a symbol σ such that the corresponding pseudodifferential operator is of trace class.
Źródło:
Studia Mathematica; 1996, 121, 1; 87-104
0039-3223
Pojawia się w:
Studia Mathematica
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Analysis of signal of X4 unmanned aerial vehicle
Autorzy:
Mięsikowska, M.
Nowakowski, M.
Lorenc, W.
Chodnicki, M.
Powiązania:
https://bibliotekanauki.pl/articles/244241.pdf
Data publikacji:
2016
Wydawca:
Instytut Techniczny Wojsk Lotniczych
Tematy:
unmanned aerial vehicles
drones
time-dependent frequency analysis
signal analysis
Opis:
Unmanned aerial vehicles are increasingly used in military service and in everyday life. Drones can be used for many purposes i.e. recreation, military applications or to increase the safety of citizens. Unmanned aerial vehicle can become a source of information, based on which object/operator can make a certain decisions. Unmanned aerial vehicles are increasingly used in ecological research. UAV can be capable of making sophisticated maps and may scan terrain for forest fires. They can contribute to safe infrastructure maintenance and management. Often, however, these objects being in the possession of civilians can become a source of danger and impact on privacy. It is therefore necessary to detect and recognize such objects in a real time. The aim of this study was to analyse the acoustic signal of unmanned aerial vehicle equipped with four rotating propellers – X4 structure (12000 rpm/min). The maximum speed of the object is 60 km/h and the ceiling to which it can operate flights reaches 1500 m AGL. The acoustic signal was acquired by Olympus LS11 digital recorder. Recordings were performed when the object is away from the recording equipment at the distance of 1 km. Analysis of the recorded signal can provide a significant information about the unmanned aerial vehicle. Results showed that some specific characteristic signal features are clearly visible in the signal even if the object is far away from the recording equipment.
Źródło:
Journal of KONES; 2016, 23, 3; 321-326
1231-4005
2354-0133
Pojawia się w:
Journal of KONES
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Modified sliding wiener-khintchin trans form
Zmodyfikowane ślizgające przetwarzanie Wienera-Chinczyna
Autorzy:
Pogribny, W.
Surma, D.
Powiązania:
https://bibliotekanauki.pl/articles/389846.pdf
Data publikacji:
2010
Wydawca:
Politechnika Bydgoska im. Jana i Jędrzeja Śniadeckich. Wydawnictwo PB
Tematy:
time-frequency analysis
Wiener-Khintchin transform
Correlation analysis
analiza czasowo-częstotliwościowa
przetwarzanie Wienera-Chinczyna
analiza korelacyjna
Opis:
The article presents the new approach to increase a speed of Sliding Discrete Wiener-Khintchin Transform (SDW-KT) algorithm on the basis of recurrent correlation analysis (CA) algorithm using. In this case it is not necessary to calculate the whole correlation function by each analyzing window position. There is taken note of analyzing window parameters selecting for sliding DW-KT, FFT, and Sliding Periodogram too. Worked out approach predominance over SFFT and Periodogram is demonstrated on examples of short noisy signal recognition.
W artykule przedstawiono opracowany nowy szybki rekurencyjny algorytm, ślizgającej dyskretnej analizy korelacyjnej (SDW-KT- Sliding Discrete Wiener-Khitnchin Transform), pozwalający na istotne zmniejszenie ilości operacji przy kolejnych przemieszczeniach okna analizy, co prowadzi do zwiększenia szybkości przetwarzania SDW-KT. Zwrócono także uwagę na dobranie parametrów okien dla ślizgających przetwarzań DW-KT, FFT (Fast Fourier Transform) i PERIODOGRAMU. Przewagi opracowanych podejść nad SFFT i ślizgającym periodogramem przedstawiono na przykładach wykrywania krótkotrwałych zaszumionych sygnałów.
Źródło:
Zeszyty Naukowe. Telekomunikacja i Elektronika / Uniwersytet Technologiczno-Przyrodniczy w Bydgoszczy; 2010, 13; 31-41
1899-0088
Pojawia się w:
Zeszyty Naukowe. Telekomunikacja i Elektronika / Uniwersytet Technologiczno-Przyrodniczy w Bydgoszczy
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Joint time-frequency and wavelet analysis - an introduction
Autorzy:
Majkowski, A.
Kołodziej, M.
Rak, R. J.
Powiązania:
https://bibliotekanauki.pl/articles/220841.pdf
Data publikacji:
2014
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
frequency analysis
time-frequency analysis
short-time Fourier transform
Gabor transform
Wigner-Ville transform
Cone-Shaped Transform
wavelet analysis
time-scale analysis
wavelet decomposition
filter banks
wavelet packets
Opis:
A traditional frequency analysis is not appropriate for observation of properties of non-stationary signals. This stems from the fact that the time resolution is not defined in the Fourier spectrum. Thus, there is a need for methods implementing joint time-frequency analysis (t/f) algorithms. Practical aspects of some representative methods of time-frequency analysis, including Short Time Fourier Transform, Gabor Transform, Wigner-Ville Transform and Cone-Shaped Transform are described in this paper. Unfortunately, there is no correlation between the width of the time-frequency window and its frequency content in the t/f analysis. This property is not valid in the case of a wavelet transform. A wavelet is a wave-like oscillation, which forms its own “wavelet window”. Compression of the wavelet narrows the window, and vice versa. Individual wavelet functions are well localized in time and simultaneously in scale (the equivalent of frequency). The wavelet analysis owes its effectiveness to the pyramid algorithm described by Mallat, which enables fast decomposition of a signal into wavelet components.
Źródło:
Metrology and Measurement Systems; 2014, 21, 4; 741-758
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Infrared devices and techniques (revision)
Autorzy:
Rogalski, A.
Chrzanowski, K.
Powiązania:
https://bibliotekanauki.pl/articles/221154.pdf
Data publikacji:
2014
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
frequency analysis
time-frequency analysis
short-time Fourier transform
Gabor transform
Wigner-Ville transform
Cone-Shaped Transform
wavelet analysis
time-scale analysis
wavelet decomposition
filter banks
wavelet packets
Opis:
The main objective of this paper is to produce an applications-oriented review covering infrared techniques and devices. At the beginning infrared systems fundamentals are presented with emphasis on thermal emission, scene radiation and contrast, cooling techniques, and optics. Special attention is focused on night vision and thermal imaging concepts. Next section concentrates shortly on selected infrared systems and is arranged in order to increase complexity; from image intensifier systems, thermal imaging systems, to space-based systems. In this section are also described active and passive smart weapon seekers. Finally, other important infrared techniques and devices are shortly described, among them being: non-contact thermometers, radiometers, LIDAR, and infrared gas sensors.
Źródło:
Metrology and Measurement Systems; 2014, 21, 4; 565-618
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Time-frequency analysis of time-variant systems
Czasowo-częstotliwościowa analiza systemów zmiennych w czasie
Autorzy:
Dziedziech, K.
Staszewski, W. J.
Uhl, T.
Powiązania:
https://bibliotekanauki.pl/articles/327978.pdf
Data publikacji:
2013
Wydawca:
Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
Tematy:
system identification
time-frequency analysis
functional ridges
Crazy Climbers
identyfikacja systemów
analiza czasowo-częstotliwościowa
grzbiety funkcji
Opis:
System identification is an important and often complex process in many areas of engineering. This process is not easy when parameters of the analysed system vary with time. In such cases classical methods fail to identify parameters properly. The work demonstrated in this paper deals with time-frequency representations for identification of natural frequencies of time-variant systems. The method involves the estimation of time-variant transfer functions. A "Crazy Climbers" algorithm - based on Monte Carlo simulations and Markov chains - is used to overcome difficulties associated with the method.
Identyfikacja parametrów systemów mechanicznych jest bardzo ważnym i skomplikowanym procesem. Proces ten jest o wiele bardziej skomplikowany kiedy dotyczy systemów mechanicznych, których parametry zmieniają się w czasie. W takim przypadku klasyczne metody identyfikacji nie są w stanie poprawnie zidentyfikować tych parametrów. Artykuł zajmuje się wykorzystaniem reprezentacji czasowo-częstotliwościowych w celu identyfikacji częstotliwości drgań rezonansowych systemów o zmiennych w czasie parametrach. Jednym z kroków podczas estymacji funkcji przejścia jest dzielenie spektrum odpowiedzi przez spektrum wymuszenia, co często prowadzi do dzielenia przez wartości bliskie zera, a to prowadzi do nieskończonych (lub niezdefiniowanych) wartości. W celu ominięcia tego problemu zastosowano probabilistyczną metodę „CrazyClimbers”, opartą na symulacjach Monte Carlo oraz łańcuchach Markova.
Źródło:
Diagnostyka; 2013, 14, 1; 37-42
1641-6414
2449-5220
Pojawia się w:
Diagnostyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Comparison of the EEG Signal Classifiers LDA, NBC and GNBC Based on Time-Frequency Features
Porównanie klasyfikatorów LDA, NBC i GNBC sygnału EEG stosujących cechy czasowo-częstotliwościowe
Autorzy:
Szuflitowska, B.
Orłowski, P.
Powiązania:
https://bibliotekanauki.pl/articles/275175.pdf
Data publikacji:
2017
Wydawca:
Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:
electroencephalograph classification
machine learning
short-time Fourier transform
time-frequency analysis
elektroencefalografia
klasyfikacja
uczenie maszynowe
krótkoczasowa transformata Fouriera
analiza czasowo-częstotliwościowa
Opis:
EEG signals are non-stationary and used to study the activities of the brain in pathology. Epilepsy belongs to the most common neurological diseases. In the paper, real EEG sequences described by a doctor as normal and epileptic (ictal and interictal) are used. In classification process these sequences are divided into training and testing subsets. The classification are performed using Short-Time Fourier Transform. Based on obtained spectrum four features have been extracted. The study presents experiments based on the analysis and classification of EEG signals using various methods, including Linear Discriminant Analysis, Naive Bayes Classifier and Gaussian Naive Bayes Classifier. The results indicated that used techniques a potential to be applied within an automatic neurologic diseases diagnosis system and could thus further increase the number of correct diagnoses.
Sygnały EEG są z definicji niestacjonarne i stosowane do badania aktywności mózgu w patologii. Epilepsja należy do najczęstszych chorób neurologicznych. W pracy użyto rzeczywistych sekwencji EEG określonych przez lekarza jako stan normalny oraz padaczka (stany napadowe oraz międzynapadowe). W procesie klasyfikacji sygnały zostały podzielone na dwa podzbiory – uczący oraz testujący. Klasyfikacja została przeprowadzona za pomocą krótkotrwałej transformaty Fouriera. Na podstawie otrzymanego widma dokonano ekstrakcji czterech cech. Badanie przedstawia eksperymenty oparte na analizie i klasyfikacji sygnałów EEG za pomocą różnych metod, w tym Liniowej Analizy Dyskryminacyjnej, Naiwnego Klasyfikatora Bayesa oraz Naiwnego Klasyfikatora Bayesa dla rozkładu Gaussa. Wyniki pokazują, że użyty algorytm może być potencjalnie stosowany w automatycznej diagnostyce schorzeń neurologicznych i może w przyszłości zwiększyć liczbę poprawnie stawianych diagnoz.
Źródło:
Pomiary Automatyka Robotyka; 2017, 21, 2; 39-45
1427-9126
Pojawia się w:
Pomiary Automatyka Robotyka
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 26

Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies