On hidden fractal model signal processing
نویسندگان
چکیده
Fractal stochastic processes are examples of semi-Markov processes where the signal behaviour is a function of the prefiltering bandwidth. In this paper we develop schemes for estimating such fractal models when they are hidden (imbedded) in noise. We reformulate this hidden fractal model (H FM) problem in the scalar case as a higher order scalar or first order 2-vector homogeneous hidden Markov model (H MM) problem in which the state consists of the signal augmented by the time to the last transition. With this reformulation, we can apply HMM signal processing techniques to obtain optimal estimates of the signals and signal model parameters, including transition probabilities and noise statistics. Also, the signal levels and fractal dimension can be estimated. Zusammenfassung. Fraktale stochastische Prozesse sind Beispiele von Semimarkovprozessen, wobei das Signalverhalten eirw Funktion der Vortilterbandbreite ist. In diesem Beitrag entwickeln wir Methoden fiir die Schiitzung solcher fraktaler Modelle, die in Rauschen ‘versteckt’ (eingebettet) sind. Wir formulieren dieses Problem der Bestimmung eines hidden fractal model (H FM) im skaleren Fall neu als ein Problem zur Bestimmung eines homogenen hidden Markov model (HMM), das entweder skalarwertig und von hoherer Ordnung ist oder vektorwertig mit zwei Komponenten und von erster Ordnung. Dabei besteht der Zustand aus dem Signal, vermebrt urn die Zeit his zum Ietzten Ubergang. Mit dieser Neuformulierung konnen wir HMM-Signalverarbeitungstechniken anwenden, urn die optimalen Schatzwerte fiir die Signale und Signalmodellparameter einschlie131ich der Ubergangswahrschei nlichkeiten und der Rauschstatistiken zu erhaften. Ebenso ktinnen die Signal pegel und die fraktale Dimension geschiitzt werden. Resum6. Les processus stochastiques fractals sent des exemples de processus semi markoviens pour Iesquels Ie comportment du signal est fonction de la Iargeur de bande du prefiltrage. Nous dtveloppons dam cet article des m6thodes permettant d’estimer de tels modeles fractals quand ils sent caches (immerges) clans Ie bruit, Nous reformulons Ie probl~me de ce modele fractal cacht (en anglais hidden fractal model, HFM) clans Ie cas scalaire comme un probleme de mod~le de Markov cache (en anglais hidden Markov model, HMM) scalaire d’ordre sup6rieur ou vectoriel de dimension deux et d’ordre un clans Iequel I’&tat est constitui par Ie signal augment< du temps jusqu’ii la derni>re transition. A I’aide de cette reformulation, nous pouvons appliquer Ies techniques de traitement de signaux HMM afirr d’obtenir [es estimations optimales des param?tres du signal et du mod.51e de signal, ce qui inclue Ies probabilitts de transition et la statistique du bruit, De plus, Ies niveaux de signal et la dimension fractale peuvent eux aussi $tre estimt%.
منابع مشابه
Adaptive Segmentation with Optimal Window Length Scheme using Fractal Dimension and Wavelet Transform
In many signal processing applications, such as EEG analysis, the non-stationary signal is often required to be segmented into small epochs. This is accomplished by drawing the boundaries of signal at time instances where its statistical characteristics, such as amplitude and/or frequency, change. In the proposed method, the original signal is initially decomposed into signals with different fr...
متن کاملAn Adaptive Segmentation Method Using Fractal Dimension and Wavelet Transform
In analyzing a signal, especially a non-stationary signal, it is often necessary the desired signal to be segmented into small epochs. Segmentation can be performed by splitting the signal at time instances where signal amplitude or frequency change. In this paper, the signal is initially decomposed into signals with different frequency bands using wavelet transform. Then, fractal dimension of ...
متن کاملAn Adaptive Segmentation Method Using Fractal Dimension and Wavelet Transform
In analyzing a signal, especially a non-stationary signal, it is often necessary the desired signal to be segmented into small epochs. Segmentation can be performed by splitting the signal at time instances where signal amplitude or frequency change. In this paper, the signal is initially decomposed into signals with different frequency bands using wavelet transform. Then, fractal dimension of ...
متن کاملDelineation of alteration zones based on artificial neural networks and concentration-volume fractal methods in the hypogene zone of porphyry copper-gold deposit, Masjed-Daghi, East Azerbaijan Province, Iran
In this paper, we aim to achieve two specific objectives. The first one is to examine the applicability of the Artificial Neural Networks (ANNs) technique in ore grade estimation. Different training algorithms and numbers of hidden neurons are applied to estimate Cu grade of borehole data in the hypogene zone of porphyry copper-gold deposit, Masjed-Daghi, East Azerbaijan Province (Iran). The ef...
متن کاملImage Resolution Enhancement with Hierarchical Hidden Fields
In any image processing involving images having scale-dependent structure, a key challenge is the modeling of these multiscale characteristics. Because single Gauss-Markov models are effective at representing only single-scale phenomena, the classic Hidden Markov Model can not perform well in the processing of more complex images, particularly near-fractal images which frequently occur in scien...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید
ثبت ناماگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید
ورودعنوان ژورنال:
- Signal Processing
دوره 24 شماره
صفحات -
تاریخ انتشار 1991