Ograniczanie wyników
Czasopisma help
Autorzy help
Lata help
Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 32

Liczba wyników na stronie
first rewind previous Strona / 2 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  independent component analysis
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 2 next fast forward last
EN
Objectives: The electroencephalographic signal is largely exposed to external disturbances. Therefore, an important element of its processing is its thorough cleaning. Methods: One of the common methods of signal improvement is the independent component analysis (ICA). However, it is a computationally expensive algorithm, hence methods are needed to decrease its execution time. One of the ICA algorithms (fastICA) and parallel computing on the CPU and GPU was used to reduce the algorithm execution time. Results: This paper presents the results of study on the implementation of fastICA, which uses some multi-core architecture and the GPU computation capabilities. Conclusions: The use of such a hybrid approach shortens the execution time of the algorithm.
EN
Independent component analysis (ICA) is usually used as a preliminary step for maternal electrocardiogram (ECG) QRS detection in fetal ECG extraction. When applying ICA to do this, a troublesome problem arises from how to automatically identify the separated maternal ECG component. In this paper we proposed a method called PRCH (short for Peak to peak entropy, R-R interval entropy, Correlation coefficient and Heart rate) for the automatic identifying. In the method, we defined four kinds of features, including amplitude, instantaneous heart rate, morphology and average heart rate, to characterize a signal, and determined some decision parameters through machine learning. Experiments and comparison with other three existed methods were given. Through taking metric F1 for evaluation, it showed that the proposed PRCH method has the highest identifying accuracy and generalization capability.
3
Content available remote EEG of game players - detecting involvement with and without ICA preprocessing
EN
The aim of this paper is to analyze the differences in the classification accuracy obtained with raw EEG data and with data preprocessed with Independent Components Analysis (ICA). Our main research question is whether ICA is able to improve the classification accuracy not only in the case of a multichannel recording but also when EEG data are recorded only from a few channels. In order to answer this question we performed an experiment with 6 game players and gathered EEG data during Dota 2 game session. We analyzed the EEG data separately for 19, 7, and 3 channels with and without ICA preprocessing. With all three number of channels and for each of the six players we obtained more precise classifiers, classifying the seconds of the game as involving or boring, after applying ICA (mean accuracy averaged over subjects: 19 channels - 0.87 (raw signals), 0.91 (after ICA); 7 channels - 0.8 (raw signals), 0.85 (after ICA); 3 channels - 0.75 (raw signals), 0.8 (after ICA)).
PL
Celem artykułu jest analiza różnic w dokładności klasyfikacji otrzymanej przy wykorzystaniu surowego sygnału EEG oraz sygnału poddanego preprocessingowi z wykorzystaniem analizy składowych niezależnych (ICA). Naszym głównym pytaniem badawczym jest to, czy ICA jest w stanie zwiększyć dokładność klasyfikacji nie tylko w przypadku wielokanałowego EEG, ale również wtedy, kiedy dane EEG są nagrywane tylko z kilku kanałów. W celu udzielenia odpowiedzi na to pytanie przeprowadziliśmy eksperyment z sześcioma graczami i zgromadziliśmy dane EEG podczas gry w grę Dota 2. Przeanalizowaliśmy dane oddzielnie dla 19, 7 i 3 kanałów z oraz bez zastosowania algorytmu ICA. Dla wszystkich trzech liczb kanałów i dla każdego z sześciu graczy otrzymaliśmy bardziej dokładne klasyfikatory, dokonujące klasyfikacji poszczególnych sekund gry jako angażujących i nudnych, po przeprowadzeniu preprocessingu z wykorzystaniem ICA (średnia dokładność dla wszystkich podmiotów: 19 kanałów - 0.87 (surowe sygnały), 0.91 (po ICA); 7 kanałów - 0.8 (surowe sygnały), 0.85 (po ICA); 3 kanały - 0.75 (surowe sygnały), 0.8 (po ICA)).
EN
We propose to tackle the problem of maternal abdominal electric signals decomposition with a combined application of independent component analysis and projective or adaptive filtering. The developed method is employed to process the four-channel abdominal signals recorded during twin pregnancy. These signals are complicated mixtures of the maternal ECG, the ECGs of the fetal twins and noise of various origin. Although the independent component analysis cannot separate the respective signals, the proposed combination of the methods deals with this task successfully. A simulation experiment confirms high efficiency of this approach.
5
Content available remote Performance comparison of ICA algorithms for audio blind source separation
EN
The aim of this paper is to compare five algorithms for Independent Component Analysis. The algorithms are compared with regard to performance for separating three and seven input signals. It also examined how time and number of independent components affect on separation precision. Professional sound recordings and their mixes were used for all tests.
PL
W artykule porównano pięć popularnych algorytmów z rodziny analizy składowych niezależnych. Algorytmy porównywane były pod kątem wydajności dla trzech oraz siedmiu sygnałów wejściowych. Badano również jak czas działania algorytmu oraz zwiększenie liczby składowych wejściowych wpływa na dokładność separacji. Do testów zastosowano profesjonalnie nagrane próbki śpiewu oraz ich mieszanki.
6
Content available remote A texture-based method for classification of schizophrenia using fMRI data
EN
This paper presents a texture-based method for classification of individuals into schizophrenia patient and healthy control groups based on their resting state functional magnetic resonance imaging (R-fMRI) data. In this research a combination of three different classifiers is proposed for classification of subjects into predefined groups. For all fMRI scans, the number of time points is reduced using principal component analysis (PCA) method, which projects data onto a new space. Then, independent component analysis (ICA) algorithm is used for estimation of the independent components (ICs). ICs are sorted based on their variance. For feature extraction a texture based operator called volume local binary patterns (VLBP) is applied on the estimated ICs. In order to obtain a set of features with large discrimination power, a two-sample t-test method is used. Finally, a test subject is classified into patient or control group using a combination of three different classifiers based on a majority vote method. The performance of the proposed method is evaluated using a leave-one-out cross validation method. Experimental results reveal that the proposed method has a very high accuracy.
PL
W artykule przedstawiono metodę identyfikacji i eliminacji artefaktów mrugania oczami z sygnału EEG z wykorzystaniem technik analizy składowych niezależnych i statystyk wyższych rzędów. Najistotniejszą cechą proponowanej metody jest fakt, że może ona być stosowana w sposób automatyczny, bez nadzoru użytkownika.
EN
This paper presents a method to identify and eliminate artifacts from EEG signal using independent component analysis and higher-order statistics. The key feature of the proposed method is that it can be applied in automatic manner, without user supervision.
PL
Obecnie istnieje coraz szersze zapotrzebowanie na urządzenia służące do oceny stanu psychofizycznego osób, w tym żołnierzy czy sportowców, w czasie ich aktywności fizycznej, a więc w ruchu. Muszą to być przyrządy noszone. Ruch ciała jest źródłem dużych zakłóceń, które utrudniają, a nawet uniemożliwiają wykonanie pomiarów za pomocą pulsoksymetrów stosowanych w diagnostyce klinicznej. W artykule w sposób skrótowy przedstawiono zasadę pomiarów utlenowania krwi tętniczej za pomocą fotopulsoksymetrów oraz dokonano przeglądu metod przetwarzania rejestrowanych sygnałów pulsoksymetrycznych mających na celu wyeliminowanie wpływu zakłóceń ruchowych na wyniki pomiarów utlenowania krwi tętniczej.
EN
Now-a-day, there is an increasing demand for devices needed for assessing a psychophysical state of people, including soldiers and sportsmen, during their physical activity, and so in moving. Such devices must be worn. Body movement is a source of high disturbances, which impede or even make impossible realization of measurements by pulse oximeters applied in clinical diagnosis. The paper briefly presents basic information on arterial blood oxygen saturation measurements using pulse oximeters, and gives a review of methods used for processing the monitored pulse oximeter signals in order to eliminate an influence of the movement disturbances on the results of oxygen arterial blood saturation measurements.
EN
Formation’s properties can be estimated indirectly using joint analysis of compressional and shear wave velocities. Shear wave data is not usually acquired during well logging, which is most likely for cost saving purposes. Even if shear data is available, the logging programs provide only sparsely sampled one-dimensional measurements: this information is inadequate to estimate reservoir rock properties. Thus, if the shear wave data can be obtained using seismic methods, the results can be used across the field to estimate reservoir properties. The aim of this paper is to use seismic attributes for prediction of shear wave velocity in a field located in southern part of Iran. Independent component analysis (ICA) was used to select the most relevant attributes to shear velocity data. Considering the nonlinear relationship between seismic attributes and shear wave velocity, multi-layer feed forward neural network was used for prediction of shear wave velocity and promising results were presented.
PL
W artykule przedstawiono metodę PCA (ang. Principal Component Analysis) oraz ICA (ang. Independent Component Analysis), jako narzędzia pomocne w procesie eliminacji artefaktów z sygnału elektroencefalograficznego. Proces rejestracji sygnału elektroencefalograficznego można zobrazować, jako BSS (ang. Blind Signals Separation). Dzięki temu możliwe jest dokonywanie estymacji nieznanych sygnałów źródłowych oraz ekstrakcji niepożądanych sygnałów zakłócających, w zakresie ich późniejszej eliminacji. W tym celu konieczne jest doskonalenie metod weryfikacji i eliminacji artefaktów z sygnału EEG. W artykule opisano możliwość zastosowania powyższych metod w zakresie sygnału EEG oraz zrealizowane zostało porównanie skuteczności ich działania.
EN
: In the paper there are presented the Principal Component Analysis (PCA) and the Independent Component Analysis (ICA) as useful tools for elimination of artefacts in an electroencephalographic signal. The process of registration of the electroencephalographic signal can be described as BSS - Blind Signals Separation. It is possible to estimate unknown source signals and to extract intrusive disturbing signals in terms of their subsequent elimination. It is necessary to improve the methods of verification and elimination of artefacts from an EEG signal. The Brain Computer Interface (BCI) technology is presented briefly in the first part of the paper. EEG signal characteristics and its acqui-sition with the non-invasive method are described in the second part. Next, there is discussed the possibility of using the PCA and ICA methods in terms of analysis of an EEG signal. Comparison of the effectiveness of these methods is presented as well. A general profile of the EEG signal processing is shown in Fig. 1. An example of use of the infomax algorithm for a real EEG signal is depicted in Fig. 2. Fig. 3 shows an exemplary Event-Related Potential (ERP) of the EEG signal.
EN
In respect to the main goal of our ongoing work for analyzing fetal electrocardiogram (FECG) signals for monitoring the health of the fetus, we investigate in this paper the possibility of extracting the fetal heart rate (FHR) directly from the abdominal composite recordings. Our proposed approach is based on a combination of Independent Component Analysis (ICA) and least mean square (LMS) adaptive filter. The FHR of the estimated FECG signal is finally compared to a reference value extracted from a FECG signal recorded by using a spiral electrode attached directly to the fetal scalp. The experimental results show that FHR can be successfully evaluated directly from the abdominal composite recordings without the need of using any external reference signal.
12
Content available remote Multidimensional independent subspace analysis by natural gradient
EN
Multidimensional Independent Subspace Analysis (MISA) as an extended Independent Component Analysis (ICA) method has been considered. The general and detailed definition, existence, uniqueness, separability of the MISA model are given and the relationships between ICA and MISA are also discussed. The natural gradient separation algorithm and corresponding simulation results for MISA are constructed based on the maximum likelihood theory and natural gradient method.
PL
W artykule zaprezentowano metodę MISA – multidimensional independent subspace analysis. Przedstawiono też metode IOCA – independent component analysis. Opracowano algorytm separacji – natural gradient separation algorithm.
EN
A new form of the nonlinearity implemented in the ICA approach is presented in the paper. The proposed independent component analysis based on differential entropy can be used for elimination of physiological artifacts from electroencephalographic signals. For verification of the quality of separation of the EEG data, the PI index is proposed. The second measure of accuracy is the normalized kurtosis which can be used in analysis of the simulated EEG data. As it has been proved, the new sigmoid function used in the ICA approach can effectively separate the EEG data.
PL
W artykule przedstawiono nową propozycję nieliniowości - sigmoidalną funkcję algebraiczną, która została zaimplementowana w algorytmie stosującym metodę analizy składowych niezależnych (ang. Independent Component Analysis). Proponowana nowa postać algorytmu wykorzystująca właściwości entropii różniczkowej, może zostać użyta także do separacji a następnie eliminacji wybranych artefaktów fizjologicznych pochodzenia ocznego i mięśniowego zarejestrowanych w zapisach EEG. W celu weryfikacji dokładności separacji sygnałów EEG zaproponowano współczynnik jakości separacji PI (ang. Performance Index). Jako drugą miarę dokładności procesu separacji wybrano wartość znormalizowanej kurtozy, która może być stosowana jedynie w przypadku separacji elektroencefalogramów zarejestrowanych z symulatora EEG. W artykule udowodniono, że użycie nowej funkcji sigmoidalnej w rozszerzonej postaci algorytmu infomax prowadzi do efektywnej separacji sygnałów EEG umożliwiając eliminację wybranych składowych niepożądanych.
EN
Functional magnetic resonance imaging (fMRI) data are acquired as a natively complex data set, however for various reasons the phase data is typically discarded. Over the past few years, interest in incorporating the phase information into the analyses has been growing and new methods for modeling and processing the data have been developed. In this paper, we provide an overview of approaches to understand the complex nature of fMRI data and to work with the utilizing the full information, both the magnitude and the phase. We discuss the challenges inherent in trying to utilize the phase data, and provide a selective review with emphasis on work in our group for developing biophysical models, preprocessing methods, and statistical analysis of the fully-complex data. Of special emphasis are the use of data-driven approaches, which are particularly useful as they enable us to identify interesting patterns in the complex-valued data without making strong assumptions about how these changes evolve over time, something which is challenging for magnitude data and even more so for the complex data. Finally, we provide our view of the current state of the art in this area and make suggestions for what is needed to make efficient use of the fully-complex fMRI data.
15
Content available remote Artifacts extraction from EEG data using the infomax approach
EN
The aim of the research is to detect and remove undesired components from EEG data by means of ICA approach. Besides classical signal analysis tools such as adaptive supervised filtering, parametric or non-parametric spectral estimation, time-frequency analysis, the proposed ICA technique can be used for detection of a wide group of artifacts from EEG data. In this paper a new form of nonlinearity implemented in the infomax approach is presented. As it has been proven experimentally, the proposed new sigmoidal function can effectively detect the selected group of artifacts from EEGs and is an useful approach to speed up computations.
EN
Independent Component Analysis (ICA) can be used for single channel audio separation, if a mixed signal is transformed into time-frequency domain and the resulting matrix of magnitude coefficients is processed by ICA. Previous works used only frequency (spectral) vectors and Kullback-Leibler distance measure for this task. New decomposition bases are proposed: time vectors and time-frequency components. The applicability of several different measures of distance of components are analysed. An algorithm for clustering of components is presented. It was tested on mixes of two and three sounds. The perceptual quality of separation obtained with the measures of distance proposed was evaluated by listening tests, indicating “beta” and “correlation” measures as the most appropriate. The “Euclidean” distance is shown to be appropriate for sounds with varying amplitudes. The perceptual effect of the amount of variance used was also evaluated.
17
Content available remote Study on White Noise Suppression for PD Signals Using ICA
EN
In this paper, the basic independent component analysis (ICA) model is used to suppress white noise for partial discharge (PD) signals. The mathematical model of ICA is described, and its application in simulation PD signals and PD pulse current signals at HVDC are investigated. The results manifest that the white noise can be effectively suppressed with keeping the most important information of PD signals.
PL
W artykule przedstawiono model niezależnej analizy składowych użyty do tłumienia białego szumu towarzyszącemu sygnałowi wyładowania niezupełnego PD. Opisano model matematyczny i jego zastosowanie w symulacji sygnału PD. Wyniki wskazują, że biały szum może być efektywnie tłumiony przy utrzymaniu wszystkich ważnych informacji sygnału PD.
18
Content available remote Methods for identification of uncorrelated forces acting in the machines
EN
In the work presented are methods of identification of uncorrelated operational forces based on orthogonal decomposition of crosspower spectrum matrix. In this purpose were used methods based on eigen- and singular value decomposition of PSD matrix. Except methods in frequency domain were used methods in time domain (ICA - Independent Component Analysis) for identification statistically independent and principal component. The methods were used to identify the number of sources of the exciting forces acting during the work of a real mechanical system.
19
Content available remote Estimating independent components by mapping onto an orthogonal manifold
EN
: Algorithms for independent component analysis (ICA) based on information-theoretic criteria optimization over differential manifolds have been devised over the last few years. The principles informing their design lead to various classes of learning rules, including the fixed-point and the geodesic-based ones. Such learning algorithms mainly differ by the way in which single learning steps are effected in the neural system's parameter space, i. e. by the action that a connection variable is moved by in the parameter space toward the optimal connection pattern. In the present paper, we introduce a new class of learning algorithms by recalling from the literature on differential geometry the concept of mapping onto manifolds, which provides a general way of acting upon a neural system's connection variable in order to optimize the learning criteria. The numerical behavior of the introduced learning algorithms is illustrated and compared with experiments carried out on mixtures of statistically-independent signals.
PL
Celem przedstawionych wyników badań jest eliminacja wybranych niepożądanych sygnałów przy użyciu analizy składowych niezależnych. W artykule przedstawiono następujące algorytmy BSS (z ang. Blind Signal Separation): HJ oraz Infomax jako narzędzia do separacji i usuwania wybranej grupy artefaktów (mruganie powiek, artefakty mięśniowe) z przebiegów EEG. Jak udowodniono w eksperymentach proponowane algorytmy adaptacyjne mogą efektywnie wykrywać i usuwać wybrane artefakty z przebiegów EEG.
EN
The aim of the performed investigations is to remove selected undesired signals by means of ICA approach. In the paper there are presented the following algorithms BSS (Blind Signal Separation): HJ and Infomax for separation and removal of selected group of artifacts (eye blinks, muscle activity) from EEG recordings. It has been proved in the experiments which are described in the paper that the proposed adaptive algorithms can effectively detect and remove these selected artifacts from EEG recordings.
first rewind previous Strona / 2 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.