Preferencje help
Widoczny [Schowaj] Abstrakt
Liczba wyników

Znaleziono wyników: 16

Liczba wyników na stronie
first rewind previous Strona / 1 next fast forward last
Wyniki wyszukiwania
Wyszukiwano:
w słowach kluczowych:  signal classification
help Sortuj według:

help Ogranicz wyniki do:
first rewind previous Strona / 1 next fast forward last
EN
The classification of low signal-to-noise ratio (SNR) underwater acoustic signals in complex acoustic environments and increasingly small target radiation noise is a hot research topic. . This paper proposes a new method for signal processing—low SNR underwater acoustic signal classification method (LSUASC)—based on intrinsic modal features maintaining dimensionality reduction. Using the LSUASC method, the underwater acoustic signal was first transformed with the Hilbert-Huang Transform (HHT) and the intrinsic mode was extracted. the intrinsic mode was then transformed into a corresponding Mel-frequency cepstrum coefficient (MFCC) to form a multidimensional feature vector of the low SNR acoustic signal. Next, a semi-supervised fuzzy rough Laplacian Eigenmap (SSFRLE) method was proposed to perform manifold dimension reduction (local sparse and discrete features of underwater acoustic signals can be maintained in the dimension reduction process) and principal component analysis (PCA) was adopted in the proces of dimension reduction to define the reduced dimension adaptively. Finally, Fuzzy C-Means (FCMs), which are able to classify data with weak features was adopted to cluster the signal features after dimensionality reduction. The experimental results presented here show that the LSUASC method is able to classify low SNR underwater acoustic signals with high accuracy.
EN
Multivariate analysis of the EEG signal for the detection of Schizophrenia condition is proposed here. Multivariate Empirical Mode Decomposition (MEMD) is used to decompose the EEG signal into Intrinsic Mode Functions (IMF) signal. The randomness measure of the IMF signal is determined by computing the entropy of the signal. Five entropy measures such as Approximate entropy, Sample entropy, Permutation entropy, Spectral entropy, and Singular Value Decomposition entropy are measured from the IMF signal. These entropy measures showed a significant difference ( p < 0.01) between the healthy controls (HC) and Schizophrenia (SZ) subjects. Many state-of-the-art (SoA) machine learning classifiers are trained on the feature matrix obtained from entropy values of the IMF signal, amongst them Support Vector Machine based on Radial Basis Function (SVM-RBF) provided the highest accuracy and F1-score of 93% for the 95 features. The area under the curve (AUC) value of 0.9831 was obtained using this classifier. These performance metrics suggests that computation of randomness measure such as entropy in the multivariate IMF domain provided better discriminating power in detection of Schizophrenia condition from the multichannel EEG signal.
PL
Wykorzystywanie sygnałów elektromiografii powierzchniowej (ang. Surface Electromyography, SEMG) w procesach sterowania systemami rehabilitacyjnymi stanowi obecnie standardową procedurę. Popularność SEMG wynika z nieinwazyjności metody oraz możliwości szybkiej i precyzyjnej identyfikacji funkcji mięśniowej. W przypadku osób małoletnich proces klasyfikacji sygnałów jest utrudniony ze względu na mniejsze rozmiary i wyższą dynamikę aktywności włókien mięśniowych niż u osób dorosłych. W związku z powyższymi uwagami, w artykule przedstawiono wyniki badań zwiększających wskaźnik poprawnej klasyfikacji wybranych ruchów dłoni dzieci. Omówiono zastosowane do tego celu modele matematyczne: k-najbliższych sąsiadów, drzewo decyzyjne oraz metodę wektorów nośnych; a także zastosowane miary i metodykę „strojenia” parametrów modeli.
EN
Overarching objective of this paper is classification of basic hand gestures by surface electromyography for healthy children. Main difference between biosignals corresponding to adults and children muscle activity is disparate growth of muscles. For this reason youngsters need separate method of signals classification. In this paper we decide to create a mathematical model and compare three classification method: a support vector machine, k nearest neighbors and decision tree methods. Furthermore we used the best set of time domain (MAV, WAMP, WL and SSC) and selected several parameters to make each model as good as possible.
PL
Celem artykułu jest przedstawienie algorytmu klasyfikacji sygnałów EEG opartego na rozwiązywaniu zagadnienia odwrotnego. Proponowana metoda klasyfikacji wykorzystuje teorię grafów. Dla surowych sygnałów zastosowano algorytm wyznaczania widmowej gęstości mocy (PSD). Wykonane testy potwierdziły poprawność klasyfikacji na poziomie przekraczającym 90%. Dzięki rozwiązaniu zagadnienia odwrotnego można było uzyskać informację o miejscach, w których sygnały związane z planowaniem ruchu mają swoje źródło.
EN
The purpose of the article is to present the testing algorithm for the classification of EEG signals based on the inverse solution. The proposed method of classification is based on the graph theory. The algorithm for determining the power spectral density (PSD) was used for the raw signals. The tests performed with the use of the automatic algorithm confirmed the accuracy of classification at the level exceeding 90%. With the solution of the inverse problem information was obtained about places where signals associated with planning movement have their sources.
EN
The article describes the algorithm of EEG signal classification with reference to the movement which was used in BCI. The algorithm is based on the reconstruction of signals performed as a result of solving the inverse problem. The data for testing the algorithm were taken from the IDIAP database. Moreover, processed data on the 18-26 Hz frequency from the headset were used. The article presented both the algorithm and the example of the test that was performed. The test included cortical areas of the brain connected with Brodmann areas 4 and 6. The correctness of the classification depends on the precision of defining the movement areas involving the kind of movement (in the case under investigation moving the right and left hand). For the data obtained from the headset, the quality of the classification depends on preprocessing of the signal and the time that the classifier devoted to learning.
PL
W artykule opisano algorytm klasyfikacji sygnałów EEG dotyczących ruchu, który wykorzystano w BCI. Algorytm jest oparty na rekonstrukcji źródeł sygnałów wykonanej w wyniku rozwiązania zagadnienia odwrotnego. Dane do testowania algorytmu zostały wzięte z bazy IDIAP. Wykorzystano też przetworzone dane z headsetu dla częstotliwości 18-26 Hz. W artykule przedstawiono zarówno algorytm jak i przykład przeprowadzonego testu. W teście uwzględniono obszary kory mózgowej związane z polami Brodmanna 4 i 6. Poprawność klasyfikacji zależy od tego, jak precyzyjnie są brane pod uwagę obszary związane z polami ruchowymi dotyczącymi rodzaju ruchu (w rozpatrywanym przypadku dotyczące ruchu prawą i lewą ręką). W przypadku danych uzyskiwanych z headsetu jakość klasyfikacji zależy od wstępnego przetworzenia sygnału oraz od czasu nauki klasyfikatora.
PL
Interfejsy mózg-komputer (Brain-Computer Interface) wykorzystują właściwości fal elektromagnetycznych mózgu rejestrowane za pomocą technik elektroencefalograficznych (EEG). Fale te są rejestrowane za pomocą elektrod na powierzchni głowy. Położenie źródeł sygnałów oraz ich natężenie znajdowane jest poprzez rozwiązanie zagadnienia odwrotnego. Proponowany w artykule algorytm do klasyfikacji sygnałów oparty jest na rekonstrukcji źródeł sygnałów. Algorytm przetestowano dla sygnałów związanych z ruchem prawą i lewą ręką, dlatego obliczenia przeprowadzono przede wszystkim dla fal o częstotliwości 20 Hz związanych m.in. z aktywnością myślową i ruchową. Użyte w teście dane były przetworzone i pochodziły z bazy Idiap. W artykule uwzględniono wyniki testów dla trzech zestawów danych, ale wobec niewielkiej różnicy między otrzymanymi wynikami, przedstawiono je tylko dla jednego zestawu. Wykorzystanie atlasów mózgu może poprawić wyniki klasyfikacji przez bardziej precyzyjne uwzględnienie obszarów mózgu związanych z konkretnym rodzajem aktywności.
EN
Brain-Computer Interfaces use the features of the electromagnetic brain waves registered with the use of electroencephalographic techniques (EEG). Signals are recorded from the surface of the scalp by means of electrodes. Source locations of signals and their strength are obtained when finding the solution to the inverse problem. The algorithm for signal classification proposed in this article is based on source reconstruction. The algorithm was tested for signals connected to the right and left hand movement, therefore calculations were conducted mainly for 20 Hz frequency waves connected with movement and imagining movement activities. The data used in the experiment, which were taken from the Idiap data base, were preprocessed. The article describes test results for three data sets, but due to the insignificant difference, the results are presented for one data set. Classification results may be improved with the use of brain atlases by taking into consideration more precise areas of the brain connected to the given activity.
EN
The article presents selected algorithms in inverse solutions in the EEG signal. When undertaking the calculations, it was assumed that the data obtained from electrodes on the surface of the head were preprocessed. As a result of using these algorithms it is possible to specify both the areas of the brain that the signals come from and the current density of the signals read by means of electrodes placed on the surface of the head. On the basis of knowing the solution to the inverse problem, an attempt was made to select the features of the signals. Then t-statistics was used to differentiate and order them.
PL
W artykule przedstawiono wybrane algorytmy rozwiązywania zagadnień odwrotnych w sygnale EEG. Przystępując do obliczeń założono, że dane uzyskane z elektrod rozmieszczonych na powierzchni głowy zostały wstępnie przetworzone. Wynikiem działania tych algorytmów jest lokalizacja obszarów mózgu, z których pochodzą sygnały oraz natężenia tych sygnałów odczytywanych za pomocą elektrod rozmieszczonych na powierzchni głowy. Znając rozwiązania zagadnienia odwrotnego podjęto też próbę selekcji cech. Wykorzystano t-statystykę do ich zróżnicowania i uszeregowania.
EN
Fetal monitoring is based on analysis of fetal heart rate signal. Visual interpretation is difficult so computer-aided systems for quantitative analysis are commonly used. The clinical interpretation guidelines provided by FIGO (Fédération Internationale de Gynécologie et d'Obstétrique) were used to develop the weighted fuzzy scoring system for qualitative assessment of the fetal state. In this work, agreement of the fuzzy classification system with the neonatal outcome assessment was analyzed. Various datasets were evaluated, depending on interpretation method of the signals which were recorded from patients. The obtained results confirmed possibility of the efficient fetal state assessment using the fuzzy inference method proposed.
9
Content available Fuzzy prediction of fetal acidemia
EN
Cardiotocography is the primary method for biophysical assessment of a fetal state. It is based mainly on the recording and analysis of fetal heart rate signal (FHR). Computer systems for fetal monitoring provide a quantitative description of FHR signals, however the effective methods for their qualitative assessment are still needed. The measurements of hydronium ions concentration (pH) in newborn cord blood is considered as the objective indicator of the fetal state. Improper pH level is a symptom of acidemia being the result of fetal hypoxia. The paper proposes a twostep analysis of signals allowing for effective prediction of the acidemia risk. The first step consists in the fuzzy classification of FHR signals. The task of fuzzy inference is to indicate signals that according to the FIGO guidelines represent the fetal wellbeing. These recordings are eliminated from the further classification with Lagrangian Support Vector Machines. The proposed procedure was evaluated using data collected with computerized fetal surveillance system. The classification results confirmed the high quality of the proposed fuzzy method of fetal state evaluation.
EN
Cardiotocography (CTG) is the main method of assessment of the fetal state during pregnancy and labour used in clinical practice. It is based on quantitative analysis of fetal heart rate, fetal movements and uterine contractions signals. The evaluation of the CTG signals can be made using criteria recommended by International Federation of Obstetrics and Gynecology. Nevertheless, the diagnosis verification is possible only after the delivery on the basis of newborn assessment. In the proposed work we evaluated the capacity of quantitative analysis of CTG traces in predicting fetal outcome. The relationship between CTG signal features and attributes of fetal outcome was assessed on the basis of ROC curves analysis. The obtained results indicate the adequate predictive capabilities of the selected CTG features especially for fetal outcome assessed with Apgar score and suggest the necessity of applying the criteria for the CTG traces evaluation that are related to the gestational age. Our study also shows the value of the CTG monitoring as a screening procedure providing appropriate confirmation of fetal wellbeing.
EN
A new supervised classification algorithm of a heavily distorted pattern (shape) obtained from noisy observations of nonstationary signals is proposed in the paper. Based on the Gabor transform of 1-D non-stationary signals, 2-D shapes of signals are formulated and the classification formula is developed using the pattern matching idea, which is the simplest case of a pattern recognition task. In the pattern matching problem, where a set of known patterns creates predefined classes, classification relies on assigning the examined pattern to one of the classes. Classical formulation of a Bayes decision rule requires a priori knowledge about statistical features characterising each class, which are rarely known in practice. In the proposed algorithm, the necessity of the statistical approach is avoided, especially since the probability distribution of noise is unknown. In the algorithm, the concept of discriminant functions, represented by Frobenius inner products, is used. The classification rule relies on the choice of the class corresponding to the max discriminant function. Computer simulation results are given to demonstrate the effectiveness of the new classification algorithm. It is shown that the proposed approach is able to correctly classify signals which are embedded in noise with a very low SNR ratio. One of the goals here is to develop a pattern recognition algorithm as the best possible way to automatically make decisions. All simulations have been performed in Matlab. The proposed algorithm can be applied to non-stationary frequency modulated signal classification and non-stationary signal recognition.
PL
W artykule przedstawiono procedurę rejestracji sygnałów przyspieszenia pochodzących z czujników biomedycznych Shimmer, sposób ich rozmieszczenia na ciele oraz opisano klasyfikator pozwalający na rozpoznawanie wybranych kategorii ruchu ludzkiego. W części eksperymentalnej artykułu zbadano wpływ filtracji dolnoprzepustowej sygnałów na skuteczność rozpoznawania typu aktywności ruchowej.
EN
In many scientific fields, especially medicine, information about human activity is crucial. The analysis of acceleration data coming from the sensors mounted on human’s limbs and trunk allows automatic classification of patients’activities (e.g. sitting, walking, getting up, etc). In this paper, a neural network based motion activity classifier and the procedure for recording signals from accelerometers are described. Owing to a very fast development of microcontrollers, it is now possible to create devices which enable real-time recording and transmission of signals from accelerometers. Today’s miniaturization enables the integration of accelerometers, microcontrollers and Bluetooth transmitters into a single matchbox-size device. Research carried out by Intel resulted in highly integrated devices and software platforms designed for networks of sensors which communicate wirelessly. Small size and weight of such devices as well as low energy consumption make the montage of sensors on a human body technically possible and comfortable for patients. The research proved that the localization of sensors on a human body has a great impact on the accuracy of motion type recognition. Many experiments addressing this subject were conducted, and finally an optimal sensors configuration was chosen. A group of 16 healthy people was observed. The acceleration signals were sampled with the frequency of 51,2 Hz whereas the G force was set within the range of 0 to 4. The 64 sample windows with the 32 samples overlap were used for the analysis. For each window, a set of parameters was extracted, which allowed the classification of signals. The research showed that the motion classifier based on neural networks ensures satisfying efficiency of motion type classification. Activity recognition was performed off-line. The accuracy of detection depended on the type of activity and the way the activity was performed. It turned out that for a better network training and testing, a greater number of signals must be collected.
EN
Cardiotocography is a biophysical method of fetal monitoring during pregnancy and labour. It is mainly based on recording and analysis of fetal heart activity. The computerized fetal monitoring systems provide the quantitative description of the recorded signals but the effective methods supporting the conclusion generation are still needed. The evaluation of the signal can be made using criteria recommended by FIGO. Nevertheless, the quantitative description of the traces is inconsistent with qualitative nature of the obstetric knowledge. Therefore, we applied the fuzzy system based on Takagi-Sugeno-Kang model to evaluate and classify signals. FIGO guidelines were used for developing a set of fuzzy conditional rules defining the system performance. The proposed system was evaluated using data collected with computerized fetal surveillance system – MONAKO. The classification results confirm the improvement of the fetal state evaluation quality while using the proposed fuzzy system support.
PL
Artykuł przedstawia prostą metodę klasyfikacji zakłóceń w sygnale elektroenergetycznym możliwą do wykorzystania w przenośnych urządzeniach monitorujących. Klasyfikacja sygnałów wykonana jest pod kątem jej zastosowania do wyboru metody kompresji sygnału elektroenergetycznego. Dokonany został podział zakłóceń elektroenergetycznych ze względu na ich podatność na kompresję metodami kompresji typu analiza-synteza (na przykładzie modelu Pronego) oraz metodę opartą na transformatach czasowo-częstotliwościowych (na przykładzie przekształcenia falkowego).
EN
The article presents a simple method for power signals classification which can be used with portable power quality monitoring systems for lossy data compression. Classifications method presented in this paper decides which algorithm of compression should be used for defined part of signal to get best compression factor and minimal reconstruction's errors. There is proposed two methods for signal compression: Prony's signals model and wavelet decomposition.
EN
Purpose: to demonstrate the possibility of finding features reliable for more precise distinguishing between normal and abnormal Pattern Electroretinogram (PERG) recordings, in Continuous Wavelet Transform (CWT) coefficients domain. To determine characteristic features of the PERG and Pattern Visual Evoked Potential (PVEP) waveforms important in the task of precise classification and assessment of these recordings. Material and methods: 60 normal PERG waveforms and 60 PVEPs as well as 47 PERGs and 27 PVEPs obtained in some retinal and optic nerve diseases were studied in the two age groups (< 50 years, > 50 years). All these signals were recorded in accordance with the guidelines of ISCEV in the Laboratory of Electrophysiology of the Retina and Visual Pathway and Static Perimetry, at the Department and Clinic of Ophthalmology of the Pomeranian Medical University. Continuous Wavelet Transform (CWT) was used for the time-frequency analysis and modelling of the PERG signal. Discriminant analysis and logistic regression were performed in statistical analysis of the PERG and PVEP signals. Obtained mathematical models were optimized using Fisher F (nI, n2) test. For preliminary evaluation of the obtained classification methods and algorithms in clinical practice, 22 PERGs and 55 PVEPs were chosen with respect to especially difficult discrimination problems ("borderline" recordings). Results: comparison between the method using CWT and standard time-domain based analysis showed that determining the maxima and minima of the PERG waves was achieved with better accuracy. This improvement was especially evident in waveforms with unclear peaks as well as in noisy signals. Predictive, quantitative models for PERGs and PVEPs binary classification were obtained based on characteristic features of the waveform morphology. Simple calculations algorithms for clinical applications were elaborated. They proved effective in distinguishing between normal and abnormal recordings. Conclusions: CWT based method is efficient in more precise assessment of the latencies of the PERG waveforms, improving separation between normal and abnormal waveforms. Filtering of the PERG signal may be optimized based on the results of the CWT analysis. Classification of the PERG and PVEP waveforms based on statistical methods is useful in preliminary interpretation of the recordings as well as in supporting more accurate assessment of clinical data.
16
Content available remote A Method for Robust Classification of QPSK Signals
EN
In this paper, the problem of classification of coherent QPSK signals, transmitted over the channel with an additive white non-Gaussian noise, is considered. Contrary to conventional QPSK detectors (clasifiers), that consist of the pair of correlators, decision devices and a multiplexer, and are commonly used in the case of the additive white Gaussian noise (AWGN) transmission channel (1), classification is based on analysis of n samples of the received QPSK signal representing a dibit. The proposed classification procedure is robust in the Huber minimax sense (2) on the class of [formula]-contaminated Gaussian noises.
first rewind previous Strona / 1 next fast forward last
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.