Wyniki wyszukiwania - Biblioteka Nauki

1

Distortion evaluation of wafelet multiband decomposition of EEG signals

100%

Walczak J. , Lewandowski M.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2007

|

tom No 53

101-112

EN

In this paper a cascade multiband filtration method based on a wavelet filters is described. This method can be an alternative solution to the traditional band-pass filters. Exemplary decomposition of EEG signal with evaluation of the filtration distortions is also included.

2

The use of double filtration in analysis of eeg signals

80%

Kawala-Janik A.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2010

|

tom z. 63

25-26

EN

In the following paper was presented double filtration of the EEG signals. The researched and analysed signals come from measurements conducted by the author of the hereof paper. The author will also hereby describe shortly one of the led experiments conducted inter alia at the Silesian University of Technology.

3

The use of the [alfha, beta, ghama] oscillations in the EEG signal

80%

Paszkiel S.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2010

|

tom z. 63

45-46

EN

This article presents the generation of the oscillation of [alfha, beta, ghama] rhythms which is directly connected with mutual correlations that occur between populations of pyramidal cells and interneurons. The significance of the oscillation of particular rhythms in the universal EEG signal is described. It is especially helpful during creating population models of this signal, which demonstrates its stochastic nature.

4

Notes on the models of brain structures based on subject literature and problems of their implementation

80%

Paszkiel S.

Zeszyty Naukowe. Elektryka / Politechnika Opolska

|

2011

|

tom z. 66

67-68

EN

Models enable to test the influence of different kinds of stimuli or changes of parameters of a model on its functioning as well as enable to formulate new hypotheses concerning a shaped system. Problems connected with implementations of models of EEG signal during conducted research are briefly described in this article.

5

Synchronous SSVEP Data Acquisition System

80%

Kotyra S. , Wójcik G. M. , Smolira M.

Annales Universitatis Mariae Curie-Skłodowska. Sectio AI, Informatica

|

2014

|

tom Vol. 14, no. 3

15--19

EN

Steady State Visually Evoked Potentials have been known for several decades and they appear in the primary visual cortex of brain as a result of light stimulation of the sense of sight. In this article a simple method for electroencephalographic data acquisition is presented. The system is based on the DSM-51 unit connected to goggles with blinking diodes and Mindset-1000 EEG amplifier with 16 channels. We present self-developed hardware and method of effective synchronization for the light stimulation and brain activity recording.

6

Concept of expert system interpreting correctness of measurement and method of the EEG signal analysis for needs of the brain-computer interface

80%

Paszkiel S.

Poznan University of Technology Academic Journals. Electrical Engineering

|

2016

|

tom No. 88

209--216

EN

The concept of construction of the expert system interpreting correctness of measurement and the method of the EEG signal analysis for needs of the brain-computer interface (BCI) are described in the article. The general orientations related with the methodology of creating the expert systems based on the knowledge base (KB) are characterised. Also, the brain-computer interface technology was described, which has been recently gaining more and more popularity within the scope of its application in control processes.

7

Estimation of the propagation direction and spectral properties of the EEG signals registered during sevoflurane anaesthesia using Directed Transfer Function method

70%

Olejarczyk E. , Kaminski M. , Marciniak R. , Byrczek T. , Stasiowski M. , Jalowiecki P. , Sobieszek A. , Zmyslowski W.

Polish Journal of Medical Physics And Engineering

|

2011

|

tom 17

|

nr 2

95-104

EN

The aim of this study was to estimate spectral properties and propagation of the EEG signals registered during sevoflurane anaesthesia between individual EEG recording channels. The intensities of activity flows were calculated for delta, theta, alpha and beta waves using the Directed Transfer Function integration procedure. It was found that delta waves played the dominant role in the EEG signal propagation during anesthesia and it was suggested that theta and alpha waves propagation could be related to the processes participating in the wakefulness control. Data obtained with DTF method were compared with data received from the analysis of cerebral blood flow with the use of PET in other laboratory. This study showed that analysis of the EEG signal propagation is useful for better understanding and thus safer induction of anaesthesia procedure.

8

Feature selection for EEG-based discrimination between imagination of left and right hand movements

70%

Binias B. , Palus H.

Measurement Automation Monitoring

|

2015

|

tom Vol. 61, No. 4

94--97

EN

: In this article was analyzed an influence of selected features on the accuracy of discrimination between imagination of right and left hand movements based on recorded EEG waveforms. The study showed a significant advantage that individual selection of features and a classification algorithm for analyzed data holds over the more general approach. The results were compared with the results obtained by the participants of the "BCI competition IV" and placed in the top three.

9

Rejestracja i analiza sygnału EEG na użytek neuromarketingu

60%

Kołodziej M. , Tarnowski P. , Majkowski A. , Rak J. R. , Dec D.

Przegląd Elektrotechniczny

|

2015

|

tom R. 91, nr 5

9-12

PL

Głównym celem eksperymentów jest znalezienie w zarejestrowanych sygnałach EEG cech, które umożliwiają rozróżnienie prezentowanych bodźców dźwiękowych o wysokim i niskim pobudzeniu emocjonalnym. Do wywołania określonych emocji wykorzystano bazę dźwięków IADS. W analizie sygnału wykorzystano wskaźniki, wbudowane w strukturę użytego oprogramowania, takie jak: Attention, Meditation, Delta (1-3 Hz), Theta (4-7 Hz) , Alpha1 (8-9 Hz), Alpha2 (10-12 Hz), Beta1 (13-17 Hz), Beta2 (18-30 Hz), Gamma1 (31-40 Hz), Gamma2 (41-50 Hz). Wykazano, że wskaźniki Attention, Alpha1, Alpha2 oraz Theta są powiązane w sposób istotny statystycznie ze stanem pobudzenia osoby badanej.

EN

The main objective of the experiments is to find, in recorded EEG signals, such features that allow to distinguish the presented sound stimuli with high and low emotional arousal. To evoke certain emotions IADS sound base was used. In signal analysis parameters built into the structure of the used software, such as Attention, Meditation, Delta (1-3 Hz), Theta (4-7 Hz) , Alpha1 (8-9 Hz), Alpha2 (10-12 Hz), Beta1 (13-17 Hz), Beta2 (18-30 Hz), Gamma1 (31-40 Hz), Gamma2 (41-50 Hz) were used. It has been shown that the parameters Attention, Alpha1, Alpha2 and Theta are related in a statistically significant way with the subject's state of arousal.

10

Outlier detection in EEG signals

60%

Duraj A. , Chomątek Ł.

Przegląd Elektrotechniczny

|

2023

|

tom R. 99, nr 1

237--240

EN

In this paper, the topic of detection of outliers in EEG signals was discussed, which facilitates making decisions about the diagnosis of a patient based on this study. We used two methods to detect outliers: the support vector machine and the k nearest neighbors method. The experiments were performed on a publicly available dataset containing EEG test results for 500 patients. The obtained results showed that the methods we used allow for the outlier detection efficiency at the level of 93%.

PL

W niniejszej pracy podjęto temat detekcji wyjątków w sygnałach EEG, co pozwala na ułatwienie podejmowania decyzji co do diagnozy pacjenta na podstawie tego badania. Do detekcji wyjątków wykorzystaliśmy dwie metody: maszynę wektorów nośnych i metodę k najblizszych sąsiadów. Eksperymenty zostały przeprowadzone na ogólnodostępnym zbiorze danych zawieraj ącym wyniki badania EEG dla 500 pacjentów. Uzyskane wyniki pokazały, że u żyte przez nas metody pozwalają na uzyskanie skuteczności detekcji wyjątków na poziomie 93%.

11

Epileptic seizure detection based on improved wavelet neural networks in long-term intracranial EEG

60%

Geng D. , Zhou W. , Zhang Y. , Geng S.

Biocybernetics and Biomedical Engineering

|

2016

|

tom Vol. 36, no. 2

375--384

EN

Automatic seizure detection is of great importance for speeding up the inspection process and relieving the workload of medical staff in the analysis of EEG recordings. In this study, a method based on an improved wavelet neural network (WNN) is proposed for automatic seizure detection in long-term intracranial EEG. WNN combines the traditional back propagation neural network (BPNN) with wavelet transform. Compared with classic WNN architectures, a modified point symmetry-based fuzzy c-means (MSFCM) algorithm is applied to the initialization of wavelet transform's translations, which has been successful in multiclass cancer classification. In addition, Fast-decaying Morlet wavelet is chosen as the activation function to make the WNN learn faster. Relative amplitude and relative fluctuation index are extracted as a feature vector to describe the variation of EEG signals, and the feature vector is then fed into WNN for classification. At last, post-processing including smoothing, channel fusion and collar technique is adopted to achieve more accurate and stable results. This system performs efficiently with the average sensitivity of 96.72%, specificity of 98.91% and false-detection rate of 0.27 h_1. The proposed approach achieves high sensitivity and low false detection rate, which demonstrates its potential for clinical usage.

12

Nowoczesna metoda komunikacji człowieka z komputerem : neurony źródłem informacji w technologii BCI

60%

Paszkiel S.

Śląskie Wiadomości Elektryczne

|

2015

|

tom Nr 2 (119)

4--5

PL

W niniejszym artykule przedstawiona została nowoczesna metoda komunikacji człowieka z komputerem, jaką jest technologia mózg-komputer. Scharakteryzowano aspekt źródła informacji w wyżej wymienionej technologii, jakim są neurony występujące w mózgu człowieka. Artykuł przedstawia także informacje na temat nowoczesnych rozwiązań technologicznych opracowanych na bazie technologii mózg-komputer dostępnych na rynku. W skrócie wymienione zostały także potencjalne zastosowania metody komunikacji mózgu człowieka z komputerem zarówno w zakresie nauk technicznych jak i społecznych.

EN

This paper presents a modern method of human-computer communication, which is the brain-computer technology. Characterized aspect of sources of information in the above technology, which neurons are present in the human brain. Article also presents information on new technological solutions developed on the basis of brain-computer technology commercially available. In short listed as a potential application of the method of communication of the human brain with a computer, both in terms of technical and society sciences.

13

Effect of Feature Extraction on Automatic Sleep Stage Classification by Artificial Neural Network

60%

Prucnal M. , Polak A. G.

Metrology and Measurement Systems

|

2017

|

tom Vol. 24, nr 2

229--240

EN

EEG signal-based sleep stage classification facilitates an initial diagnosis of sleep disorders. The aim of this study was to compare the efficiency of three methods for feature extraction: power spectral density (PSD), discrete wavelet transform (DWT) and empirical mode decomposition (EMD) in the automatic classification of sleep stages by an artificial neural network (ANN). 13650 30-second EEG epochs from the PhysioNet database, representing five sleep stages (W, N1-N3 and REM), were transformed into feature vectors using the aforementioned methods and principal component analysis (PCA). Three feed-forward ANNs with the same optimal structure (12 input neurons, 23 + 22 neurons in two hidden layers and 5 output neurons) were trained using three sets of features, obtained with one of the compared methods each. Calculating PSD from EEG epochs in frequency sub-bands corresponding to the brain waves (81.1% accuracy for the testing set, comparing with 74.2% for DWT and 57.6% for EMD) appeared to be the most effective feature extraction method in the analysed problem.

14

Comparison of information on sleep apnoea contained in two symmetric EEG recordings

60%

Prucnal M. A. , Polak A. G.

Metrology and Measurement Systems

|

2019

|

tom Vol. 26, nr 2

229--239

EN

Electroencephalogram (EEG) is one of biomedical signals measured during all-night polysomnography to diagnose sleep disorders, including sleep apnoea. Usually two central EEG channels (C3-A2 and C4-A1) are recorded, but typically only one of them are used. The purpose of this work was to compare discriminative features characterizing normal breathing, as well as obstructive and central sleep apneas derived from these central EEG channels. The same methodology of feature extraction and selection was applied separately for the both synchronous signals. The features were extracted by combined discrete wavelet and Hilbert transforms. Afterwards, the statistical indexes were calculated and the features were selected using the analysis of variance and multivariate regression. According to the obtained results, there is a partial difference in information contained in the EEG signals carried by C3-A2 and C4-A1 EEG channels, so data from the both channels should be preferably used together for automatic sleep apnoea detection and differentiation.

15

Gray-level co-occurrence matrix of Fourier synchrosqueezed transform for epileptic seizure detection

51%

Mamli S. , Kalbkhani H.

Biocybernetics and Biomedical Engineering

|

2019

|

tom Vol. 39, no. 1

87--99

EN

Epilepsy is a brain disorder that many persons of different ages in the world suffer from it. According to the world health organization, epilepsy is characterized by repetitive seizures and more electrical discharge in a group of brain neurons results in sudden physical actions. The aim of this paper is to introduce a new method to classify epileptic phases based on Fourier synchro-squeezed transform (FSST) of electroencephalogram (EEG) signals. FSST is a time-frequency (TF) analysis and provides sharper TF estimates than the conventional short-time Fourier transform (STFT). Absolute of FSST of EEG signal is computed and segmented into five non-overlapping frequency sub-bands as delta (d), theta (u), alpha (a), beta (b), and gamma (g). Each sub-band is considered as a gray-scale image and then we propose to obtain the gray-level co-occurrence matrix (GLCM) of each sub-band as features. We concatenate the features of different sub-bands to obtain the final feature vector. After selecting informative features by infinite latent feature selection (ILFS) method, the support vector machine (SVM) and K-nearest neighbor (KNN) classifiers are used separately to classify EEG signals. We use the EEG signals from Bonn University database and different combinations of its sets are considered. Simulation results show that the proposed method efficiently classifies the EEG signals and can be used to determine the phase of epilepsy.

16

Dekompozycja sygnałów EEG w dziedzinie czasu przy zastosowaniu transformacji Hilberta-Huanga HHT

51%

Gawędzki W. , Socha M. , Sławik P.

Przegląd Elektrotechniczny

|

2015

|

tom R. 91, nr 5

33-36

PL

Do dekompozycji sygnałów EEG w dziedzinie czasu zastosowana została empiryczna metoda EMD (ang. Empirical Mode Decomposition), która w wersji rozszerzonej o transformację Hilberta funkcjonuje pod nazwą transformacji HHT (ang. Hilbert-Huang Transform). Transformacja ta umożliwia poprawną dekompozycję sygnału EEG na sumę quasi-harmonicznych składowych, których amplitudy oraz częstotliwości są parametrycznymi funkcjami czasu. W przeciwieństwie do stosowanych aktualnie w diagnostyce transformacji Fouriera DFT oraz STFT nadaje się ona do analizy zjawisk o charakterze zarówno nieliniowym jak i niestacjonarnym.

EN

An Empirical Mode Decomposition method extended with the Hilbert transform (Hilbert-Huang Transform) was used for EEG decomposition in time domain. This transformation allows for proper EEG signal decomposition into quasi-harmonic components that amplitudes and frequencies are time dependence functions. In contrast to commonly used in diagnostic’s DFT and STFT transformations, proposed method is suitable for non-stationary and nonlinear phenomenon’s.

17

Neurofeedback - eksperymenty w LabVIEW

51%

Rak R. J. , Majkowski A. , Kołodziej M. , Sułko G.

Przegląd Elektrotechniczny

|

2013

|

tom R. 89, nr 10

263-265

PL

W artykule przedstawiono aplikację do samodzielnego treningu umysłu z wykorzystaniem neurofeedbacku. Aplikacja została stworzona w środowisku LabVIEW, z użyciem otwartej platformy BCI2000. Najważniejsze części aplikacji to: moduł zbierania danych oraz moduł przetwarzania sygnału EEG przy użyciu szybkiego przekształcenia Fouriera. Kluczowym elementem systemu jest moduł, który dla określonej przez użytkownika częstotliwości, dokonuje pomiaru energii sygnału. Wyniki wyświetlane są na panelu aplikacji użytkownika, zapewniając pożądane sprzężenie zwrotne.

EN

This paper presents an application for self-training of the mind with the use of neurofeedback. The application was developed in LabVIEW environment, using the open BCI2000 platform. The most important parts of the application are data acquisition module and EEG signal processing module implementing Fast Fourier Transform. The key element of the system is the module that, for a user-specified frequency, measures signal energy. The results are then displayed to provide the desired feedback.

18

Brain-computer interaction analysis based on EEG signal and gaze-tracking information

51%

Kaszuba K. , Kostek B.

Elektronika : konstrukcje, technologie, zastosowania

|

2012

|

tom Vol. 53, nr 5

21-25

EN

The article presents an attempt to integrate EEG signal analysis with information about human visual activities, i.e. gaze fixation point. The results from gaze-tracking-based measurement were combined with the standard EEG analysis. A search for correlation between the brain activity and the region of the screen observed by the user was performed. The preliminary stage of the study consists in electrooculography (EOG) signal processing. The EOG signal was obtained in a series of experiments and served as reference data. An attempt to correlate this Information with the EEG signal analysis is described and multiple approaches of signal pre-processing, feature extraction and classification are applied.

PL

W niniejszym artykule podjęto próbę analizy sygnału EEG z informacją o aktywności wzrokowej człowieka w kontekście interfejsów mózg-komputer. Wykorzystano funkcjonalności rejestratora sygnału EEG oraz systemu śledzenia punktu fiksacji wzroku. Poszukiwana była korelacja pomiędzy obserwowanym obszarem ekranu a aktywnością mózgu. Sygnał EOG, nagrany w trakcie serii wstępnych eksperymentów, posłużył jako dane referencyjne. Zbadano możliwość automatycznej detekcji podobnej informacji w sygnale EEG poprzez zastosowanie różnych metod wstępnego przetwarzania, ekstrakcji cech sygnału oraz zastosowaniu różnych klasyfikatorów.

19

Komunikacja człowieka z komputerem za pomocą sygnału EEG

51%

Byczuk M. , Materka A.

Elektronika : prace naukowe

|

2003

|

tom nr 8

35-52

PL

Praca zawiera przegląd technik analizy sygnału EEG (elektro-encefalograficznego) stosowanych do komunikacji człowieka z komputerem i wybranych systemów wykorzystujących te techniki. Opisano w niej również autorski prototypowy system akwizycji sygnału EEG, przeznaczony do prowadzenia badań naukowych w zakresie rozwoju metod analizy tego sygnału do zastosowań w interfejsach BCI (brain-computer interface). Omówiono schemat blokowy skonstruowanego układu i obwody kompensacji zakłóceń. Przedstawiono wyniki pierwszych eksperymentów przeprowadzonych z użyciem układu prototypowego, potwierdzające jego przydatność do cyfrowej analizy sygnałów EEG, w środowisku typowego laboratorium elektronicznego, bez dodatkowego ekranowania.

EN

The aim of this work is to design a multi-channel mixed-signal system for EEG signal acquisition in brain-computer interfaces. The paper contains a review of EEG signal analysis methods that are used in human-computer communication syste ms. Selected syste ms of this type are described in more detail. A prototype, single-channel sub-system architecture is characterized featuring sufficiently high noise immunity and common-mode rejection to allow EEG signal acquisition. Optical isolation is used for safe circuit operation in a typical office environment. Each channel incorporates 3 integrated-circuit instrumentation amplifiers with a total gain of 80 dB. A single-chip controller is used to work out digital signals to drive 10-bit analog to digital converters. First experimental results are presented, measured using a battery-operated prototype. It is demonstrated that the circuit suppresses very effectively the 50 Hz interference in a typical research laboratory and allows clear detection of alpha-waves via Fourier spectrum analysis of acquired EEG signal, without any special case or shielding. It is expected that the system will be useful to provide a basis for research in the area of development of brain-computer interfaces to technical devices, e.g. as an aid for handicapped persons.

20

Classification of EEG signal by methods of machine learning

51%

Alyamani A. , Yasniy O.

Applied Computer Science

|

2020

|

tom Vol. 16, no 4

56--63

EN

Electroencephalogram (EEG) signal of two healthy subjects that was available from literature, was studied using the methods of machine learning, namely, decision trees (DT), multilayer perceptron (MLP), K-nearest neighbours (kNN), and support vector machines (SVM). Since the data were imbalanced, the appropriate balancing was performed by Kmeans clustering algorithm. The original and balanced data were classified by means of the mentioned above 4 methods. It was found, that SVM showed the best result for the both datasets in terms of accuracy. MLP and kNN produce the comparable results which are almost the same. DT accuracies are the lowest for the given dataset, with 83.82% for the original data and 61.48% for the balanced data.