Automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning / 生物医学工程学杂志

The existing automatic sleep staging algorithms have the problems of too many model parameters and long training time, which in turn results in poor sleep staging efficiency. Using a single channel electroencephalogram (EEG) signal, this paper proposed an automatic sleep staging algorithm for stochastic depth residual networks based on transfer learning (TL-SDResNet). Firstly, a total of 30 single-channel (Fpz-Cz) EEG signals from 16 individuals were selected, and after preserving the effective sleep segments, the raw EEG signals were pre-processed using Butterworth filter and continuous wavelet transform to obtain two-dimensional images containing its time-frequency joint features as the input data for the staging model. Then, a ResNet50 pre-trained model trained on a publicly available dataset, the sleep database extension stored in European data format (Sleep-EDFx) was constructed, using a stochastic depth strategy and modifying the output layer to optimize the model structure. Finally, transfer learning was applied to the human sleep process throughout the night. The algorithm in this paper achieved a model staging accuracy of 87.95% after conducting several experiments. Experiments show that TL-SDResNet50 can accomplish fast training of a small amount of EEG data, and the overall effect is better than other staging algorithms and classical algorithms in recent years, which has certain practical value.

An Adaptive Method for Detecting and Removing EEG Noise / 中国医疗器械杂志

To solve the problem of real-time detection and removal of EEG signal noise in anesthesia depth monitoring, we proposed an adaptive EEG signal noise detection and removal method. This method uses discrete wavelet transform to extract the low-frequency energy and high-frequency energy of a segment of EEG signals, and sets two sets of thresholds for the low-frequency band and high-frequency band of the EEG signal. These two sets of thresholds can be updated adaptively according to the energy situation of the most recent EEG signal. Finally, we judge the level of signal interference according to the range of low-frequency energy and high-frequency energy, and perform corresponding denoising processing. The results show that the method can more accurately detect and remove the noise interference in the EEG signal, and improve the stability of the calculated characteristic parameters.

Suicide cases in developed and emerging countries: an analysis using wavelets / Casos de suicídio em países desenvolvidos e emergentes: uma análise usando ondaletas

OBJECTIVE: The aim of this study was to use a wavelet technique to determine whether the number of suicides is similar between developed and emerging countries. METHODS: Annual data were obtained from World Health Organization (WHO) reports from 1986 to 2015. Discrete nondecimated wavelet transform was used for the analysis, and the Daubechies wavelet function was applied with five-level decomposition. Regarding clustering, energy (variance) was used to analyze the clusters and visualize the clustering process. We constructed a dendrogram using the Mahalanobis distance. The number of groups was set using a specific function in the R program. RESULTS: The cluster analysis verified the formation of four groups as follows: Japan, the United States and Brazil were distinct and isolated groups, and other countries (Austria, Belgium, Chile, Israel, Mexico, Italy and the Netherlands) constituted a single group. CONCLUSION: The methods utilized in this paper enabled a detailed verification of countries with similar behaviors despite very distinct socioeconomic, geographic and climate characteristics.

OBJETIVO: Verificar se existe relação de similaridade entre o número de suicídio em países desenvolvidos e emergentes usando a técnica de ondaletas. MÉTODOS: Os dados anuais foram obtidos a partir do relatório da Organização Mundial da Saúde (OMS), no período de 1986 a 2015. Para análise, foi empregada a transformada discreta não decimada de ondaleta (NDWT), a função ondaleta aplicada foi a Daubechies com cinco níveis de decomposição. Com relação ao agrupamento, utilizou-se a energia (variância) para analisar os clusters e, para a visualização do processo de clusterização, trabalhamos com o dendograma, no qual se empregou a distância de Mahalanobis. A quantidade de grupos foi definida por meio da função NbCluster. RESULTADOS: A partir da análise de cluster, verificou-se a formação de quatros grupos. No qual, Japão e Estados Unidos e Brasil localizam-se em grupos distintos e isolados. E os demais países (Áustria, Bélgica, Chile, Israel, México, Itália e Holanda) em um único grupo. CONCLUSÃO: Utilizando esse método, foi possível verificar com mais detalhes quais países apresentaram comportamentos semelhantes, mesmo apresentando características bem distintas entre si, tanto socioeconômica, geográfica e climática.

Research on automatic removal of ocular artifacts from single channel electroencephalogram signals based on wavelet transform and ensemble empirical mode decomposition / 生物医学工程学杂志

The brain-computer interface (BCI) systems used in practical applications require as few electroencephalogram (EEG) acquisition channels as possible. However, when it is reduced to one channel, it is difficult to remove the electrooculogram (EOG) artifacts. Therefore, this paper proposed an EOG artifact removal algorithm based on wavelet transform and ensemble empirical mode decomposition. Firstly, the single channel EEG signal is subjected to wavelet transform, and the wavelet components which involve EOG artifact are decomposed by ensemble empirical mode decomposition. Then the predefined autocorrelation coefficient threshold is used to automatically select and remove the intrinsic modal functions which mainly composed of EOG components. And finally the 'clean' EEG signal is reconstructed. The comparative experiments on the simulation data and the real data show that the algorithm proposed in this paper solves the problem of automatic removal of EOG artifacts in single-channel EEG signals. It can effectively remove the EOG artifacts when causes less EEG distortion and has less algorithm complexity at the same time. It helps to promote the BCI technology out of the laboratory and toward commercial application.

Application of Improved Wavelet Threshold in Denoising of ECG Signals / 中国医疗器械杂志

The ECG signal is susceptible to interference from the external environment during the acquisition process, affecting the analysis and processing of the ECG signal. After the traditional soft-hard threshold function is processed, there is a defect that the signal quality is not high and the continuity at the threshold is poor. An improved threshold function wavelet denoising is proposed, which has better regulation and continuity, and effectively solves the shortcomings of traditional soft and hard threshold functions. The Matlab simulation is carried out through a large amount of data, and various processing methods are compared. The results show that the improved threshold function can improve the denoising effect and is superior to the traditional soft and hard threshold denoising.

Mild poikilocapnic hypoxia increases very low frequency haemoglobin oxygenation oscillations in prefrontal cortex

BACKGROUND: The aim of the study was to investigate the effect of mild cerebral hypoxia on haemoglobin oxygenation (HbO2), cerebrospinal fluid dynamics and cardiovascular physiology. To achieve this goal, four signals were recorded simultaneously: blood pressure, heart rate / electrocardiogram, HbO2 from right hemisphere and changes of subarachnoid space (SAS) width from left hemisphere. Signals were registered from 30 healthy, young participants (2 females and 28 males, body mass index = 24.5 ± 2.3 kg/m2, age 30.8 ± 13.4 years). RESULTS: We analysed the recorded signals using wavelet transform and phase coherence. We demonstrated for the first time that in healthy subjects exposed to mild poikilokapnic hypoxia there were increases in very low frequency HbO2 oscillations (< 0.052 Hz) in prefrontal cortex. Additionally, SAS fluctuation diminished in the whole frequency range which could be explained by brain oedema. CONCLUSIONS: Consequently the study provides insight into mechanisms governing brain response to a mild hypoxic challenge. Our study supports the notion that HbO2 and SAS width monitoring might be beneficial for patients with acute lung disease.

Research on the detection algorithm of electrocardiogram characteristic wave based on energy segmentation and stationary wavelet transform / 生物医学工程学杂志

The detection of electrocardiogram (ECG) characteristic wave is the basis of cardiovascular disease analysis and heart rate variability analysis. In order to solve the problems of low detection accuracy and poor real-time performance of ECG signal in the state of motion, this paper proposes a detection algorithm based on segmentation energy and stationary wavelet transform (SWT). Firstly, the energy of ECG signal is calculated by segmenting, and the energy candidate peak is obtained after moving average to detect QRS complex. Secondly, the QRS amplitude is set to zero and the fifth component of SWT is used to locate P wave and T wave. The experimental results show that compared with other algorithms, the algorithm in this paper has high accuracy in detecting QRS complex in different motion states. It only takes 0.22 s to detect QSR complex of a 30-minute ECG record, and the real-time performance is improved obviously. On the basis of QRS complex detection, the accuracy of P wave and T wave detection is higher than 95%. The results show that this method can improve the efficiency of ECG signal detection, and provide a new method for real-time ECG signal classification and cardiovascular disease diagnosis.

An anesthesia depth computing method study based on wavelet transform and artificial neural network / 生物医学工程学杂志

General anesthesia is an essential part of surgery to ensure the safety of patients. Electroencephalogram (EEG) has been widely used in anesthesia depth monitoring for abundant information and the ability of reflecting the brain activity. The paper proposes a method which combines wavelet transform and artificial neural network (ANN) to assess the depth of anesthesia. Discrete wavelet transform was used to decompose the EEG signal, and the approximation coefficients and detail coefficients were used to calculate the 9 characteristic parameters. Kruskal-Wallis statistical test was made to these characteristic parameters, and the test showed that the parameters were statistically significant for the differences of the four levels of anesthesia: awake, light anesthesia, moderate anesthesia and deep anesthesia (

Ortogonalización de derivaciones de electrocardiograma / Orthogonalization of electrocardiographic derivations

Introducción: El delineador de señales electrocardiográficas (ECG) multiderivación basado en la transformada wavelet posee alta resolución espacial y permite eliminar las diferencias interderivación que aparecen tradicionalmente en los métodos uniderivación. Para esto necesita de derivaciones de señales electrocardiográficas ortogonales entre sí para la obtención de un bucle espacial. Objetivo: Desarrollar métodos de ortogonalización de dos o tres derivaciones de señales electrocardiográficas que permitan la generalización del delineador multiderivación basado en la transformada wavelet en cualquier base de datos señales electrocardiográficas con más de una derivación. Métodos: Se implementaron tres métodos de ortogonalización de derivaciones de señales electrocardiográficas: ortogonalización de dos derivaciones a partir de la proyección de vectores, ortogonalización a partir de componentes principales y ortogonalización a partir del método clásico de Gram-Schmidt. Resultados: Se comparó el funcionamiento del delineador multiderivación de ECG cuando es usado cada método de ortogonalización, mediante el cálculo de la media aritmética y la desviación estándar teniendo en cuenta diferentes combinaciones de derivaciones de ambas bases de datos para cada una de las marcas analizadas. Los mejores resultados se obtuvieron con el método análisis de componentes principales y el peor comportamiento con el método de ortogonalización de dos derivaciones. Conclusiones: Los algoritmos de ortogonalización que obtuvieron los mejores resultados fueron los basados en tres derivaciones ortogonales, en la que fue ligeramente superior la descomposición en componentes principales y, por tanto, se considera el método más adecuado para la generalización del delineador multiderivación(AU)

Introduction: The wavelet transform-based multiderivation electrocardiographic (ECG) signal delineator has high spatial resolution and makes it possible to eliminate interderivation differences traditionally appearing in uniderivation methods. But this requires electrocardiographic signal derivations orthogonal to one another to obtain a spatial loop. Objective: Develop orthogonalization methods of two or three electrographic signal derivations allowing generalization of the wavelet transform-based multiderivation delineator in any electrographic signal database with more than one derivation. Methods: Three orthogonalization methods were implemented for electrocardiographic signal derivations: vector projection-based two-derivation orthogonalization, principal component-based orthogonalization, and orthogonalization based on the Gram-Schmidt classic method. Results: A comparison was performed between the operation of the ECG multiderivation delineator when used with each orthogonalization method. The comparison was based on estimation of the arithmetic mean and standard deviation bearing in mind different combinations of derivations from both databases for each of the marks analyzed. The best results were obtained with the principal component analysis method and the worst ones with the two-derivation orthogonalization method. Conclusions: The orthogonalization algorithms obtaining the best results were those based on three orthogonal derivations, in which decomposition into principal components was slightly higher. This is therefore considered to be the most appropriate method for generalization of the multiderivation delineator(AU)

Detection and Classification of Brain Tumor in MRI Images Using Wavelet Transform and Convolutional Neural Network

A brain tumoris a mass of abnormal cells in the brain. Brain tumors can be benignor malignant. Conventional diagnosis of a brain tumor by the radiologist, is done by examining a set of images produced by magnetic resonance imaging (MRI).Many computer-aided detection (CAD) systems have been developed in order to help the radiologist reach his goal of correctly classifying the MRI image. Convolutional neural networks (CNNs) have been widely used in the classification of medical images. This paper presents anovel CAD technique for the classification of brain tumors in MRI images The proposed system extracts features from the brain MRI images by utilizingthe strong energy compactness property exhibited by the Discrete Wavelet transform (DWT). The Wavelet features are then applied to a CNNto classify the input MRI image. Experimental results indicate that the proposed approach outperforms other commonly used methods and gives an overall accuracy of 98.5%.

Evaluation of genome similarities using a wavelet-domain approach

Abstract INTRODUCTION: Tuberculosis is listed among the top 10 causes of deaths worldwide. The resistant strains causing this disease have been considered to be responsible for public health emergencies and health security threats. As stated by the World Health Organization (WHO), around 558,000 different cases coupled with resistance to rifampicin (the most operative first-line drug) have been estimated to date. Therefore, in order to detect the resistant strains using the genomes of Mycobacterium tuberculosis (MTB), we propose a new methodology for the analysis of genomic similarities that associate the different levels of decomposition of the genome (discrete non-decimated wavelet transform) and the Hurst exponent. METHODS: The signals corresponding to the ten analyzed sequences were obtained by assessing GC content, and then these signals were decomposed using the discrete non-decimated wavelet transform along with the Daubechies wavelet with four null moments at five levels of decomposition. The Hurst exponent was calculated at each decomposition level using five different methods. The cluster analysis was performed using the results obtained for the Hurst exponent. RESULTS: The aggregated variance, differenced aggregated variance, and aggregated absolute value methods presented the formation of three groups, whereas the Peng and R/S methods presented the formation of two groups. The aggregated variance method exhibited the best results with respect to the group formation between similar strains. CONCLUSION: The evaluation of Hurst exponent associated with discrete non-decimated wavelet transform can be used as a measure of similarity between genome sequences, thus leading to a refinement in the analysis.

Mejoramiento de contraste y segmentación en imágenes de úlceras del pie diabético / Contrast enhancement and segmentation in diabetic foot ulcer images

Introducción: El 3 a 5 por ciento de los pacientes diabéticos en Cuba sufren úlcera del pie diabético. Las imágenes fotográficas de estas úlceras permiten hacer evaluaciones cuantitativas de los tratamientos. En Cuba, dicha evaluación se hace manual o semiautomáticamente. No se registra software cubano que automáticamente realice la medición de las áreas de la lesión y permita conocer las características de la úlcera, antes y después de la aplicación de un tratamiento. Objetivo: Comparar cualitativamente métodos de preprocesamiento y segmentación de la úlcera, dada la ausencia de una regla de oro. Método: Estudio descriptivo y transversal en 6 pacientes diabéticos del Instituto Nacional de Angiología y Cirugía Vascular en octubre de 2018, con lesiones de grado I-IV en la escala de Wagner. Se utilizó el marco estereotáxico para extremidades FrameHeber03® para obtener imágenes planimétricas estandarizadas de las úlceras. Se obtuvieron 51 imágenes de úlceras que se preprocesaron mediante el algoritmo Transformada Wavelet Discreta Logarítmica en un modelo S-LIP y se determinó su borde mediante los métodos de segmentación Chan-Vese, modelo de mezclas gaussianas y GrabCut. Resultados: Se mostró la utilidad de preprocesar las imágenes para lograr mejores resultados en la segmentación. El mejor y más factible método de segmentación fue el de mezclas gaussianas. Los algoritmos resultaron ser más precisos en pacientes de piel oscura, debido al mayor contraste entre la piel y el borde de la úlcera. Conclusiones: El algoritmo de segmentación automática de mezclas gaussianas. puede incluirse en un software para medir el área de la úlcera(AU)

Introduction: The 3 to 5 percent of Cuban diabetic patients suffer from diabetic foot ulcer. The diabetic foot ulcer photographic images allow quantitative evaluations of a treatment. In Cuba, the ulcer area measurement is done manually or semi-automatically. There is no Cuban software reported that automatically measures the area, and allows knowing the state of the foot ulcer before and after a treatment. Goal: To compare qualitatively (given the absence of a gold standard) ulcer´s pre-processing and segmentation methods. Method: We develop a descriptive and transversal study with 6 diabetic patients from Nacional Institute of Angiology and Vascular Surgery during October, 2018, with lesions of degree I-IV in the Wagner scale. The stereotaxic frame FrameHeber03® was used for obtaining planimetric images of the ulcers. In all, 51 ulcer images were obtained, and then we pre-processed it by Logarithmic Discrete Wavelet Transform under a S-LIP model, and found the ulcer border with the segmentation methods Chan-Vese, Gaussian Mixture Model (GMM), and GrabCut. Results: The pre-processing step was crutial for obtaining good results in the segmentation step. The best performance was reached by the GMM segmentation method. The algorithms were more accurate in images with black skin patients, due to the high contrast between the skin and the ulcer border. Conclusions: The automatic segmentation method (GMM) could be included in a software for detecting the border of the diabetic foot ulcer(AU)

A Mattress System of Recognizing Sleep Postures Based on BCG Signal / 中国医疗器械杂志

Sleep posture recognition is the core index of diagnosis and treatment of positional sleep apnea syndrome. In order to detect body postures noninvasively, we developed a portable approach for sleep posture recognition using BCG signals with their morphological difference. A type of piezo-electric polymer film sensor was applied to the mattress to acquire BCG, the discrete wavelet transform with cubic B-spline was used to extract characteristic parameters and a naive Bayes learning phase was adapted to predict body postures. Eleven healthy subjects participated in the sleep simulation experiments. The results indicate that the mean error obtained from heart rates was 0.04±1.3 beats/min (±1.96 SD). The final recognition accuracy of four basic sleep postures exceeded 97%, and the average value was 97.9%. This measuring system is comfortable and accurate, which can be streamlined for daily sleep monitoring application.

Time–frequency localization using three-tap biorthogonal wavelet filter bank for electrocardiogram compressions

A joint time–frequency localized three-band biorthogonal wavelet filter bank to compress Electrocardiogram signals is proposed in this work. Further, the use of adaptive thresholding and modified run-length encoding resulted in maximum data volume reduction while guaranteeing reconstructing quality. Using signal-to-noise ratio, compression ratio (C(R)), maximum absolute error (E(MA)), quality score (Q(s)), root mean square error, compression time (C(T)) and percentage root mean square difference the validity of the proposed approach is studied. The experimental results deduced that the performance of the proposed approach is better when compared to the two-band wavelet filter bank. The proposed compression method enables loss-less data transmission of medical signals to remote locations for therapeutic usage.

Multi class disorder detection of magnetic resonance brain images using composite features and neural network

Brain disorder recognition has becoming a promising area of study. In reality, some disorders share similar features and signs, making the task of diagnosis and treatment challenging. This paper presents a rigorous and robust computer aided diagnosis system for the detection of multiple brain abnormalities which can assist physicians in the diagnosis and treatment of brain diseases. In this system, we used energy of wavelet sub bands, textural features of gray level co-occurrence matrix and intensity feature of MR brain images. These features are ranked using Wilcoxon test. The composite features are classifi ed using back propagation neural network. Bayesian regulation is adopted to fi nd the optimal weights of neural network. The experimentation is carried out on datasets DS-90 and DS-310 of Harvard Medical School. To enhance the generalization capability of the network, fi vefold stratifi ed cross validation technique is used. The proposed system yields multi class disease classifi cation accuracy of 100% in diff erentiating 90 MR brain images into 18 classes and 97.81% in diff erentiating 310 MR brain images into 6 classes. The experimental results reveal that the composite features along with BPNN classifi er create a competent and reliable system for the identifi cation of multiple brain disorders which can be used in clinical applications. The Wilcoxon test outcome demonstrates that standard deviation feature along with energies of approximate and vertical sub bands of level 7 contribute the most in achieving enhanced multi class classifi cation performance results.

Real-time premature ventricular contractions detection based on Redundant Discrete Wavelet Transform

Abstract Introduction Premature Ventricular Contraction (PVC) is among the most common types of ventricular cardiac arrhythmia. However, it only poses danger if the person suffers from a heart disease, such as heart failure. Hence, this is an important factor to consider in heart disease people. This paper presents an ECG real-time analysis system for PVC detection. Methods This system is based on threshold adaptive methods and Redundant Discrete Wavelet Transform (RDWT), with a real-time approach. This analysis is based on wavelet coefficients energy for PVC detection. It is presented also a study to find the most indicated wavelet mother for ECG analysis application among the following wavelet families: Daubechies, Coiflets and Symlets. The system detection performance was validated on the MIT-BIH Arrhythmia Database. Results The best results were verified with db2 wavelet mother: the Sensitivity Se = 99.18%, Positive Predictive Value P+ = 99.15% and Specificity Sp = 99.94%, on 80.872 annotated beats, and 61.2 s processing speed for a half-hour record. Conclusion The proposed system exhibits reliable PVC detection, with real-time approach, and a simple algorithmic structure that can be implemented in many platforms.

An Improved Classification System for Brain Tumours Using Wavelet Transform and Neural Network / Un sistema de clasificación mejorado para los tumores cerebrales usando la transformada de ondeletas y la red neuronal

ABSTRACT This paper presents an improved classification system for brain tumours using wavelet transform and neural network. The anisotropic diffusion filter was used for image denoising, and the performance of the oriented rician noise reducing anisotropic diffusion (ORNRAD) filter was validated. The segmentation of the denoised image was carried out by fuzzy c-means clustering. The features were extracted using symlet and coiflet wavelet transforms, and the Levenberg-Marquardt algorithm based neural network was used to classify the magnetic resonance (MR) images. This classification technique of MR images was tested and analysed with existing methods, and its performance was found to be satisfactory with a classification accuracy of 93.24%. The developed system could assist physicians in classifying MR images for better decision-making.

RESUMEN Este artículo presenta un sistema de clasificación mejorado para los tumores de cerebro usando la transformada de ondeletas (transformada wavelet) y la red neuronal. El filtro de difusión anisotrópica fue utilizado para la eliminación del ruido de la imagen, y se validó el funcionamiento del filtro de difusión anisotrópica orientado a reducir el ruido riciano (ORNRAD, siglas en inglés). La segmentación de la imagen 'desruidizada ' (denoised) fue realizada mediante el agrupamiento difuso c-means fuzzy. Las características fueron extraídas usando las transformadas de ondeletas symlet y coiflet, y la red neuronal basada en el algoritmo de Levenberg-Marquardt fue utilizada para clasificar las imágenes de resonancia magnética (RM) imágenes. Esta técnica de clasificación de imágenes de RM fue probada y analizada con métodos existentes, y se halló que su rendimiento era satisfactorio con una precisión de clasificación de 93.24%. El sistema desarrollado podría ayudar a los médicos a clasificar imágenes de RM para una mejor toma de decisiones.

Comparative study on evaluation algorithms for neck muscle fatigue based on surface electromyography signal / 生物医学工程学杂志

The purpose of this study is to compare the differences among neck muscle fatigue evaluation algorithms and to find a more effective algorithm which can provide a human factor quantitative evaluation method for neck muscle fatigue during bending over the desk. We collected surface electromyography signal of sternocleidomastoid muscle of 15 subjects using wireless physiotherapy Bio-Radio when they bent over the desk using memory pillows for 12 minutes. Five algorithms including mean power frequency, spectral moments ratio, discrete wavelet transform, fuzzy approximation entropy and the complexity algorithms were used to calculate the corresponding muscle fatigue index. The least squares method was used to calculate the corresponding coefficient of determination and slope of the linear regression of the muscle fatigue metric. The coefficient of determination evaluates anti-interference ability of algorithms. The maximum vertical distance which is obtained by the Kolmogorov-Smirnov test for the slopes evaluates the ability to distinguish fatigue of algorithms. The results indicate that in the aspect of anti-interference ability, the fuzzy approximation entropy has the largest when using memory pillows with different heights. When the fuzzy approximate entropy is compared with average power frequency or the discrete wavelet transform, the differences are significant ( < 0.05). In terms of distinguishing the degree of fatigue, the approximate entropy is still the largest, with a maximum of 0.496 7. Fuzzy approximation entropy is superior to other algorithms in ability of anti-interference and distinguishing fatigue. Therefore, fuzzy approximation entropy can be used as a better evaluation algorithm in the evaluation of cervical muscle fatigue.

Abnormal electroencephalogram features extraction of autistic children based on wavelet transform combined with empirical modal decomposition / 生物医学工程学杂志

Early detection and timely intervention are very essential for autism. This paper used the wavelet transform and empirical mode decomposition (EMD) to extract the features of electroencephalogram (EEG), to compare the feature differences of EEG between the autistic children and healthy children. The experimental subjects included 25 healthy children (aged 5-10 years old) and 25 children with autism (20 boys and 5 girls aged 5-10 years old) respectively. The alpha, beta, theta and delta rhythm wave spectra of the C3, C4, F3, F4, F7, F8, FP1, FP2, O1, O2, P3, P4, T3, T4, T5 and T6 channels were extracted and decomposed by EMD decomposition to obtain the intrinsic modal functions. Finally the support vector machine (SVM) classifier was used to implement assessment of autism and normal classification. The results showed that the accuracy could reach 87% and which was nearly 20% higher than that of the model combining the wavelet transform and sample entropy in the paper. Moreover, the accuracy of delta (1-4 Hz) rhythm wave was the highest among the four kinds of rhythms. And the classification accuracy of the forehead F7 channel, left FP1 channel and T6 channel in the temporal region were all up to 90%, which expressed the characteristics of EEG signals in autistic children better.

A research for single trial detection of error related negativity / 生物医学工程学杂志

Error related negativity (ERN) is generated in frontal and central cortical regions when individuals perceive errors. Because ERN has low signal-to-noise ratio and large individual difference, it is difficult for single trial ERN recognition. In current study, the optimized electroencephalograph (EEG) channels were selected based on the brain topography of ERN activity and ERN offline recognition rate, and the optimized EEG time segments were selected based on the ERN offline recognition rate, then the low frequency time domain and high frequency time-frequency domain features were analyzed based on wavelet transform, after which the ERN single detection algorithm was proposed based on the above procedures. Finally, we achieved average recognition rate of 72.0% ± 9.6% in 10 subjects by using the sample points feature in 0~3.9 Hz and the power and variance features in 3.9~15.6 Hz from the EEG segments of 200~600 ms on the selected 6 channels. Our work has the potential to help the error command real-time correction technique in the application of online brain-computer interface system.