Principal component analysis-enhanced cosine radial basis function neural network for robust epilepsy and seizure detection.

A novel principal component analysis (PCA)-enhanced cosine radial basis function neural network classifier is presented. The two-stage classifier is integrated with the mixed-band wavelet-chaos methodology, developed earlier by the authors, for accurate and robust classification of electroencephalogram (EEGs) into healthy, ictal, and interictal EEGs. A nine-parameter mixed-band feature space discovered in previous research for effective EEG representation is used as input to the two-stage classifier. In the first stage, PCA is employed for feature enhancement. The rearrangement of the input space along the principal components of the data improves the classification accuracy of the cosine radial basis function neural network (RBFNN) employed in the second stage significantly. The classification accuracy and robustness of the classifier are validated by extensive parametric and sensitivity analysis. The new wavelet-chaos-neural network methodology yields high EEG classification accuracy (96.6%) and is quite robust to changes in training data with a low standard deviation of 1.4%. For epilepsy diagnosis, when only normal and interictal EEGs are considered, the classification accuracy of the proposed model is 99.3%. This statistic is especially remarkable because even the most highly trained neurologists do not appear to be able to detect interictal EEGs more than 80% of the times.     

The combined technique for detection of artifacts in clinical electroencephalograms of sleeping newborns

In this paper, we describe a new method combining the polynomial neural network and decision tree techniques in order to derive comprehensible classification rules from clinical electroencephalograms (EEGs) recorded from sleeping newborns. These EEGs are heavily corrupted by cardiac, eye movement, muscle, and noise artifacts and, as a consequence, some EEG features are irrelevant to classification problems. Combining the polynomial network and decision tree techniques, we discover comprehensible classification rules while also attempting to keep their classification error down. This technique is shown to outperform a number of commonly used machine learning technique applied to automatically recognize artifacts in the sleep EEGs.     

A wavelet-chaos methodology for analysis of EEGs and EEG subbands to detect seizure and epilepsy

A wavelet-chaos methodology is presented for analysis of EEGs and delta, theta, alpha, beta, and gamma subbands of EEGs for detection of seizure and epilepsy. The nonlinear dynamics of the original EEGs are quantified in the form of the correlation dimension (CD, representing system complexity) and the largest Lyapunov exponent (LLE, representing system chaoticity). The new wavelet-based methodology isolates the changes in CD and LLE in specific subbands of the EEG. The methodology is applied to three different groups of EEG signals: 1) healthy subjects; 2) epileptic subjects during a seizure-free interval (interictal EEG); 3) epileptic subjects during a seizure (ictal EEG). The effectiveness of CD and LLE in differentiating between the three groups is investigated based on statistical significance of the differences. It is observed that while there may not be significant differences in the values of the parameters obtained from the original EEG, differences may be identified when the parameters are employed in conjunction with specific EEG subbands. Moreover, it is concluded that for the higher frequency beta and gamma subbands, the CD differentiates between the three groups, whereas for the lower frequency alpha subband, the LLE differentiates between the three groups.     

Brain maturation estimation using neural classifier

Quantitative electroencephalographic (EEG) signal analysis has revealed itself as an important diagnostic tool in the last few years. Through the use of signal processing techniques, new quantitative representations of EEG data are obtained. To automate the diagnosis, a problem of supervised classification must be solved on these. Artificial neural networks provide an alternative to more traditional classifier systems for this task. The authors perform a comparison between several classifiers in a particular problem, the brain maturation prediction. The data preprocessing/feature extraction process and the methodology for making the comparison are described. Performance of the methods is evaluated in terms of estimated percentage of correctly classified subjects     

Multiple channel detection of steady-state visual evoked potentials for brain-computer interfaces

In this paper, novel methods for detecting steady-state visual evoked potentials using multiple electroencephalogram (EEG) signals are presented. The methods are tailored for brain-computer interfacing, where fast and accurate detection is of vital importance for achieving high information transfer rates. High detection accuracy using short time segments is obtained by finding combinations of electrode signals that cancel strong interference signals in the EEG data. Data from a test group consisting of 10 subjects are used to evaluate the new methods and to compare them to standard techniques. Using 1-s signal segments, six different visual stimulation frequencies could be discriminated with an average classification accuracy of 84%. An additional advantage of the presented methodology is that it is fully online, i.e., no calibration data for noise estimation, feature extraction, or electrode selection is needed.     

Two-stage unbuffered CFOA based non-inverting resistive-feedback amplifier: a study based on the description of the operational transconductance conveyor (OTC)

EEG signal contains some specific patterns that predict neuro-developmental impairments of a premature newborn. Extracting these patterns from a set of EEG records provides a dataset to be used in machine learning in order to implement an intelligent classification system that predict prognosis of the baby. In a previous work we proved that inter-burst intervals (IBI) found in the EEG records predicts abnormal outcomes of the premature. A bibliographic study on the amplitude of an EEG signal, with the annotations of the neuro-pediatricians, showed that low amplitudes in EEG signal are strongly correlated with an abnormal prognosis of the premature, similar to that of IBI. According to these hypotheses, we present in this paper, a segmentation methodology on the amplitude of bursts intervals of EEG signal into 3 segments: low, medium and high, in addition to the inter-burst intervals. We create a new algorithm that detects 6 important parameters in each interval of these 4 segments. After applying this new methodology, we obtain a new classified dataset that contains 24 parameters extracted from these 4 segments to obtain with gestational age of the preterm and the day of recording 26 input attributes and one output which is the class (normal, sick or risky). Finally we validate the pertinence of these attributes using artificial neural network.     

基于同步性脑网络的支持张量机情绪分类研究

一直以来,情绪是心理学、教育学、信息科学等多个学科的研究热点,脑电信号(EEG)因其客观、不易伪装的特点,在情绪识别领域受到广泛关注。由于人类情绪是大脑多个脑区相互作用产生的,该文提出一种基于同步性脑网络的支持张量机情绪分类算法(SBN-STM),该算法采用相位锁定值(PLV)构建了同步性脑网络,分析多导联脑电信号之间的同步性和相关性,并生成2阶张量序列作为训练集,运用支持张量机(STM)模型实现正负情绪的二分类。该文基于DEAP脑电情绪数据库,详细分析了同步性脑网络张量序列的选取方法,最佳张量序列窗口的大小和位置,解决了传统情绪分类算法特征冗余的问题,提高了模型训练速度。仿真实验表明,基于支持张量机的同步性脑网络分类方法的情绪准确率优于支持向量机、C4.5决策树、人工神经网络、K近邻等以向量为特征的情绪分类模型。     

Analysis on Design of Kohonen-network System Based on Classification of Complex Signals

The key methods of detection and classification of the electroencephalogram(EEG) used in recent years are introduced . Taking EEG for example, the design plan of Kohonen neural network system based on detection and classification of complex signals is proposed, and both the network design and signal processing are analyzed, including pre-processing of signals, extraction of signal features, classification of signal and network topology, etc.     

Multiclass support vector machines for EEG-signals classification.

In this paper, we proposed the multiclass support vector machine (SVM) with the error-correcting output codes for the multiclass electroencephalogram (EEG) signals classification problem. The probabilistic neural network (PNN) and multilayer perceptron neural network were also tested and benchmarked for their performance on the classification of the EEG signals. Decision making was performed in two stages: feature extraction by computing the wavelet coefficients and the Lyapunov exponents and classification using the classifiers trained on the extracted features. The purpose was to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. Our research demonstrated that the wavelet coefficients and the Lyapunov exponents are the features which well represent the EEG signals and the multiclass SVM and PNN trained on these features achieved high classification accuracies.     

小波滤波与AR模型在脑电信号处理的应用

针对脑-计算机接口技术中的脑电信号处理、事件相关同步和事件相关去同步的特点,提出了一种基于离散小波滤波和AR模型来提取脑电信号特征向量的方法。利用Daubechies类小波函数对脑电信号进行4层分解,然后使用Burg算法提取脑电信号8阶AR模型系数,最后用BP神经网络进行分类和比较。得到最优的正确率为71.64%,小波滤波的效果要优于FIR滤波器。     

Gaussian process modeling of EEG for the detection of neonatal seizures

Gaussian process (GP) probabilistic models have attractive advantages over parametric and neural network modeling approaches. They have a small number of tuneable parameters, can be trained on relatively small training sets, and provide a measure of prediction certainty. In this paper, these properties are exploited to develop two methods of highlighting the presence of neonatal seizures from electroencephalograph (EEG) signals. In the first method, the certainty of the GP model prediction is used to indicate the presence of seizures. In the second approach, the hyperparameters of the GP model are used. Tests are carried out with a feature set of ten EEG measures developed from various signal processing techniques. Features are evaluated using a neural network classifier on 51 h of real neonatal EEG. The GP measures, in particular, the prediction certainty approach, produce a high level of performance compared to other modeling methods and methods currently in clinical use for EEG analysis, indicating that they are an important and useful tool for the real-time detection of neonatal seizures.     

基于有记忆递归神经网络的脑电特征情感识别研究

为了提高脑电信号多分类的情感识别率,文中选用上海交通大学提供的SEED脑电信号数据集,对其进行分频带特征提取。将脑电数据的微分熵特征、微分不对称性特征和有理不对称性特征通过线性动力系统平滑特征后,与功率谱密度特征进行分类效果比较,再利用有记忆递归神经网络的方法进行分类,发现提取的微分熵特征经过分类的效果好。在对3种情感进行分类的过程中,采用长短时记忆神经网络分类相比于其他机器学习方法识别率有所提高,情感识别的平均准确率可达到95.045 9%。     

Classification of mass and normal breast tissue: a convolution neural network classifier with spatial domain and texture images

The authors investigated the classification of regions of interest (ROI's) on mammograms as either mass or normal tissue using a convolution neural network (CNN). A CNN is a backpropagation neural network with two-dimensional (2-D) weight kernels that operate on images. A generalized, fast and stable implementation of the CNN was developed. The input images to the CNN were obtained from the ROI's using two techniques. The first technique employed averaging and subsampling. The second technique employed texture feature extraction methods applied to small subregions inside the ROI. Features computed over different subregions were arranged as texture images, which were subsequently used as CNN inputs. The effects of CNN architecture and texture feature parameters on classification accuracy were studied. Receiver operating characteristic (ROC) methodology was used to evaluate the classification accuracy. A data set consisting of 168 ROIs containing biopsy-proven masses and 504 ROI's containing normal breast tissue was extracted from 168 mammograms by radiologists experienced in mammography. This data set was used for training and testing the CNN. With the best combination of CNN architecture and texture feature parameters, the area under the test ROC curve reached 0.87, which corresponded to a true-positive fraction of 90% at a false positive fraction of 31%. The authors' results demonstrate the feasibility of using a CNN for classification of masses and normal tissue on mammograms.     

卷积神经网络在脑疲劳检测中的研究

脑疲劳是由于持续进行脑力劳动导致的一种状态，脑电被认为是脑疲劳状态检测的最佳工具。如何选取合适的脑疲劳特征成为脑疲劳检测的关键问题，传统模式识别中手动提取特征会产生信息损失，针对脑电的时空特性，本文设计了具有时域卷积核、空间域卷积核的深层卷积神经网络和浅层卷积神经网络两种网络结构，将特征提取和状态分类合二为一，对正常态与疲劳态脑电数据进行分类，可视化了卷积神经网络的空间域卷积核。结果表明，浅层卷积神经网络平均分类正确率为98.868%，深层卷积神经网络平均分类正确率为98.217%，均高于传统分类方法，通过空间域卷积核的可视化，能够了解不同导联在网络中的参与程度，验证了该模型在脑疲劳检测任务中具有很高的有效性，同时为脑疲劳检测提供了新思路。      

Nonlinear considerations in EEG signal classification

We investigate the effect of incorporating modeling of nonlinearity on the classification of electroencephalogram (EEG) signals using an artificial neural network (ANN). It is observed that the ANN's predictive ability is improved after preprocessing EEG signals using a particular nonlinear modeling technique, viz. a bilinear model, compared with those obtained by using a particular classical linear analysis method, viz. an autoregressive (AR) model. Until recently, linear time-invariant Gaussian modeling has dominated the development of time series modeling and feature extraction. The advantage of such classical models lies in the fact that a complete signal processing theory is available. In the case of EEG signals, where the underlying theory regarding the dynamical law governing the generation of these signals (e,g., the underlying physiological factors) is not completely understood, a case can be made for using improved signal processing models that are not subject to linear constraints. Such models should recognize important features of the observed data that may not be well modeled by a linear time-invariant model. It is known that EEG signals are nonstationary, and it is possible that they may be nonlinear as well. Thus, one way of gaining further insights on the structure of EEG signals is to introduce nonlinear models and higher order spectra. This paper compares the results of classification using a linear AR model with those obtained from a bilinear model. It is shown that in certain cases, the nonlinearity of the EEG signals is an important factor that ought to be taken into consideration during preprocessing of the signals prior to the classification task     

NNERVE: Neural Network Extraction of Repetitive Vectors forElectromyography. I. Algorithm

Artificial neural network (ANN) based signal processing methods have been shown to have significant robustness in processing complex, degraded, noisy, and unstable signals. A novel approach to automated electromyogram (EMG) signal decomposition, using an ANN processing architecture, is presented here. Due to the lack of a priori knowledge of motor unit action potential (MUAP) morphology, the EMG decomposition must be performed in an unsupervised manner. An ANN classifier, consisting of a multilayer perceptron neural network and employing a novel unsupervised training strategy, is proposed. The ANN learns repetitive appearances of MUAP waveforms from their suspected occurrences in a filtered EMG signal in an autoassociative learning task. The same training waveforms are fed into the trained ANN and the output of the ANN is fed back to its input, giving rise to a dynamic retrieval net classifier. For each waveform in the data, the network discovers a feature vector associated with that waveform. For each waveform, classification is achieved by comparing its feature vector with those of the other waveforms. Firing information of each MUAP is further used to refine the classification results of the ANN classifier. Then, individual MUAP waveform shapes are derived and their firing tables are created     

一种特征压缩及分类神经网络的研究

由于多对多类问题的高维数据无法直接观察其聚类和分布特性，本文采用神经网络法实现自适应主元特征提取（ＡＰＥＸ），以压缩特征空间的维数，并保持足够的信息来鉴别事物之间的类型，它可有效地提取信号的主要特征和抑制噪声，我们将高维数据压缩影射到２或３维，从而实现特征数据的可视性分析，显示物体对象间的类似程度和关系结构，并采用高阶函数的神经网络对其进行了非线性分类，同时与ＢＰ网络的非线性分类能力进行了实验比较     

Multiview Classification and Dimensionality Reduction of Scalp and Intracranial EEG Data through Tensor Factorisation

Electroencephalography (EEG) signals arise as mixtures of various neural processes which occur in particular spatial, frequency, and temporal brain locations. In classification paradigms, algorithms are developed that can distinguish between these processes. In this work, we apply tensor factorisation to a set of EEG data from a group of epileptic patients and factorise the data into three modes; space, time, and frequency with each mode containing a number of components or signatures. We train separate classifiers on various feature sets corresponding to complementary combinations of those modes and components and test the classification accuracy for each set. The relative influence on the classification accuracy of the respective spatial, temporal, or frequency signatures can then be analysed and useful interpretations can be made. Additionaly, we show that through tensor factorisation we can perform dimensionality reduction by evaluating the classification performance with regards to the number of components in each mode and also by rejecting components with insignificant contribution to the classification accuracy.     

面向癫痫脑电图信号识别的径向基最小最大概率分类树

脑电图(EEG)信号检测和识别是癫痫病的重要诊断手段。径向基函数神经网络具有出色的逼近能力和泛化性能,能直接识别出不同状态的脑电信号,但其透明性和可解释性差,忽视了不同类别数据间可分性的不同。对此,该文提出一种基于径向基函数神经网络和最小最大概率决策技术的分类树,采用一对一策略和排除法,更多考虑了类间可分性的不同。针对脑电信号识别的实验表明,所提方法结构清晰,分类能力强,可解释性更好。     

Classification of multispectral remote sensing data using aback-propagation neural network

The suitability of a back-propagation neural network for classification of multispectral image data is explored. A methodology is developed for selection of both training parameters and data sets for the training phase. A new technique is also developed to accelerate the learning phase. To benchmark the network, the results are compared to those obtained using three other algorithms: a statistical contextual technique, a supervised piecewise linear classifier, and an unsupervised multispectral clustering algorithm. All three techniques were applied to simulated and real satellite imagery. Results from the classification of both Monte Carlo simulation and real imagery are summarized