Optimal Sparse Autoencoder Based Sleep Stage Classification Using Biomedical Signals

The recently developed machine learning (ML) models have the ability to obtain high detection rate using biomedical signals. Therefore, this article develops an Optimal Sparse Autoencoder based Sleep Stage Classification Model on Electroencephalography (EEG) Biomedical Signals, named OSAE-SSCEEG technique. The major intention of the OSAE-SSCEEG technique is to find the sleep stage disorders using the EEG biomedical signals. The OSAE-SSCEEG technique primarily undergoes preprocessing using min-max data normalization approach. Moreover, the classification of sleep stages takes place using the Sparse Autoencoder with Smoothed Regularization (SAE-SR) with softmax (SM) approach. Finally, the parameter optimization of the SAE-SR technique is carried out by the use of Coyote Optimization Algorithm (COA) and it leads to boosted classification efficiency. In order to ensure the enhanced performance of the OSAE-SSCEEG technique, a wide ranging simulation analysis is performed and the obtained results demonstrate the betterment of the OSAE-SSCEEG technique over the recent methods.     

Classification of sleep stages based on LSTAR model

Sleep study is very important in the health since sleep disorders affect the productivity of individuals. One of the important topics in sleep research is the classification of sleep stages using the electroencephalogram (EEG) signal. Electrical activities of brain are measured by EEG signal in the laboratory. In real-world environments, EEG signal is also used in portable monitoring devices to analyze sleep. In this study, we propose an efficient method for classification of sleep stages. EEG signals are examined by a new model from autoregressive (AR) family, namely logistic smooth transition autoregressive (LSTAR) to study sleep process. In contrast to the AR model, LSTAR is a non-linear one; therefore, it is suitable for modeling non-linear signals such as EEG. In the current research, at first, each 30-second epoch of EEG signal is decomposed into the time-frequency sub-bands using the double-density dual-tree discrete wavelet transform (D3TDWT). In the second step, LSTAR model is used for feature extraction from each sub-band. Next, the dimension of feature vector is reduced by tensor locality preserving projection (tensor LPP) method, and then the obtained features are given to classifier to determine the stage of each epoch based on the number of considered classes. After classifying sleep stages, some misclassified epochs can be corrected according to the smoothing rule. We consider different classifiers and evaluate their performance. The results indicate the efficiency of the proposed method in comparison with the recently introduced methods in terms of accuracy and Kappa coefficient.     

Complex networks approach for EEG signal sleep stages classification

Sleep stage scoring is a challenging task. Most of existing sleep stage classification approaches rely on analysing electroencephalography (EEG) signals in time or frequency domain. A novel technique for EEG sleep stages classification is proposed in this paper. The statistical features and the similarities of complex networks are used to classify single channel EEG signals into six sleep stages. Firstly, each EEG segment of 30 s is divided into 75 sub-segments, and then different statistical features are extracted from each sub-segment. In this paper, feature extraction is important to reduce dimensionality of EEG data and the processing time in classification stage. Secondly, each vector of the extracted features, which represents one EEG segment, is transferred into a complex network. Thirdly, the similarity properties of the complex networks are extracted and classified into one of the six sleep stages using a k-means classifier. For further investigation, in the statistical features extraction phase two statistical features sets are tested and ranked based on the performance of the complex networks. To investigate the classification ability of complex networks combined with k-means, the extracted statistical features were also forwarded to a k-means and a support vector machine (SVM) for comparison. We also compare the proposed method with other existing methods in the literature. The experimental results show that the proposed method attains better classification results and a reasonable execution time compared with the SVM, k-means and the other existing methods. The research results in this paper indicate that the proposed method can assist neurologists and sleep specialists in diagnosing and monitoring sleep disorders.     

基于CNN-BiLSTM的自动睡眠分期算法

睡眠分期是睡眠数据分析的基础,针对目前睡眠分期存在的依赖人工提取、人工判别效率低、自动睡眠分期准确率不高等问题,本文研究模型是基于卷积神经网络和双向长短时记忆神经网络2个深度学习神经网络相结合的,利用脑电信号来进行自动睡眠分期的模型方法.算法能提取得到原始脑电信号的梅尔频谱,利用卷积神经网络和双向长短时记忆神经网络进行...     

A Bayesian approach for sleep and wake classification based on dynamic time warping method

Sleep plays a significant role in human’ smental and physical health. Recently, the associations between lack of sleep and weight gain, development of cancer and many other health problems have been recognized. Then monitoring the sleep and wake state all night is becoming a hotspot issue. Traditionally it classified by a PSG recording which is very costly and uncomfortable. Nowadays, with the advance of internet of things, many convenient wearable devices are being used for medical use, like measuring the heart rate (HR), blood pressure and other signals. With the sleep quality monitor problem, the key question is how to discriminate the sleep and weak stage from these signals. This paper proposed a Bayesian approach based on dynamic time warping (DTW) method for sleep and wake classification. It used HR and surplus pulse O2 (SPO2) signals to analyze the sleep states and the occurrence of some sleep-related problems. DTW is an algorithm that searches an optimal alignment between time series with scaling and shifting and Bayesian methods have been successfully used for object classification in many study. In this paper, a three-step process is used for sleep and wake classification. In the first step, the DTW is used to extract features of the original HR and SPO2 signals. Then a probabilistic model is introduced for using the Bayesian classification for uncertain data. And in the classification step, the DTW features are used as the training dataset in the Bayesian approach for sleep and wake classification. Finally, a case study form a real-word applications, collected from the website of the Sleep Heart Health Study, is presented to shown the feasibility and advantages of the DTW-based Bayesian approach.     

Automated detection of cyclic alternating pattern and classification of sleep stages using deep neural network

The visual sleep stages scoring by human experts is the current gold standard for sleep analysis. However, this method is tedious, time-consuming, prone to human errors, and unable to detect microstructure of sleep such as cyclic alternating pattern (CAP) which is an important diagnostic factor for the detection of sleep disorders such as insomnia and obstructive sleep apnea (OSA). The CAP is only observed as subtle changes in the electroencephalogram (EEG) signals during non-rapid eye movement (NREM) sleep, making it very difficult for human experts to discern. Hence, it is important to have an automated system developed using artificial intelligence for accurate and robust detection of CAP and sleep stages classification. In this study, a deep learning model based on 1-dimensional convolutional neural network (1D-CNN) is proposed for CAP detection and homogenous 3-class sleep stages classification, namely wakefulness (W), rapid eye movement (REM) and NREM sleep. The proposed model is developed using standardized EEG recordings. Our developed CNN network achieved good model performance for 3-class sleep stages classification with a classification accuracy of 90.46%. Our proposed model also yielded a classification accuracy of 73.64% using balanced CAP dataset, and sensitivity of 92.06% with unbalanced CAP dataset. Our proposed model correctly identified majority of A-phases which comprised of only 12.6% in the unbalanced dataset. The performance of the developed prototype is ready to be tested with more data before clinical application.

     

基于双向LSTM卷积网络与注意力机制的自动睡眠分期模型

针对现阶段深度睡眠分期模型存在的梯度消失、对时序信息学习能力较弱等问题,提出一种基于双向长短时记忆卷积网络与注意力机制的自动睡眠分期模型。将少样本类别的睡眠脑电数据通过过采样方式进行数据增强后,利用带残差块的卷积神经网络学习数据特征表示,再通过带注意力层的双向长短时记忆网络挖掘深层时序信息,使用Softmax层实现睡眠分期的自动判别。实验使用Sleep-EDF数据集中19晚单通道脑电信号对模型进行交叉验证,取得了较高的分类准确率和宏平均F₁值,优于对比方法。该方法能够有效缓解睡眠分期判别中少数类分类性能较低的问题,并提高了深度睡眠分期模型的整体分类性能。     

Automatic classification of sleep stages based on the time-frequency image of EEG signals

In this paper, a new method for automatic sleep stage classification based on time-frequency image (TFI) of electroencephalogram (EEG) signals is proposed. Automatic classification of sleep stages is an important part for diagnosis and treatment of sleep disorders. The smoothed pseudo Wigner–Ville distribution (SPWVD) based time-frequency representation (TFR) of EEG signal has been used to obtain the time-frequency image (TFI). The segmentation of TFI has been performed based on the frequency-bands of the rhythms of EEG signals. The features derived from the histogram of segmented TFI have been used as an input feature set to multiclass least squares support vector machines (MC-LS-SVM) together with the radial basis function (RBF), Mexican hat wavelet, and Morlet wavelet kernel functions for automatic classification of sleep stages from EEG signals. The experimental results are presented to show the effectiveness of the proposed method for classification of sleep stages from EEG signals.     

Automatic recognition of alertness level from EEG by using neural network and wavelet coefficients

Electrophysiological recordings are considered a reliable method of assessing a person's alertness. Sleep medicine is asked to offer objective methods to measure daytime alertness, tiredness and sleepiness. As EEG signals are non-stationary, the conventional method of frequency analysis is not highly successful in recognition of alertness level. This paper deals with a novel method of analysis of EEG signals using wavelet transform, and classification using ANN. EEG signals were decomposed into the frequency sub-bands using wavelet transform and a set of statistical features was extracted from the sub-bands to represent the distribution of wavelet coefficients. Then these statistical features were used as an input to an ANN with three discrete outputs: alert, drowsy and sleep. The error back-propagation neural network is selected as a classifier to discriminate the alertness level of a subject. EEG signals were obtained from 30 healthy subjects. The group consisted of 14 females and 16 males with ages ranging from 18 to 65 years and a mean age of 33.5 years, and a Body Mass Index (BMI) of 32.4±7.3 kg/m². Alertness level and classification properties of ANN were tested using the data recorded in 12 healthy subjects, whereby the EEG recordings were not used to train the ANN. The statistics were used as a measure of potential applicability of the ANN. The accuracy of the ANN was 95±3% alert, 93±4% drowsy and 92±5% sleep.     

Application of adaptive neuro-fuzzy inference system for vigilance level estimation by using wavelet-entropy feature extraction

This paper presents the application of adaptive neuro-fuzzy inference system (ANFIS) model for estimation of vigilance level by using electroencephalogram (EEG) signals recorded during transition from wakefulness to sleep. The developed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. This study comprises of three stages. In the first stage, three types of EEG signals (alert signal, drowsy signal and sleep signal) were obtained from 30 healthy subjects. In the second stage, for feature extraction, obtained EEG signals were separated to its sub-bands using discrete wavelet transform (DWT). Then, entropy of each sub-band was calculated using Shannon entropy algorithm. In the third stage, the ANFIS was trained with the back-propagation gradient descent method in combination with least squares method. The extracted features of three types of EEG signals were used as input patterns of the three ANFIS classifiers. In order to improve estimation accuracy, the fourth ANFIS classifier (combining ANFIS) was trained using the outputs of the three ANFIS classifiers as input data. The performance of the ANFIS model was tested using the EEG data obtained from 12 healthy subjects that have not been used for the training. The results confirmed that the developed ANFIS classifier has potential for estimation of vigilance level by using EEG signals.     

Detecting rapid eye movement sleep using a single EEG signal channel

Sleep stage scoring is generally determined in a polysomnographic (PSG) study where technologists use electroencephalogram (EEG), electromyogram (EMG), and electrooculogram (EOG) signals to determine the sleep stages. Such a process is time consuming and labor intensive. To reduce the workload and to improve the sleep stage scoring performance of sleep experts, this paper introduces an intelligent rapid eye movement (REM) sleep detection method that requires only a single EEG channel. The proposed approach distinguishes itself from previous automatic sleep staging methods by introducing two sets of auxiliary features to help resolve the difficulties caused by interpersonal EEG signal differences. In addition to adopting conventional time and frequency domain features, two empirical rules are introduced to enhance REM detection performance based on sleep being a continuous process. The approach was tested with 779,661 epochs obtained from 947 overnight PSG studies. The REM sleep detection results show a kappa coefficient at 0.752, an accuracy level of 0.930, a sensitivity score of 0.814, and a positive predictive value of 0.775. The results also show that the performance of the approach varies with the ratio of REM sleep and the severity of sleep apnea of the subjects. The experimental results also show that it is possible to improve the performance of an automatic sleep staging method by tailoring it to subgroups of persons that have similar sleep architecture and clinical characteristics.     

基于双通道脑电信号的在线实时睡眠分期系统

当代社会睡眠问题日益突出,及时检测评估睡眠质量有助于诊断睡眠疾病.针对目前市面上睡眠监测类产品发展参差不齐的现状,本文搭建了一个基于双通道脑电信号的在线实时睡眠分期系统,利用第三方接口脑环获取脑电数据,结合CNN-BiLSTM神经网络模型,在PC电脑端实现了在线的实时睡眠分期与音乐调控功能.系统使用基于卷积神经网络CNN和双向长短时记忆神经网络BiLSTM相结合的算法模型对脑电信号进行自动特征提取,CNN能够提取高阶特征, BiLSTM可以捕捉睡眠数据前后的依赖性和关联性,睡眠分期准确率更高.实验结果表明,本文算法模型在Sleep-EDF公共数据集上的四分类任务中取得了92.33%的分期准确率,其Kappa系数为0.84,本系统的实时睡眠分期功能在自采集睡眠数据分期实验中取得79.17%的分期准确率,其Kappa系数为0.70.相比其他睡眠监测类产品,本系统睡眠分期准确率更高,应用场景更多样,实时性和可靠性强,并且可以根据分期结果对用户进行相应的音乐调控,改善用户睡眠质量.     

Adaptive neuro-fuzzy inference system employing wavelet coefficients for detection of alterations in sleep EEG activity during hypopnoea episodes

The Obstructive Sleep Apnoea Hypopnoea Syndrome (OSAH) means “cessation of breath” during the sleep hours and the sufferers often experience related changes in the electrical activity of the brain and heart. This paper describes the application of adaptive neuro-fuzzy inference system (ANFIS) model for automatic detection of alterations in the human electroencephalogram (EEG) activities during hypopnoea episodes. Decision making was performed in two stages: feature extraction by computation of wavelet coefficients and classification by the ANFIS trained with the backpropagation gradient descent method in combination with the least squares method. The EEG signals (pre and during hypopnoea) from three electrodes (C3, C4 and O2) were used as input patterns of the three ANFIS classifiers. To improve diagnostic accuracy, the fourth ANFIS classifier (combining ANFIS) was trained using the outputs of the three ANFIS classifiers as input data. The proposed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. Some conclusions concerning the saliency of features on detecting any possible changes in the human EEG activity due to hypopnoea (mild case of cessation of breath) occurrences were drawn through analysis of the ANFIS. The performance of the ANFIS model was evaluated in terms of training performance and classification accuracies and the results confirmed that the proposed ANFIS model has potential in detecting changes in the human EEG activity due to hypopnoea episodes.     

Windowed electroencephalographic signal classifier based on continuous neural networks with delays in the input

This study reports the design and implementation of a pattern recognition algorithm aimed to classify electroencephalographic (EEG) signals based on a class of dynamic neural networks (NN) described by time delay differential equations (TDNN). This kind of NN introduces the signal windowing process used in different pattern classification methods. The development of the classifier included a new set of learning laws that considered the impact of delayed information on the classifier structure. Both, the training and the validation processes were completely designed and evaluated in this study. The training method for this kind of NN was obtained by applying the Lyapunov theory stability analysis. The accuracy of training process was characterized in terms of the number of delays. A parallel structure (similar to an associative memory) with fixed (obtained after training) weights was used to execute the validation stage. Two methods were considered to validate the pattern classification method: a generalization-regularization and the k-fold cross validation processes (k = 5). Two different classes were considered: normal EEG and patients with previous confirmed neurological diagnosis. The first one contains the EEG signals from 100 healthy patients while the second contains information of epileptic seizures from the same number of patients. The pattern classification algorithm achieved a correct classification percentage of 92.12% using the information of the entire database. In comparison with similar pattern classification methods that considered the same database, the proposed CNN proved to achieve the same or even better correct classification results without pre-treating the EEG raw signal. This new type of classifier working in continuous time but using the delayed information of the input seems to be a reliable option to develop an accurate classification of windowed EEG signals.     

Non-linear analysis of EEG signals at various sleep stages

Application of non-linear dynamics methods to the physiological sciences demonstrated that non-linear models are useful for understanding complex physiological phenomena such as abrupt transitions and chaotic behavior. Sleep stages and sustained fluctuations of autonomic functions such as temperature, blood pressure, electroencephalogram (EEG), etc., can be described as a chaotic process. The EEG signals are highly subjective and the information about the various states may appear at random in the time scale. Therefore, EEG signal parameters, extracted and analyzed using computers, are highly useful in diagnostics. The sleep data analysis is carried out using non-linear parameters: correlation dimension, fractal dimension, largest Lyapunov entropy, approximate entropy, Hurst exponent, phase space plot and recurrence plots. These non-linear parameters quantify the cortical function at different sleep stages and the results are tabulated.     

面向运动想象脑电图识别的镜卷积神经网络

目的 脑电图（electroencephalogram,EEG）是一种灵活、无创、非侵入式的大脑监测方法,广泛应用于运动想象脑机接口系统中,运动想象脑电图识别精度是决定系统性能的关键因素。然而由于脑电图采集时间长、个体差异大等原因,导致单个受试者可用于模型训练的样本数量少,严重影响了卷积神经网络在脑电图识别任务中的表现。为此,本文提出一种镜卷积神经网络（mirror convolutional neural network,MCNN）模型,使用集成学习与数据扩增方法提高运动想象脑电图识别精度。方法 在训练阶段,基于源脑电通过互换左右侧脑电通道构造镜像脑电,并与源脑电一起用于源卷积网络训练,有效扩增了训练样本;在预测阶段,复制已训练源卷积网络作为镜像卷积网络,将测试集中的源脑电输入源卷积网络,构造的镜像脑电输入镜像卷积网络,集成源卷积网络与镜像卷积网络输出的类别预测概率,形成最终类别预测。结果 为了验证模型的有效性和通用性,基于3种不同运动想象脑电图识别卷积网络模型分别构造镜卷积网络,并在第4届脑机接口大赛2a与2b数据集上进行实验验证。实验结果与原始模型相比,运动想象四分类和二分类准确率分别平均提高了4.83%和4.61%,显著提高了识别精度。结论 本文面向运动想象脑电图识别,提出了镜卷积神经网络模型,通过集成学习与数据扩增方法提高运动想象识别精度,有效改善了运动想象脑机接口性能。     

Detection and classification of sleep apnea using genetic algorithms and SVM‐based classification of thoracic respiratory effort and oximetric signal features

Sleep apnea is a relatively prevalent breathing disorder characterized by temporary interruptions in airflow during sleep. There are 2 major types of sleep apnea. Obstructive sleep apnea occurs when air cannot flow through the upper airway despite efforts to breathe. Central sleep apnea occurs when the brain fails to signal to the muscles to maintain breathing. The standard diagnostic test is polysomnography, which is expensive and time consuming. The aim of this study was to design an automatic diagnostic and classifying algorithm for sleep apneas employing thoracic respiratory effort and oximetric signals. This algorithm was trained and tested applying a database of 54 subjects who had undergone polysomnography. A feature extraction stage was conducted to compute features. An optimal genetic algorithm was applied to select optimal features of these 2 kinds of signals. The classification technique was based on the support vector machine classifier to classify the selected features in 3 classes as healthy, obstructive, and central sleep apnea events. The results show that our automated classification algorithm can diagnose sleep apnea and its types with an average accuracy level of 90.2% (87.5‐95.8) in the test set and 90.9% in the validation set with high acceptable accuracy.     

基于混合神经网络的脑电时空特征情感分类

提出一种脑电图（electroencephalograph,简称EEG）数据表示方法,将一维链式EEG向量序列转换成二维网状矩阵序列,使矩阵结构与EEG电极位置的脑区分布相对应,以此来更好地表示物理上多个相邻电极EEG信号之间的空间相关性.再应用滑动窗将二维矩阵序列分成一个个等长的时间片段,作为新的融合了EEG时空相关性的数据表示.还提出了级联卷积-循环神经网络（CASC_CNN_LSTM）与级联卷积-卷积神经网络（CASC_CNN_CNN）这两种混合深度学习模型,二者都通过CNN卷积神经网络从转换的二维网状EEG数据表示中捕获物理上相邻脑电信号之间的空间相关性,而前者通过LSTM循环神经网络学习EEG数据流在时序上的依赖关系,后者则通过CNN卷积神经网络挖掘局部时间与空间更深层的相关判别性特征,从而精确识别脑电信号中包含的情感类别.在大规模脑电数据集DEAP上进行被试内效价维度上两类情感分类实验,结果显示,所提出的CASC_CNN_LSTM和CASC_CNN_CNN网络在二维网状EEG时空特征上的平均分类准确率分别达到93.15%和92.37%,均高于基准模型和现有最新方法的性能,表明该模型有效提高了EEG情感识别的准确率和鲁棒性,可以有效地应用到基于EEG的情感分类与识别相关应用中.     

Estimating vigilance level by using EEG and EMG signals

We developed a new method for estimation of vigilance level by using both EEG and EMG signals recorded during transition from wakefulness to sleep. Previous studies used only EEG signals for estimating the vigilance levels. In this study, it was aimed to estimate vigilance level by using both EEG and EMG signals for increasing the accuracy of the estimation rate. In our work, EEG and EMG signals were obtained from 30 subjects. In data preparation stage, EEG signals were separated to its subbands using wavelet transform for efficient discrimination, and chin EMG was used to verify and eliminate the movement artifacts. The changes in EEG and EMG were diagnosed while transition from wakefulness to sleep by using developed artificial neural network (ANN). Training and testing data sets consist of the subbanded components of EEG and power density of EMG signals were applied to the ANN for training and testing the system which gives three situations for the vigilance level of the subject: awake, drowsy, and sleep. The accuracy of estimation was about 98–99% while the accuracy of the previous study, which uses only EEG, was 95–96%.     

免疫多域特征融合的多核学习SVM运动想象脑电信号分类

针对多通道四类运动想象(Motor imagery, MI)脑电信号(Electroencephalography, EEG)的分类问题, 提出免疫多域特征融合的多核学习SVM (Support vector machine)运动想象脑电信号分类算法.首先, 通过离散小波变换(Discrete wavelet transform, DWT)提取脑电信号的时频域特征, 并利用一对多公共空间模式(One versus the rest common spatial patterns, OVR-CSP)提取脑电信号的空域特征, 融合时频空域特征形成特征向量.其次, 利用多核学习支持向量机(Multiple kernel learning support vector machine, MKL-SVM)对提取的特征向量进行分类.最后, 利用免疫遗传算法(Immune genetic algorithm, IGA)对模型的相关参数进行优化, 得到识别率更高的脑电信号分类模型.采用BCI2005desc-Ⅲa数据集进行实验验证, 对比结果表明, 本文所提出的分类模型有效地解决了传统单域特征提取算法特征单一、信息描述不足的问题, 更准确地表达了不同受试者个性化的多域特征, 取得了94.21%的识别率, 优于使用相同数据集的其他方法.