Automatic arrhythmia detection based on time and time-frequency analysis of heart rate variability

We have developed an automatic arrhythmia detection system, which is based on heart rate features only. Initially, the RR interval duration signal is extracted from ECG recordings and segmented into small intervals. The analysis is based on both time and time-frequency (t-f) features. Time domain measurements are extracted and several combinations between the obtained features are used for the training of a set of neural networks. Short time Fourier transform and several time-frequency distributions (TFD) are used in the t-f analysis. The features obtained are used for the training of a set of neural networks, one for each distribution. The proposed approach is tested using the MIT-BIH arrhythmia database and satisfactory results are obtained for both sensitivity and specificity (87.5 and 89.5%, respectively, for time domain analysis and 90 and 93%, respectively, for t-f domain analysis).     

An improved procedure for detection of heart arrhythmias with novel pre‐processing techniques

The objective of this study is to develop an algorithm to detect and classify six types of electrocardiogram (ECG) signal beats including normal beats (N), atrial pre‐mature beats (A), right bundle branch block beats (R), left bundle branch block beats (L), paced beats (P), and pre‐mature ventricular contraction beats (PVC or V) using a neural network classifier. In order to prepare an appropriate input vector for the neural classifier several pre‐processing stages have been applied. Initially, a signal filtering method is used to remove the ECG signal baseline wandering. Continuous wavelet transform is then applied in order to extract features of the ECG signal. Next, principal component analysis is used to reduce the size of the data. A well‐known neural network architecture called the multi‐layered perceptron neural network is then utilized as the final classifier to classify each ECG beat as one of six groups of signals under study. Finally, the MIT‐BIH database is used to evaluate the proposed algorithm, resulting in 99.5% sensitivity, 99.66% positive predictive accuracy and 99.17% total accuracy.     

Integration of independent component analysis and neural networks for ECG beat classification

In this paper, we propose a scheme to integrate independent component analysis (ICA) and neural networks for electrocardiogram (ECG) beat classification. The ICA is used to decompose ECG signals into weighted sum of basic components that are statistically mutual independent. The projections on these components, together with the RR interval, then constitute a feature vector for the following classifier. Two neural networks, including a probabilistic neural network (PNN) and a back-propagation neural network (BPNN), are employed as classifiers. ECG samples attributing to eight different beat types were sampled from the MIT-BIH arrhythmia database for experiments. The results show high classification accuracy of over 98% with either of the two classifiers. Between them, the PNN shows a slightly better performance than BPNN in terms of accuracy and robustness to the number of ICA-bases. The impressive results prove that the integration of independent component analysis and neural networks, especially PNN, is a promising scheme for the computer-aided diagnosis of heart diseases based on ECG.     

ECG beat classifier designed by combined neural network model

This paper illustrates the use of combined neural network model to guide model selection for classification of electrocardiogram (ECG) beats. The ECG signals were decomposed into time-frequency representations using discrete wavelet transform and statistical features were calculated to depict their distribution. The first level networks were implemented for ECG beats classification using the statistical features as inputs. To improve diagnostic accuracy, the second level networks were trained using the outputs of the first level networks as input data. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified with the accuracy of 96.94% by the combined neural network. The combined neural network model achieved accuracy rates which were higher than that of the stand-alone neural network model.     

Adaptive gait detection based on foot-mounted inertial sensors and multi-sensor fusion

Gait detection plays an important role in areas where spatial-temporal gait parameters are needed. Inertial sensors are now sufficiently small in size and light in weight for collection of human gait data with body sensor networks (BSNs). However, gait detection methods usually rely on careful sensor alignment and a set of rule-based thresholds, which are brittle or difficult to implement. This paper presents an adaptive method for gait detection, which models human gait with a hidden Markov model (HMM), and employs a neural network (NN) to deal with the raw measurements and feed the HMM with classifications. Six gait events are involved for a detailed analysis, i.e., heel strike, foot flat, mid-stance, heel off, toe off, and mid-swing. In order to obtain enough gait data for training a gait model, the gait events are labeled by a rule-based detection method, in which the predefined rules are verified with an optical motion capture system. Experiments were conducted by nine subjects, based on a dual-sensor configuration with one sensor on each foot. Detection performance is quantified using metrics of accuracy, sensitivity and specificity, and the averaged performance values are 98.11%, 94.32% and 98.86% respectively with a timing error less than 2.5 ms.     

基于判别式分析和神经网络的特征选择方法

为了获得重要的特征集合,提出了一种基于判别式分析算法和神经网络的特征选择方法。通过最小化扩展互熵误差函数来训练神经网络,这一误差函数的使用减小了神经网络传输函数的导数,降低了输出敏感度。该方法首先利用判别式分析算法得到一个有序的特征队列,然后通过正则化神经网络进行特征的选择,特征选择过程是基于单个特征的移除带来验证数据集上分类误差变化这一原理。与其他基于不同原理的四种方法进行了比较,实验结果表明,利用该算法训练的网络能够获得较高分类准确率。     

Implementing wavelet transform/mixture of experts network for analysis of electrocardiogram beats

Abstract: Mixture of experts (ME) is a modular neural network architecture for supervised learning. This paper illustrates the use of the ME network structure to guide model selection for classification of electrocardiogram (ECG) beats. The expectation maximization algorithm is used for training the ME so that the learning process is decoupled in a manner that fits well with the modular structure. The ECG signals were decomposed into time–frequency representations using discrete wavelet transforms and statistical features were calculated to depict their distribution. The ME network structure was implemented for ECG beats classification using the statistical features as inputs. To improve classification accuracy, the outputs of expert networks were combined by a gating network simultaneously trained in order to stochastically select the expert that is performing the best at solving the problem. Five types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat, partial epilepsy beat) obtained from the Physiobank database were classified with an accuracy of 96.89% by the ME network structure. The ME network structure achieved accuracy rates which were higher than those of the stand-alone neural network models.     

基于自适应噪声添加的防御对抗样本的算法

深度神经网络容易受到对抗样本的攻击。为了解决这个问题,一些工作通过向图像中添加高斯噪声来训练网络,从而提高网络防御对抗样本的能力,但是该方法在添加噪声时并没有考虑到神经网络对图像中不同区域的敏感性是不同的。针对这一问题,提出了梯度指导噪声添加的对抗训练算法。该算法在训练网络时,根据图像中不同区域的敏感性向其添加自适应噪声,在敏感性较大的区域上添加较大的噪声抑制网络对图像变化的敏感程度,在敏感性较小的区域上添加较小的噪声提高其分类精度。在Cifar-10数据集上与现有算法进行比较,实验结果表明,该方法有效地提高了神经网络在分类对抗样本时的准确率。     

Statistics over features of ECG signals

This paper presented the usage of statistics over the set of the features representing the electrocardiogram (ECG) signals. Since classification is more accurate when the pattern is simplified through representation by important features, feature extraction and selection play an important role in classifying systems such as neural networks. Multilayer perceptron neural network (MLPNN) architectures were formulated and used as basis for detection of variabilities of the ECG signals. Four types of ECG beats (normal beat, congestive heart failure beat, ventricular tachyarrhythmia beat, atrial fibrillation beat) obtained from the Physiobank database were classified. The selected Lyapunov exponents, wavelet coefficients and the power levels of power spectral density (PSD) values obtained by eigenvector methods of the ECG signals were used as inputs of the MLPNN trained with Levenberg–Marquardt algorithm. The classification results confirmed that the proposed MLPNN has potential in detecting the variabilities of the ECG signals.     

基于BiGRU深度神经网络的心肌梗死检测

针对目前智能医疗诊断领域的研究现状,结合心电信号的时序性和多导联关联性特点,为降低心肌梗死疾病的误诊率,提出一种基于双向门控循环单元神经网络(Bidirectional Gated Recurrent Unit,BiGRU)和多导联心电图(electrocardiogram,ECG)信号的深度神经网络学习算法。对原始心电信号进行去噪处理,分割成心拍序列;将心拍序列送入深度神经网络训练模型学习分类;采用Physikalisch-Technische Bundesanstalt(PTB)心电数据库验证多导联BiGRU算法。算法对心梗检测的灵敏度为99.93%、特异性为99.72%、准确率为99.89%。实验结果表明,该算法的检测效果明显优于其他文献的检测算法,对提高心肌梗死的正确诊断率具有重要意义。     

Periodic symmetric functions, serial addition, and multiplicationwith neural networks

This paper investigates threshold based neural networks for periodic symmetric Boolean functions and some related operations. It is shown that any n-input variable periodic symmetric Boolean function can be implemented with a feedforward linear threshold-based neural network with size of O(log n) and depth also of O(log n), both measured in terms of neurons. The maximum weight and fan-in values are in the order of O(n). Under the same assumptions on weight and fan-in values, an asymptotic bound of O(log n) for both size and depth of the network is also derived for symmetric Boolean functions that can be decomposed into a constant number of periodic symmetric Boolean subfunctions. Based on this results neural networks for serial binary addition and multiplication of n-bit operands are also proposed. It is shown that the serial addition can be computed with polynomially bounded weights and a maximum fan-in in the order of O(log n) in O(n/log n) serial cycles. Finally, it is shown that the serial multiplication can be computed in O(n) serial cycles with O(log n) size neural gate network, and with O(n log n) latches.     

粒子群优化算法在神经网络控制中的应用

考虑粒子群优化算法在不确定系统的自适应控制中的应用。神经网络在不确定系统的自适应控制中起着重要作用。但传统的梯度下降法训练神经网络时收敛速度慢,容易陷入局部极小,且对网络的初始权值等参数极为敏感。为了克服这些缺点,提出了一种基于粒子群算法优化的RBF神经网络整定PID的控制策略。首先,根据粒子群算法的基本原理提出了优化得到RBF神经网络输出权、节点中心和节点基宽参数的初值的算法。其次,再利用梯度下降法对控制器参数进一步调节。将传统的神经网络控制与基于粒子群优化的神经网络控制进行了对比,结果表明,后者有更好逼近精度。以PID控制器参数整定为例,对一类非线性控制系统进行了仿真。仿真结果表明基于粒子群优化的神经网络控制具有较强的鲁棒性和自适应能力。     

The selection of weight accuracies for Madalines

The sensitivity of the outputs of a neural network to perturbations in its weights is an important consideration in both the design of hardware realizations and in the development of training algorithms for neural networks. In designing dense, high-speed realizations of neural networks, understanding the consequences of using simple neurons with significant weight errors is important. Similarly, in developing training algorithms, it is important to understand the effects of small weight changes to determine the required precision of the weight updates at each iteration. In this paper, an analysis of the sensitivity of feedforward neural networks (Madalines) to weight errors is considered. We focus our attention on Madalines composed of sigmoidal, threshold, and linear units. Using a stochastic model for weight errors, we derive simple analytical expressions for the variance of the output error of a Madaline. These analytical expressions agree closely with simulation results. In addition, we develop a technique for selecting the appropriate accuracy of the weights in a neural network realization. Using this technique, we compare the required weight precision for threshold versus sigmoidal Madalines. We show that for a given desired variance of the output error, the weights of a threshold Madaline must be more accurate.     

多核并行脉冲神经网络模拟器的设计

脉冲神经网络属于第三代人工神经网络,它是更具有生物可解释性的神经网络模型。随着人们对脉冲神经网络不断深入地研究,不仅神经元空间结构更为复杂,而且神经网络结构规模也随之增大。以串行计算的方式,难以在个人计算机上实现脉冲神经网络的模拟仿真。为此,设计了一个多核并行的脉冲神经网络模拟器,对神经元进行编码与映射,自定义路由表解决了多核间的网络通信,以时间驱动为策略,实现核与核间的动态同步,在模拟器上进行脉冲神经网络的并行计算。以Izhikevich脉冲神经元为模型,在模拟环境下进行仿真实验,结果表明多核并行计算相比传统的串行计算在效率方面约有两倍的提升,可为类似的脉冲神经网络的模拟并行化设计提供参考。     

SIMULATING LARGE NEURAL ASSEMBLIES OF UNRELIABLE COMPONENTS

Neural networks, artificial or biophysical, consist of large numbers of neurons that communicate by sending impulses via synapses. One interesting observation is that due to the presence of massive parallelism and redundancy, neural networks are often inherently fault tolerant. If a small number of neurons or synapses are disconnected the network still performs most, if not all, of its functions correctly. It is exactly this property we are interested in when studying neural networks. There is, however, a problem if one tries to analyze neural networks within a formal framework such as the McCulloch and Pitts (1943) calculus: neural nets are too large to analyze without proper tools. Alternatively, one could simulate neural networks on a computer system. We propose to model neural networks by means of networks of finite automata in order to simulate large neural assemblies of unreliable components.     

Multilead ECG analysis

This paper describes the results of our recent research in computer-assisted ECG/VCG interpretation. It comprises new developments which were initiated by the advent of relatively inexpensive microcomputers. Our previous systems performed an off-line analysis of ECGs. Currently, there is a trend to move computer power near to the patient and to provide on-line analysis of ECGs. Besides the advantage of the direct availability of the ECG interpretation, quality control will reduce the number of uninterpretable ECGs and hence the number of repeated recordings. This paper describes the requirements that were established for a system for on-line ECG analysis. The system is based on our modular approach, just like our off-line system, Modular ECG ANalysis System (MEANS). Changes in the methods and software had to be made mainly because of the simultaneity of all ECG leads and the concurrency of the processing tasks. Other modifications and extensions of the algorithms necessary to meet the requirements of on-line ECG interpretation especially those related to processing speed, are discussed, and evaluation results are presented.     

Sensitivity Analysis for Decision Boundaries

A novel approach is presented to visualize and analyze decision boundaries for feedforward neural networks. First order sensitivity analysis of the neural network output function with respect to input perturbations is used to visualize the position of decision boundaries over input space. Similarly, sensitivity analysis of each hidden unit activation function reveals which boundary is implemented by which hidden unit. The paper shows how these sensitivity analysis models can be used to better understand the data being modelled, and to visually identify irrelevant input and hidden units.     

Development of neural network committee machines for automatic forest fire detection using lidar

Lidar has considerable potential as an early forest fire detection technique, presenting considerable advantages when compared to the passive detection methods based on infrared cameras currently in common use, due to its higher sensitivity, ability to accurately locate the fire and the fact that it does not need line of sight to the flames. The method has recently been demonstrated by the authors, but its automation requires the availability of a rapid signal analysis technique, for prompt alarm emission whenever required. In the present paper a novel method of classifying lidar signals using committee machines composed of neural networks is proposed. A new method based on ROC curves and the Neyman-Pearson criterion is used to choose the optimal number of training epochs for each neural network in order to avoid overfitting. The best committee machine, obtained on the basis of these principles and selected to lead to the lowest percentage of false alarms for a true detection percentage of 90% for a test set created by adding random noise to patterns obtained experimentally, was composed of three single-layer perceptrons and presented a true detection efficiency of 94.4% and 0.553% of false alarms in the validation set.     

延迟离散Hopfield型神经网络异步收敛性

离散Ｈｏｐｆｉｅｌｄ型神经网络的一个重要性质是异步运动方式下总能收敛到稳定态。同步运行方式下总能收敛到周期不超过２的极限环,它是该模型可以用于联想记忆设计,组合设计计算的理论基础,文中给出了延迟离散Ｈｏｐｆｉｅｌｄ型网络的收敛性定理,在异步运动方式下,证明了对称连接权阵的收敛性定理,推广了已有的离散Ｈｏｐｆｉｅｌｄ型网络的收敛性结果,给出了能量函数极大值点与延迟离散Ｈｏｐｆｉｅｌｄ型网络的稳定态的