小波变换与概率神经网络的心电图分类

提出了一种实时高效的心电图分类理论与方法。首先对心电图进行六尺度小波分解,将含有主要噪声的尺度进行系数置零,再将剩余层进行小波重构,从而达到除噪的目的。利用数学形态学定位心电图P、Q、R、S、T波位置,并提取计算各波间距离和斜率等12个特征值作为概率神经网络的输入向量,从而实现心电图的六分类。     

小波网络和RBF网络的抗噪语音识别

针对目前在噪音环境下语音识别系统性能较差的问题,利用小波神经网络融合了小波变换良好的时频局域化性质和RBF神经网络具有最佳分类能力和辨识能力等特性。构建了一个用小波基替代RBF网络中激活函数的小波-RBF神经网络结构,并采用全监督训练算法,实现了基于小波-RBF网络的抗噪语音识别系统。实验结果表明该系统比RBF网络具有更好的识别效果,尤其在噪声环境下,具有更强的鲁棒性。     

Discrete harmony search based expert model for epileptic seizure detection in electroencephalography

Seizure detection and classification using signal processing methods has been an important issue of research for the last two decades. In the present study, a novel scheme was presented to detect epileptic seizure activity with very fast and highest accuracy from background electro encephalogram (EEG) data recorded from epileptic and normal subjects. The proposed scheme is based on discrete wavelet packet transform (DWT) with energy, entropy, standard deviation, mean, kurtosis, skewness and entropy estimation at each node of the decomposition tree followed by application of probabilistic neural network (PNN). Normal as well as epileptic EEG epochs were decomposed into approximation and details coefficients till sixth-level using DWT packet. Discrete harmony search with modified differential operator was used to select the optimal features out of all above mentioned statistical and non-statistical parameters. In order to demonstrate the efficacy of the proposed algorithm for classification purpose using PNN, we have implemented 10-fold cross validation. Clinical EEG data recorded from normal as well as epileptic subjects are used to test the performance of this new scheme. It is found that the detection rate is 100% accurate with same level of sensitivity and specificity.     

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.     

基于小波矩和BP网络的声音识别

目前大多数声音识别系统在无噪声环境下可以达到很高的识别率,但是在噪声环境下,识别率急剧下降。针对这个问题,提出一种基于小波矩和BP网络的声音识别方法。根据声音信号生成声谱图;通过小波矩对声谱图进行特征提取,选取有代表性意义的特征参数;根据选取的参数进行BP网络分类识别,从而识别声音的种类。实验结果表明,该方法在不同噪声种类以及不同信噪比的噪声环境下仍然具有较好的识别效果,克服了低信噪比下识别率低的缺陷。     

基于小波混沌神经网络的语音识别*

基于语音信号的时变特性,提出了一种新型神经网络语音识别方法——小波混沌神经网络方法,即把小波变换和混沌特性引入到神经元,构成小波混沌神经网络,将这种神经网络用于语音识别,并与常用的BP神经网络识别方法进行了比较。实验结果表明,小波混沌神经网络的平均识别率要高于同等条件下常用的神经网络方法的识别率。     

Discrimination of quarry blasts and earthquakes in the vicinity of Istanbul using soft computing techniques

The purpose of this article is to demonstrate the use of feedforward neural networks (FFNNs), adaptive neural fuzzy inference systems (ANFIS), and probabilistic neural networks (PNNs) to discriminate between earthquakes and quarry blasts in Istanbul and vicinity (the Marmara region). The tectonically active Marmara region is affected by the Thrace-Eski?ehir fault zone and especially the North Anatolian fault zone (NAFZ). Local MARNET stations, which were established in 1976 and are operated by the Kandilli Observatory and Earthquake Research Institute (KOERI), record not only earthquakes that occur in the region, but also quarry blasts. There are a few quarry-blasting areas in the Gaziosmanpa?a, Çatalca, Ömerli, and Hereke regions. Analytical methods were applied to a set of 175 seismic events (2001-2004) recorded by the stations of the local seismic network (ISK, HRT, and CTT stations) operated by the KOERI National Earthquake Monitoring Center (NEMC). Out of a total of 175 records, 148 are related to quarry blasts and 27 to earthquakes. The data sets were divided into training and testing sets for each region. In all the models developed, the input vectors consist of the peak amplitude ratio (S/P ratio) and the complexity value, and the output is a determination of either earthquake or quarry blast. The success of the developed models on regional test data varies between 97.67% and 100%.     

基于有限长脉冲响应滤波器和aTrous算法的小波心电信号去噪

微弱低频的心电信号采集中容易受到外界环境的干扰,必须先对其进行预处理才能用于心脏疾病的诊断。Mallat算法的小波分解重构法不能有效滤除心电信号中的工频和肌电干扰;小波阈值法不能有效滤除心电信号中的工频和基线漂移,重构的心电信号会产生伪吉布斯现象。针对以上情况,提出了一种基于有限长脉冲响应滤波器(FIR)和aTrous算法的小波去噪方法。该方法综合运用了50Hz陷波器、aTrous算法小波分解重构法和小波阈值法。仿真郑州大学第二附属医院和MIT-BIH心率失常数据库的心电信号表明,该方法能够有效去除心电信号中的工频和基线漂移,大幅度衰减肌电干扰,同时有效消除伪吉布斯现象。     

基于听觉感知和概率神经网络的语音识别模型

提出了一种基于Bark子波变换和概率神经网络（PNN）的语音识别模型。利用符合人耳听觉特性的Bark滤波器组进行信号重构并提取语音特征,然后利用训练好的概率神经网络进行识别。通过训练大量语音样本来构成语音识别库,并建立综合识别系统。实验结果表明该方法与传统的LPCC/DTW和MFCC/DWT方法相比,识别率分别提高了14.9%和10.1%,达到了96.9%的识别率。     

基于小波分解和优选的VLBP特征的表情识别方法*

提出一种基于小波分解和优选的VLBP特征的表情识别方法。该方法首先通过小波分解将原始图像分为几个不同频率的子图像来增强图像信息,然后用VLBP算子对不同频率的子图像运用不同的分块大小提取特征,采用神经网络贡献分析对特征进行选择,最后用SVM分类器进行识别。实验表明,该方法比单纯从原图像中提取VLBP特征更加有效,识别率更高,并且VLBP特征的提取速度快,可用于实时的人脸表情识别。     

卷积神经网络在心拍类识别中的应用

心电图（ECG）心拍分类对心脏疾病的临床诊断具有重要意义,但是ECG四类心拍间数据不平衡问题严重制约着心拍分类性能的提升。针对这一问题,以卷积神经网络（CNN）为基础,首先在组合四类心拍等量数据基础上构建用于表达噪声及四类心拍间共性信息的通用CNN模型,接着以通用CNN模型为基础分别在四类心拍数据上构建四个更为有效表达对应心拍类别倾向性信息的类别CNN模型,最后综合四个类别CNN模型的输出判别心拍类型。在MIT-BIH心电图数据库上的实验结果显示,该方法的平均灵敏度为99.68%、平均阳性检测率是98.58%、综合指标是99.12%,显著优于二级联合聚类法在MIT-BIH心电图数据库上的分类性能。     

Authentication of WSN for Secured Medical Data Transmission Using Diffie Hellman Algorithm

The applications of wireless sensor network (WSN) exhibits a significant rise in recent days since it is enveloped with various advantageous benefits. In the medical field, the emergence of WSN has created marvelous changes in monitoring the health conditions of the patients and so it is attracted by doctors and physicians. WSN assists in providing health care services without any delay and so it plays predominant role in saving the life of human. The data of different persons, time, places and networks have been linked with certain devices, which are collectively known as Internet of Things (IOT); it is regarded as the essential requirement of people in recent days. In the health care monitoring system, IOT plays a magnificent role, which has produced the real time monitoring of patient’s condition. However the medical data transmission is accomplished quickly with high security by the routing and key management. When the data from the digital record system (cloud) is accessed by the patients or doctors, the medical data is transferred quickly through WSN by performing routing. The Probabilistic Neural Network (PNN) is utilized, which authenticates the shortest path to reach the destination and its performance is identified by comparing it with the Dynamic Source Routing (DSR) protocol and Energy aware and Stable Routing (ESR) protocol. While performing routing, the secured transmission is achieved by key management, for which the Diffie Hellman key exchange is utilized, which performs encryption and decryption to secure the medical data. This enables the quick and secured transmission of data from source to destination with improved throughput and delivery ratio.     

Adaptive output-feedback regulation for nonlinear delayed systems using neural network

A novel adaptive neural network （NN） output-feedback regulation algorithm for a class of nonlinear time-varying timedelay systems is proposed. Both the designed observer and controller are independent of time delay. Different from the existing results, where the upper bounding functions of time-delay terms are assumed to be known, we only use an NN to compensate for all unknown upper bounding functions without that assumption. The proposed design method is proved to be able to guarantee semi-global uniform ultimate boundedness of all the signals in the closed system, and the system output is proved to converge to a small neighborhood of the origin. The simulation results verify the effectiveness of the control scheme.     

基于遗传算法和小波神经网络的语音识别研究

小波神经网络算法(WNN)易陷入局部极小,收敛速度慢,全局搜索能力弱,而遗传算法(GA)具有高度并行、随机、自适应搜索性能和全局寻优的特点。因此,将遗传算法和小波神经网络结合起来形成一种训练神经网络的混合算法——GA-WNN算法。仿真实验结果表明,该算法有效地缩短了识别时间,提高了网络训练速度和语音的识别率。     

自适应阈值小波滤波及其在ECG消噪中的应用

采集的心电信号,各类噪声往往覆盖了其有用信号的全频段范围,通常的方法难以有效消噪。讨论了将非线性阈值函数h引入小波消噪中,通过训练信号来确定各尺度下的h函数参数,然后采用阈值自适应的小波滤波进行心电信号消噪的方法。通过和Donoho的小波阈值消噪法对实测心电信号消噪比较,说明了该方法在心电消噪方面的有效性,且在消噪后波形不失真方面具有更好的优越性。     

基于小波和余弦变换的神经网络人脸识别法

提出了利用小波变换和余弦变换与 BP 神经网络相结合的人脸识别方法。将人脸图像归一化后进行小波变换,再用余弦变换对低频信号提取特征向量,达到降维和去除干扰的目的,并把特征向量送进 BP 神经网络训练。识别时,对人脸图像进行相同的变换后,送入神经网络进行辨别。实验结果表明,该算法优于传统的人脸识别法。     

A self-evolving functional-linked wavelet neural network for control applications

The structure of a neural network is determined by time-consuming trial-and-error tuning procedure in advance for the reason that it is difficult to consider the balance between the neuron number and the desired performance. To attack this problem, a self-evolving functional-linked wavelet neural network (SFWNN) is proposed. Without the need for preliminary knowledge, a self-evolving approach demonstrates that the properties of generating and pruning the hidden neurons automatically. Then, an adaptive self-evolving functional-linked wavelet neural control (ASFWNC) system which is composed of a neural controller and a supervisory compensator is proposed. The neural controller uses a SFWNN to online estimate an ideal controller and the supervisory compensator is designed to eliminate the effect of the approximation error introduced by the neural controller upon the system stability in the Lyapunov sense. To investigate the capabilities of the proposed ASFWNC approach, it is applied to a chaotic system and a DC motor. The simulation and experimental results show that favorable control performance can be achieved by the proposed ASFWNC scheme.     

A comparative study of wavelet families for EEG signal classification

Over the past two decades, wavelet theory has been used for the processing of biomedical signals for feature extraction, compression and de-noising applications. However the question as to which wavelet family is the most suitable for analysis of non-stationary bio-signals is still prevalent among researchers. This paper attempts to find the most useful wavelet function among the existing members of the wavelet families for electroencephalogram signal (EEG) analysis. The EEGs considered for this study belong to both normal as well as abnormal signals like epileptic EEG. Important features such as energy, entropy and standard deviation at different sub-bands were computed using the wavelet functions—Haar, Daubechies (orders 2-10), Coiflets (orders 1-10), and Biorthogonal (orders 1.1, 2.4, 3.5, and 4.4). Feature vectors were used to model and train the Probabilistic Neural Network (PNN) and the classification accuracies were evaluated for each case. The results obtained from PNN classifier were compared with Support Vector Machine (SVM) classifier. From the statistical analysis, it was found that Coiflets 1 is the most suitable candidate among the wavelet families considered in this study for accurate classification of the EEG signals. In this work, we have attempted to improve the computing efficiency as it selects the most suitable wavelet function that can be used for EEG signal processing efficiently and accurately with lesser computational time.     

基于小波神经网络的空调系统传感器故障诊断

详细阐述了小波神经网络(WNN)的原理、结构,并对传统的BP算法进行了改进。以空调系统传感器故障检测问题为目标,提出了基于WNN的故障诊断方法。通过采集天津博物馆中的传感器数据,对训练好的WNN进行了传感器故障诊断能力的验证,对温度传感器的1℃偏差故障、0.05℃/s速率漂移故障、完全故障、与不同方差下的精度等级下降故障进行了仿真,结果表明:这种方法对传感器故障具有很好的诊断效果。     

一种求解优化问题的新型小波混沌神经网络

基于神经元的自反馈项可产生混沌的现象,将Gauss小波函数作为混沌神经元的自反馈项。分析了Gauss小波的尺度和平移参数对神经元动力学的影响,提出了自反馈连接权和Gauss小波尺度双重模拟退火的混沌神经元。构建了混沌神经网络模型,分析了由Gauss小波函数产生的附加能量函数对网络优化能力的影响。优化问题的仿真结果表明,该网络能够以较快的速度找到优化问题的全局最优解。