Discriminant analysis of multivariate time series: Application to diagnosis based on ECG signals

In analysing ECG data, the main aim is to differentiate between the signal patterns of healthy subjects and those of individuals with specific heart conditions. We propose an approach for classifying multivariate ECG signals based on discriminant and wavelet analyses. For this purpose we use multiple-scale wavelet variances and wavelet correlations to distinguish between the patterns of multivariate ECG signals based on the variability of the individual components of each ECG signal and on the relationships between every pair of these components. Using the results of other ECG classification studies in the literature as references, we demonstrate that our approach applied to 12-lead ECG signals from a particular database compares favourably. We also demonstrate with real and synthetic ECG data that our approach to classifying multivariate time series out-performs other well-known approaches for classifying multivariate time series.     

Cloud enabled fractal based ECG compression in wireless body sensor networks

E-health applications deal with a huge amount of biological signals such as ECG generated by body sensor networks (BSN). Moreover, many healthcare organizations require access to these records. Therefore, cloud is widely used in healthcare systems to serve as a central service repository. To minimize the traffic going to and coming from cloud ECG compression is one of the proposed solutions to overcome this problem. In this paper, a new fractal based ECG lossy compression technique is proposed. It is found that the ECG signal self-similarity characteristic can be used efficiently to achieve high compression ratios. The proposed technique is based on modifying the popular fractal model to be used in compression in conjunction with the iterated function system. The ECG signal is divided into equal blocks called range blocks. Subsequently, another down-sampled copy of the ECG signal is created which is called domain. For each range block the most similar block in the domain is found. As a result, fractal coefficients (i.e. parameters defining fractal compression model) are calculated and stored inside the compressed file for each ECG signal range block. In order to make our technique cloud friendly, the decompression operation is designed in such a way that allows the user to retrieve part of the file (i.e. ECG segment) without decompressing the whole file. Therefore, the clients do not need to download the full compressed file before they can view the result. The proposed algorithm has been implemented and compared with other existing lossy ECG compression techniques. It is found that the proposed technique can achieve a higher compression ratio of 40 with lower Percentage Residual Difference (PRD) Value less than 1%.     

Feature selection for ECG signal processing using improved genetic algorithm and empirical mode decomposition

This paper proposes a novel scheme of feature selection, which employs a modified genetic algorithm that uses a variable-range searching strategy and empirical mode decomposition (EMD). Combined with support vector machines (SVMs), a new pattern recognition method for electrocardiograph (ECG) is developed. First, the ECG signal is decomposed into intrinsic mode functions (IMFs) that represent signal characteristics with sample oscillatory modes. Then, the modified genetic algorithm with variable-range encoding and dynamic searching strategy is used to optimize statistical feature subsets. Next, a statistical model based on receiver operating characteristic (ROC) analysis is developed to select the dominant features. Finally, the SVM-based pattern recognition model is used to classify different ECG patterns. Comparative studies with peer-reviewed results and two other well-known feature selection methods demonstrate that the proposed method can select dominant features in processing ECG signal, and achieve better classification performance with lower feature dimensionality.     

Myocardial infarction classification with multi-lead ECG using hidden Markov models and Gaussian mixture models

This study presented a new diagnosis system for myocardial infarction classification by converting multi-lead ECG data into a density model for increasing accuracy and flexibility of diseases detection. In contrast to the traditional approaches, a hybrid system with HMMs and GMMs was employed for data classification. A hybrid approach using multi-leads, i.e., lead-V1, V2, V3 and V4 for myocardial infarction were developed and HMMs were used not only to find the ECG segmentations but also to calculate the log-likelihood value which was treated as statistical feature data of each heartbeat's ECG complex. The 4-dimension feature vector extracted by HMMs was clustered by GMMs with different numbers of distribution (disease and normal data). SVMs classifier was also examined for comparison with our system in experimental result. There were total 1129 samples of heartbeats from clinical data, including 582 data with myocardial infarction and 547 normal data. The sensitivity of this diagnosis system achieved 85.71%, specificity achieved 79.82% and accuracy achieved 82.50% statistically.     

基于小波变换的涡喷发动机遥测数据分析方法研究

在飞行试验中,由于涡喷发动机遥测数据有限,因此要对其故障进行准确分析定位存在很大难度。利用小波变换对涡喷发动机涡轮转速、喷嘴前压力等遥测数据经过去噪提取后,找出奇异点,并经系统去噪筛选,形成数据文件,利用BP神经网络的模式分类功能,发现故障出现的时刻及部件,并结合研制过程中地面试车数据库,可实现准确定位涡喷发动机故障部位及类型。实际应用证明方法实用有效,可进一步推广到其他系统或部件的故障分析工作中。     

一种超宽线性范围低通带衰减的OTA-C心电信号滤波器设计

介绍了一种基于全差分运算跨导放大器（OTA）的超宽线性范围低通带衰减的五阶Butterworth低通滤波器。该滤波器主要应用于可穿戴式无线体域网的UWB健康监护与遥测系统。为了提高OTA-C滤波器线性范围,对典型小跨导电路的源极负反馈结构进行了改进,并将共源共栅结构作为OTA的输出级以减少滤波器的通带衰减。为了适应生物医学芯片的低功耗特性,基于OTA结构的电路工作在亚阈值区。电路基于SMIC 0.18-μm CMOS工艺进行设计并流片。测试结果表明,滤波器的通带衰减仅为6.2dB,-3-dB频率为276 Hz;对于输入100 Hz、0.8 VPP的正弦信号,该滤波器的总谐波失真（THD）为56.8 dB。利用该滤波器对含有噪声干扰的ECG信号进行滤波, 结果证明了该滤波器能有效地滤除噪声干扰。     

一种级联的激光主动成像图像融合降噪算法

针对激光主动成像图像混合噪声的特点,提出了一种投票中值滤波和整数提升小波级联的融合降噪算法。首先对激光图像进行噪声像素点检测,区分噪声点与非噪声点;而后采用投票中值滤波对噪声点进行处理,抑制脉冲噪声;然后采用整数提升小波变换对图像进行Bayes自适应阈值去噪,抑制散斑噪声;最后通过逆变换得到去噪图像。通过实验比对结果表明,该方法在具有良好的去噪、边缘保持性能的同时,还具有较为理想的实时性。     

一种适用于心电信号检测的高阶连续时间OTA-C滤波器设计

提出一种适合心电信号（ECG）检测的OTA-C滤波器。为了达到低功耗、低截止频率、高直流增益、高阻带衰减、低谐波失真的目的,滤波器采用五阶巴特沃斯全差分低通滤波结构和高增益的两级单端输出OTA,其中OTA电路采用亚阈值区驱动、电流分流和源极负反馈等技术。采用SMIC 0.18-μm 1P6M CMOS工艺进行电路、版图设计及优化。仿真结果表明,滤波器在静态功耗为17.6 μW,截止频率为240 Hz,直流增益为-6 dB,阻带衰减为120 dB每十倍频,三次谐波失真小于-62 dB@ 400 mV,适合应用于心电信号检测模拟前端。     

基于间接示功图测量的电潜柱塞泵故障诊断研究与应用

在分析电潜柱塞泵工作原理的基础上,结合柱塞式抽油泵的结构,建立了机组运行的理论示功图,对其进行了深入分析。以功率信号作为故障信息,提出一种基于间接示功图测量的电潜柱塞泵故障诊断方法,并描述了小波去噪方法绘制实测示功图的主要过程。针对机组典型故障,在室内模拟平台和现场油井上对该方法的准确性进行了验证实验与分析。测试结果表明:故障诊断效果较好。     

光纤陀螺实时小波去噪中的阈值选取

在使用小波域阈值滤波方法消除光纤陀螺输出噪声时,阈值的确定和阈值函数的选取是两个关键问题,它们直接关系到小波滤波的滤波效果,目前关于此方面的讨论较多基于离线分析。在综合考虑了实时性与滤波效果后提出了一种改进的阈值确定方法,并针对强制去噪动态性能差的问题提出了一种新的小波系数处理策略,最后利用LabVIEW软件对该算法进行了工程实现。通过试验验证,此方法在不影响滤波效果的前提下具有实时性能好的优点,具有较好的工程应用价值。