Fast ECG data compression algorithms suitable for microprocessor systems

ECG data compression techniques have received extensive attention in ECG analysis. Numerous data compression algorithms for ECG signals have been proposed during the last three decades. We describe two algorithms based on the scan-along polygonal approximation algorithm (SAPA) that are suitable for multichannel ECG data reduction on a microprocessor-based system. One represents a modification of SAPA (MSAPA) which adopts the method of integer division table searching to speed up data reduction; the other (CSAPA) combines MSAPA and TP, a turning-point algorithm, to preserve ST segment signals. Results show that our algorithms achieve a compression ratio of more than 5:1 and a percent rms difference (PRD) to the original signal of less than 3.5%. In addition, the maximum execution time of MSAPA for processing one data point is about 50μ s. Moreover, the CSAPA algorithm retains all of the details of the ST segment, which are important in ischaemia diagnosis, by employing the TP algorithm.     

脑电信号数据压缩及棘波识别的小波神经网络方法

本文在对小波神经网络及其算法研究的基础上,提出了一种对脑电信号压缩表达和痫样脑电棘波识别的新方法。实验结果显示,小波网络在大量压缩数据的同时,能够较好的恢复原有信号,另外,在脑电信号的时频谱等高线图上,得到了易于自动识别的棘波和棘慢复合波特征,说明此方法在电生理信号处理和时频分析方面有着光明的应用前景。     

Electrocardiogram Data Compression Techniques for Cardiac Healthcare Systems: A Methodological Review

Objective: Globally, cardiovascular diseases (CVDs) are one of the most leading causes of death. In medical screening and diagnostic procedures of CVDs, electrocardiogram (ECG) signals are widely used. Early detection of CVDs requires acquisition of longer ECG signals. It has triggered the development of personal healthcare systems which can be used by cardio-patients to manage the disease. These healthcare systems continuously record, store, and transmit the ECG data via wired/wireless communication channels. There are many issues with these systems such as data storage limitation, bandwidth limitation and limited battery life. Involvement of ECG data compression techniques can resolve all these issues.Method: In the past, numerous ECG data compression techniques have been proposed. This paper presents a methodological review of different ECG data compression techniques based on their experimental performance on ECG records of the Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database.Results: It is observed that experimental performance of different compression techniques depends on several parameters. The existing compression techniques are validated using different distortion measures.Conclusion: This study elaborates advantages and disadvantages of different ECG data compression techniques. It also includes different validation methods of ECG compression techniques. Although compression techniques have been developed very widely but the validation of compression methods is still a prospective research area to accomplish an efficient and reliable performance.     

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.     

Nonlinear analysis of continuous ECG during sleep I. Reconstruction

In recent years evidence has accumulated that ECG signals are of a nonlinear nature. It has been recognized that strictly periodic cardiac rhythms are not accompanied by healthy conditions but, on the contrary, by pathological states. Therefore, the application of methods from nonlinear system theory for the analysis of ECG signals has gained increasing interest. Crucial for the application of nonlinear methods is the reconstruction (embedding) of the time series in a phase space with appropriate dimension. In this study continuous ECG signals of 12 healthy subjects recorded during different sleep stages were analysed. Proper embedding dimension was determined by application of two techniques – the false nearest neighbours method and the saturation of the correlation dimension. Results for the ECG signals were compared with findings for simulated data (quasiperiodic dynamics, Lorenz data, white noise) and for phase randomized surrogates. Findings obtained with the two approaches suggest that embedding dimensions from 6 to 8 may be regarded as suitable for the topologically proper reconstruction of ECG signals. Received: 7 June 1999 / Accepted in revised form: 10 December 1999     

基于SOPC技术的多路并行ECG实时检测分析系统的设计

针对目前心电监护设备微型化、实时性、高采样率、存储量大等实际需求,采用了一种基于最新的SOPC（System On a Programmable Chip）技术的心电检测系统的设计。将DSP和MCU的功能集成在一块FPGA上,在FPGA内部实现多路心电信号的并行处理,由SD卡记录较长时间的连续心电信号,并实现心电信号的实时分析和心律失常的预警等扩展功能。     

Arrhythmic Heartbeat Classification Using 2D Convolutional Neural Networks

BackgroundElectrocardiogram (ECG) is a method of recording the electrical activity of the heart and it provides a diagnostic means for heart-related diseases. Arrhythmia is any irregularity of the heartbeat that causes an abnormality in the heart rhythm. Early detection of arrhythmia has great importance to prevent many diseases. Manual analysis of ECG recordings is not practical for quickly identifying arrhythmias that may cause sudden deaths. Hence, many studies have been presented to develop computer-aided-diagnosis (CAD) systems to automatically identify arrhythmias.MethodsThis paper proposes a novel deep learning approach to identify arrhythmias in ECG signals. The proposed approach identifies arrhythmia classes using Convolutional Neural Network (CNN) trained by two-dimensional (2D) ECG beat images. Firstly, ECG signals, which consist of 5 different arrhythmias, are segmented into heartbeats which are transformed into 2D grayscale images. Afterward, the images are used as input for training a new CNN architecture to classify heartbeats.ResultsThe experimental results show that the classification performance of the proposed approach reaches an overall accuracy of 99.7%, sensitivity of 99.7%, and specificity of 99.22% in the classification of five different ECG arrhythmias. Further, the proposed CNN architecture is compared to other popular CNN architectures such as LeNet and ResNet-50 to evaluate the performance of the study.ConclusionsTest results demonstrate that the deep network trained by ECG images provides outstanding classification performance of arrhythmic ECG signals and outperforms similar network architectures. Moreover, the proposed method has lower computational costs compared to existing methods and is more suitable for mobile device-based diagnosis systems as it does not involve any complex preprocessing process. Hence, the proposed approach provides a simple and robust automatic cardiac arrhythmia detection scheme for the classification of ECG arrhythmias.     

Comparison of three methods for beat-to-beat-interval extraction from continuous blood pressure and electrocardiogram with respect to heart rate variability analysis.

In recent years the analysis of heart rate variability (HRV) has become a suitable method for characterizing autonomous cardiovascular regulation. The aim of this study was to investigate the differences in HRV estimated from continuous blood pressure (BP) measurement by different methods in comparison to electrocardiogram (ECG) signals. The beat-to-beat intervals (BBI) were simultaneously extracted from the ECG and blood pressure of 9 cardiac patients (10 min, Colin system, 1000-Hz sampling frequency). For both data types, slope, peak, and correlation detection algorithms were applied. The short-term variability was calculated using concurrent 10-min BP and ECG segments. The root mean square errors in comparison to ECG slope detection were: 1.74 ms for ECG correlation detection; 5.42 ms for ECG peak detection; 5.45 ms for BP slope detection; 5.75 ms for BP correlation detection; and 11.96 ms for BP peak detection. Our results show that the variability obtained with ECG is the most reliable. Moreover, slope detection is superior to peak detection and slightly superior to correlation detection. In particular, for ECG signals with higher frequency characteristics, peak detection often exhibits more artificial variability. Besides measurement noise, respiratory modulation and pulse transit time play an important role in determining BBI. The slope detection method applied to ECG should be preferred, because it is more robust as regards morphological changes in the signals, as well as physiological properties. As the ECG is not recorded in most animal studies, distal pulse wave measurement in combination with correlation or slope detection may be considered an acceptable alternative.     

Shape identification of electrocardiographic ST segment based on radial basis function neural network

The types of myocardial ischemia can be revealed by electrocardiographic (ECG) ST segment.Effective measurement and electrocardiographic analysis of ST as well as calculation of displacement and shape change of ST segment can help doctors diagnose coronary heart disease and myocardial ischemia,especially for asymptomatic myocardial ischemia.Therefore,it is a very important subject in clinical practice to measure and classify the ECG ST segment.In this paper,we introduce a computerized automatic identification method of the electrocardiographic ST segment shape with radial basis function neural network based on adaptive fuzzy system,which has a better effect than other methods.It helps to analyze the reason of the ST segment change and confirm the position of myocardial ischemia,and is useful for doctor diagnosis.     

Dynalets: A new method for modelling and compressing biological signals. Applications to physiological and molecular signals

The biological information coming from electrophysiologic sensors like ECG, pulse sensor or from molecular signal devices like NMR spectrometry has to be visualized and manipulated in a compressed way for an efficient medical use by clinicians, if stored in scientific data bases or in personalized patient records repositories. Here, we define a new transform called Dynalet based on Liénard ordinary differential equations susceptible to model the mechanism at the source of the studied signal, and we propose to apply this new technique first to the modelling and compression of real biological periodic signals like ECG and pulse rhythm. We consider that the cardiovascular activity results from the summation of cellular oscillators located in the cardiac sinus node and we show that, as a result, the van der Pol oscillator (a particular Liénard system) fits well the ECG signal and the pulse signal. The reconstruction of the original signal (pulse or ECG) using Dynalet transform is then compared with that of Fourier, counting the number of parameters to be set for obtaining an expected signal-to-noise ratio. Then, we apply the Dynalet transform to the modelling and compression of molecular spectra obtained by protein NMR spectroscopy. The reconstruction of the original signal (peak) using Dynalet transform is again compared with that of Fourier. After reconstructing visually the peak, we propose to periodize the signal and give it to hear, the whole process being called the protein “stethoscope”.     

基于小波变换的混合二维ECG数据压缩方法

提出了一种新的基于小波变换的混合二维心电(electrocardiogram,ECG)数据压缩方法。基于ECG数据的两种相关性,该方法首先将一维ECG信号转化为二维信号序列。然后对二维序列进行了小波变换,并利用改进的编码方法对变换后的系数进行了压缩编码:即先根据不同系数子带的各自特点和系数子带之间的相似性,改进了等级树集合分裂(setpartitioninghierarchicaltrees,SPIHT)算法和矢量量化(vectorquantization,VQ)算法;再利用改进后的SPIHT与VQ相混合的算法对小波变换后的系数进行了编码。利用所提算法与已有具有代表性的基于小波变换的压缩算法和其他二维ECG信号的压缩算法,对MIT/BIH数据库中的心律不齐数据进行了对比压缩实验。结果表明:所提算法适用于各种波形特征的ECG信号,并且在保证压缩质量的前提下,可以获得较大的压缩比。     

ECG compression using the context modeling arithmetic coding with dynamic learning vector–scalar quantization

Electrocardiogram (ECG) compression can significantly reduce the storage and transmission burden for the long-term recording system and telemedicine applications. In this paper, an improved wavelet-based compression method is proposed. A discrete wavelet transform (DWT) is firstly applied to the mean removed ECG signal. DWT coefficients in a hierarchical tree order are taken as the component of a vector named tree vector (TV). Then, the TV is quantized with a vector–scalar quantizer (VSQ), which is composed of a dynamic learning vector quantizer and a uniform scalar dead-zone quantizer. The context modeling arithmetic coding is finally employed to encode those quantized coefficients from the VSQ. All tested records are selected from the Massachusetts Institute of Technology-Beth Israel Hospital arrhythmia database. Statistical results show that the compression performance of the proposed method outperforms several published compression algorithms.     

Elements for a general memory structure: properties of recurrent neural networks used to form situation models

We study how individual memory items are stored assuming that situations given in the environment can be represented in the form of synaptic-like couplings in recurrent neural networks. Previous numerical investigations have shown that specific architectures based on suppression or max units can successfully learn static or dynamic stimuli (situations). Here we provide a theoretical basis concerning the learning process convergence and the network response to a novel stimulus. We show that, besides learning “simple” static situations, a nD network can learn and replicate a sequence of up to n different vectors or frames. We find limits on the learning rate and show coupling matrices developing during training in different cases including expansion of the network into the case of nonlinear interunit coupling. Furthermore, we show that a specific coupling matrix provides low-pass-filter properties to the units, thus connecting networks constructed by static summation units with continuous-time networks. We also show under which conditions such networks can be used to perform arithmetic calculations by means of pattern completion.     

Computationally Efficient Cosine Modulated Filter Bank Design for ECG Signal Compression

In this work, computationally efficient and reliable cosine modulated filter banks (CMFBs) are designed for Electrocardiogram (ECG) data compression. First of all, CMFBs (uniform and non-uniform) are designed using interpolated finite impulse response (IFIR) prototype filter to reduce the computational complexity. To reduce the reconstruction error, linear iteration technique is applied to optimize the prototype filter. Then after, non-uniform CMFB is used for ECG data compression by decomposing ECG signal into various frequency bands. Subsequently, thresholding is applied for truncating the insignificant coefficients. The estimation of the threshold value is done by examining the significant energy of each band. Further, Run-length encoding (RLE) is utilized for improving the compression performance. The method is applied to MIT-BIH arrhythmia database for performance analysis of the proposed work. The experimental observations demonstrate that the proposed method has accomplished high compression ratio with the admirable quality of signal reconstruction. The proposed work provides the average values of compression ratio (CR), percent root mean square difference (PRD), percent root mean square difference normalized (PRDN), quality score (QS), correlation coefficient (CC), maximum error (ME), mean square error (MSE), and signal to noise ratio (SNR) are 23.86, 1.405, 2.55, 19.08, 0.999, 0.12, 0.054 and 37.611 dB, respectively. The proposed 8-channel uniform filter bank is used to detect the R-peak locations of the ECG signal. The comparative analysis shows that beats (locations and amplitudes) of both signals (original and reconstructed signals) are same.     

Reassessment of morphological characteristics in freshwater eels (genus Anguilla, Anguillidae) shows congruence with molecular phylogeny estimates

The morphology-based phylogeny of freshwater eels, proposed by V. Ege in 1939, has been accepted as the basis of eel classification since that time. However, this has been called into question by recent molecular studies. Most of the morphological characteristics recognized by Ege are morphometric. Since methods for the application of morphometric data to phylogeny construction have not been fully established, it is unclear whether the observed discrepancies between morphological and molecular data arise from intrinsic differences or from flawed analyses. Here, we have used two methods to assemble evolutionary trees from distance matrices constructed according to Ege's data, the neighbor-joining (NJ) method and the minimum network (MinNet) method; the latter is based on an evolutionary algorithm. After reanalysing Ege's morphological data, we found that both methods gave results consistent with those based on molecular data, although not with Ege's original classification. Therefore, we speculate that some morphological features Ege used to subdivide the eel groups may not be synapomorphic as he proposed, but symplesiomorphic or convergent . The method developed here may prove useful for constructing phylogeny for taxon groups where only continuous morphometric characteristics are recognized, such as the freshwater eels.     

Shape identification of electrocardiographic ST segment based on radial basis function neural network

The types of myocardial ischemia can be revealed by electrocardiographic (ECG) ST segment. Effective measurement and electrocardiographic analysis of ST as well as calculation of displacement and shape change of ST segment can help doctors diagnose coronary heart disease and myocardial ischemia, especially for asymptomatic myocardial ischemia. Therefore, it is a very important subject in clinical practice to measure and classify the ECG ST segment. In this paper, we introduce a computerized automatic identification method of the electrocardiographic ST segment shape with radial basis function neural network based on adaptive fuzzy system, which has a better effect than other methods. It helps to analyze the reason of the ST segment change and confirm the position of myocardial ischemia, and is useful for doctor diagnosis. Translated from Acta Biophysica Sinica, 2005, 21(6): 443–448 [译自: 生物物理学报]     

ECG signal compression using ASCII character encoding and transmission via SMS

Software based efficient and reliable ECG data compression and transmission scheme is proposed here. The algorithm has been applied to various ECG data of all the 12 leads taken from PTB diagnostic ECG database (PTB-DB). First of all, R-peaks are detected by differentiation and squaring technique and QRS regions are located. To achieve a strict lossless compression in the QRS regions and a tolerable lossy compression in rest of the signal, two different compression algorithms have used. The whole compression scheme is such that the compressed file contains only ASCII characters. These characters are transmitted using internet based Short Message Service (SMS) and at the receiving end, original ECG signal is brought back using just the reverse logic of compression. It is observed that the proposed algorithm can reduce the file size significantly (compression ratio: 22.47) preserving ECG signal morphology.     

Numerical bifurcation analysis of distance-dependent on-center off-surround shunting neural networks

 On-center off-surround shunting neural networks are often applied as models for content-addressable memory (CAM), the equilibria being the stored memories. One important demand of biological plausible CAMs is that they function under a broad range of parameters, since several parameters vary due to postnatal maturation or learning. Ellias, Cohen and Grossberg have put much effort into showing the stability properties of several configurations of on-center off-surround shunting neural networks. In this article we present numerical bifurcation analysis of distance-dependent on-center off-surround shunting neural networks with fixed external input. We varied four parameters that may be subject to postnatal maturation: the range of both excitatory and inhibitory connections and the strength of both inhibitory and excitatory connections. These analyses show that fold bifurcations occur in the equilibrium behavior of the network by variation of all four parameters. The most important result is that the number of activation peaks in the equilibrium behavior varies from one to many if the range of inhibitory connections is decreased. Moreover, under a broad range of the parameters the stability of the network is maintained. The examined network is implemented in an ART network, Exact ART, where it functions as the classification layer F2. The stability of the ART network with the F2-field in different dynamic regimes is maintained and the behavior is functional in Exact ART. Through a bifurcation the learning behavior of Exact ART may even change from forming local representations to forming distributed representations. Received: 23 January 1996 / Accepted in revised form: 1 July 1996     

A New Method for Nonlinear Dynamic Analysis of the Multi-kinetics Neural Mass Model

ObjectiveThe aim was to use a new method to analyze the nonlinear dynamic characteristics of the multi-kinetics neural mass model. We hope that this new method can be as an auxiliary judgment tool for the diagnosis of brain diseases and the identification of brain activity states.MethodsWe apply the Lorenz plot to analyze the nonlinear dynamic characteristics of electroencephalogram (EEG) signals from the multi-kinetics neural mass models. The standard deviations in two orthogonal directions of the Lorenz plot are further used to quantify the nonlinear dynamic characteristics of EEG signals.ResultsThe results show that the normalized signal frequency power spectrum may not be able to distinguish normal EEG signals and epileptiform spikes, but the Lorenz plot can distinguish the normal EEG signals and epileptiform spikes effectively. For EEG signals with multi-rhythms, the Lorenz plot of all the simulated signals are oval, but the value of SD1/SD2 increases monotonically when the multi-rhythm EEG signals change from low frequency to high frequency.ConclusionThe Lorenz plot of EEG signals with different rhythms presents different distribution. It is an effective nonlinear analysis method for EEG signals.