基于改进的RAKEL算法的心电图诊断分类

心电图（ECG）数据通常包含多种病症,而ECG诊断是一个典型的多标签分类问题。在多标签分类方法中,RAKEL算法将标签集随机分解为若干个大小为k的子集,并建立LP分类器进行训练;然而由于没有充分考虑标签间的相关性,LP分类器中容易产生一些标签组合所对应样本稀少的情况,从而影响预测性能。为了充分考虑标签间的相关性,提出一种基于贝叶斯网络的RAKEL算法BN-RAKEL。首先利用贝叶斯网络找到标签间的相关性,确定候选标签子集;然后对每个标签采用基于信息增益的特征选择算法确定其最优特征空间,并针对每个候选标签子集利用最优特征空间相似性来检测其相关程度,以确定最终的具有强相关性的标签子集;最后在标签子集的最优特征空间上训练LP分类器。在实际的ECG数据集上,与多标签K近邻（ML-KNN）、RAKEL、CC和基于FP-Growth的RAKEL算法FI-RAKEL进行对比,结果显示所提算法在召回率和F-score上最少提高了3.6个百分点和2.3个百分点。实验结果表明,BN-RAKEL算法有较好的预测性能,能有效提升ECG诊断的准确性。     

Semisupervised Sparse Multilinear Discriminant Analysis

Various problems are encountered when adopting ordinary vector space algorithms for high-order tensor data input. Namely, one must overcome the Small Sample Size （SSS） and overfitting problems. In addition, the structural information of the original tensor signal is lost during the vectorization process. Therefore, comparable methods using a direct tensor input are more appropriate. In the case of electrocardiograms （ECGs）, another problem must be overcome; the manual diagnosis of ECG data is expensive and time consuming, rendering it difficult to acquire data with diagnosis labels. However, when effective features for classification in the original data are very sparse, we propose a semisupervised sparse multilinear discriminant analysis （SSSMDA） method. This method uses the distribution of both the labeled and the unlabeled data together with labels discovered through a label propagation Mgorithm. In practice, we use 12-lead ECGs collected from a remote diagnosis system and apply a short-time-fourier transformation （STFT） to obtain third-order tensors. The experimental results highlight the sparsity of the ECG data and the ability of our method to extract sparse and effective features that can be used for classification.     

A new ECG beat clustering method based on kernelized fuzzy c-means and hybrid ant colony optimization for continuous domains

The kernelized fuzzy c-means algorithm uses kernel methods to improve the clustering performance of the well known fuzzy c-means algorithm by mapping a given dataset into a higher dimensional space non-linearly. Thus, the newly obtained dataset is more likely to be linearly seprable. However, to further improve the clustering performance, an optimization method is required to overcome the drawbacks of the traditional algorithms such as, sensitivity to initialization, trapping into local minima and lack of prior knowledge for optimum paramaters of the kernel functions. In this paper, to overcome these drawbacks, a new clustering method based on kernelized fuzzy c-means algorithm and a recently proposed ant based optimization algorithm, hybrid ant colony optimization for continuous domains, is proposed. The proposed method is applied to a dataset which is obtained from MIT–BIH arrhythmia database. The dataset consists of six types of ECG beats including, Normal Beat (N), Premature Ventricular Contraction (PVC), Fusion of Ventricular and Normal Beat (F), Artrial Premature Beat (A), Right Bundle Branch Block Beat (R) and Fusion of Paced and Normal Beat (f). Four time domain features are extracted for each beat type and training and test sets are formed. After several experiments it is observed that the proposed method outperforms the traditional fuzzy c-means and kernelized fuzzy c-means algorithms.     

心电信号采集记录系统的设计

为了更好地解决心电信号的采集和处理问题,设计了以高性能DSP芯片TMS320C32x为核心心电信号的采集记录系统,对心电信号的放大、滤波部分的硬件设计进行了重点研究并针对实际应用设计了检测电路,以C语言为基础设计了系统软件和针对于心电信号处理的自适应滤波器,实践证明该系统能很好地完成对心电信号的采集、滤波和记录。     

A H-QoS-demand personalized home physiological monitoring system over a wireless multi-hop relay network for mobile home healthcare applications

For the elderly and chronic patients with cardiovascular disease who live alone, it is necessary to constantly monitor their physiological parameters, especially the electrocardiogram (ECG), to effectively prevent and control their health condition and even to provide urgent treatment or care while an emergency such as the abnormal variation of heart rate (HR) occurs. In this paper, a wireless in-home physiological monitoring system, based on multi-hop relay communications, which can ubiquitously and continuously monitor the patient's ECG at any time or any place at home without space limit and the “dead spot” due to the extended communication coverage by multi-hop wireless connectivity, is proposed. The system consists of a mobile-care device, which is responsible for capturing and wirelessly sending the patient's ECG data, a wireless multi-hop relay network (WMHRN) that is in charge of relaying the data sent by the former, and a residential gateway (RG), which is responsible for gathering and uploading the received ECG data to the remote care server through the Internet to carry out the patient's health condition monitoring and the management of pathological data. However, in order to assure that the ECG data can be effectively and timely forwarded, from the mobile-care device to the RG through the WMHRN, to meet the healthcare quality of service (H-QoS) demand for reliable and real-time end-to-end ECG transmission, the analysis of WMHRN latency in data-forwarding stage and the deployment consideration of wireless relay nodes are investigated in detail in this work. Moreover, an emergency alert service using short message service (SMS), based on the detection of abnormal variation of HR, is also used in the RG to further enhance the healthcare service quality. A prototype of this system has been developed and implemented. Finally, the experimental results are presented to verify the feasibility of the proposed system.     

深度稀疏自编码器在ECG特征提取中的应用

针对心电（ECG）信号智能分析模型中,复杂波形的特征提取困难,人工设计特征造成源信号特征丢失,标签样本不足等问题,提出了一种基于深度稀疏自编码器（Deep Sparse Auto-Encoders,DSAEs）的ECG特征提取方法。该方法在DSAEs进行贪婪逐层训练时,采用适应性矩阵估计（Adaptive moment estimation,Adam）对网络权重进行寻优,以此获得最优参数组合,同时提取出高层隐含层的输出,并作为ECG高度抽象的低维特征。最后利用支持向量机（Support Vector Machines,SVM）构建分类模型,完成对ECG的特征分类。使用MIT-BIH心律失常数据库的ECG数据进行仿真实验,结果表明,提出的ECG特征提取方法能有效地分层抽取特征,提高分类识别准确率。     

一种实时心电图数据压缩算法

提出了一种实时心电图ＥＣＧ数据压缩算法。它是将自适应变门限算法与转折点算法相结合。自适应变门限算法是对ＡＺＴＥＣ算法的改进．它计算ＥＣＧ信号的几个统计参数来确定可变门限值。转折点算法是分析采样点的趋势并只存储每对连续的采样点中的一个。它保留信号的斜坡标志发生变化的峰点和谷点。本文算法兼有这两种算法的优点。这种算法在较高压缩比的情况下重建心电图信号失真较小．     

分类技术在心电图自动诊断模型中的应用比较

提高心电图诊断的有效性和准确性的关键在于心电图分类的质量。文中针对这一情况，详细论述了利用各种分类技术对提取的心电图特征数据进行分类的方法，并在比较各种分类算法的基础上，提出了一种基于CBR的心电图自动诊断系统的结构模型。     

Application of InP Neural Network to ECG BeatClassification

This paper presents an application of a hybrid neural network structure to the classification of the electrocardiogram (ECG) beats. Three different feature extraction methods are comparatively examined: discrete cosine transform, wavelet transform and a direct method. Classification performances, training times and the numbers of nodes of Kohonen network, Restricted Coulomb Energy (RCE) network and the hybrid neural network are presented. To increase the classification performance and to decrease the number of nodes, the hybrid neural network is trained by Genetic Algorithms (GAs). Ten types of ECG beats obtained from the MIT-BIH database and from a real-time ECG measurement system are classified with a success of 98% by using the hybrid neural network structure and discrete cosine transform together.