用于心力变化趋势评价的基于概率神经网络的心音识别算法

讨论了用于评估心力变化趋势的心音识别算法，包含了对不同运动条件下记录的心音样本的识别。尤其是讨论了对剧烈运动负荷后记录的心音进行的识别。提出的算法包括两个相互联系的方法。第一个是基于概率神经网络的算法，用于识别静息状态和轻微运动状态；第二个是基于心音本身特点的算法，用于对剧烈运动（本研究中约定的全运动量）后心音的识别。最后，使用该算法对45个在静息状态和轻微运动（1／4运动量）状态下记录的正常和异常心音的样本，以及28个剧烈运动后记录的心音样本进行了识别。结果表明94％的样本可被正确识别和分类。这个识别算法为后续的心音分析研究提供了可靠基础。     

Optimal feature selection for the assessment of vocal fold disorders

Unilateral vocal fold paralysis, vocal fold polyp, and vocal fold nodules are the most common types of neurogenic and organic vocal disorders. This article aims to distinguish these types of vocal diseases into four different classes for the purpose of automatic screening. Firstly, the reconstructed signal at each wavelet packet decomposition sub-band in five levels of decomposition with mother wavelet of (db10) is used to extract the nonlinear features of self-similarity and approximate entropy. Also, wavelet packet coefficients are used to measure energy and Shannon entropy features at different spectral sub-bands. Consequently, to find a discriminant feature vector, three different methods have been applied: Davies-Bouldin (DB) criteria, genetic algorithm (GA) with the fitness functions of support vector machine's (SVM) and k-nearest neighbor's (KNN) recognition rates. Finally, obtained feature vectors have been passed on to SVM and KNN classifiers. The results show that a feature vector of length 12 obtained by the optimization method of GA with the fitness function of SVM's recognition rate fed to SVM classifier achieves the highest classification accuracy of 91%. Furthermore, nonlinear features play an important role in pathological voice classification by participating rate of approximately 67% in the optimal feature vector.     

Self-regulation of exercise intensity by estimated time limit scale

The purpose of this study was to evaluate the validity of the estimated time limit scale (ETL), which deals with a subjective prediction of how long the current exercise intensity can be maintained, for regulating exercise intensity using typical estimation-production procedure. Thirty-six male athletes performed a continuous incremental test and two discontinuous tests with randomized workloads (estimation tests at 65, 75, 85 and 95% of the maximal power output, and production tests: subjects have to use the ETL values which were collected for each power during the estimation test in order to manually product the corresponding workload). The intraclass correlation coefficient for the power output between estimation and production tests is good for exercises at 75, 85 and 95% MAP (0.81, 0.85 and 0.96, respectively). Moreover, mean differences both for power output and cardiorespiratory data were not significantly different between estimation and production tests for exercises at 85 and 95% MAP. Consequently, the validity to prescribe an exercise intensity from the ETL scale is attested in these athletes particularly for high exercise intensities on cycloergometer.     

A genetic algorithm–support vector machine method with parameter optimization for selecting the tag SNPs

SNPs (Single Nucleotide Polymorphisms) include millions of changes in human genome, and therefore, are promising tools for disease-gene association studies. However, this kind of studies is constrained by the high expense of genotyping millions of SNPs. For this reason, it is required to obtain a suitable subset of SNPs to accurately represent the rest of SNPs. For this purpose, many methods have been developed to select a convenient subset of tag SNPs, but all of them only provide low prediction accuracy. In the present study, a brand new method is developed and introduced as GA–SVM with parameter optimization. This method benefits from support vector machine (SVM) and genetic algorithm (GA) to predict SNPs and to select tag SNPs, respectively. Furthermore, it also uses particle swarm optimization (PSO) algorithm to optimize C and γ parameters of support vector machine. It is experimentally tested on a wide range of datasets, and the obtained results demonstrate that this method can provide better prediction accuracy in identifying tag SNPs compared to other methods at present.     

Influence of exercise intensity and joint angle on endurance time prediction of sustained submaximal isometric knee extensions

The purpose of endurance time (T (lim)) prediction is to determine the exertion time of a muscle contraction before it occurs. T (lim) prediction would then allow the evaluation of muscle capacities limiting fatigue and deleterious effects associated with exhaustive exercises. The present study aimed to analyze the influence of exercise intensity and joint angle on T (lim) prediction using changes in surface electromyographic (sEMG) signals recorded during the first moments of the exercise. Fifteen male performed four knee extensions sustained until exhaustion that were different in exercise intensity (20% or 50% of maximal voluntary torque-MVT) and in joint angle (40 or 70o, 0° = full extension). T (lim) prediction was explored using some parameters of the sEMG signals from rectus femoris, vastus medialis and vastus lateralis muscles. Changes in sEMG parameters (root mean square, mean power frequency and frequency banding 6-30 Hz) were expressed using the slope of the linear regression and the area ratio index. Results indicated that relationships between changes in sEMG signal and T (lim) (0.51 < r < 0.83) were greater for experimental conditions associated with higher exercise intensity (50% MVT) and so to lower time duration. Knee joint angle had little influence on T (lim) prediction results. Results also showed higher T (lim) prediction considering spectral parameters and area ratio. This could be in relation to differences in relative contribution of central and peripheral fatigue that seems to change according to the exercise intensity, but also to the influence of psychological factors that increases with the duration of the task.     

Automated recognition of patients with obstructive sleep apnoea using wavelet-based features of electrocardiogram recordings

Patients with obstructive sleep apnoea syndrome (OSAS) are at increased risk of developing hypertension and other cardiovascular diseases. This paper explores the use of support vector machines (SVMs) for automated recognition of patients with OSAS types (±) using features extracted from nocturnal ECG recordings, and compares its performance with other classifiers. Features extracted from wavelet decomposition of heart rate variability (HRV) and ECG-derived respiration (EDR) signals of whole records (30 learning sets from physionet) are presented as inputs to train the SVM classifier to recognize OSAS± subjects. The optimal SVM parameter set is then determined by using a leave-one-out procedure. Independent test results have shown that an SVM using a subset of a selected combination of HRV and EDR features correctly recognized 30/30 of physionet test sets. In comparison, classification performance of K-nearest neighbour, probabilistic neural network, and linear discriminant classifiers on test data was lower. These results, therefore, demonstrate considerable potential in applying SVM in ECG-based screening and can aid sleep specialists in the initial assessment of patients with suspected OSAS.     

基于心电-脉搏波的心血管疾病识别研究

为实现心血管疾病的早期筛查,降低心血管疾病临床检测的成本。本研究基于上肢脉搏波传导速度（PWV）及脉搏波相关血液动力学基础理论,采集了总计51人的脉搏波与心电信号数据,提取了包括3种PWV和脉搏波特征参数总计16个特征参数,将不同的PWV与脉搏波特征组成3个样本特征数据集,分别建立了基于K近邻学习（KNN）和支持向量机（SVM）的心血管疾病识别模型。KNN模型分类准确率为66.28%,SVM模型分类准确率为84.3%,并通过对比不同PWV对模型性能的影响,确定了用于血管评估的最优脉搏波传导速度pwvm。研究表明基于SVM建立的分类模型对心血管疾病识别有一定可靠性,为低成本的心血管疾病早期筛查提供了新思路,也为穿戴式心血管系统监测提供了基础。     

High efficient system for automatic classification of the electrocardiogram beats

Automatic classification of the electrocardiogram (ECG) signals is an important subject for clinical diagnosis of heart disease. This study investigates the design of a high-efficient system to classify five types of ECG beat namely normal beats and four manifestations of heart arrhythmia, in twofold. First, we propose a system that includes two main modules: a feature extraction module and a classification module. Feature extraction module extracts a suitable combination of the ECG’s morphological characteristics and timing interval features. Discrete wavelet transform is used to extract the morphological features. In the classification module, a multi-class support vector machine (SVM)-based classifier is employed. The parameters of this system are determined based on a trial and error method and its performance is evaluated for the MIT-BIH arrhythmia database. Extensive experiments on the parameters of this system such as classifier kernels and various types of features are conducted. These experiments show that in SVM training, the kernels, kernel parameters, and feature selection have very important roles for SVM classification accuracy. Therefore, most appropriates of these parameters should be used for SVM training. Then at the second fold, a novel hybrid intelligent system (HIS) is proposed that consists of three main modules. In the HIS, further to the two mentioned modules, an optimization module is added. In this module, a genetic algorithm is used for optimization of the relevant parameters of system. These parameters are: wavelet filter type for feature extraction, wavelet decomposition level, and classifier’s parameters. Experimental results show that optimization improves the recognition system, efficiently, and HIS is more superior to the system, which as constant parameters.     

常见伤口感染细菌高场不对称波形离子迁移谱识别算法

目的:使用模式识别算法对常见伤口感染细菌（大肠杆菌、金黄色葡萄球菌、铜绿假单胞菌）TH肉汤培养液及纯TH培养液的高场不对称波形离子迁移谱（FAIMS图谱）进行分类识别。 方法:使用FAIMS分析仪收集了4种样品的训练及测试样本。预处理后,用主成分分析和线性判别分析对样本进行降维和特征提取,得到了训练集和测试集的空间三维分布模型,再用最近邻规则算法进行样本识别。 结果:特征提取后,正负模式样本均具有良好的分离效果,并且正模式可分性明显优于负模式。当K取合适的值时,正负模式识别率分别可达90%和70%以上。对于本文的数据模型,K取值等于或最接近每类样本数的奇数为最佳。 结论:该种算法可用于常见伤口感染细菌肉汤培养液FAIMS图谱的分类及识别。     

Remote protein homology detection and fold recognition using two-layer support vector machine classifiers

Remote protein homology detection and fold recognition refer to detection of structural homology in proteins where there are small or no similarities in the sequence. To detect protein structural classes from protein primary sequence information, homology-based methods have been developed, which can be divided to three types: discriminative classifiers, generative models for protein families and pairwise sequence comparisons. Support Vector Machines (SVM) and Neural Networks (NN) are two popular discriminative methods. Recent studies have shown that SVM has fast speed during training, more accurate and efficient compared to NN. We present a comprehensive method based on two-layer classifiers. The 1st layer is used to detect up to superfamily and family in SCOP hierarchy using optimized binary SVM classification rules. It used the kernel function known as the Bio-kernel, which incorporates the biological information in the classification process. The 2nd layer uses discriminative SVM algorithm with string kernel that will detect up to protein fold level in SCOP hierarchy. The results obtained were evaluated using mean ROC and mean MRFP and the significance of the result produced with pairwise t-test was tested. Experimental results show that our approaches significantly improve the performance of remote protein homology detection and fold recognition for all three different version SCOP datasets (1.53, 1.67 and 1.73). We achieved 4.19% improvements in term of mean ROC in SCOP 1.53, 4.75% in SCOP 1.67 and 4.03% in SCOP 1.73 datasets when compared to the result produced by well-known methods. The combination of first layer and second layer of BioSVM-2L performs well in remote homology detection and fold recognition even in three different versions of datasets.     

Bispectral analysis and genetic algorithm for congestive heart failure recognition based on heart rate variability

This paper proposes a congestive heart failure (CHF) recognition method that includes features calculated from the bispectrum of heart rate variability (HRV) diagrams and a genetic algorithm (GA) for feature selection. The roles of the bispectrum-related features and the GA feature selector are investigated. Features calculated from the subband regions of the HRV bispectrum are added into a feature set containing only regular time-domain and frequency-domain features. A support vector machine (SVM) is employed as the classifier. A feature selector based on genetic algorithm proceeds to select the most effective features for the classifier. The results confirm the effectiveness of including bispectrum-related features for promoting the discrimination power of the classifier. When compared with the other two methods in the literature, the proposed method (without GA) outperforms both of them with a high accuracy of 96.38%. More than 3.14% surpluses in accuracies are observed. The application of GA as a feature selector further elevates the recognition accuracy from 96.38% to 98.79%. When compared to the Isler and Kuntalp's impressive results recently published in the literature that also uses GA for feature selection, the proposed method (with GA) outperforms them with more than 2.4% surpass in the recognition accuracy. These results confirm the significance of recruiting bispectrum-related features in a CHF classification system. Moreover, the application of GA as feature selector can further improve the performance of the classifier.     

基于点袋理论的肝脏CT图像分析

当前医学CT图像的病理识别过多地依靠医生经验,为了将机器辅助诊断引入病理识别中,本文采用点袋理论对肝癌和正常肝脏的CT图像进行分析研究.从100张CT图像中挑选出40张具有特征的CT图像,预处理后,先利用尺度不变特征变换（scale invariant feature,SIFT）描述CT图像特征点,再经过k均值（k-means）聚类,最后使用支持向量机（support vector machine,SVM）机器学习算法实现CT图像的识别和分类.实验结果表明,当采用Gaussian 径向基（RBF）核运算时识别可取得85%的正确率.该研究说明点袋法有较好的分类效果和较好的发展空间.     

Effects of isokinetic, isotonic and isometric submaximal exercise on heart rate and blood pressure

The purpose of the present study was to compare arterial pressure (AP) and heart rate (HR) responses to submaximal isokinetic, isotonic and isometric exercises currently employed in physical rehabilitation therapy in terms of both magnitude and time-course. To this aim AP and HR were continuously and noninvasively measured in ten healthy subjects performing isokinetic, isotonic and isometric exercises at the same relative intensity. Isokinetic and isotonic exercises consisted of 30 knee extension/flexion repetitions at 40% of maximal effort. Isokinetic speed was set at 180°?·?s^?1. Isometric exercise consisted of a 60-s knee extension at 40% maximal voluntary contraction. The AP showed a rapid and marked increase from the onset of all types of exercise progressing throughout the exercises. Peak systolic (SAP) and diastolic (DAP) arterial pressure were 190.7 (SEM 8.9) and 121.6 (SEM 7.8) mmHg during isokinetic and 197.6 (SEM 11.2) and 128.3 (SEM 7.7) mmHg during isotonic exercise, respectively. During isometric exercise peak SAP and DAP were 168.1 (SEM 6.3) and 102.1 (SEM 3.7) mmHg, respectively [both lower compared to isokinetic and isotonic exercise (P??1, continuing to rise throughout the exercises. The HR response to isometric exercise was significantly less (P?相似文献   

Analysis of EEG signals by combining eigenvector methods and multiclass support vector machines

A new approach based on the implementation of multiclass support vector machine (SVM) with the error correcting output codes (ECOC) is presented for classification of electroencephalogram (EEG) signals. In practical applications of pattern recognition, there are often diverse features extracted from raw data which needs recognizing. Decision making was performed in two stages: feature extraction by eigenvector methods and classification using the classifiers trained on the extracted features. The aim of the study is classification of the EEG signals by the combination of eigenvector methods and multiclass SVM. The purpose is to determine an optimum classification scheme for this problem and also to infer clues about the extracted features. The present research demonstrated that the eigenvector methods are the features which well represent the EEG signals and the multiclass SVM trained on these features achieved high classification accuracies.     

基于共空间模式算法和支持向量机二重分类的癫痫发病预测

目前癫痫患者的发病预测手段十分耗时且易受主观因素干扰,因此文中提出了一种基于共空间模式算法(CSP)和支持向量机(SVM)二重分类的癫痫发病自动预测方法。此方法将提取空域特征的共空间模式算法应用到癫痫脑电信号检测中,但是该算法未考虑信号的非线性动力学特征且忽略了其时频信息,所以在特征提取阶段选取了标准差、熵和小波包能量这几种互补特征来进行组合。分类过程采取一种基于支持向量机的全新二重分类模式,即将癫痫患者正常期、发作间期和发作期三个阶段分成正常期和准发病期(包括发作间期和发作期)两类进行支持向量机识别,然后对属于准发病期的样本进行发作间期和发作期的分类,最终实现三个时期的分类识别。实验数据来自德国波恩大学的癫痫研究数据库。实验结果显示,第一重分类平均识别率为98.73%,第二重分类平均识别率可达99.90%。结果表明,引入空域特征和二重分类模式能够有效解决众多文献中发作间期和发作期识别率不高的问题,提升各个时期的识别效率,为癫痫患者的发病预测提供有效的检测手段。     

Effects of exercise intensity and duration on nocturnal heart rate variability and sleep quality

Acute physical exercise may affect cardiac autonomic modulation hours or even days during the recovery phase. Although sleep is an essential recovery period, the information on nocturnal autonomic modulation indicated by heart rate variability (HRV) after different exercises is mostly lacking. Therefore, this study investigated the effects of exercise intensity and duration on nocturnal HR, HRV, HR, and HRV-based relaxation, as well as on actigraphic and subjective sleep quality. Fourteen healthy male subjects (age 36 ± 4 years, maximal oxygen uptake 49 ± 4 ml/kg/min) performed five different running exercises on separate occasions starting at 6 p.m. with HR guidance at home. The effect of intensity was studied with 30 min of exercises at intensities corresponding to HR level at 45% (easy), 60% (moderate) and 75% (vigorous) of their maximal oxygen uptake. The effect of duration was studied with 30, 60, and 90 min of moderate exercises. Increased exercise intensity elevated nocturnal HR compared to control day (p < 0.001), but it did not affect nocturnal HRV. Nocturnal HR was greater after the day with 90- than 30- or 60-min exercises (p < 0.01) or control day (p < 0.001). Nocturnal HRV was lower after the 90-min exercise day compared to control day (p < 0.01). Neither exercise intensity nor duration had any impact on actigraphic or subjective sleep quality. The results suggest that increased exercise intensity and/or duration cause delayed recovery of nocturnal cardiac autonomic modulation, although long exercise duration was needed to induce changes in nocturnal HRV. Increased exercise intensity or duration does not seem to disrupt sleep quality.     

Identifying splicing sites in eukaryotic RNA: support vector machine approach

We introduce a new method for splicing sites prediction based on the theory of support vector machines (SVM). The SVM represents a new approach to supervised pattern classification and has been successfully applied to a wide range of pattern recognition problems. In the process of splicing sites prediction, the statistical information of RNA secondary structure in the vicinity of splice sites, e.g. donor and acceptor sites, is introduced in order to compare recognition ratio of true positive and true negative. From the results of comparison, addition of structural information has brought no significant benefit for the recognition of splice sites and had even lowered the rate of recognition. Our results suggest that, through three cross validation, the SVM method can achieve a good performance for splice sites identification.     

Citespace软件可视化分析运动与认知

文题释义： CiteSpace：是一款可视化文献分析软件,能够显示一个学科或知识域在一定时期发展的趋势与动向,形成若干研究前沿领域的演进历程。CiteSpace可视化可以形成知识资源及其关联的图形,能够绘制、挖掘、分析和显示知识间的相互关系,识别重要的文献,有助于了解和预测科学前沿和动态,挖掘开辟新的未知领域。 脑源性神经营养因子(brain-derived neurotrophic factor,BDNF)：是1982年Barde等首先在猪脑中发现的一种具有神经营养作用的蛋白质。脑源性神经营养因子及其受体分布在中枢神经系统、周围神经系统、内分泌系统、骨和软骨组织等广泛区域内,但主要是在中枢神经系统内表达,其中海马和皮质的含量最高。脑源性神经营养因子是一种对于突触可塑性、学习和记忆都很重要的蛋白分子。 背景：目前还没有关于“运动与认知”领域的CiteSpace可视化分析。 目的：运动对认知领域的研究越来越受重视,梳理该领域的研究进展,为相关领域研究者提供借鉴与参考。 方法：对Web of Science核心合集数据库进行检索,文献检索式为：(TI=(exercise AND cognit*) OR TI=(exercise AND learning) OR TI=(exercise AND memory) OR TI=(exercise AND feeling) OR TI=(exercise AND thinking) OR TI=(exercise AND imagination) OR TI=(exercise AND language) OR TI=(exercise AND perception)) AND文献类型：(Article OR Review)。检索时间跨度为“1989-01-01/ 2018-12-25”。以Web of Science数据库中所收录的2 175篇相关文献为内容,利用CiteSpace软件进行可视化分析。 结果与结论：近30年来,“运动与认知”领域的研究得到了快速的发展,发文最多的国家与地区分布于北美和欧洲。该领域的研究既包含了应用性研究也包含了基础性研究,并且几乎涉及所有与认知相关的疾病研究。运动方式以有氧运动为主,但不同形式有氧运动如何影响不同人群的认知水平并不清楚。该领域通过众多学科经典的研究方法研究其认知相关指标与神经生物学指标。该领域包含了两大知识群,“运动对认知的改变”及“运动改变认知的机制”。在未来的研究中,还需加强跨地区及跨国家的合作;加强对各种运动的形式及强度的研究,寻找改善不同人群认知水平的最适运动;尽可能的使用多种指标评判运动对认知的影响。 ORCID: 0000-0002-8563-0495(李慧军) 中国组织工程研究杂志出版内容重点：组织构建;骨细胞;软骨细胞;细胞培养;成纤维细胞;血管内皮细胞;骨质疏松;组织工程     

Stimulated and voluntary fatiguing contractions of quadriceps femoris differently disturb postural control

Muscle fatigue affects muscle strength and postural control. However, it is not known whether impaired postural control after fatiguing muscular exercise depends on the nature of the muscle contraction. To answer this question, the present study analyzes changes in postural control after two fatiguing exercises of equal duration and intensity but that induced different magnitudes of strength loss. The effects of fatiguing contractions of the femoris quadriceps were compared for voluntary muscular contraction (VOL) and neuromuscular electrical stimulation (ES) on muscle strength and postural control. Seventeen subjects completed these two fatiguing exercises. Maximal voluntary contraction (MVC) and postural control were recorded using an isokinetic dynamometer and a force platform that recorded the center of foot pressure. Recordings were performed before and after the completion of both fatiguing tasks. Results indicate that, after a fatiguing exercise, the ES exercise affected MVC more than the VOL exercise. Inversely, postural control was disturbed more after VOL exercise than after ES exercise. In conclusion, postural control disturbance is influenced by the nature of the muscular contraction (voluntary vs. non-voluntary) and the type of the motor unit solicited (tonic vs. phasic) rather than by the magnitude of strength loss.     

Support vector machine-based arrhythmia classification using reduced features of heart rate variability signal

OBJECTIVE: This paper presents an effective cardiac arrhythmia classification algorithm using the heart rate variability (HRV) signal. The proposed algorithm is based on the generalized discriminant analysis (GDA) feature reduction scheme and the support vector machine (SVM) classifier. METHODOLOGY: Initially 15 different features are extracted from the input HRV signal by means of linear and nonlinear methods. These features are then reduced to only five features by the GDA technique. This not only reduces the number of the input features but also increases the classification accuracy by selecting most discriminating features. Finally, the SVM combined with the one-against-all strategy is used to classify the HRV signals. RESULTS: The proposed GDA- and SVM-based cardiac arrhythmia classification algorithm is applied to input HRV signals, obtained from the MIT-BIH arrhythmia database, to discriminate six different types of cardiac arrhythmia. In particular, the HRV signals representing the six different types of arrhythmia classes including normal sinus rhythm, premature ventricular contraction, atrial fibrillation, sick sinus syndrome, ventricular fibrillation and 2 degrees heart block are classified with an accuracy of 98.94%, 98.96%, 98.53%, 98.51%, 100% and 100%, respectively, which are better than any other previously reported results. CONCLUSION: An effective cardiac arrhythmia classification algorithm is presented. A main advantage of the proposed algorithm, compared to the approaches which use the ECG signal itself is the fact that it is completely based on the HRV (R-R interval) signal which can be extracted from even a very noisy ECG signal with a relatively high accuracy. Moreover, the usage of the HRV signal leads to an effective reduction of the processing time, which provides an online arrhythmia classification system. A main drawback of the proposed algorithm is however that some arrhythmia types such as left bundle branch block and right bundle branch block beats cannot be detected using only the features extracted from the HRV signal.