Tumor classification by combining PNN classifier ensemble with neighborhood rough set based gene reduction

Since Golub applied gene expression profiles (GEP) to the molecular classification of tumor subtypes for more accurately and reliably clinical diagnosis, a number of studies on GEP-based tumor classification have been done. However, the challenges from high dimension and small sample size of tumor dataset still exist. This paper presents a new tumor classification approach based on an ensemble of probabilistic neural network (PNN) and neighborhood rough set model based gene reduction. Informative genes were initially selected by gene ranking based on an iterative search margin algorithm and then were further refined by gene reduction to select many minimum gene subsets. Finally, the candidate base PNN classifiers trained by each of the selected gene subsets were integrated by majority voting strategy to construct an ensemble classifier. Experiments on tumor datasets showed that this approach can obtain both high and stable classification performance, which is not too sensitive to the number of initially selected genes and competitive to most existing methods. Additionally, the classification results can be cross-verified in a single biomedical experiment by the selected gene subsets, and biologically experimental results also proved that the genes included in the selected gene subsets are functionally related to carcinogenesis, indicating that the performance obtained by the proposed method is convincing.     

Gene selection for tumor classification using neighborhood rough sets and entropy measures

With the development of bioinformatics, tumor classification from gene expression data becomes an important useful technology for cancer diagnosis. Since a gene expression data often contains thousands of genes and a small number of samples, gene selection from gene expression data becomes a key step for tumor classification. Attribute reduction of rough sets has been successfully applied to gene selection field, as it has the characters of data driving and requiring no additional information. However, traditional rough set method deals with discrete data only. As for the gene expression data containing real-value or noisy data, they are usually employed by a discrete preprocessing, which may result in poor classification accuracy. In this paper, we propose a novel gene selection method based on the neighborhood rough set model, which has the ability of dealing with real-value data whilst maintaining the original gene classification information. Moreover, this paper addresses an entropy measure under the frame of neighborhood rough sets for tackling the uncertainty and noisy of gene expression data. The utilization of this measure can bring about a discovery of compact gene subsets. Finally, a gene selection algorithm is designed based on neighborhood granules and the entropy measure. Some experiments on two gene expression data show that the proposed gene selection is an effective method for improving the accuracy of tumor classification.     

Classification of surface EMG signals using optimal wavelet packet method based on Davies-Bouldin criterion

In this paper we present an optimal wavelet packet (OWP) method based on Davies-Bouldin criterion for the classification of surface electromyographic signals. To reduce the feature dimensionality of the outputs of the OWP decomposition, the principle components analysis was employed. Then we chose a neural network classifier to discriminate four types of prosthesis movements. The proposed method achieved a mean classification accuracy of 93.75%, which outperformed the method using the energy of wavelet packet coefficients (with mean classification accuracy 86.25%) and the fuzzy wavelet packet method (87.5%).     

Study on reconstruction of rectal sensation based on wavelet packet analysis and SVM strategy

To control anal incontinence, we have developed an artificial anal sphincter system with sensor feedback. The artificial anal sphincter system is a novel hydraulic-electric muscle which mainly comprises an artificial anal sphincter, a wireless power supply subsystem, and a rectal sensation reconstruction subsystem. To investigate the features of the patients’ rectal sensation, we have developed an in vitro experimental platform of artificial anal sphincter. In vitro experiments have been performed, and demonstrate that the traditional threshold method is not suitable for predicting the time for defecation. The traditional threshold method only uses single-dimensional pressure time series which may contain a few interdependent components simultaneously. A wavelet packet analysis algorithm is employed to extract the feature vector of the rectal pressure signal, then the rectal sensation prediction model is constructed based on a support vector machine for defecation pattern recognition. The results show that the proposed method is an effective approach for the reconstruction of patients’ rectal sensation.     

MUAP extraction and classification based on wavelet transform and ICA for EMG decomposition

We have developed an effective technique for extracting and classifying motor unit action potentials (MUAPs) for electromyography (EMG) signal decomposition. This technique is based on single-channel and short periodȁ9s real recordings from normal subjects and artificially generated recordings. This EMG signal decomposition technique has several distinctive characteristics compared with the former decomposition methods: (1) it bandpass filters the EMG signal through wavelet filter and utilizes threshold estimation calculated in wavelet transform for noise reduction in EMG signals to detect MUAPs before amplitude single threshold filtering; (2) it removes the power interference component from EMG recordings by combining independent component analysis (ICA) and wavelet filtering method together; (3) the similarity measure for MUAP clustering is based on the variance of the error normalized with the sum of RMS values for segments; (4) it finally uses ICA method to subtract all accurately classified MUAP spikes from original EMG signals. The technique of our EMG signal decomposition is fast and robust, which has been evaluated through synthetic EMG signals and real EMG signals.     

一种改进距离的局部线性嵌入算法的基因表达谱数据分类

针对基因表达谱样本数据少、维度高、噪声大的特点,维数约减十分必要。由于基因表达谱数据是以一种高维非线性的向量存在,传统的降维方法使得一些本质维数较低的高维数据无法投影到低维空间中,为此本文引入一种改进距离的局部线性嵌入(LLE)算法对其进行降维。由于原始的LLE方法对近邻个数参数非常敏感,为了增强算法对近邻参数的鲁棒性,文中提出了一种改进距离来度量样本点之间的距离,从而降低了样本点分布不均匀对算法的影响。实验结果表明,改进距离的LLE方法能够有效地提取分类特征信息,并能够在保持较高的分类正确率的前提下大幅度地降低基因数据的维数。     

Separation of electrocardiographic and encephalographic components based on signal averaging and wavelet shrinkage techniques

During ambulatory monitoring, it is often required to record the electroencephalogram (EEG) and the electrocardiogram (ECG) simultaneously. It would be ideal if both EEG and ECG can be obtained with one measurement. We introduce an algorithm combining the wavelet shrinkage and signal averaging techniques to extract the EEG and ECG components from an EEG lead signal to a noncephalic reference (NCR). The evaluation using simulation data and measured data showed that the normalized power spectrum unvaried in all frequency bands for the EEG components, and the sensitivity and specificity of R-wave detection for the ECG component were nearly 100%.     

Evaluation of blood access dysfunction based on a wavelet transform analysis of shunt murmurs

We investigated shunt murmurs based on wavelet transform analysis as a new method for assessing vascular access function. In the present study, in patients with venous stenosis near an arteriovenous fistula (A-V fistula), a sensor was placed at different positions around the stenosis and shunt murmur signals obtained using a measurement system were subjected to time–frequency analysis based on wavelet transforms. The shunt murmurs obtained from the stenotic region closely represented some features of murmurs that are often referred to as “high-pitch” murmurs in the clinical setting. In contrast, shunt murmurs obtained about 5 cm downstream of the stenotic region closely represented some features of murmurs that are often referred to as “low-pitch” murmurs in the clinical setting. Furthermore, with the aim of extending the lifespan of arteriovenous grafts (A-V grafts) by detecting and treating stenotic lesions before the A-V graft becomes occluded, we evaluated the possibility of utilizing the present shunt murmur analysis for monitoring stenosis in such A-V grafts. When shunt murmurs from patients with A-V grafts were analyzed, the results suggested that the blood flow through the venous anastomosis of the graft was the most turbulent. This present method whereby blood flow in an A-V fistula is assessed based on the frequency distribution on a time–frequency plane by wavelet transform analysis is advantageous because findings are not markedly affected by sensor attachment. Furthermore, because the sensor is attached using an adhesive collar, measurements can be taken over a short period of time before each dialysis session.     

再生障碍性贫血TNF-α基因多态性和蛋白表达水平的相关研究

目的探讨北方地区汉族人肿瘤坏死因子-α(TNF-α)基因型别的多态性和TNF-α蛋白表达与再生障碍性贫血(AA)的相关性。方法对36例AA患者采用酶联免疫分析法(ELISA)测定TNF-α含量,应用顺序特异性引物聚合酶链反应(PCR-SSP)方法检测TNF-α基因型别的多态性变化,并与31名健康献血者对照。结果AA组血中TNF-α蛋白含量(1.960±0.103)显著高于对照组(1.17±0.075),P<0.01;AA组TNF-α(308A)等位基因频率(40.12%)显著高于对照组(9.68%),P<0.01,提示该等位基因频率和血中TNF-α蛋白表达增高与AA相关。结论中国北方地区汉族人TNF-α基因308位点的多易感态性和TNF-α蛋白表达与AA的易感性相关联,TNF-α(308A)等位基因可能是AA的易感基因之一。     

Automatic classification of infant sleep based on instantaneous frequencies in a single-channel EEG signal

This study presents a novel approach for the electroencephalogram (EEG) signal quantification in which the empirical mode decomposition method, a time–frequency method designated for nonlinear and non-stationary signals, decomposes the EEG signal into intrinsic mode functions (IMF) with corresponding frequency ranges that characterize the appropriate oscillatory modes embedded in the brain neural activity acquired using EEG.     

基于能量估计的小波阈值与经验模态分解相结合的滤波方法研究

本文针对基于经验模态分解(EMD)的时空滤波器存在的固有模态函数分量中频率混叠交叉,导致有用信号与噪声一起被滤除的问题,结合小波在时间、尺度两域表征信号局部特征的特性,提出了一种基于能量估计实现EMD分解层数确定,小波变换阈值处理与EMD相结合的时空滤波方法。该方法既利用小波变换多分辨率的特性,又结合EMD的自适应分解与希尔伯特(Hilbert)谱分析中瞬时频率与能量意义的关系,从而解决了有用信号在滤波时被削弱的问题。以MIT/BIH标准心电数据库数据为对象的实验结果表明,该方法对于生理信号这一类强噪声下的微弱信号是一种有效的数据处理方法。     

Single-trial classification of elementary comparison processes on the basis of instantaneous EEG and MEG coherences

The present study is focused on the evidence of possible single-trial EEG/MEG analysis of information processing. The discrimination between thinking modalities of concept activation and pattern comparison for single tasks of elementary comparison procedures is investigated. A neural network classifier with backpropagation learning algorithm is used. The input vector is constructed by parameters of instantaneous coherence (13-20 Hz) between several channel pairs of the EEG and/or of the MEG. Thereby, the strength of synchronization and the time location of synchronization phenomena are taken into consideration. The combination of EEG and MEG coherence parameters led to a classification accuracy of 85-94% for single subjects. Generally, results reached by neural network classifier show a better generalization than linear discriminant analysis.     

基于极限梯度提升和深度神经网络共同决策的心音分类方法

心音是诊断心血管疾病常用的医学信号之一。本文对心音正常/异常的二分类问题进行了研究,提出了一种基于极限梯度提升(XGBoost)和深度神经网络共同决策的心音分类算法,实现了对特征的选择和模型准确率的进一步提升。首先,本文对预处理后的心音信号进行心音分割,在此基础上提取了5个大类的特征,前4类特征采用递归特征消除法进行特征选择,作为XGBoost分类器的输入,最后一类为梅尔频率倒谱系数(MFCC),作为长短时记忆网络(LSTM)的输入。考虑到数据集的不平衡性,本文在两种分类器中皆使用了加权改进的方法。最后采用异质集成决策方法得到预测结果。将本文所提心音分类算法应用于PhysioNet网站在2016年发起的PhysioNet心脏病学挑战赛(CINC)所用公开心音数据库,以测试灵敏度、特异性、修正后的准确率以及F得分,结果分别为93%、89.4%、91.2%、91.3%,通过与其他研究者应用机器学习、卷积神经网络(CNN)等方法的结果比较,在准确率和灵敏度上有明显提高,证明了本文方法能有效地提高心音信号分类的准确性,在部分心血管疾病的临床辅助诊断应用中有很大的潜力。     

Graz brain-computer interface II: towards communication between humans and computers based on online classification of three different EEG patterns

The paper describes work on the brain-computer interface (BCI). The BCI is designed to help patients with severe motor impairment (e.g. amyotropic lateral sclerosis) to communicate with their environment through wilful modification of their EEG. To establish such a communication channel, two major prerequisites have to be fulfilled: features that reliably describe several distinctive brain states have to be available, and these features must be classified on-line, i.e. on a single-trial basis. The prototype Graz BCI II, which is based on the distinction of three different types of EEG pattern, is described, and results of online and offline classification performance of four subjects are reported. The online results suggest that, in the best case, a classification accuracy of about 60% is reached after only three training sessions. The offline results show how selection of specific frequency bands influences the classification performance in singletrial data.     

A fluorescence method for homogeneous detection of influenza A DNA sequence based on guanine-quadruplex-N-methylmesoporphyrin IX complex and assistance-DNA inhibition

In his study, we report a fluorescence method for homogeneous detection of influenza A (H1N1) DNA sequence based on G-quadruplex-NMM complex and assistance-DNA (A-DNA) inhibition. The quadruplex-based functional DNA (QBF-DNA), composed of a complementary probe to the target H1N1 DNA sequence and G-rich fragment, was designed as the signal DNA. The A-DNA consisted of two parts, one part was complementary to target H1N1 DNA and the other part was complementary to the signal DNA. In the absence of target H1N1 DNA, the G-rich fragment of QBF-DNA can form G-quadruplex-NMM complex, which outputted a fluorescent signal. With the presence of target H1N1 DNA, QBF-DNA, and A-DNA can simultaneously hybridize with target H1N1 DNA to form double-helix structure. In this case, the A-DNA partially hybridized with the QBF-DNA, which inhibited the formation of G-quadruplex-NMM complex, leading to the decrease of fluorescent signal. Under the optimum conditions, the fluorescence intensity was inversely proportional to the concentration of target H1N1 DNA over the range from 25 to 700 pmol/L with a detection limit of 8 pmol/L. In addition, the method is target specific and practicability, and would become a new diagnostic assay for H1N1 DNA sequence and other infectious diseases.