基于融合特征的短语音汉语声调自动识别方法

提出一种基于韵律特征(基频、时长)和梅尔倒谱系数(Mel-Frequency Cepstral Coefficient,MFCC)特征的融合特征进行短语音汉语声调识别的方法,旨在利用两种特征的优势提高短语音汉语声调识别率。该融合特征包括7个根据不同模型得到的韵律特征和统计参数以及4个从每个音段的梅尔倒谱系数计算得来的对数化后验概率,使用高斯混合模型表示4个声调的倒谱特征的分布。实验分两步:第一步,将基于韵律特征和倒谱特征的分类器在决策阶段混合起来进行声调分类,分别赋予两个分类器权重,计算倒谱特征和韵律特征在声调分类任务中的权重;第二步,将基于字的韵律特征和基于帧的倒谱特征结合起来生成融合特征的超向量,使用融合特征进行汉语声调识别,根据准确率、未加权平均召回率(Unweigted Average Recall,UAR)和科恩卡帕(Cohen’s Kappa)系数3个指标,比较并评估5种分类器(两种设置的高斯混合模型,后向传播神经网络,支持向量机和卷积神经网络(Convolutional Neural Network,CNN))在不平衡数据集上的分类效果。实验结果表明:(1)倒谱特征方法能够提高汉语声调的识别率,该特征在总体分类任务中的权重为0.11;(2)基于融合特征的深度学习(CNN)方法对声调的识别率最高,为87.6%,与高斯混合模型的基线系统相比,提高了5.87%。该研究证明了倒谱特征法能够提供与韵律特征法互补的信息,从而提高短语音汉语声调识别率;同时,该方法可以运用到韵律检测和副语言信息检测等相关研究中。     

基于EMD和分形盒维数的旋转机械耦合故障诊断方法研究

针对旋转机械耦合故障的诊断问题,提出一种基于EMD（Empirical Mode Decomposition）和分形盒维数的诊断方法。该方法结合EMD对非线性信号处理的自适应性和分形盒维数能对非线性行为定量描述的特点,先对故障信号进行EMD处理,得到含有故障特征的本征模式函数(Intrinsic Mode Function,简称IMF),然后求出各IMF的盒维数,通过盒维数的比较分析进行故障诊断。构造了含有裂纹-碰摩-松动耦合故障的转子-轴承系统动力学模型,用龙格库塔法求出故障模型振动信号。通过对耦合故障信号进行分析,得到耦合故障特征向量,并与传统的边界谱诊断方法比较,证明该方法对旋转机械耦合故障诊断的有效性和优越性。     

Performance analysis of classifiers for colon cancer detection from dimensionality reduced microarray gene data

Cancer disease is accountable for many deaths that are over 9.6 million in 2018 and roughly one out of six deaths occur because of cancer worldwide. The colon cancer is the second prominent source of death of around 1.8 million cases. This research is inclined to detect the colon cancer from microarray dataset. It will aids the experts to distinguish the cancer cells from normal cells for appropriate determination and treatment of cancer at earlier stages that leads to increase the survival rate of the patients. The high dimensionality in microarray dataset with less samples and more attributes creates lag in the detection capability of the classifier. Hence there is a need for dimensionality reduction techniques to preserve the significant genes that are prominent in the disease classification. In this article, at first ANOVA method used to select the best genes and then principal component analysis (PCA) and fuzzy C-means clustering (FCM) techniques are further employed to choose relevant genes. The PCA and FCM features are classified using model, discriminant, regression, hybrid, and heuristic-based classifiers. The attained results show that the heuristic classifier with PCA features is encapsulated an average classification accuracy of 97.92% for classifying both the colon cancer and normal samples. Also, for FCM features, the Heuristic classifier is maintained at an average classification accuracy of 99.48% and 97.92% for classifying the colon cancer and normal samples, respectively. The Heuristic classifier outperforms with high accuracy than all other classifiers in the classification of colon cancer.     

HHT的理论依据探讨--Hilbert变换的局部乘积定理

希尔伯特-黄变换（Hilbert—Huang Transform，简称HHT）是上世纪90年末才出现的一种非平稳信号分析方法，对于这种方法的理论框架还有值得深入探讨的空间。为了进一步，探索HHT的理论依据，本文从分析HHT的固有模态函数（Intrinsic Mode Function，简称IMF）的定义入手，在Hilbert变换的Bedrosian乘积定理基础上提出了Hilbert变换的局部乘积定理，采用理论推导和物理意义分析相结合的方法巧妙地论证了这一定理，从而首次为HHT中IMF的定义、瞬时频率的计算公式、经验模态分解（Empirical Mode Docomposition，简称EMD）及其收敛性等系列问题提供了较统一的理论依据。     

基于EMD-SVD模型和SVM滚动轴承故障模式识别

针对滚动轴承振动信号的非平稳特性和在现实条件下难以获取大量故障样本的实际情况,提出一种经验模态分解、奇异值分解、Renyi熵和支持向量机相结合的故障诊断方法。运用经验模态分解方法对其去噪信号进行分析,利用互相关系数准则对固有模式分量进行筛选,再对所选分量重构相空间得到吸引子轨道矩阵;对矩阵进行奇异值分解求取奇异值,再计算这些奇异值的Renyi熵以组成故障特征向量,并将其作为支持向量机的输入以识别滚动轴承的故障类型。最后,利用实际滚动轴承试验数据的诊断与对比试验验证了该方法的有效性和泛化能力。     

Classification of Electroencephalogram Signals Using LSTM and SVM Based on Fast Walsh-Hadamard Transform

Classification of electroencephalogram (EEG) signals for humans can be achieved via artificial intelligence (AI) techniques. Especially, the EEG signals associated with seizure epilepsy can be detected to distinguish between epileptic and non-epileptic regions. From this perspective, an automated AI technique with a digital processing method can be used to improve these signals. This paper proposes two classifiers: long short-term memory (LSTM) and support vector machine (SVM) for the classification of seizure and non-seizure EEG signals. These classifiers are applied to a public dataset, namely the University of Bonn, which consists of 2 classes –seizure and non-seizure. In addition, a fast Walsh-Hadamard Transform (FWHT) technique is implemented to analyze the EEG signals within the recurrence space of the brain. Thus, Hadamard coefficients of the EEG signals are obtained via the FWHT. Moreover, the FWHT is contributed to generate an efficient derivation of seizure EEG recordings from non-seizure EEG recordings. Also, a k-fold cross-validation technique is applied to validate the performance of the proposed classifiers. The LSTM classifier provides the best performance, with a testing accuracy of 99.00%. The training and testing loss rates for the LSTM are 0.0029 and 0.0602, respectively, while the weighted average precision, recall, and F1-score for the LSTM are 99.00%. The results of the SVM classifier in terms of accuracy, sensitivity, and specificity reached 91%, 93.52%, and 91.3%, respectively. The computational time consumed for the training of the LSTM and SVM is 2000 and 2500 s, respectively. The results show that the LSTM classifier provides better performance than SVM in the classification of EEG signals. Eventually, the proposed classifiers provide high classification accuracy compared to previously published classifiers.     

基于线性判别分析的决策融合脑电意识动态分类

脑电信号的识别与分类是脑机接口技术的热点研究问题,单一分类器不能很好利用特征以及分类器的适应性,导致识别的准确率很难进一步提高,基于线性判别分析的分类决策级融合策略,可用于提高脑-机接口系统的分类准确率。首先,通过分离出两种分类器的假性试验特征,从这两种方法中选择更有可能正确决策提高分类准确性;其次为了测量每个决策的不确定性,使用与所对应分类器的最大和第二大相关系数提取特征向量。基于这一思想,提出了一种新的决策选择器,该方法通过整合两种基于线性判别分析的算法选择更有可能是准确的决策,从而达到提高脑电信号分类准确度。实验结果表明,该方法通过与精度相近的算法相结合在运动想象数据分类上获得了较好的分类准确率。     

Hilbert-Huang变换端点效应问题的探讨

为了克服Hilbert-Huang变换中的端点效应，利用时变参数ARMA（Autoregressive Moving Average）模型对信号进行外延后再进行EMD（Empirical Mode Decomposition）分解，在一定程度上克服了EMD方法的端点效应问题；同时利用时变参数ARMA模型对IMF（Intrinsic Mode Function）分量进行延拓后再进行Hilbert变换，有效地抑制了Hilbert变换中的端点效应，可以得到准确的瞬时频率和瞬时幅值。     

希尔伯特-黄变换的统一理论依据研究

希尔伯特-黄变换（HHT）是上世纪末出现的一种分析非线性、非平稳信号的有效新方法，但其理论依据还不太明朗，尤其缺乏统一理论依据。从分析HHT的基本模式函数（IMF）定义入手，在Hilbert变换的Bedrosian乘积定理基础上提出了Hilbert变换的局部乘积定理，采用理论推导和物理意义分析相结合的方法对其进行了论证。然后应用这一定理对HHT中的IMF定义、瞬时频率计算公式、经验模式分解（EMD）方法及其收敛性等问题给出了统一解释，从而初步为HHT提供，一个统一理论依据。     

EMD的LabVIEW实现及其在滚动轴承故障诊断中的应用

针对LabVIEW工具箱中缺少EMD算法的问题,对LabVIEW进行二次开发,实现EMD（EmpiricalMode Decomposition）的算法及HHT（Hilbert Huang Transform）分析方法。并且提出利用EMD的高频IMF（Intnnsic Mode Function）进行共振解调提取轴承故障特征信息的方法。故障诊断实例证明,该方法与传统共振解调方法相比,具有较大的优势。     

基于EMD的胶合板损伤声发射信号特征提取及神经网络模式识别

摘要：针对胶合板损伤声发射信号的非平稳性和损伤类别特征相互重叠的实际情况,提出了基于经验模态分解(Empirical Mode Decomposition, EMD)和BP神经网络相结合的信号特征提取和识别方法。首先对损伤声发射信号进行EMD分解,筛选出包含主要信息的本征模态函数（Intrinsic Mode Function, IMF）分量;其次构建以各IMF分量的能量占比作为表征各损伤信号的特征向量;最后以提取的特征向量为输入样本,建立BP神经网络模式分类器对四类胶合板损伤信号进行识别。五层胶合板损伤的实测数据表明,该方法能够准确地提取出声发射信号特征并对其损伤类型进行有效地识别。     

基于声振信号EMD分解的轻微碰摩故障诊断方法研究

针对转子系统局部碰摩故障特征及声音振动信号特点,采用一种基于声振信号经验模式分解(Empirical Mode Decomposition简称EMD)的轻微局部碰摩故障诊断方法对滑动轴承碰摩故障进行特征提取。由于EMD分解不需要固定的基函数,根据信号特征自适应的调整,从而实现碰摩特征及旋转激励背景信号自动分解。通过设计滑动轴承缺油工况轴承碰摩试验,并进行振动全息测试分析,将所得声振信号本征模式函数时域特征和边界谱特征与转子径向位移及轴承座加速度信号对比分析,确定了碰摩部件;从而证明基于声振信号EMD分解的碰摩故障诊断方法的有效性。     

利用聚合经验模态分解抑制振动信号中的模态混叠

传统EMD易于造成分解模态的混叠,混叠后的IMF分量失去原有物理意义。聚合经验模态分解(ensemble empirical mode decomposition,EEMD),是一种将噪声辅助分析应用于经验模态分解中的新方法,可以较好的抑制EMD分解中产生的模态混叠现象,将其应用于振动信号的模态提取中,取得较好的工程效果。     

基于改进EMD-ICA的结构模态参数识别研究

该文针对频带滤波改进经典经验模态分解(EmpiricalModeDecomposition,EMD)的模态分解能力不足时产生过多虚假模态的问题以及真正本征模函数(IntrinsicModeFunction,IMF)的判定问题,提出了将改进EMD与独立分量相结合的信号分析方法。该方法不需要人为预先设定阈值,能够自动分离出真正的IMF分量,消除改进EMD过程中产生的虚假模态,保障EMD分解信号的有效性。然后利用随机减量技术获得各IMFs的自由模态,最后利希尔伯特变换和最小二乘拟合技术相结合的方法来识别出结构的频率和阻尼比,并通过两个数值算例和一个七层钢框架的模态试验予以验证。研究结果表明：该方法可有效解决改进EMD的缺陷,并成功识别出结构的模态参数。     

基于EMD和MKD的滚动轴承故障诊断方法

针对滚动轴承早期微弱故障特征难以提取的问题,提出基于经验模态分解(Empirical Mode Decomposition,EMD)与最大峭度解卷积(Maximum Kurtosis Deconvolution, MKD)的滚动轴承故障特征提取方法。利用EMD方法分解振动信号得到一组固有模态分量(Intrinsic Mode Function,IMF),然后根据时域峭度和包络谱峭度,筛选出敏感IMF分量进行信号重构。然后对重构信号进行最大峭度解卷积处理以增强故障信息,最后得到包络功率谱,从而获得轴承故障特征频率信息。通过实验台信号验证了所述方法的有效性及优点。     

Development of machine learning‐based real time scheduling systems: using ensemble based on wrapper feature selection approach

There are two items that significantly enhance the generalisation ability (i.e. classification accuracy) of machine learning‐based classifiers: feature selection (including parameter optimisation) and an ensemble of the classifiers. Accordingly, the objective in this study is to develop an ensemble of classifiers based on a genetic algorithm (GA) wrapper feature selection approach for real time scheduling (RTS). The proposed approach can better enhance the generalisation ability of the RTS knowledge base (i.e. classifier) in comparison with three classical machine learning‐based classifier RTS systems, including the GA‐based wrapper feature selection mechanism, in terms of the prediction accuracy of 10‐fold cross validation as measured according to all the performance criteria. The proposed ensemble classifier RTS also provides better system performance than the three machine learning‐based RTS systems, including the GA‐based wrapper feature selection mechanism and heuristic dispatching rules, under all the performance criteria, over a long period in a flexible manufacturing system (FMS) case study.     

Fractional gravitational search-radial basis neural network for bone marrow white blood cell classification

Automotive image segmentation systems are becoming an important tool in the medical field for disease diagnosis. The white blood cell (WBC) segmentation is crucial, because it plays an important role in the determination of the diseases and helps experts to diagnose the blood disease disorders. The precise segmentation of the WBCs is quite challenging because of the complex contents in the bone marrow smears. In this paper, a novel neural network (NN) classifier is proposed for the classification of the bone marrow WBCs. The proposed NN classifier integrates the fractional gravitation search (FGS) algorithm for updating the weight in the radial basis function mapping for the classification of the WBC based on the cell nucleus feature. The experimentation of the proposed FGS-RBNN classifier is carried on the images collected from the publically available dataset. The performance of the proposed methodology is evaluated over the existing classifier approaches using the measures accuracy, sensitivity, and specificity. The results show that the classification using the nucleus features alone can be utilized to achieve the classification with the better accuracy. Moreover, the classification performance of the proposed FGS-RBNN is better than the existing classifiers, and it is proved to be the efficacious classifier with a classification accuracy of 95%.     

滚动轴承故障的EMD诊断方法研究

提出了一种基于经验模式分解（Empirical Mode Decomposition，EMD）的滚动轴承故障诊断方法。这种方法中，局部损伤滚动轴承产生的高频调幅信号成分被EMD分解作为本征模函数分离出来，然后用Hilbert变换得到其包络信号，计算包络谱，就能够提取滚动轴承故障特征频率。该方法被用于分析实验台上采集的具有内圈损伤及外圈损伤的滚动轴承振动信号。分析结果表明，与传统的包络解调方法相比，新方法能够更有效地提取轴承故障特征，诊断轴承故障，因而具有重要的实用价值。     

Detection and classification of microcalcification from digital mammograms with firefly algorithm,extreme learning machine and non-linear regression models: A comparison

In this study, abnormalities in medical images are analysed using three classifiers, and the results are compared. Breast cancer remains a major public health problem among women worldwide. Recently, many algorithms have evolved for the investigation of breast cancer diagnosis through medical imaging. A computer-aided microcalcification detection method is proposed to categorise the nature of breast cancer as either benign or malignant from input mammogram images. The standard mammogram image corpus, the Mammogram Image Analysis Society database is utilised, and feature extraction is performed using five different wavelet families at level 4 and level 6 decomposition. The work is accomplished through firefly algorithm (FA), extreme learning machine (ELM) and least-square-based non-linear regression (LSNLR) classifiers. The performance of the classifiers is compared by benchmark metrics, such as total error rate, specificity, sensitivity, area under the receiver operating characteristic curve, precision, F1 score and the Matthews correlation coefficient. As validation of the classifier results, a kappa analysis is included to determine the agreement among classifiers. The LSNLR classifier attains a 3% to 7% improvement in average accuracy compared with the average classification accuracy of the FA (86.75%) and ELM (90.836%) classifiers.