Superior foetal electrocardiogram signal elicitation using a novel artificial intelligent Bayesian methodology

Innumerable casualties due to intrauterine hypoxia are a major worry during prenatal phase besides advanced patient monitoring with latest science and technology. Hence, the analysis of foetal electrocardiogram (fECG) signals is very vital in order to evaluate the foetal heart status for timely recognition of cardiac abnormalities. Regrettably, the latest technology in the cutting edge field of biomedical signal processing does not seem to yield the desired quality of fECG signals required by physicians, which is the major cause for the pathetic condition. The focus of this work is to extort non-invasive fECG signal with highest possible quality with a motive to support physicians in utilizing the methodology for the latest intrapartum monitoring technique called STAN (ST analysis) for forecasting intrapartum foetal hypoxia. However, the critical quandary is that the non-invasive fECG signals recorded from the maternal abdomen are affected by several interferences like power line interference, baseline drift interference, electrode motion interference, muscle movement interference and the maternal electrocardiogram (mECG) being the dominant interference. A novel hybrid methodology called BANFIS (Bayesian adaptive neuro fuzzy inference system) is proposed. The BANFIS includes a Bayesian filter and an adaptive neuro fuzzy filter for mECG elimination and non-linear artefacts removal to yield high quality fECG signal. Kalman filtering frame work has been utilized to estimate the nonlinear transformed mECG component in the abdominal electrocardiogram (aECG). The adaptive neuro fuzzy filter is employed to discover the nonlinearity of the nonlinear transformed version of mECG and to align the estimated mECG signal with the maternal component in the aECG signal for annulment. The outcomes of the investigation by the proposed BANFIS system proved valuable for STAN system for efficient prediction of foetal hypoxia.     

基于t分布的贝叶斯深度学习模型及其应用

贝叶斯深度学习(BDL)融合了贝叶斯方法与深度学习(DL)的互补优势,成为复杂问题中不确定性建模与推断的强大工具.本文构建了基于t分布和循环随机梯度汉密尔顿蒙特卡罗采样算法的BDL框架,并基于数据不确定性和模型定不确定性给出了不确定性的度量.为了验证模型框架的有效性和适用性,我们分别基于人工神经网络(ANN)、卷积神经网络(CNN)和循环神经网络(RNN)构建了相应的BDL模型,并将模型应用于全球15个股票指数预测,实证结果显示:1)该框架在ANN、CNN和RNN下均适用,对全部指数的预测效果均很出色; 2)在预测精度和通用性方面,基于t分布BDL的模型比基于正态分布的BDL模型具有显著优越性; 3)在给定不确定性阈值之下的预测MAE比初始MAE显著提升,表明文中定义的不确定性是有效的,对不确定性建模具有重要意义.鉴于该BDL框架在预测精度、易于拓展和具备提供预测不确定性度量的优势,其在金融和其他具有复杂数据特征的领域均有广阔的应用前景.     

基于BO-DKELM的滚动轴承故障诊断

滚动轴承作为旋转机械中的必需元件,其任何故障都可能导致机器乃至整个系统发生故障,从而导致巨大的经济损失和时间的浪费,因此必须要及时准确地诊断滚动轴承故障。针对传统极限学习机中模型参数对滚动轴承故障诊断精度影响较大的问题,提出了一种基于贝叶斯优化的深度核极限学习机的滚动轴承故障诊断方法。首先,将自动编码器与核极限学习机相结合,构建了深度核极限学习机(Deep kernel extreme learning machine, DKELM)模型。其次,利用贝叶斯优化(Bayesian optimization, BO)算法对DKELM中的超参数进行寻优,使得训练数据集和验证数据集在DKELM模型中的分类错误率之和最低。然后,将测试数据集输入到训练好的BO-DKELM中进行故障诊断。最后,采用凯斯西储大学轴承故障数据集对所提方法进行验证,最终故障诊断精度为99.6%,与深度置信网络和卷积神经网络等传统智能算法进行对比,所提方法具有更高的故障诊断精度。     

A gray correlation based Bayesian network model for fault source diagnosis of multistage process – Small sample manufacturing system

Fault source diagnosis methodology is one of the key technologies of quality control and assurance for multi-source & multi-stage manufacturing processes, especially in small sample manufacturing systems. By analyzing the existing research on fault source diagnosis methods, a Bayesian network-based methodology is proposed. Gray correlation theory and mechanism analysis method are used in the process of Bayesian network model construction to reduce the dependence of sample data size for structure learning in the process of small sample manufacturing of complex products. In addition, two fault source diagnosis methods based on manufacturing principle analysis and reverse Bayesian network respectively are proposed. The strategy of the combined use of the two methods in the actual manufacturing scenes is given to cope with the fault source diagnosis scenario in the real manufacturing process. In the end, an example from an actual factory is provided to validate the effectiveness and efficiency of the proposed model and methodologies.     

基于统计分析的PCB组装缺陷特征学习方法*

为了减少自动光学检测系统对用户经验的依赖,提出了一种基于统计分析的PCB组装缺陷特征学习方法。该方法通过对良品和不良品样本图像的统计学习优选出分类能力强的特征,再采用最小风险贝叶斯决策得到特征分类参数。实验结果表明,该算法有效地简化了用户检测程序的编程和调试,提高了AOI的使用效率和准确率。     

基于深度学习的临床心电图分类算法

心电图反映了人体心脏健康状况,是临床诊断心血管类疾病的重要依据。随着心电图数量的快速增长,计算机辅助心电图分析的需求愈加迫切,心电图自动分类作为实现计算机辅助心电图分析不可或缺的技术手段,具有重要的医学价值。由于心电信号非常微弱、抗干扰性差,传统心电图分类算法存在测试集上效果好,实际临床应用效果欠佳的问题。为此,本文研究一种基于多导联二维结构的一维卷积ResNet网络结构,通过平移起始点、“加噪”等数据增强手段增 加训练样本多样性,并采用Focal Loss损失函数优化病人个体的心电图分类模型。该模型利用2万条完整的8导联心电图数据,共计34类心电异常事件进行分类实验,取得了0.91的F1值、93.96%的准确率和87.89%的召回率的分类性能。实验结果表明,该心电图分类算法模型具有较优的深层特征挖掘与分类能力,验证了其在心电异常自动分类上的有效性。     

基于遗传禁忌算法的贝叶斯网边定向方法

针对贝叶斯网边定向过程中存在的问题,提出一种基于遗传禁忌算法的贝叶斯网边定向方法,该方法将禁忌搜索的＂多样化＂引入遗传算法的交叉算子和变异算子中,生成禁忌交叉算子和禁忌变异算子,并对航班离港延误骨架模型进行定向,仿真实验结果表明,该方法是有效可行的。     

基于迁移学习的小样本齿轮箱故障诊断方法

实际工程场景中齿轮箱受工况、环境等因素影响,数据难以满足特征分布相同、训练数据充足等条件,如何在变工况情况下对齿轮故障进行诊断是故障诊断领域一大难点。为此,提出了一种结合Logistic混沌麻雀搜索优化算法(LSSA)与深度置信网络(DBN)的智能故障诊断方法,即LSSADBN。首先,将时域振动信号进行快速傅里叶变换(FFT)转换为频域信号作为训练数据集,运用Logistic混沌映射对SSA种群进行初始化,采用LSSA方法对训练数据集进行DBN结构寻优;使用最优结构DBN对源域训练集进行预训练,并加入少量目标域样本用于反向权重调优,最终实现在小样本情况下对目标域齿轮箱健康状况的准确识别。实验对比结果证明,LSSADBN方法在模型调优阶段具有更快的收敛速度,且针对不同的目标域进行迁移时都具备较高的准确率,LSSADBN方法的研究对小样本情况下的齿轮箱故障诊断具有一定的应用价值。     

单导程心电图的身份识别

提出新的生物识别方法,以心电图信号来识别人员的身份,心电图被用来诊断心脏某些方面的疾病,其与每个人的心脏位置、大小及胸部构造,年龄、性别、体重、情绪、运动状况等因素有关,因此每个人的心电图不尽相同。所采用的单导程心电图为低频一维信号,易于处理,信号直接可由贴在双手上的电极片测得,其量测电路成本低廉．方法是应用遗传算法与粒子群最佳化来调整动态模型参数,使其合成波形与受测者心电图逼近,再将此组参数输入到神经网络来识别个人身份,实验结果显示对于30个人的识别成功率可达96％以上。     

Early Skin Disease Identification Using eep Neural Network

Skin lesions detection and classification is a prominent issue and difficult even for extremely skilled dermatologists and pathologists. Skin disease is the most common disorder triggered by fungus, viruses, bacteria, allergies, etc. Skin diseases are most dangerous and may be the cause of serious damage. Therefore, it requires to diagnose it at an earlier stage, but the diagnosis therapy itself is complex and needs advanced laser and photonic therapy. This advance therapy involves financial burden and some other ill effects. Therefore, it must use artificial intelligence techniques to detect and diagnose it accurately at an earlier stage. Several techniques have been proposed to detect skin disease at an earlier stage but fail to get accuracy. Therefore, the primary goal of this paper is to classify, detect and provide accurate information about skin diseases. This paper deals with the same issue by proposing a high-performance Convolution neural network (CNN) to classify and detect skin disease at an earlier stage. The complete methodology is explained in different folds: firstly, the skin diseases images are pre-processed with processing techniques, and secondly, the important feature of the skin images are extracted. Thirdly, the pre-processed images are analyzed at different stages using a Deep Convolution Neural Network (DCNN). The approach proposed in this paper is simple, fast, and shows accurate results up to 98% and used to detect six different disease types.     

Bayesian nonstationary source separation

A Bayesian nonstationary source separation algorithm is proposed in this paper to recover nonstationary sources from noisy mixtures. In order to exploit the temporal structure of the data, we use a time-varying autoregressive (TVAR) process to model each source signal. Then variational Bayesian (VB) learning is adopted to integrate the source model with blind source separation (BSS) in probabilistic form. Our separation algorithm makes full use of temporally correlated prior information and avoids overfitting in separation process. Experimental results demonstrate that our vbICA-TVAR algorithm learns the temporal structure of sources and acquires cleaner source reconstruction.     

Bayesian sparse solutions to linear inverse problems with non-stationary noise with Student-t priors

Bayesian approach has become a commonly used method for inverse problems arising in signal and image processing. One of the main advantages of the Bayesian approach is the possibility to propose unsupervised methods where the likelihood and prior model parameters can be estimated jointly with the main unknowns. In this paper, we propose to consider linear inverse problems in which the noise may be non-stationary and where we are looking for a sparse solution. To consider both of these requirements, we propose to use Student-t prior model both for the noise of the forward model and the unknown signal or image. The main interest of the Student-t prior model is its Infinite Gaussian Scale Mixture (IGSM) property. Using the resulted hierarchical prior models we obtain a joint posterior probability distribution of the unknowns of interest (input signal or image) and their associated hidden variables. To be able to propose practical methods, we use either a Joint Maximum A Posteriori (JMAP) estimator or an appropriate Variational Bayesian Approximation (VBA) technique to compute the Posterior Mean (PM) values. The proposed method is applied in many inverse problems such as deconvolution, image restoration and computed tomography. In this paper, we show only some results in signal deconvolution and in periodic components estimation of some biological signals related to circadian clock dynamics for cancer studies.     

基于深度贝叶斯主动学习的高光谱图像分类

针对高光谱图像分类中标记样本获取费时费力,无标记数据难以得到有效利用以及主动学习与深度学习结合难等问题,结合贝叶斯深度学习与主动学习的最新进展,提出一种基于深度贝叶斯的主动学习高光谱图像分类算法。利用少量标记样本训练一个卷积神经网络模型,根据与贝叶斯方法结合的主动学习采样策略从无标记样本中选择模型分类最不确定性的样本,选取的样本经人工标记后加入到训练集重新训练模型,减小模型不确定性,提高模型分类精度。通过PaviaU高光谱图像分类的实验结果表明,在少量的标记样本下,提出的方法比传统的方法分类效果更好。     

数据驱动的RF信号深度调制识别方法

基于卷积结构的信号调制识别神经网络的识别性能受信号调制类型种类限制。例如,在12 dB信噪比条件下,同时对24种信号调制类型进行识别,其识别准确率仅为80%。若需要进一步提高识别性能,则要求更复杂的网络模型,导致网络训练所需数据集规模和硬件资源成本增大。鉴于此,针对无线电信号特征,设计一种适用于无线电信号调制识别的紧致残差神经网络,将其作为信号调制类型特征学习和特征提取工具,实现从原始I、Q数据到信号调制类型的端到端识别。利用迁移学习降低网络重新训练所需样本数,增强在无线信道响应发生变化时的环境适应能力,降低训练阶段所需的硬件资源和训练数据集规模。研究表明,当信道脉冲响应改变时,所提的信号调制识别神经网络在信噪比为12 dB条件下的识别性能达到95%,多个对比实验验证本文所设计神经网络的识别性能具有优势。     

基于过完备字典的体域网压缩感知心电重构

针对体域网远程监护中心对重构的心电信号（Electrocardiogram,ECG）精度要求高和体域网（Body sensor network,BSN）低功耗问题,提出基于过完备字典的体域网压缩感知心电重构方法. 该方法利用压缩感知理论,在传感节点端利用随机二进制矩阵对心电信号进行观测,观测值被传送至远程监护中心后,再利用基于K-SVD算法训练得到的过完备字典和块稀疏贝叶斯学习重构算法对心电信号进行重构. 仿真结果表明,当心电信号压缩率在70%～95%时,基于K-SVD过完备字典比基于离散余弦变换基的压缩感知心电重构信噪比高出5～22dB. 该方法具有信号重构精度高、功耗低和易于硬件实现的优点.     

基于Bayesian方法的鲁棒约束LMS算法

输入信号的方向向量出现偏差时,最小均方误差算法会出现收敛速度慢、输出性能下降、不稳定等问题.本文针对这些问题,对传统LMS(least mean squares)算法进行了改进,提出了基于Bayesian方法的鲁棒约束LMS算法.该算法利用信号的先验信息对实际信号方向向量进行估计,有效地抑制了方向向量偏差的影响,并提高了系统的鲁棒性.阵列输出的信干噪比得到了改善,更加接近最优值.仿真实验验证了该算法的有效性和可行性.     

贝叶斯网络结构学习的发展与展望

从最初的概率贝叶斯网络构建阶段到涌现大量研究成果的因果贝叶斯网络结构学习阶段,本文完整地回顾了贝叶斯网络结构学习的整个发展历程,并对该领域当前存在的问题及相关研究进行分析论述,给出了研究展望.值得一提的是,贝叶斯网络结构学习正在成为因果数据挖掘的主流.     

基于贝叶斯网络的克隆代码有害性预测

在软件开发过程中,程序员的复制、粘贴活动会产生大量的克隆代码,而那些发生不一致变化的克隆代码往往对程序是有害的。为了解决该问题,有效地发现程序中的有害克隆代码,提出一种基于贝叶斯网络的克隆有害性预测方法。首先,结合软件缺陷研究领域与克隆演化领域的相关研究成果,提出了两大类表征克隆代码信息的特征,分别是静态特征和演化特征;其次,通过贝叶斯网络核心算法来构建克隆有害性预测模型;最后,预测有害克隆代码发生的可能性。在5款C语言开源软件共99个版本上对克隆有害性预测模型的性能进行评估,实验结果表明该方法能够有效地实现对克隆代码有害性的预测,降低有害克隆代码对软件的威胁,提高软件质量。     

基于Bayesian方法的鲁棒约束最小二乘恒模算法

在实际通信环境中,信号方向向量偏差会导致线性约束最小二乘恒模算法(LSCMA)的性能急剧下降,针对这一问题,提出了基于Bayesian方法的鲁棒约束LSCMA算法并对其性能进行了分析。该算法根据接收到的采样信号和信号的先验信息对实际信号方向向量进行估计,进而推导出权重向量的迭代公式,降低了信号波达方向的不确定性,对信号方向向量偏差具有较强的鲁棒性,从而可以保证阵列输出的信干噪比接近最优值。本文采用递推方法来计算逆矩阵,大大地降低了计算复杂度,能够满足实时处理的要求。仿真实验结果与理论分析表明,与线性约束LSCMA算法相比,所提鲁棒自适应波束形成算法具有更好的性能,且能适应实际复杂的通信环境。     

基于深度学习的磁芯表面缺陷检测研究

在产品表面缺陷智能检测过程中,存在缺陷样本收集困难、样本不平衡、目标尺寸小和难以定位等问题。针对磁芯表面缺陷检测中存在的问题进行了研究,提出了一种基于深度学习的图像增强和检测方法,首先利用结合高斯混合模型的深度卷积生成对抗网络生成磁芯缺陷图像,然后结合泊松融合方法产生增强的数据集,最后基于YOLO-v3网络,实现了磁芯表面缺陷的智能检测。实验表明,该方法能够生成质量更高、缺陷更明显的图像,检测准确度提升了5.6%。