基于心音传感阵列ICA 信号处理的冠心病诊断的研究

通过研究冠脉血流动力学和心脏心音产生的机理，首次提出了将独立分量分析（ICA）方法应用于心音信号处理并达到自动检测冠心病的目的。在本系统中，信号采集系统采用了高灵敏度传感器列阵对正常人及冠心病患者胸部的多个部位进行检测。经预处理后的信号最后通过计算机进行数据采集。应用独立分量分析的方法将心脏舒张期的心音信号进行分离，并将各心音分量的统计特征参数作为输入参量输入到径向其函数网络（RBF网络）进行训练和识别。实验结果说明，独立分量分析结合人工神经网络的心音信号的分析方法是一种较为有效的诊断冠状动脉疾病的无创伤方法。     

基于小波和独立分量分析的煤矸界面识别

为了解决综采工作面放顶煤开采过程中煤矸界面识别问题,给出了一种基于小波去噪和独立分量分析相结合的煤矸放落声信号特征提取算法.利用小波分析对传声器实时采集的声信号进行降噪处理,提高信噪比.利用独立分量分析方法片煤矸混合声信号进行盲源分离,分别提取出煤和矸石的独立声谱特征信号.选取该信号的统计特征值作为神经网络分类器的输入...     

声表面波气体探测器控制电路设计与优化

声表面波气体探测器包括声表面波传感器阵列、富集器、气泵、温度控制器等部件。基于8051单片机为探测器设计了一套控制电路并编写了控制程序,通过调节控制电路改变探测器的工作参数,分别测试了采样气泵流速、富集器的吸附时间与解吸附时间对声表面波气体探测器性能的影响,为优化探测器性能提供了实验依据。     

带参考向量的ICA电子鼻背景干扰消除算法

针对电子鼻伤口感染检测中的背景干扰问题,提出一种带参考向量的独立分量分析(ICA)背景干扰消除算法。利用ICA分解传感器阵列信号并提取独立分量,通过计算独立分量与参考向量的相关性,区分有用信号和背景干扰,采用神经网络分类器进行模式识别。实验结果表明,该算法能消除电子鼻背景干扰,提高伤口感染检测的准确率。     

基于最大判别熵的有监督独立分量分析方法

独立分量分析(indepentlent component analysis,ICA)是目前非常活跃的一个研究领域,在盲源分离、信号处理等方面有着广泛的应用．特别是在特征提取方面,由于其处理非高斯分布的数据的能力,引起了广泛关注,取得了很好的效果．但是传统的独立分量分析方法的思想都是通过定义一个衡量分量独立性的目标函数来求解问题,在应用到特征提取方面时,没有考虑到提取的独立分量对于识别和分类问题的重要性．为了克服传统ICA算法的不足,从信息论角度出发,选择判别熵作为衡量类别之问差异的度量,提出了基于最大判别熵的有监督独立分量分析方法(SICA-MJE),并在人脸识别和虹膜识别应用中进行了验证,取得了很好的实验结果。     

A simplified approach to independent component analysis

Independent Component Analysis (ICA) is one of the fastest growing fields in the area of neural networks and signal processing. Blind Source Separation (BSS) is one of the applications of ICA. In this paper, ICA has been used for separating unknown source signals. BSS is used to extract independent signal components from their observed linear mixtures at an array of sensors. Various statistical techniques based on information theoretic and algebraic approaches exist for performing ICA. In this paper, we have used an objective function based on independence criterion of the signals. Optimisation of this objective function yields a neural algorithm along with a non-linear function for signal separation. Performance of the algorithm for artificially generated signals as well as audio signals has been evaluated.     

Grouping Separated Frequency Components by Estimating Propagation Model Parameters in Frequency-Domain Blind Source Separation

This paper proposes a new formulation and optimization procedure for grouping frequency components in frequency-domain blind source separation (BSS). We adopt two separation techniques, independent component analysis (ICA) and time-frequency (T-F) masking, for the frequency-domain BSS. With ICA, grouping the frequency components corresponds to aligning the permutation ambiguity of the ICA solution in each frequency bin. With T-F masking, grouping the frequency components corresponds to classifying sensor observations in the time-frequency domain for individual sources. The grouping procedure is based on estimating anechoic propagation model parameters by analyzing ICA results or sensor observations. More specifically, the time delays of arrival and attenuations from a source to all sensors are estimated for each source. The focus of this paper includes the applicability of the proposed procedure for a situation with wide sensor spacing where spatial aliasing may occur. Experimental results show that the proposed procedure effectively separates two or three sources with several sensor configurations in a real room, as long as the room reverberation is moderately low.     

An independent component analysis-based disturbance separation scheme for statistical process monitoring

In this paper, an independent component analysis (ICA)-based disturbance separation scheme is proposed for statistical process monitoring. ICA is a novel statistical signal processing technique and has been widely applied in medical signal processing, audio signal processing, feature extraction and face recognition. However, there are still few applications of using ICA in process monitoring. In the proposed scheme, ICA is first applied to in-control training process data to determine the de-mixing matrix and the corresponding independent components (ICs). The IC representing the white noise information of the training data is then identified and the associated row vector of the IC in the de-mixing matrix is preserved. The preserved row vector is then used to generate the monitoring IC of the process data under monitoring. The disturbances in the monitoring process can be effectively enhanced in the monitoring IC. Finally, the traditional exponentially weighted moving average control chart is used to the monitoring IC for process control. For evaluating the effectiveness of the proposed scheme, simulated manufacturing process datasets with step-change disturbance are evaluated. Experiments reveal that the proposed monitoring scheme outperforms the traditional control charts in most instances and thus is effective for statistical process monitoring.     

Feature Extraction Using Independent Components of Each Category

We describe an application of independent component analysis (ICA) to pattern recognition in order to evaluate the effectiveness of features extracted by ICA. We propose a recognition method suitable for independent components that consists of modules for each category. A module has two parts: feature extraction and classification. Features are independent components estimated by ICA and outputs of modules are candidates for categories. These candidates are combined and categories are decided with a majority rule. This recognition method is applied to two tasks: hand-written digits in the MNIST database and acoustic diagnosis for a compressor as real-world tasks. A FastICA algorithm is applied to extracting independent features in the proposed method. Through recognition experiments, we demonstrate that the ICA of each category extracts useful features for these tasks and the independent components are superior to the principal components in recognition accuracy. Manabu Kotani - Deceased     

基于极化和复用的SAW传感器阵列

针对谐振型声表面波(SAW)温度传感器难以灵活构建较大规模传感器阵列的问题,结合天线技术,基于极化和复用的思想,通过频分、时分、空间角度分集和极化,研究实现较大规模的SAW传感器阵列的方法。并通过实际测试,实验结果表明:在略微增加发射天线数目的代价下,阵列规模迅速增大,阵列中的传感器元能得到有效辨识。实验结果验证了设计方法的可行性。     

基于改进的独立分量分析的人脸识别方法

将独立分量分析（Independent Component Analysis，ICA）作为人脸特征提取方法。ICA所提取的特征分类能力强、相互独立，对像素间高阶统计特性敏感，并且不易受光照变化的影响。实验结果表明，基于IcA的人脸特征提取方法的识别性能优于特征脸法。针对传统的ICA算法（Informax算法）存在迭代次数多，难收敛，并且需要人工设定步长来调整学习速度的不足，本文采用FastICA作为ICA的快速算法，并将其关键迭代步骤加以改进，减少了耗时的雅可比矩阵求逆的运算次数。所提出的改进的FastICA具有无需人工参与，收敛速度快，迭代次数少的优点。在特征选择方面，本文将遗传算法（Genetie Algorithm，GA）应用到独立分量的选择与优化中，从而在保证较高识别性能的前提下，获得最优的人脸特征子集。     

基于独立分子量分析的图象分离技术及应用

简要介绍了有关独立分量分析的基本理论和算法,探讨了独立分量分析在序列图象处理方面的应用,提出了基于独立分量分析的运动目标检测新方法,同时用独立分量分析方法对含有运动目标的序列图象进行了独立分量分离的试验,试验中,首先获取序列图象的独立分量和模型混合矩阵,然后将含有背景干扰的独立分量置零,并用混合矩阵进行逆运算,从而获得非常清晰的运动目标轨迹,试验结果表明,这种独立分量分析方法具有良好的盲源分离性能,而且在运动目标检测等方面,基于独立分量分析的检测方法较传统的检测方法更有效。     

聚苯胺-多壁碳纳米管薄膜SAW NO2传感器

将聚苯胺-多壁碳纳米管聚合物沉积于声表面波(SAW)气体传感器的敏感区,形成敏感薄膜,实现了室温下对不同体积分数NO2的检测.研究表明:这种传感器具有很高的敏感性,良好的重复性和低体积分数检测极限.同时,单一聚苯胺薄膜也做了对比测量,实验结果表明:聚苯胺-多壁碳纳米管聚合物敏感膜比单一聚苯胺薄膜具有更高的敏感性和更短的...     

Influence of intermediate hydrogel layer and amount of binding sites on the signal response of surface acoustic wave biosensors

Surface acoustic wave (SAW) devices based on horizontally polarized surface shear waves allow direct and label-free detection of biomolecules in real time. Binding reactions on SAW sensor surfaces are detected by determining changes in surface wave velocity caused mainly by mass loading or viscoelasticity changes in the sensing layer. In many cases, analyte-specific capture molecules or ligands are covalently bound on the sensor surface via an intermediate hydrogel layer. It is a fact that the SAW signal response strongly depends on the nature of the hydrogel matrix due to different relative changes of its acousto-mechanical parameters such as density and viscoelasticity. We studied the effect of different hydrogels in two affinity assays. One assay used a low amount of immobilized capture molecules, the other a high amount of immobilized ligands as binding sites in the sensing layer. Significant variations of the SAW signal response were observed. However, performing the assay with immobilized capture molecules resulted in decreasing signal height with increasing molar mass of the hydrogel whereas a reverse signal behavior was obtained performing the assay with immobilized ligands. This means that each affinity system requires its specific hydrogel matrix to obtain maximal signal response.     

独立成分相关分析的自适应故障监测方法

工业过程数据具有动态、非高斯等特性.独立成分分析(independent component analysis, ICA)既可以分析数据的非高斯形式,又可以极大地去除多变量间的耦合且满足独立性要求.本文引入粒子群算法优化ICA模型参数,自适应地确定独立成分个数.同时,提出一种基于隐马尔科夫链模型(hidden Markov model, HMM)的自适应检测限设计方法,将时间相关数据块的特征信息变化作为过程故障的检测依据.首先利用由时间窗方法确定的独立成分组成监测矩阵来训练HMM模型,旨在提高独立成分间相关性水平的表示能力;然后将得到的HMM模型对监测矩阵进行相关性评估,并在一定容许裕度的基础上设计评估值的自适应因子及检测限,并据此监测特征信息变化,动态地进行在线故障检测.最后, Tennessee Eastman (TE)仿真平台的实验结果表明了所提方法的有效性.     

基于WIFI的无线声表面波传感器信号采集系统

将声表面波传感器与信号无线保真(WIFI)技术相结合,提出了一种基于WIFI的无线声表面波传感器信号采集系统.该系统由声表面波传感器、信号调理电路、处理器、WIFI模块和无线接收终端组成.声表面波传感器混频后的信号经过信号调理电路后,转换为处理器可计频的低频方波信号,并通过WIFI模块将采集到的信号无线发送到接收终端.通过一个输出信号范围在100 kHz~350 kHz声表面波传感器信号采集系统的实现,对该系统的结构、性能进行了验证和测试.实验结果表明,该系统可以实现测试范围内信号的采集、发送和无线接收,系统输入信号与无线接收终端接收信号之间的平均绝对误差为0.843 kHz,最大相对误差为0.51%,无障碍环境有效采集范围约为100 m,有障碍环境有效采集范围约为50 m.     

Method for increasing reliability in gas detection based on indicator gradient in a sensor array

We present a method for analyte detection using an optical sensor array. The method is implemented in an ammonia gas detector, using a pH sensitive dye. The array is composed of four sensors, each coated with a different concentration of the dye. The resulting signal vector is collected by measuring the absorption at a single wavelength, at each sensor. Simple correlation of the signal vector with an expected gradient-like response enables detection of ammonia. Moreover, it improves immunity to false signals created by changes in illumination intensity and the humidity of the environment. The method of detection is generic and applicable to sensor arrays where the probe concentration can be controlled.     

Statistical process monitoring with independent component analysis

In this paper we propose a new statistical method for process monitoring that uses independent component analysis (ICA). ICA is a recently developed method in which the goal is to decompose observed data into linear combinations of statistically independent components [1 and 2]. Such a representation has been shown to capture the essential structure of the data in many applications, including signal separation and feature extraction. The basic idea of our approach is to use ICA to extract the essential independent components that drive a process and to combine them with process monitoring techniques. I², I_e² and SPE charts are proposed as on-line monitoring charts and contribution plots of these statistical quantities are also considered for fault identification. The proposed monitoring method was applied to fault detection and identification in both a simple multivariate process and the simulation benchmark of the biological wastewater treatment process, which is characterized by a variety of fault sources with non-Gaussian characteristics. The simulation results clearly show the power and advantages of ICA monitoring in comparison to PCA monitoring.     

基于超支化聚合物的声表面波化学毒剂传感器

基于声表面波（SAW）技术的化学毒剂传感器在检测下限、响应速度以及减小温度、湿度交叉敏感等方面还需进一步提高。提出了在SAW双端口谐振器上涂敷超支化聚合物的方法提高传感器的检测下限和灵敏度。通过建立Van Dyke模型,分析了敏感膜对SAW化学毒剂传感器Q值、插入损耗以及电路阻抗匹配的影响。利用谐振器代替延迟线,确保了器件具有插入损耗、高Q值的特点。实验证实,在谐振器的中心栅结构上涂覆聚合物可以减小粘弹性聚合物对谐振器插损、Q值以及输入输出阻抗的影响。对设计的化学毒剂传感器进行了沙林毒剂检测实验,采用315MHz的SAW谐振器结合超支化聚合物膜,检测沙林气体浓度为5．0mg／m^3。实验表明：这种传感器的灵敏度可达到600Hz／mg／m^3,响应时间为50s,恢复时间约为60s。     

基于独立分量分析的图像特征提取及去噪

探讨了一种新的多元统计分析方法———独立分量分析在图像特征提取及噪声去除中的应用。利用基于信息传输最大原则的infomax算法对自然图像的基向量进行迭代学习。实验表明,提取的基向量在空间频率上具有方向性和局部性,描述了输入自然景物图像的边缘特征。结合软门限算子,实现了图像中高斯噪声的去除。