基于独立成分分析和量子粒子群算法的胎儿心电提取

胎儿心电图(FECG)是反映胎儿心脏电生理活动的一项客观指标,获取的FECG受到母体心电图(MECG)的干扰,如何快捷、有效的提取FECG成为重要的研究课题。在非侵入方式下,FECG的提取算法中独立成分分析(ICA)算法被认为是效果最好的方法,但现有求解其分解矩阵的算法收敛性能都不太高。量子粒子群(QPSO)算法是一种收敛于全局的智能优化算法。因此,提出了一种结合QPSO的ICA方法。研究结果表明,与其他在非侵入方式下的主要提取算法相比,这种方法能更清晰准确地提取出有用信号,为胎儿的健康检测提供了更好的方法。     

基于独立成分和小波分析的胎儿心电提取

背景：在胎儿心电信号的采集过程中,会受到母体和其他噪声的强干扰,如何快捷与有效地提取出胎儿心电将成为重要的研究课题。 目的：采用结合独立成分分析和小波分析的方法对来自于同一母体的观测信号进行独立分量分离,得到有效的胎儿心电。 方法：结合独立成分分析和小波分析的算法进行胎儿心电的特征提取,首先对含噪信号进行小波变换,去除奇异信号和非平稳随机信号,然后对小波重构后的信号运用快速独立成分分析算法进行成分分析。 结果与结论：在胎儿心电信号的采集过程中,会受到母体和其他噪声的强干扰,但这些信号都是随机的,不相关的,可以认为它们间是相互独立的。采用结合独立成分和小波分析的方法对来自于同一母体的观测信号进行独立分量分离,得到有效的胎儿心电。实验证明该方法是一种有效的方法。     

Spectral analysis of the fetal electrocardiogram

The spectral curves of the averaged fetal and maternal electrocardiograms as recorded from the abdomen were studied. The power spectrums were obtained using a technique which includes the subtraction of an averaged maternal ECG waveform using cross-correlation function and fast Fourier transform algorithm. The spectral curves of the averaged maternal and fetal ECG waveforms obtained from 21 pregnant women who had gestation periods of 32–41 weeks were studied. It was found that the poor signal to noise ratio, the high rate of coincidence between maternal and fetal ECGs and the similar frequency spectra of the signal and the noise components make an analysis of the abdominal ECG using conventional filtering technique rarely possible and an alternative method should be used.     

Recovering dipole sources from scalp-recorded event-related-potentials using component analysis: principal component analysis and independent component analysis.

Principal component analysis (PCA) and independent component analysis (ICA) were examined in their ability to recover dipole sources from simulated data. Datasets of EEG segments were generated that contained cortical sources that were temporally overlapping or non-overlapping, and dipole sources with varying degree of spatial orthogonality. For temporal overlapping sources, both PCA and ICA resulted in components that required multiple-source equivalent current dipole models. The spatially overlapping sources affected the PCA method more than ICA, resulting in single PCA components in which all non-orthogonal sources were represented. For both PCA and ICA, dipole models with fixed-location dipoles successfully accounted for most of the variance in the component weights, even when the spatial or temporal overlap of the generating sources required multiple-dipole models.     

空间ICA在fMRI数据上的应用与分析

独立成分分析(ICA)技术试图将多维数据分解成若干个相互统计独立的分量。时间ICA和空间ICA都可以用于分析功能核磁共振成像(fMRI)数据。但由于fMRI数据空间维数远远大于时间维数，为计算方便，在分析fMRI数据时。则更多的使用空间ICA方法。本文在单任务激励实验中，利用ICA方法从fMRI数据中分离出若干个与任务相关的独立分量，其中包括与任务相关的恒定分量(CTR)和与任务相关的暂态分量(TTR)；通过将这些独立分量进行空间映射，得到了与任务相关的脑部激活区域。将此结果与SPM的分析比较，得到了一致的结果。在对结果的分析中，我们进一步指出了ICA方法的特点和局限性。     

Noise reduction in magnetocardiography by singular value decomposition and independent component analysis

In the routine recording of magnetocardiograms (MCGs), it is necessary to underline the problem of noise cancellation. Source separation has often been suggested to solve this problem. In this paper, blind source separation (BSS), by means of singular value decomposition (SVD) and independent component analysis (ICA), was used for noise reduction in MCG data to improve the signal to noise ratio. Special techniques, based on statistical parameters, for identifying noise and disturbances, have been introduced to automatically eliminate noise-related and disturbance-related components before reconstructing cleaned data sets. The results show that ICA and SVD can detect and remove a variety of noise and artefact sources from MCG data, as well as from stress MCG.     

Adaptive independent component analysis of multichannel electrogastrograms.

The electrogastrogram (EGG), a cutaneous measurement of gastric electrical activity, can be severely contaminated by endogenous biological noise sources such as respiratory signal. Therefore it is important to establish effective artifact removal methods. In this paper, a novel blind signal separation method with a flexible non-linearity is introduced and applied to extract the gastric slow wave from multichannel EGGs. Simulation results show that our algorithm is able to separate a wide range of source signals, including mixtures of Gaussian sources. On real data, we demonstrate the successful applications of our procedure to extract the gastric slow wave from multichannel EGGs. As a result, the extracted clean gastric slow wave can be used to facilitate further analysis, e.g. as a reference signal for multichannel adaptive enhancement of the EGG.     

基于独立成分分析和随机森林判别法的Microarray分析及在分子生物学中的应用

提出基于独立成分分析（ICA）和随机森林判别的Microarray分析方法。该方法先采用独立成分分析获取高阶统计信息,提取Microarray数据特征,达到降维的目的。再应用提取的特征,采用随机森林判别法对样本进行分类。数值分析结果表明,提取5个特征就可以使袋外样本OOB（out of bag）的分类错误率达到7．89％。该方法有效地降低了特征空间维数,具有较高的正确识别率,提高了算法的鲁棒性和灵活性。     

基于小波变换和独立分量分析的心室晚电位识别

由于晚电位(VLP)信号本身的复杂性以及生物个体差异,其检测的敏感性和特异性还不太高.因此探索和完善晚电位分析方法 的研究很有意义.本文提出了一种结合小波变换WT(wavelet transform)和独立分量分析(independent component analysis,IEA)的VLP特征提取新方法--WICA.新方法的主要思路是先对心电信号进行小波变换.得到多导的小波变换系数序列,再对系数序列用ICA寻求解混阵W和分解出的晚电位独立分量.实验结果表明,WICA方法 在一定程度上能够克服传统方法检测分辨率较低的弱点,并能获得较好的VLP识别.     

Molecular diagnosis of human cancer type by gene expression profiles and independent component analysis

The precise diagnosis of cancer type based on microarray data is of particular importance and is also a challenging task. We have devised a novel pattern recognition procedure based on independent component analysis (ICA). Different from the conventional cancer classification methods, which are limited in their clinical applicability of cancer diagnosis, our method extracts explicitly, by ICA algorithm, a set of specific diagnostic patterns of normal and tumor tissues corresponding to a set of biomarkers for clinical use. We validated our procedure with the colon and prostate cancer data sets and achieved good diagnosis (>90%) on the data sets studied here. This technique is also suitable for the identification of diagnostic expression patterns for other human cancers and demonstrates the feasibility of simple and accurate molecular cancer diagnostics for clinical implementation.     

An fMRI study of acupuncture using independent component analysis

In this paper, we studied the brain functional networks corresponding to the traditional multiple-block acupuncture task paradigm. Due to the complexity and sustainability seen during acupuncture, we wanted to investigate whether or not the effects during acupuncture are changing according to the multiple-block paradigm. We introduced the data driven method of independent component analysis (ICA) to identify brain functional networks activated during the course of acupuncture and to isolate different networks likely related to different aspects of the acupuncture experience. The comparisons between different resting states disclosed the discrepancies between the pre- and post-needling effects in the brain. Furthermore, the distinction between needle stimulation and the resting state indicated that there existed different functional brain networks. These results also portray time variability during the course of acupuncture.     

Colonic pressure data processing based on independent component analysis

The Colonic manometry is an important technique to evaluate human colonic motor functions, which are critical for doctors to understand the pathology of intestinal diseases like slow transit constipation (STC) and colonic inertia (CI). However, in the obtained pressure signals, several patterns of colonic motor activities as well as noises mixed together, which made it difficult to observe the information people really needed. In this article, a new method was proposed to extract patterns of colonic motility from the mixed signals, so that researchers could study them thoroughly. Colonic pressure recordings from 26 volunteers were obtained by the water-perfused manometry catheters. Then independent component analysis (ICA) was introduced, which successfully separated colonic motility patterns and noises into four independent components. And according to the rhythm of contractions examined by ICA, subjects' colonic motility could be divided into three types: regular rhythm (12 subjects), slow rhythm (8 subjects) and disordered (6 subjects), which exactly accorded with their original diagnosis.     

Performance comparison of independent component analysis algorithms for fetal cardiac signal reconstruction: a study on synthetic fMCG data

Independent component analysis (ICA) algorithms have been successfully used for signal extraction tasks in the field of biomedical signal processing. We studied the performances of six algorithms (FastICA, CubICA, JADE, Infomax, TDSEP and MRMI-SIG) for fetal magnetocardiography (fMCG). Synthetic datasets were used to check the quality of the separated components against the original traces. Real fMCG recordings were simulated with linear combinations of typical fMCG source signals: maternal and fetal cardiac activity, ambient noise, maternal respiration, sensor spikes and thermal noise. Clusters of different dimensions (19, 36 and 55 sensors) were prepared to represent different MCG systems. Two types of signal-to-interference ratios (SIR) were measured. The first involves averaging over all estimated components and the second is based solely on the fetal trace. The computation time to reach a minimum of 20 dB SIR was measured for all six algorithms. No significant dependency on gestational age or cluster dimension was observed. Infomax performed poorly when a sub-Gaussian source was included; TDSEP and MRMI-SIG were sensitive to additive noise, whereas FastICA, CubICA and JADE showed the best performances. Of all six methods considered, FastICA had the best overall performance in terms of both separation quality and computation times.     

独立成分分析在生物医学信号处理中的应用

独立成分分析(independentcomponentanalysis熏ICA)已经成功地应用到生物医学信号处理中,并被证明是一种分析生物医学信号的强有力的工具,近年来一直受到国内外学者的广泛关注。本文系统地介绍了独立成分分析在生物医学信号(EEG,MEG,fMRI)处理中的应用,分析了其应用方法,最后简要地探讨了独立成分分析应用到生物医学信号中的优势及存在的一些不足。     

An fMRI study of acupuncture using independent component analysis

While the hypothalamus has been implicated in the regulation of energy balance, the central mechanisms and neural circuit that coordinate the feeding response to energy deficit have not been fully clarified. To better understand the role of the hypothalamus in mediating hyperphagic responses to food deprivation or glucoprivation, we examined the feeding responses in rats in which the medial hypothalamus (MH) was isolated from the rest of the brain. The isolation of the MH was performed with a Halasz's knife cut, and experiments were performed 7 days after the operation. Food consumption between 9:00 a.m. and 11:00 a.m. in rats which had been fasted overnight was significantly increased compared to that in rats which had access to food ad libitum before the measurement in both the sham and MH-isolated groups, and the absolute values of food consumption in fasted rats were not significantly different between the groups. On the other hand, while an injection of 2-deoxy-d-glucose, which blocks glucose utilization, significantly increased food consumption for 2 h after injection compared to a saline injection in the sham group, it did not increase food intake compared to saline injection in the MH-isolated groups. Thus, it is demonstrated that glucoprivation is not an effective stimulus to induce feeding in MH-isolated rats.     

Fetal heart rate monitoring based on independent component analysis

In this paper, an algorithm based on independent component analysis (ICA) for extracting the fetal heart rate (FHR) from maternal abdominal electrodes is presented. Three abdominal ECG channels are used to extract the FHR in three steps: first preprocessing procedures such as DC cancellation and low-pass filtering are applied to remove noise. Then the algorithm for multiple unknown source extraction (AMUSE) algorithm is fed to extract the sources from the observation signals include fetal ECG (FECG). Finally, FHR is extracted from FECG. The method is shown to be capable of completely revealing FECG R-peaks from observation leads even with a SNR=-200dB using semi-synthetic data.     

Removal of large muscle artifacts from transcranial magnetic stimulation-evoked EEG by independent component analysis

We present two techniques utilizing independent component analysis (ICA) to remove large muscle artifacts from transcranial magnetic stimulation (TMS)-evoked EEG signals. The first one is a novel semi-automatic technique, called enhanced deflation method (EDM). EDM is a modification of the deflation mode of the FastICA algorithm; with an enhanced independent component search, EDM is an effective tool for removing the large, spiky muscle artifacts. The second technique, called manual method (MaM) makes use of the symmetric mode of FastICA and the artifactual components are visually selected by the user. In order to evaluate the success of the artifact removal methods, four different quality parameters, based on curve comparison and frequency analysis, were studied. The dorsal premotor cortex (dPMC) and Broca’s area (BA) were stimulated with TMS. Both methods removed the very large muscle artifacts recorded after stimulation of these brain areas. However, EDM was more stable, less subjective, and thus also faster to use than MaM. Until now, examining lateral areas of the cortex with TMS—EEG has been restricted because of strong muscle artifacts. The methods described here can remove those muscle artifacts, allowing one to study lateral areas of the human brain, e.g., BA, with TMS—EEG.     

Applicability of independent component analysis on high-density microelectrode array recordings

Emerging complementary metal oxide semiconductor (CMOS)-based, high-density microelectrode array (HD-MEA) devices provide high spatial resolution at subcellular level and a large number of readout channels. These devices allow for simultaneous recording of extracellular activity of a large number of neurons with every neuron being detected by multiple electrodes. To analyze the recorded signals, spiking events have to be assigned to individual neurons, a process referred to as "spike sorting." For a set of observed signals, which constitute a linear mixture of a set of source signals, independent component (IC) analysis (ICA) can be used to demix blindly the data and extract the individual source signals. This technique offers great potential to alleviate the problem of spike sorting in HD-MEA recordings, as it represents an unsupervised method to separate the neuronal sources. The separated sources or ICs then constitute estimates of single-neuron signals, and threshold detection on the ICs yields the sorted spike times. However, it is unknown to what extent extracellular neuronal recordings meet the requirements of ICA. In this paper, we evaluate the applicability of ICA to spike sorting of HD-MEA recordings. The analysis of extracellular neuronal signals, recorded at high spatiotemporal resolution, reveals that the recorded data cannot be modeled as a purely linear mixture. As a consequence, ICA fails to separate completely the neuronal signals and cannot be used as a stand-alone method for spike sorting in HD-MEA recordings. We assessed the demixing performance of ICA using simulated data sets and found that the performance strongly depends on neuronal density and spike amplitude. Furthermore, we show how postprocessing techniques can be used to overcome the most severe limitations of ICA. In combination with these postprocessing techniques, ICA represents a viable method to facilitate rapid spike sorting of multidimensional neuronal recordings.     

Constrained independent component analysis approach to nonobtrusive pulse rate measurements

Nonobtrusive pulse rate measurement using a webcam is considered. We demonstrate how state-of-the-art algorithms based on independent component analysis suffer from a sorting problem which hinders their performance, and propose a novel algorithm based on constrained independent component analysis to improve performance. We present how the proposed algorithm extracts a photoplethysmography signal and resolves the sorting problem. In addition, we perform a comparative study between the proposed algorithm and state-of-the-art algorithms over 45 video streams using a finger probe oxymeter for reference measurements. The proposed algorithm provides improved accuracy: the root mean square error is decreased from 20.6 and 9.5 beats per minute (bpm) for existing algorithms to 3.5 bpm for the proposed algorithm. An error of 3.5 bpm is within the inaccuracy expected from the reference measurements. This implies that the proposed algorithm provided performance of equal accuracy to the finger probe oximeter.