Independent Component Analysis를 이용한 fMRI신호 분석

문찬홍,나동규,박현욱,유재욱,이은정,변홍식 대한자기공명의과학회 1999 Investigative Magnetic Resonance Imaging Vol.3 No.2

fMRI의 신호는 매우 다양한 종류의 선호들이 혼합된 상태이며 , 비록 몇 가지의 요소에 대해 모델링하여 그 선호 형태를 추측할 수 있으나 모든 신호를 정확하게 분리하여 뇌신경의 활성화를 반영하는 신호만을 선택적으로 알아 내기는 어려운 일이다. 또한 뇌와 신체의 생리적 현상으로 발생하는 잡음뿐아니라 움직임이나 계기의 잡음은 fMRl의 데이터 분석을더욱 어렵게 한다. 따라서 실제 뇌신경의 활성화를 정확히 나타내는 참고데이터(reference data)를 선택하는 것은 힘든 일이며, 뇌신경의 활성화를 반영하는 의미 있는 여러 신호 형태에 대한 분석은 현재 fMRl의 후처리 (post-processing) 분석 방법에서 하나의 연구 과제라 할 수 있다. 본 연구에서는 prioriknow­-ledge 혹은 참고 데이터가 필요 없는 분석 방법인 Independent Component Analysis (lCA) 를 이용하여 fMRI선호를 분석하였다. ICA는 현재 많이 사용되고 있는 상관 분석 방법에 비해 신호의 형태를 분석하는 데에 보다 효과적일 수 있으며, 지연된 반응 형태를 갖는 신호나 움직임에 의한 신호의 패턴을 분리하여 분석할 수 있다. 한편, ICA만으후 fMRl의 신호에 따라 분석이 효과적이지 못한 경우 Principal Component Analysis(PCA) threshold, wavelet spatial f filtering, 부분적 영상 분석 방법들을 ICA전에 수행 함으로써 보다 효과적인 분석을 수행할 수 있다. ICA는 fMRl 신호의 형태 분석에 효과적인 방법이라고 생각하며, 데이터의 자유도를 감소 하기 위해서는 선 필터링 (pre-filtering) 방법들이 적용될 수 있다. The fMRI signals are composed of many various signals. It is very difficult to find the accurate parameter for the model of fMRI signal containing only neural activity, though we may estimating the signal patterns by the modeling of several signal components. Besides the nose by the physiologic motion, the motion of object and noise of MR instruments make it more difficult to analyze signals of fMRI. Therefore, it is not easy to select an accurate reference data that can accurately reflect neural activity, and the method of an analysis of various signal patterns containing the information of neural activity is an issue of the post-processing methods for fMRI. In the present study, fMRI data was analyzed with the Independent Component Analysis(ICA) method that doesn't need a priori-knowledge or reference data. ICA can be more effective over the analytic method using cross-correlation analysis and can separate the signal patterns of the signals with delayed response or motion related components. The Principal component Analysis (PCA) threshold, wavelet spatial filtering and analysis of a part of whole images can be used for the reduction of the freedom of data before ICA analysis, and these preceding analyses may be useful for a more effective analysis. As a result, ICA method will be effective for the degree of freedom of the data.

Metabolic Module Mining Based on Independent Component Analysis in Arabidopsis thaliana

Xiao Han,김재연,Cong Chen,현태경,Ritesh Kumar 한국분자세포생물학회 2012 Molecules and cells Vol.34 No.3

Independent Component Analysis (ICA) has been intro-duced as one of the useful tools for gene-functional dis-covery in animals. However, this approach has been poorly utilized in the plant sciences. In the present study, we have exploited ICA combined with pathway enrichment analysis to address the statistical challenges associated with genome-wide analysis in plant system. To generate an Arabidopsis metabolic platform, we collected 4,373 Affy- metrix ATH1 microarray datasets. Out of the 3,232 metabolic genes and transcription factors, 99.47% of these genes were identified in at least one component, indicating the coverage of most of the metabolic pathways by the components. During the metabolic pathway enrichment analysis, we found components that indicate an independent regulation between the isoprenoid biosynthesis pathways. We also utilized this analysis tool to investigate some transcription factors involved in secondary cell wall bio-genesis. This approach has identified remarkably more transcription factors compared to previously reported analysis tools. A website providing user-friendly searching and downloading of the entire dataset analyzed by ICA is available at http://kimjy.gnu.ac.kr/ICA.files/slide0002.htm. ICA combined with pathway enrichment analysis might provide a powerful approach for the extraction of the components responsible for a biological process of interest in plant systems.

독립성분의 순서화 방법 비교

최은빈,조수림,박미라 한국통계학회 2017 응용통계연구 Vol.30 No.6

Independent component analysis is a multivariate approach to separate mixed signals into original signals. It is the most widely used method of blind source separation technique. ICA uses linear transformations such as principal component analysis and factor analysis, but differs in that ICA requires statistical independence and non-Gaussian assumptions of original signals. PCA have a natural ordering based on cumulative proportion of explained variance; howerver, ICA algorithms cannot identify the unique optimal ordering of the components. It is meaningful to set order because major components can be used for further analysis such as clustering and low-dimensional graphs. In this paper, we compare the performance of several criteria to determine the order of the components. Kurtosis, absolute value of kurtosis, negentropy, Kolmogorov-Smirnov statistic and sum of squared coefficients are considered. The criteria are evaluated by their ability to classify known groups. Two types of data are analyzed for illustration. 독립성분분석은 혼합된 신호에서 원신호들을 분리하기 위해서 사용되는 다변량 분석방법으로서, 블라인드 음원 분리 중 가장 널리 사용되는 방법이다. 독립성분분석은 주성분분석이나 요인분석과 같이 선형변환을 사용하지만, 원신호들의 통계적 독립과 비정규성 가정을 필요로 한다는 점에서 다르다. 설명되는 분산의 누적비율이 클수록 더 중요한 성분을 의미하게 되는 주성분분석과 달리, 독립성분분석에서는 독립성분들의 중요순서를 결정하는데 적절한 유일한 기준이 정해지지 않는다. 군집분석이나 차원축소된 그래프 작성 등과 같은 후속 연구를 진행하기 위해서는 일부의 주요 독립성분을 사용하게 되므로, 성분의 순서를 정하는 것은 의미가 있다. 본 연구에서는 성분의 순서를 결정하기 위한 몇 가지 기준의 성능을 비교하였다. 첨도와 첨도의 절댓값, 음의 엔트로피, 콜모고로프-스미르노프 통계량, 계수제곱합을 이용한 방법이 고려되었다. 이들은 알려진 그룹을 분류하는 능력을 기준으로 평가되었다. 두 가지 형태의 자료를 이용한 분석결과를 제시하였다.

Power line interference noise elimination method based on independent component analysis in wavelet domain for magnetotelluric signal

Xiaoling Cao,Liangjun Yan 한국자원공학회 2018 Geosystem engineering Vol.21 No.5

With the urbanization in recent years, the power line interference noise in electromagnetic signal is increasing day by day, and has gradually become an unavoidable component of noises in magnetotelluric signal detection. Therefore, a kind of power line interference noise elimination method based on independent component analysis in wavelet domain for magnetotelluric signal is put forward in this paper. The method first uses wavelet decomposition to change single-channel signal into multi-channel signal, and then takes advantage of blind source separation principle of independent component analysis to eliminate power line interference noise. There is no need to choose the layer number of wavelet decomposition and the wavelet base of wavelet decomposition according to the observed signal. On the treatment effect, it is better than the previous power line interference removal method based on independent component analysis. Through the de-noising processing to actual magnetotelluric measuring data, it is shown that this method makes both the apparent resistivity curve near 50 Hz and the phase curve near 50 Hz become smoother and steadier than before processing, i.e., it effectively eliminates the power line interference noise.

피부색소 흡수 스펙트럼을 이용한 카메라 RGB 신호의 피부색 성분 분석

김정엽 ( Kim Jeong Yeop ) 한국정보처리학회 2022 정보처리학회논문지. 소프트웨어 및 데이터 공학 Vol.11 No.1

본 논문에서는 멜라닌과 헤모글로빈 등의 피부 색상을 구성하는 주요한 요소들을 카메라의 RGB 신호로부터 직접 계산하는 방법을 제안한다. 피부 색상의 주요한 요소들은 통상적으로 특정한 장비를 이용하여 분광 반사도를 측정하고, 측정된 빛의 일부 파장에서의 값들을 중심으로 재구성하는 방법을 사용한다. 이와 같은 방법으로 산출된 값들은 멜라닌 지수, 홍반 지수와 같은 것들이 있으며, 분광반사도 측정 장치나 다중스펙트럼 카메라 등의 특수한 장비를 필요로 한다. 일반적인 디지털 카메라로부터 이와 같은 성분요소들에 대한 직접적인 계산방법은 찾아보기 어려우며, 독립성분 분석(Independent Component Analysis)을 이용하여 멜라닌과 헤모글로빈의 농도를 간접적으로 계산하는 방법은 제안되어 있다. 이 방법은 일정한 RGB 영상의 영역을 대상으로 하여, 주성분 분석(Principal Component Analysis)과 유사한 방식으로 멜라닌과 헤모글로빈의 특성벡터를 추출하고, 농도를 계산할 수 있다. 이 방법의 단점은 일정한 영역의 화소 그룹을 입력으로 이용하기 때문에 화소단위의 직접적인 계산이 어렵고, 추출된 특성벡터는 최적화 방식으로 구현하기 때문에 실행할 때마다 다른 값으로 계산되는 경향이 있다. 최종적인 계산은 특성벡터 자체를 활용하지 않고, RGB 좌표계로 다시 변환하여 멜라닌과 헤모글로빈의 성분을 나타내는 영상 형태로 결정된다. 이 방법의 단점을 개선하기 위하여 제안하는 방법은 특성벡터를 활용하여 RGB 좌표계가 아닌 특징 공간에서 멜라닌과 헤모글로빈의 성분 값을 계산하는 것과, 일반적인 디지털 카메라를 이용하여 피부색에 해당하는 분광 반사도를 계산하는 방법, 분광 반사도를 이용하여 멜라닌과 옥시헤모글로빈, 디옥시헤모글로빈, 카로티노이드 등의 피부색소를 구성하는 세부 성분들의 계산방법 등이다. 제안한 방법은 분광 반사도 측정 장치나 다중 스펙트럼 카메라 등의 특수한 장비를 필요로 하지 않으며, 기존 방법과는 달리 화소단위의 직접적인 계산이 가능하고, 반복 실행에도 동일한 특성을 얻을 수 있다. 제안한 방법은 기존에 비하여 성능의 안정성을 나타내는 표준편차가 15% 수준으로 낮게 나타나 6배 정도의 안정적인 성능을 가진 것으로 추정된다. In this paper, a method to directly calculate the major elements of skin color such as melanin and hemoglobin from the RGB signal of the camera is proposed. The main elements of skin color typically measure spectral reflectance using specific equipment, and reconfigure the values at some wavelengths of the measured light. The values calculated by this method include such things as melanin index and erythema index, and require special equipment such as a spectral reflectance measuring device or a multi-spectral camera. It is difficult to find a direct calculation method for such component elements from a general digital camera, and a method of indirectly calculating the concentration of melanin and hemoglobin using independent component analysis has been proposed. This method targets a region of a certain RGB image, extracts characteristic vectors of melanin and hemoglobin, and calculates the concentration in a manner similar to that of Principal Component Analysis. The disadvantage of this method is that it is difficult to directly calculate the pixel unit because a group of pixels in a certain area is used as an input, and since the extracted feature vector is implemented by an optimization method, it tends to be calculated with a different value each time it is executed. The final calculation is determined in the form of an image representing the components of melanin and hemoglobin by converting it back to the RGB coordinate system without using the feature vector itself. In order to improve the disadvantages of this method, the proposed method is to calculate the component values of melanin and hemoglobin in a feature space rather than an RGB coordinate system using a feature vector, and calculate the spectral reflectance corresponding to the skin color using a general digital camera. Methods and methods of calculating detailed components constituting skin pigments such as melanin, oxidized hemoglobin, deoxidized hemoglobin, and carotenoid using spectral reflectance. The proposed method does not require special equipment such as a spectral reflectance measuring device or a multi-spectral camera, and unlike the existing method, direct calculation of the pixel unit is possible, and the same characteristics can be obtained even in repeated execution. The standard diviation of density for melanin and hemoglobin of proposed method was 15% compared to conventional and therefore gives 6 times stable.

Projection spectral analysis: A unified approach to PCA and ICA with incremental learning

강훈,이현수 한국전자통신연구원 2018 ETRI Journal Vol.40 No.5

Projection spectral analysis is investigated and refined in this paper, in order to unify principal component analysis and independent component analysis. Singular value decomposition and spectral theorems are applied to nonsymmetric correlation or covariance matrices with multiplicities or singularities, where projections and nilpotents are obtained. Therefore, the suggested approach not only utilizes a sum‐product of orthogonal projection operators and real distinct eigenvalues for squared singular values, but also reduces the dimension of correlation or covariance if there are multiple zero eigenvalues. Moreover, incremental learning strategies of projection spectral analysis are also suggested to improve the performance.

Projection Spectral Analysis

강훈,하준수 제어·로봇·시스템학회 2015 International Journal of Control, Automation, and Vol.13 No.6

This study investigates ‘Projection Spectral Analysis’, which generalizes ‘Principal or Independent Component Analysis’ by dealing with a non-symmetric square correlation or covariance matrix with multiplicities or singularities. This type of covariance matrix is decomposed into projections and nilpotents according to the spectral theorem. Projection spectral analysis solves a learning problem by reducing the dimension for multiple zero eigenvalues, and may be applied to a non-symmetric co-variance with distinct eigenvalues. This method involves a sum-product of orthogonal projection operators and real distinct eigenvalues for a symmetric covariance, which makes it equivalent to principal component analysis. However, it becomes independent component analysis if the covariance is not symmetric.

Fast Image Compression Using Over-complete ICAMM

Chih-Cheng Peng,Chih-Hong Kao,Sheng-Ping Hsieh 제어로봇시스템학회 2010 제어로봇시스템학회 국제학술대회 논문집 Vol.2010 No.10

This paper presents a new over complete ICAMM to make decomposition the basis for low-bit high-speed image compression on image sub-blocks. Although the over complete independent component analysis basic number is much larger than the original data dimension, most of the coefficients will be zero after performing the basis transform so that this algorithm reaches the low bit-rate compression goal. The over complete independent component effect approximates the wavelet basis functions. This is different from the discrete cosine function and wavelet function in that the independent component is relevant to the data itself. When using the over complete independent component analysis to decompose the image sub-blocks, it can divide self-adaptive learning into several subgroups based on the different characteristics of the text images. Each subgroup has a set of corresponding over complete independent components. In this way, it can be more efficient to reduce the bit rate use. At the same time the information in the subgroup can also be used in image transmission based on the different encodings. The experimental results show that our proposed approach achieves low bit-rate image compression.

Dynamic pattern decoding of source-reconstructed MEG or EEG data: Perspective of multivariate pattern analysis and signal leakage

Gohel, Bakul,Lim, Sanghyun,Kim, Min-Young,Kwon, Hyukchan,Kim, Kiwoong Elsevier 2018 Computers in biology and medicine Vol.93 No.-

<P><B>Abstract</B></P> <P>Recently, an increasing number of studies have employed multivariate pattern analysis (MVPA) rather than univariate analysis for the dynamic pattern decoding of event-related responses recorded with a MEG/EEG sensor. The use of the MVPA approach for source-reconstructed MEG/EEG data is uncommon. For these data, we need to consider the source orientation information and the signal leakage among brain regions. In the present study, we evaluate the perspective of the MVPA approach in the context of source orientation information and signal leakage in source-reconstructed MEG data. We perform face vs. tool object category decoding (FvsT-OCD) of event-related responses from single or multiple voxels from a brain region using a univariate analysis approach and/or the MVPA approach. We also propose and perform symmetric signal leakage correction of source-reconstructed data using an independent component analysis-based approach. FvsT-OCD using single voxel information shows higher sensitivity for the MVPA approach than univariate analysis, as the MVPA approach efficiently utilizes information on all three dipole orientations and is less affected by inter-subject variability. The MVPA approach shows higher sensitivity for FvsT-OCD when considering information from multiple voxels than for a single voxel in a brain region. This finding suggests that the MVPA approach captures the latent multivoxel distributed pattern. However, the results may be partly or entirely attributable to signal leakage between brain regions, as the sensitivity is substantially reduced after signal leakage correction. A consideration of signal leakage is therefore essential during the evaluation of MVPA outcomes.</P> <P><B>Highlights</B></P> <P> <UL> <LI> The multivariate pattern analysis (MVPA) is increasingly used in cognitive studies. </LI> <LI> Use of the MVPA approach is uncommon for source-reconstructed M/EEG data analysis. </LI> <LI> The study takes account of the source orientation and signal leakage issue. </LI> <LI> The MVPA method can effectively use information from all three source orientations. </LI> <LI> Signal leakage and its correction significantly influence the MVPA outcomes. </LI> </UL> </P>

수면2기 중 활동 뇌파 성분

이일근,한설희,김한영,오지영,김희진,강중구,권요영,박기종,손영민,정기영,염명걸 대한수면연구학회 2006 Journal of sleep medicine Vol.3 No.1

Background : Sleep EEG is not an inactive electrical phenomenon but a active restorative process which is not understood in detail. Understanding stage2 sleep EEG with K complex and sleep spindle can be helpful for the demonstration of sleep physiology related with EEG source generation by specific brain regions. This study has been performed for better understanding stage2 sleep from electrical point of view using ICA (Independent Component Analysis) method. Methods : Stage2 sleep EEG was recorded from 23 normal subjects. Independent EEG components were investigated after running ICA with individual EEG followed by group IC analysis including scalp topography, IC dipole source localization, and percent variance analyses. Results : After applying inclusion criteria to identified IC's from each subjects, three major components were obtained. They are anterior cingulate (IC_AC), midline frontal (IC_MF), and midline parietal (IC_MP) components. They explained 43.4% of the whole stage2 sleep EEG (20.3% by IC_MF, 14.5% by IC_AC, and 8.6% by IC_MP). Conclusions : Significant part of stage2 sleep EEG was generated by midline structures such as anterior cingulate, midline frontal and midling parietal regions which are related with thalamocortical mechanism for the generation of sleep phenomenon. Further analysis can clarify the electrophysiological basis of sleep EEG.