Application Of Independent Component Analysis Research Articles

Noise subtraction from KAGRA O3GK data using Independent Component Analysis

During April 7–21 2020, KAGRA conducted its first scientific observation in conjunction with the GEO600 detector. The dominant noise sources during this run were found to be suspension control noise in the low-frequency range and acoustic noise in the mid-frequency range. In this study, we show that their contributions in the observational data can be reduced by a signal processing method called independent component analysis (ICA). The model of ICA is extended from that studied in the initial KAGRA data analysis to account for frequency dependence, while the linearity and stationarity of the coupling between the interferometer and the noise sources are still assumed. We identify optimal witness sensors in the application of ICA, leading to successful mitigation of these two dominant contributions. We also analyze the stability of the transfer functions for the entire two weeks of data to investigate the applicability of the proposed subtraction method in gravitational wave searches.

Data-Driven Approach toward Long-Term Equipment Condition Assessment in Sterile Drug Product Manufacturing.

A two-stage data-driven methodology for long-term equipment condition assessment in drug product manufacturing is presented with a case study for a commercially operating aseptic filling line. The methodology leverages process monitoring data. Sensor measurements are partitioned using process information and maintenance schedules that are available on different databases. Data is processed to tackle heterogeneity in sources and formats. The data is cleaned to remove the effects of short-term variabilities and to enhance underlying long-term trends. Two approaches are presented for data analysis: first, anomaly detection using independent component analysis (ICA), where clusters of outliers are identified. The frequency and timing of such outliers yield important insights regarding maintenance schedules and actions. The second approach enables condition monitoring using principal component analysis (PCA). Long-term operational baselines are identified and shifts therein are linked with different process and equipment faults. This approach highlights the impact of equipment deterioration on shifting operational data baselines and shows the potential for the combined application of ICA and PCA for equipment condition monitoring. It can be applied within predictive maintenance applications where the installation of new specialized sensors is difficult, like in the pharmaceutical industry.

Mapping land subsidence and aquifer system properties of the Willcox Basin, Arizona, from InSAR observations and independent component analysis

Long-term excessive groundwater exploitation for agricultural, domestic and stock applications has resulted in substantial ground subsidence in Arizona, USA, and especially in the Willcox Groundwater Basin. The land subsidence rate of the Willcox Basin has not declined but has rather increased in recent years, posing a threat to infrastructure, aquifer systems, and ecological environments. In this study, we first investigate the spatiotemporal characteristics of land subsidence in the Willcox Groundwater Basin using an interferometric synthetic aperture radar (InSAR) time series analytical approach with L-band ALOS and C-band Sentinel-1 SAR data acquired from 2006 to 2020. The overall deformation patterns are characterized by two major zones of subsidence, with the mean subsidence rate increasing with time from 2006 to 2020. An approach based on independent component analysis (ICA) was adopted to separate the mixed InSAR time series signal into a set of independent signals. The application of ICA to the Willcox Basin not only revealed that two different spatiotemporal deformation features exist in the basin but also filtered the residual errors in InSAR observations to enhance the deformation time series. Integrating the InSAR deformation and groundwater level data, the response of the aquifer skeletal system to the change in hydraulic head was quantified, and the hydromechanical properties of the aquifer system were characterized. Historical spatiotemporal storage loss from 1990 to 2020 was also estimated using InSAR measurements, hydraulic head and estimated skeletal storativity. Understanding the characteristics of land surface deformation and quantifying the response of aquifer systems in the Willcox Basin and other groundwater basins elsewhere are important in managing groundwater exploitation to sustain the mechanical health and integrity of aquifer systems.

Development of Machine-Learning Algorithms for Recognition of Subjects' Upper Limb Movement Intention Using Electroencephalogram Signals.

This study aims to classify rest and upper limb movements execution and intention using electroencephalogram (EEG) signals by developing machine-learning (ML) algorithms. Five different MLs are implemented, including k-Nearest Neighbor (KNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), Support Vector Machine (SVM), and Random Forest (RF). The EEG data from fifteen healthy subjects during motor execution (ME) and motor imagination (MI) are preprocessed with Independent Component Analysis (ICA) to reduce eye-blinking associated artifacts. A sliding window technique varying from 1 s to 2 s is used to segment the signals. The majority voting (MV) strategy is employed during the post-processing stage. The results show that the application of ICA increases the accuracy of MI up to 6%, which is improved further by 1-2% using the MV (p<0.05). However, the improvement in the accuracies is more significant in MI (>5%) than in ME (<1%), indicating a more significant influence of eye-blinking artifacts in the EEG signals during MI than ME. Among the MLs, both RF and SVM consistently produced better accuracies in both ME and MI. Using RF, the 2 s window size produced the highest accuracies in both ME and MI than the smaller window sizes.

NIRS-ICA: A MATLAB Toolbox for Independent Component Analysis Applied in fNIRS Studies.

Independent component analysis (ICA) is a multivariate approach that has been widely used in analyzing brain imaging data. In the field of functional near-infrared spectroscopy (fNIRS), its promising effectiveness has been shown in both removing noise and extracting neuronal activity-related sources. The application of ICA remains challenging due to its complexity in usage, and an easy-to-use toolbox dedicated to ICA processing is still lacking in the fNIRS community. In this study, we propose NIRS-ICA, an open-source MATLAB toolbox to ease the difficulty of ICA application for fNIRS studies. NIRS-ICA incorporates commonly used ICA algorithms for source separation, user-friendly GUI, and quantitative evaluation metrics assisting source selection, which facilitate both removing noise and extracting neuronal activity-related sources. The options used in the processing can also be reported easily, which promotes using ICA in a more reproducible way. The proposed toolbox is validated and demonstrated based on both simulative and real fNIRS datasets. We expect the release of the toolbox will extent the application for ICA in the fNIRS community.

On the Achievability of Blind Source Separation for High-Dimensional Nonlinear Source Mixtures.

For many years, a combination of principal component analysis (PCA) and independent component analysis (ICA) has been used for blind source separation (BSS). However, it remains unclear why these linear methods work well with real-world data that involve nonlinear source mixtures. This work theoretically validates that a cascade of linear PCA and ICA can solve a nonlinear BSS problem accurately-when the sensory inputs are generated from hidden sources via nonlinear mappings with sufficient dimensionality. Our proposed theorem, termed the asymptotic linearization theorem, theoretically guarantees that applying linear PCA to the inputs can reliably extract a subspace spanned by the linear projections from every hidden source as the major components-and thus projecting the inputs onto their major eigenspace can effectively recover a linear transformation of the hidden sources. Then subsequent application of linear ICA can separate all the true independent hidden sources accurately. Zero-element-wise-error nonlinear BSS is asymptotically attained when the source dimensionality is large and the input dimensionality is sufficiently larger than the source dimensionality. Our proposed theorem is validated analytically and numerically. Moreover, the same computation can be performed by using Hebbian-like plasticity rules, implying the biological plausibility of this nonlinear BSS strategy. Our results highlight the utility of linear PCA and ICA for accurately and reliably recovering nonlinearly mixed sources and suggest the importance of employing sensors with sufficient dimensionality to identify true hidden sources of real-world data.

ICA Based Sensors Fault Diagnosis: An Audio Separation Application

Independent component analysis (ICA) is a well known technique of blind source separation (BSS) and is used in various applications, e.g. speech, biomedical, communication, robotics, leakage detection, vibration analysis and machinery fault diagnosis. The ICA technique estimates the original source signals from the recorded multidimensional mixed signals through various sensors from any physical process. In case one or more sensor becomes faulty the separation of mixed signals becomes very difficult. In machinery, ICA is used to diagnose faults in its rotating parts that is a major concern of public safety. In case of faulty sensors, fault diagnosis becomes difficult. Moreover, in certain situations of wireless sensor networks some of the sensors fail to collect accurate information. Therefore, to collect accurate information in case of sensor failure, fault diagnosis technique is required. In this paper, a sensor fault diagnosis technique called the state observing technique (SOT) is developed to first diagnose faults in the system and then identify the faulty sensors. Also the extended sensor technique (EST) is developed to improve the separation performance of the ICA algorithm in case of faulty sensors based on information provided by the SOT technique. Effectiveness of the proposed SOT–EST technique is evaluated through extensive simulations utilizing the FastICA algorithm of ICA. To the best of our knowledge, we are the first to discuss the sensor fault diagnosis in the ICA applications.

Introducing a Deflationary Approach to Space-Time ICA that uses temporal methods in Brain Signals Processing.

For the extraction of underlying sources of brain activity, time structure-based techniques for applying Independent Component Analysis (ICA) have been demonstrably more robust than state-of-the-art statistical-based methods, such as FastICA. Since the early application of conventional ICA on electroencephalogram (EEG) recordings, Space-Time ICA (ST-ICA) has emerged as more capable approach for extracting complex underlying activity, but not without the 'curse of dimensionality'. The challenges in the future development of ST-ICA will require a focus on the optimisation of the mixing matrix, and on component clustering techniques. This paper proposes a new optimisation approach for the mixing matrix, which makes ST-ICA more tractable, when using a time structure-based ICA technique, LSDIAG. Such techniques rely on constructing a multi-layer covariance matrix, Cxk of the original dataset to generate the inverse of the mixing matrix; Csk = WCxkWT. This means a simple truncation of the mixing matrix is not appropriate. To overcome this, we propose a deflationary approach to optimise a much smaller mixing matrix - based on the absolute values of the diagonals of the co-variance matrix, Csk, to represent the underlying sources. The preliminary results of the new technique applied to different channels of EEG recorded using the standard 10-20 system - including the full selection of all channels - are very promising.Clinical Relevance-The potential of this deflationary approach for Space-Time ICA, seeks to allow clinicians to identify underlying sources in the brain - that both spatially and spectrally overlap - to be identified, whilst making the 'dimensionality' challenges more tractable. In the long run, applications of this technique could enhance certain brain-computer interface paradigms.

Effects of Independent Component Analysis on Magnetoencephalography Source Localization in Pre-surgical Frontal Lobe Epilepsy Patients.

Objective: Magnetoencephalography source imaging (MSI) of interictal epileptiform discharges (IED) is a useful presurgical tool in the evaluation of drug-resistant frontal lobe epilepsy (FLE) patients. Yet, failures in MSI can arise related to artifacts and to interference of background activity. Independent component analysis (ICA) is a popular denoising procedure but its clinical application remains challenging, as the selection of multiple independent components (IC) is controversial, operator dependent, and time consuming. We evaluated whether selecting only one IC of interest based on its similarity with the average IED field improves MSI in FLE.Methods: MSI was performed with the equivalent current dipole (ECD) technique and two distributed magnetic source imaging (dMSI) approaches: minimum norm estimate (MNE) and coherent Maximum Entropy on the Mean (cMEM). MSI accuracy was evaluated under three conditions: (1) ICA of continuous data (Cont_ICA), (2) ICA at the time of IED (IED_ICA), and (3) without ICA (No_ICA). Localization performance was quantitatively measured as actual distance of the source maximum in relation to the focus (Dmin), and spatial dispersion (SD) for dMSI.Results: After ICA, ECD Dmin did not change significantly (p > 0.200). For both dMSI techniques, ICA application worsened the source localization accuracy. We observed a worsening of both MNE Dmin (p < 0.05, consistently) and MNE SD (p < 0.001, consistently) for both ICA approaches. A similar behaviour was observed for cMEM, for which, however, Cont_ICA seemed less detrimental.Conclusion: We demonstrated that a simplified ICA approach selecting one IC of interest in combination with distributed magnetic source imaging can be detrimental. More complex approaches may provide better results but would be rather difficult to apply in real-world clinical setting. In a broader perspective, caution should be taken in applying ICA for source localization of interictal activity. To ensure optimal and useful results, effort should focus on acquiring good quality data, minimizing artifacts, and determining optimal candidacy for MEG, rather than counting on data cleaning techniques.

Order and phase ambiguities correction in the ICA based separation of speech signals

Independent component analysis (ICA) blindly separates mixed recorded signals and is employed in various engineering disciplines like speech, biomedical, communication, robotics, leakage detection, vibration analysis and machinery fault diagnosis. Order and phase indeterminacies exist in the ICA post processed signals. These indeterminacies appear due to the use of non-linearities in the development of the ICA algorithms which also restrict the practical applications of ICA. This issue of indeterminacies is not very well explored in the research. In the literature, the signals order ambiguity is resolved using various criterion that can order the signals in ascending or descending order based on a defined criteria. Although, in practice, it is required that the separated signals should be in the order of the mixing source signals. Moreover, the phase correction performed in the literature is through complicated signal processing techniques. In this paper, we propose an efficient and more rational signals ordering and phase correction technique. The proposed technique orders the separated signals in the order of the mixing source signals that makes the proposed technique more practical. Further, we have analysed the resultant mixing and un-mixing matrices, to overcome the phase and order ambiguities in the ICA post processed signals. Audio signals have been utilized for simulation purpose. Furthermore, we have utilize the FastICA algorithm to observe the effectiveness of the proposed signals ordering and phase correction technique (SOPCT). The simple mathematical formulation and efficient simulation performance make the SOPCT technique, a best choice for the practical scenarios.

Independent Component Analysis for Unraveling the Complexity of Cancer Omics Datasets.

Independent component analysis (ICA) is a matrix factorization approach where the signals captured by each individual matrix factors are optimized to become as mutually independent as possible. Initially suggested for solving source blind separation problems in various fields, ICA was shown to be successful in analyzing functional magnetic resonance imaging (fMRI) and other types of biomedical data. In the last twenty years, ICA became a part of the standard machine learning toolbox, together with other matrix factorization methods such as principal component analysis (PCA) and non-negative matrix factorization (NMF). Here, we review a number of recent works where ICA was shown to be a useful tool for unraveling the complexity of cancer biology from the analysis of different types of omics data, mainly collected for tumoral samples. Such works highlight the use of ICA in dimensionality reduction, deconvolution, data pre-processing, meta-analysis, and others applied to different data types (transcriptome, methylome, proteome, single-cell data). We particularly focus on the technical aspects of ICA application in omics studies such as using different protocols, determining the optimal number of components, assessing and improving reproducibility of the ICA results, and comparison with other popular matrix factorization techniques. We discuss the emerging ICA applications to the integrative analysis of multi-level omics datasets and introduce a conceptual view on ICA as a tool for defining functional subsystems of a complex biological system and their interactions under various conditions. Our review is accompanied by a Jupyter notebook which illustrates the discussed concepts and provides a practical tool for applying ICA to the analysis of cancer omics datasets.

Extracting Pathway-level Signatures from Proteogenomic Data in Breast Cancer Using Independent Component Analysis

Recent advances in the multi-omics characterization necessitate knowledge integration across different data types that go beyond individual biomarker discovery. In this study, we apply independent component analysis (ICA) to human breast cancer proteogenomics data to retrieve mechanistic information. We show that as an unsupervised feature extraction method, ICA was able to construct signatures with known biological relevance on both transcriptome and proteome levels. Moreover, proteome and transcriptome signatures can be associated by their respective correlation with patient clinical features, providing an integrated description of phenotype-related biological processes. Our results demonstrate that the application of ICA to proteogenomics data could lead to pathway-level knowledge discovery. Potential extension of this approach to other data and cancer types may contribute to pan-cancer integration of multi-omics information.

Temperature and precipitation variability in eastern Anatolia: Results from independent component analysis of Lake Van sediment data spanning the last 250 kyr BP

In this study, we present the results of independent component analysis (ICA) of previously published Lake Van data covering the last 250 kyr BP, to shed light on the precipitation and temperature regime in eastern Anatolia. The data processed were the element intensities of Ca, Fe, K, Mn, and Si analyzed by XRF core scanner; concentrations of TOC and CaCO3 content; and B* (color reflectance) from the Ahlat Ridge sediment record. Our analysis is based on application of ICA on the data by changing the initial random unit vector several times and clustering possible independent components through average-link agglomeration. As components extracted by ICA do not have a hierarchy, mutual information, which is a measure of information content between two random variables, is used as a measure of similarity by which to select candidate components. As a result, we argue, the independent component (Van-IC8), which shows the highest similarity to the Greenland δ18O record and visually similar to other regional temperature indicating data, can be read as a proxy for temperature variability. We also assert that the independent component (Van-IC7) which has the highest similarity to B* and visually similar to other regional precipitation proxies, and with the lake level reconstruction from another sediment profile from Lake Van is a proxy of precipitation variability across the region. Our results show that the region's temperature approximately maps onto global records, i.e. warm during interglacials and cold during stadials. However, the precipitation proxy reveals that the region was not dry, or at least as wet as it is today, during the end of the MIS 6 and the LGM. The MIS 5e/c and Holocene were characterized by a wet period followed by dry intervals and Dansgaard/Oeschger events are characterized as being warm and wet.

Independent component analysis: An introduction

Independent component analysis (ICA) is a widely-used blind source separation technique. ICA has been applied to many applications. ICA is usually utilized as a black box, without understanding its internal details. Therefore, in this paper, the basics of ICA are provided to show how it works to serve as a comprehensive source for researchers who are interested in this field. This paper starts by introducing the definition and underlying principles of ICA. Additionally, different numerical examples in a step-by-step approach are demonstrated to explain the preprocessing steps of ICA and the mixing and unmixing processes in ICA. Moreover, different ICA algorithms, challenges, and applications are presented.

S3-4. Independent component analysis derived features for electrocorticographic brain-machine interfaces

Recent progress in Brain Machine Interface (BMI) research using signals from subdural electrocorticographical (ECoG) arrays implanted over primary motor cortex has demonstrated the potential for successful decoding of participant’s arm or hand movement. Concurrent advances in wireless implantable electrode technology are further shortening the gap between existing systems and real functioning rehabilitative neural prosthetics for use by patients with motor system disorders. However the long-term stability and effectiveness of BMI technologies depends crucially on the stability and effectiveness of the feature extraction and decoding algorithms used to translate the neural signals into behavioural commands. Given the limited density and coverage of ECoG channel arrays, it is critical to reliably extract as much of the available information as possible. While some success has been achieved using channel-based features, we have recently shown that improvement may be gained by first applying the Independent Component Analysis (ICA) method to the ECoG channel data to separate and isolate relevant cortical signals. In this talk, we will present some preliminary results of application of ICA to ECoG data for the derivation of features for BMI applications and comparison to standard approaches. We discuss the interpretation of the ICA features and suggest directions for future improvements.

Real-space analysis of radiation-induced specific changes with independent component analysis.

A method of analysis is presented that allows for the separation of specific radiation-induced changes into distinct components in real space. The method relies on independent component analysis (ICA) and can be effectively applied to electron density maps and other types of maps, provided that they can be represented as sets of numbers on a grid. Here, for glucose isomerase crystals, ICA was used in a proof-of-concept analysis to separate temperature-dependent and temperature-independent components of specific radiation-induced changes for data sets acquired from multiple crystals across multiple temperatures. ICA identified two components, with the temperature-independent component being responsible for the majority of specific radiation-induced changes at temperatures below 130 K. The patterns of specific temperature-independent radiation-induced changes suggest a contribution from the tunnelling of electron holes as a possible explanation. In the second case, where a group of 22 data sets was collected on a single thaumatin crystal, ICA was used in another type of analysis to separate specific radiation-induced effects happening on different exposure-level scales. Here, ICA identified two components of specific radiation-induced changes that likely result from radiation-induced chemical reactions progressing with different rates at different locations in the structure. In addition, ICA unexpectedly identified the radiation-damage state corresponding to reduced disulfide bridges rather than the zero-dose extrapolated state as the highest contrast structure. The application of ICA to the analysis of specific radiation-induced changes in real space and the data pre-processing for ICA that relies on singular value decomposition, which was used previously in data space to validate a two-component physical model of X-ray radiation-induced changes, are discussed in detail. This work lays a foundation for a better understanding of protein-specific radiation chemistries and provides a framework for analysing effects of specific radiation damage in crystallographic and cryo-EM experiments.

Separation of Sources From Single-Channel EEG Signals Using Independent Component Analysis

The electroencephalogram (EEG) signals are often mixed with several sources such as electrooculogram and electromyogram signals. Independent component analysis (ICA) is often used to separate the sources from the multichannel EEG signals. Recently, the use of portable EEG devices has gained much attention due to their low power consumption and the ability to record the EEG signals in home environment. However, these systems are equipped with single or few EEG channels, and hence the direct application of ICA is not possible. In this paper, we proposed an efficient technique to separate the sources from single-channel EEG signals by combining the singular spectrum analysis (SSA) and ICA techniques. In this technique, the single-channel EEG data are first decomposed into multivariate data using SSA. Later, ICA is applied on the multivariate data to extract the source signals. In order to validate the performance of the proposed technique, we carried out the simulation on synthetic and real life EEG signals. In addition, we have also studied the performance of the proposed technique for detecting the seizures. The performance measures of a seizure detection classifier such as receiver operating curve, true positive rate, and false positive rate are obtained and found that the proposed technique exhibits better performance compared with the existing methods.

Adulteration of clove essential oil: Detection using a handheld Raman spectrometer

AbstractEssential oils are highly appreciated substances used as row materials in the food, cosmetics and pharmaceutical industry. Due to its biological activity and properties, the oil extracted from clove (Eugenia caryophyllus) has gained economic importance, and this is the main reason why adulterated clove essential oils have appeared in the market. The detection of adulteration is a fundamental task to ensure the quality of industrial products and, therefore, to protect the consumers from potential harmful products. In order to test the suitability of Raman spectroscopy to detect adulteration in essential oils, nineteen samples of commercial clove essential oil were measured with a handheld device and their Raman spectra analyzed. The Raman spectrum of a sample of authentic clove essential oil is dominated by bands of its main component eugenol. Principal component analysis (PCA) and independent component analysis (ICA) were applied in order to identify the adulterated samples and to assess the quality of the authentic samples. It was found that two samples were adulterated by the addition of benzyl alcohol and a third one by the addition of a vegetable oil. The adulteration by addition of benzyl alcohol is easy to detect by a quick inspection of the Raman spectrum, since this compound shows an intense band at 1003 cm‐1. However, the detection of adulteration by the addition of other substances (e.g., vegetable oils) requires the application of multivariable analysis, i.e., PCA or ICA. The results show that Raman spectroscopy is an appropriate technique for quality control of clove essential oil.

Ten Key Observations on the Analysis of Resting-state Functional MR Imaging Data Using Independent Component Analysis.

For more than 20 years, the powerful, flexible family of independent component analysis (ICA) techniques has been used to examine spatial, temporal, and subject variation in functional magnetic resonance (fMR) imaging data. This article provides an overview of 10 key principles in the basic and advanced application of ICA to resting-state fMR imaging. ICA's core advantages include robustness to artifact; false-positives and autocorrelation; adaptability to variant study designs; agnosticism to the temporal evolution of fMR imaging signals; and ability to extract, identify, and analyze neural networks. ICA remains in the vanguard of fMRI methods development.

MEG Based Functional Connectivity: Application of ICA to Alleviate Signal Leakage

BackgroundMagnetoencephalography (MEG) provides a promising, non-invasive medium for characterizing high temporal brain dynamics and functional connectivity (FC) networks. MEG based studies often include a source space signal reconstruction from the sensor data. However, spatial filters or inverse solutions that are used for source signal reconstruction induce a linear interaction between the source signals, and this phenomenon is often termed as a signal leakage. Therefore, the observed FC between the source signals may be partially or entirely due to signal leakage. In the present study, we demonstrated the usefulness of independent component analysis (ICA) to orthogonalize reconstructed source signals to suppress signal leakage before FC computation. We also compared the ICA based orthogonalization approach to commonly used linear regression, and orthogonalization in complex domain (Hipp orthogonalization) approaches. MethodsWe used band-limited (i.e. alpha and beta frequency bands) amplitude time series correlation as a measure of FC. Before FC computation, the seed and test voxel time series were orthogonalized using ICA, linear regression and Hipp orthogonalization methods to suppress the signal leakage. We performed an evaluation using simulated MEG data and real resting state MEG data. ResultsAnalysis of simulated MEG data indicates that ICA based orthogonalization approach effectively suppressed the spurious FC due to signal leakage where the false positive rate was as per expectation. Analysis of real resting MEG signal showed that ICA based orthogonalization efficiently suppress the spurious FC for test voxels located nearby to the seed voxel where the signal leakage is very much likely. However, it didn't suppress the actual FC for test voxels located remotely from the seed voxel where the signal leakage is unlikely. ConclusionICA based orthogonalization offers a straightforward and efficient alternative tool to alleviate the spurious FC due to signal leakage in reconstructed MEG source signals.