Kernel Independent Component Analysis Research Articles

Notice of Violation of IEEE Publication Principles: Fault Detection Using Industrial Video Information

Notice of Violation of IEEE Publication Principles Fault Detection Using Industrial Video Information by Y. Zhang, Z. Wang, Y. Fu and X. Li, in the IEEE Transactions on Industrial Electronics, vol. PP, no. 99 After careful and considered review of the content of this paper and associated multimedia content by a duly constituted expert committee, this work has been found to be in violation of IEEE's Publication Principles. This paper and associated multimedia files contain fraudulent data and images. Due to the nature of this violation, reasonable effort should be made to remove all past references to this paper and refrain from future references. In this study, a new data-modelling algorithm, referred to as relaxed independent component analysis, is proposed for the purpose of industrial video process monitoring. The contributions are as follows. (1) Physical variables and image data are unified in a framework to propose fault detection method of industrial process for the first time. (2) We find that independent components are sensitive to extract features of image and physical variables. In original KICA method, KPCA+ICA are used to extract nonlinear independent components. Since ICA is linear method, the original method only extracts semi-nonlinear independent components. In our method, the complete nonlinear independent components are extracted using the independence criterion. (3) A process monitoring approach of relaxed independent component analysis is presented. When applied to the monitoring of an electrical fused magnesia furnace, it can effectively improve the accuracy of forecasting the non-Gaussian process and reduce the ratio of false alarms compared to kernel principle component analysis and traditional kernel independent component analysis.

Food safety testing by negentropy-sorted kernel independent component analysis based on infrared spectroscopy

In the field of food safety testing, variety, brand, origin, and adulteration are four important factors. In this study, a novel food safety testing method based on infrared spectroscopy is proposed to investigate these factors. Fourier transform infrared spectroscopy data are analyzed using negentropy-sorted kernel independent component analysis (NS-kICA) as the feature optimization method. To rank the components, negentropy is performed to measure the non-Gaussian independent components. In our experiment, the proposed method was run on four datasets to comprehensively investigate the variety, brand, origin, and adulteration of agricultural products. The experimental results show that NS-kICA outperforms conventional feature selection methods. The support vector machine model outperforms the backpropagation artificial neural network and partial least squares models. The combination of NS-kICA and support vector machine (SVM) is the best method for achieving high, stable, and efficient recognition performance. These findings are of great importance for food safety testing.

Novel reduced kernel independent component analysis for process monitoring

Kernel independent component analysis (KICA), as a nonlinear extension monitoring method of independent component analysis (ICA), has attracted significant attention. To accomplish different monitoring tasks for nonlinear systems with non-Gaussian data distribution, many modified algorithms based on KICA have also been designed. However, most of the existing methods suffer from defects; for example, the computation time increases with the number of training samples and the models are insensitive to minor faults. Nevertheless, there is currently limited research on addressing these defects, which greatly limits their application in industrial processes. To fill these gaps, a novel reduced kernel independent component analysis (NRKICA) method is proposed to reduce the computation complexity and improve the ability of minor fault detection at the same time. In this approach, an important factor is defined to measure the ability of the samples to represent the properties of the system. In addition, then the top-n important observations are selected to build a data dictionary. To improve the sensitivity to minor faults, the [Formula: see text] and [Formula: see text] statistics are redesigned by introducing information from past observations. Besides, the kernel parameter is optimized by the tabu search algorithm. The proposed method is applied to fault detection with a numerical example and the Tennessee Eastman process (TEP), and the experimental results verify the effectiveness and sensitivity of the proposed method.

A Dual Self-Calibrating Framework for Noninvasive Fetal ECG R-Peak Detection

Fetal heart rate (fHR) is critical for assessing fetal health and diagnosing disorders such as fetal distress, congenital heart disease, and intrauterine growth retardation. With the rapid development of the Internet of Medical Things (IoT), fetal R-peak detection plays an important role in diagnosing heart defects during pregnancy. However, due to the nonlinear mixing of multiple sources in the non-invasive signals and the low signal-to-noise ratio (SNR), it is difficult to obtain accurate R-peak detection result. This article presents a dual Self-calibrating system based on a Spectral Attention Kernel Independent Component Analysis (SA-KICA) module and a Selfcalibrating fetal R-peak detection (SC-FRD) module. SA-KICA is an ICA-based calibration module constructed by SA mechanism, which was sought from Short-Time Fourier Transform (STFT) and was shipped back to original signal with convolution to achieve perfect maternal electrocardiogram (MECG) separation in high-dimensional linear separable space. Then a periodic and morphological based Channel Selector is designed to select the optimal MECG. After MECG removal, to further improve the performance of fetal R-peak detection, the SC-FRD module is introduced to utilize the interior peak information and selfcalibrating strategy, which includes variance-based fetal R-peak seed selection, time-varying coarse prediction and adaptive probability mask calibration. The proposed framework is a primary attempt to concurrently introduce the nonlinear feature, spectral information and self-calibrating strategy in the field of fetal ECG processing. The framework achieved excellent performance in fetal R-peak detection accuracy on a simulated dataset and two public datasets with varying divergence and richness of resources. The experimental results show that our framework is superior to existing methods and can be used as a potential fetal monitoring method in the application of Internet of Medical Things. The code is released in https://github.com/bfyjr/NI-FECG-Extraction.

A condition evaluation ensemble for power metering HPLC units within complex data scenarios

Abstract The High-Speed Power Line Carrier Communication (HPLC) enables the connections among power metering devices in integrated energy systems, and thus their satisfying operations are indispensable for system reliabilities. In order to more precisely diagnose their conditions especially in real complex data scenes, a multi-model evaluation ensemble is proposed in this paper. Firstly, typical IoT application contexts of customer-side metering equipment are analyzed, thus the corresponding main impact factors along with their performance evaluation indices can be probed. Next, to handle the multi-source, heterogeneous, high-dimensional datasets during applications, the Kernel Independent Component Analysis (KICA) is established to diminish data dimensionalities, thus the individual weights of each index can be rated. On the other hand, the Component Importance Measure (CIM) model is built to differentiate the impact degree of each indicator on the overall IoT connection performance, where the influence of dissimilar index on the entire performance, rather than the proportion or frequency, will be directly assessed to determine their impact weights. Ergo, a comprehensive diagnosis can be achieved via these two-fold total weights accordingly. Finally, the feasibility and effectiveness of the proposed method can be verified by an empirical case study, which is conducive to further improving the accuracy and rationality of HPLC condition evaluations.

Comprehensive Monitoring of Complex Industrial Processes with Multiple Characteristics

Traditional onefold data-driven methods for fault detection in complex process industrial systems with high-dimensional, linear, nonlinear, Gaussian, and non-Gaussian coexistence often have less than satisfactory monitoring performance because only a single distribution of process variables is considered. To address this problem, a hybrid fault detection model based on PCA-KPCA-ICA-KICA-BI (Bayesian inference) is proposed, taking into account the advantages of principal component analysis (PCA), kernel principal component analysis (KPCA), independent component analysis (ICA), and kernel independent component analysis (KICA) in terms of dimensionality reduction and feature extraction. Foremost, this paper proposed a nonlinear evaluation method and divided the feature variables into Gaussian linear blocks, Gaussian nonlinear blocks, non-Gaussian linear blocks, and non-Gaussian nonlinear blocks by using the Jarque–Bera (JB) test and nonlinear discrimination method. Each division was monitored by the PCA-KPCA-ICA-KICA model, and finally the Bayesian fusion strategy proposed in this study is used to synthesize the detection results for each block. The hybrid model helps in evaluating variable features and bettering detection performance. Ultimately, the superiority of this hybrid model was verified through the Tennessee Eastman (TE) process and the Continuous Stirred Tank Reactor (CSTR) process, and the fault monitoring results showed an average accuracy of 85.91% for this hybrid model.

Enterprise Management Performance Evaluation Model Using Improved Fuzzy Clustering Algorithm in IoT Networks

Enterprise core competence is closely related to enterprise management performance, and it is important to evaluate enterprise management performance. However, the current enterprise management performance evaluation model has the problems of high eigenvalues of sample data, low cumulative contribution and correlation, high error rate in the calculation of business management performance evaluation index weights, low evaluation accuracy, and long evaluation time. Therefore, the enterprise management performance evaluation model using improved fuzzy clustering algorithm in Internet of things (IoT) networks is proposed. First, in the IoT architecture, the enterprise management performance evaluation index system is established by using the balanced scorecard theory. Second, the evaluation index system is reduced in dimensionality by combining principal component analysis and kernel-independent component analysis, the fuzzy C-mean clustering algorithm based on the objective function is designed, and finally, the improved fuzzy clustering algorithm is obtained to establish the enterprise management performance evaluation model, the reduced evaluation index system is input, and the evaluation results are output. The results show that the sample data eigenvalue of this model is low. The maximum error rate of weight calculation is 2.3%, the accuracy is always more than 95%, and the average value of evaluation time is 0.57 s, which effectively realize enterprise management performance evaluation in IoT networks.

Research on fault detection and identification methods of nonlinear dynamic process based on ICA

Abstract In the present study, nonlinear dynamic process data are mapped into the kernel state space by kernel gauge variable analysis method to obtain decorrelated state data. The time-lapse covariance matrix of the state data is weighted and summed to obtain the time-lapse structure matrix of the state data, and then supervised kernel independent component analysis (SKICA) is established, the independent component feature data is extracted from the status data and the monitoring statistics are constructed to detect the process faults. The data show that kernel independent component analysis (ICA) method (KICA) method can detect slow fault faster than the ICA method, except that the statistical detection ability of F3 and FS is reduced, and the KICA method can significantly improve the detection performance of other faults and statistics. By analyzing the detection results of SKICA method, it is obvious that in the detection process of all five kinds of slow faults, the fault detection capability of SKICA is better than that of ICA and KICA. The results of continuous stirred reactor simulation system show that, compared with the basic linear process, the slow fault detection has a good monitoring performance, it can detect the small deviation in the process sensitively and give alarm information to the slow fault in time, to improve the fault detection rate.

Bearing fault diagnosis based on kernel independent component analysis and antlion optimization

Fault diagnosis of gearboxes based on vibration signal processing is challenging, as vibration signals collected by acceleration sensors are typically a nonlinear mixture of unknown signals. Furthermore, the number of source signals is usually larger than that of sensors because of the practical limitation on sensor positions. Hence, the fault characterization is actually a nonlinear underdetermined blind source separation (NUBSS) problem. In this paper, a novel NUBSS algorithm based on kernel independent component analysis (KICA) and antlion optimization (ALO) is proposed to address the technical challenge. The mathematical model demonstrates the nonlinear mixing of source signals in the underdetermined cases. Ensemble empirical mode decomposition is used as a preprocessing tool to decompose the observed signals into a set of intrinsic mode functions that suffers from the problem of redundant components. The correlation coefficient is utilized to eliminate the redundant components. An adaptive threshold singular value decomposition method is proposed to estimate the number of source signals. Then a whitening process is carried out to transform the overdetermined blind source separation (BSS) into determined BSS, which can be solved by the KICA method. However, the reasonable selection of parameters in KICA limits its application to some extent. Therefore, ALO and Fisher’s linear discriminant analysis are adopted to further enhance the accuracy of the KICA method. The separation performance of the proposed method is assessed through simulation. The numerical results show that the proposed method can accurately estimate the number of source signals and attains a higher separation quality in tackling nonlinear mixed signals when compared with the existing methods. Finally, the inner ring fault experiment is conducted to preliminarily validate the practicability of the proposed method in bearing fault diagnosis.

An improved MAMA-EMD for the automatic removal of EOG artifacts

The separation of electrooculogram (EOG) and electroencephalogram (EEG) is a potential problem in brain-computer interface (BCI). Especially, it is necessary to accurately remove EOG, as a disturbance, from the measured EEG in brain disease diagnosis, EEG-based rehabilitation systems, etc. Due to the interaction between the eye and periocular musculature, a multipoint spike is often produced in EEG for each ocular activity. Masking-aided minimum arclength empirical mode decomposition (MAMA-EMD) was developed to robustly decompose time series with impulse-like noise. However, the decomposition performance of MAMA-EMD was limited in the case of one impulse with multiple contiguous spike points. In this paper, MAMA-EMD was improved (called IMAMA-EMD) by supplementing the minimum arclength criterion, and it was combined with kernel independent component analysis (KICA), yielding an automatic EOG artifact removal method, denoted as KIIMME. The multi-channel contaminated EEG signals were separated into several independent components (ICs) by KICA. Then, IMAMA-EMD was applied to the EOG-related ICs decomposition to generate a set of inherent mode functions (IMFs), the low frequency ones, which have higher correlation with EOG components, were removed, and the others were employed to construct ‘clean’ EEG. The proposed KIIMME was evaluated and compared with other methods on semisimulated and real EEG data. Experimental results demonstrated that IMAMA-EMD effectively eliminated the influence of multipoint spike on sifting process, and KIIMME improved the removal accuracy of EOG artifacts from EEG while retaining more useful neural data. This improvement is of great significance to research on brain science as well as BCI.

A data-driven Bayesian network learning method for process fault diagnosis

This paper presents a data-driven methodology for fault detection and diagnosis (FDD) by integrating the principal component analysis (PCA) with the Bayesian network (BN). Though the integration of PCA-BN for FDD purposes has been studied in the past, the present work makes two contributions for process systems. First, the application of correlation dimension (CD) to select principal components (PCs) automatically. Second, the use of Kullback-Leibler divergence (KLD) and copula theory to develop a data-based BN learning technique. The proposed method uses a combination of vine copula and Bayes’ theorem (BT) to capture nonlinear dependence of high-dimensional process data which eliminates the need for discretization of continuous data. The data-driven integrated PCA-BN framework has been applied to two processing systems. Performance of the proposed methodology is compared with the independent component analysis (ICA), kernel principal component analysis (KPCA), kernel independent component analysis (KICA), and their integrated frameworks with the BN. The comparative study suggests that the proposed framework provides superior performance.

A denoising carbon price forecasting method based on the integration of kernel independent component analysis and least squares support vector regression

During the past few decades, accurately forecasting carbon price has become a significant research field and aroused concerns from both scholars and policymakers, which contributes the Organized Exchange to scientifically and rationally allocate a fixed-quantity of carbon emissions among prospective polluters. The conventional forecasting approaches, however, suffer from the poor prediction accuracy due to the nonlinearity and non-stationarity of the carbon price series. Meanwhile, monitoring and filtering the inherent noise in carbon price series, which are the main steps in the forecasting model, are perceived as the challenging tasks to work in. To address these obstacles, a denoising-hybridization procedure, which is a hybrid model of extreme-point symmetric mode decomposition (ESMD), kernel independent component analysis (KICA) and least squares support vector regression (LSSVR), is put forward for predicting the carbon price. Firstly, the carbon price is decomposed into several intrinsic mode functions (IMFs) via the ESMD method. Secondly, independent components (ICs), which reflect the internal formation mechanism, are separated out from the IMFs via KICA method. Further, the IC comprised of the noise is eliminated according to the results of noise monitoring. Finally, the LSSVR method is applied to the remaining ICs for achieving the forecasting results of carbon price, wherein the particle swarm optimization (PSO) algorithm is employed to synchronously optimize the hyper parameters in LSSVR. The empirical results on four carbon futures prices from European Union Emissions Trade System (EU ETS) demonstrate the effectiveness and robustness of the promoted denoising-hybridization procedure. Comparative experiments illustrate the superiority of the proposed method from the perspective of statistical performance criteria.

SVM Based on Gaussian and Non-Gaussian Double Subspace for Fault Detection

In industrial production processes, the data usually have high-dimensional characteristics. When a support vector machine (SVM) is used for fault detection, it takes a long time to run. For high-dimensional data, principal component analysis (PCA) and independent component analysis (ICA) are very effective dimensionality reduction algorithms. Since the data follow different distributions in industrial processes, PCA is commonly used to process Gaussian-distributed data, and ICA is used to process non-Gaussian distributed data. Addressing these limitations, a novel fault detection method of SVM based on Gaussian and non-Gaussian double subspace (DSSVM) is proposed. The Kolmogorov-Smirnov (KS) test is used to determine the normal distribution characteristics of the process variables in the original data. The process variables are divided into a Gaussian subspace and a non-Gaussian subspace. Fault detection models of the Gaussian subspace are established based on PCA, and models of the non-Gaussian subspace are based on ICA. To reduce the effect of autocorrelation among process variables on the SVM, the delay and time difference input characteristics are introduced into the principal components obtained in the Gaussian subspace and independent components obtained in the non-Gaussian subspace. Finally, the time delay matrix and time difference matrix are combined, and the SVM model is used for fault detection and monitoring. The DSSVM method reduces the data dimensions and eliminates the effect of autocorrelation among process variables on the detection results. The proposed method is applied to a multivariable numerical simulation and the Tennessee-Eastman industrial process. Comparisons with simulation results for the kernel principal component analysis (KPCA), kernel independent component analysis (KICA), SVM and the statistical process monitoring method based on variable distribution characteristics (VDSPM) further verify the effectiveness of the algorithm.

Kernal based speaker specific feature extraction and its applications in iTaukei cross language speaker recognition

Extraction and classification algorithms based on kernel nonlinear features are popular in the new direction of research in machine learning. This research paper considers their practical application in the iTaukei automatic speaker recognition system (ASR) for cross-language speech recognition. Second, nonlinear speaker-specific extraction methods such as kernel principal component analysis (KPCA), kernel independent component analysis (KICA), and kernel linear discriminant analysis (KLDA) are summarized. The conversion effects on subsequent classifications were tested in conjunction with Gaussian mixture modeling (GMM) learning algorithms; in most cases, computations were found to have a beneficial effect on classification performance. Additionally, the best results were achieved by the Kernel linear discriminant analysis (KLDA) algorithm. The performance of the ASR system is evaluated for clear speech to a wide range of speech quality using ATR Japanese C language corpus and self-recorded iTaukei corpus. The ASR efficiency of KLDA, KICA, and KLDA technique for 6 sec of ATR Japanese C language corpus 99.7%, 99.6%, and 99.1% and equal error rate (EER) are 1.95%, 2.31%, and 3.41% respectively. The EER improvement of the KLDA technique-based ASR system compared with KICA and KPCA is 4.25% and 8.51% respectively.

Randomized independent component analysis and linear discriminant analysis dimensionality reduction methods for hyperspectral image classification

Dimensionality reduction is an important step in processing the hyperspectral images (HSI) to overcome the curse of dimensionality problem. Linear dimensionality reduction methods such as Independent component analysis (ICA) and Linear discriminant analysis (LDA) are commonly employed to reduce the dimensionality of HSI. These methods fail to capture non-linear dependency in the HSI data, as data lies in the nonlinear manifold. To handle this, nonlinear transformation techniques based on kernel methods were introduced for dimensionality reduction of HSI. However, the kernel methods involve cubic computational complexity while computing the kernel matrix, and thus its potential cannot be explored when the number of pixels (samples) are large. In literature a fewer number of pixels are randomly selected to partial to overcome this issue, however this sub-optimal strategy might neglect important information in the HSI. In this paper, we propose randomized solutions to the ICA and LDA dimensionality reduction methods using Random Fourier features, and we label them as RFFICA and RFFLDA. Our proposed method overcomes the scalability issue and to handle the non-linearities present in the data more efficiently. Experiments conducted with two real-world hyperspectral datasets demonstrates that our proposed randomized methods outperform the conventional kernel ICA and kernel LDA in terms overall, per-class accuracies and computational time.

Integrating Canonical Variate Analysis and Kernel Independent Component Analysis for Tennessee Eastman Process Monitoring

Integrating Canonical Variate Analysis and Kernel Independent Component Analysis for Tennessee Eastman Process Monitoring

Improve the spectral clustering by integrating a new modularity similarity index and out-of-sample extension

Spectral clustering is one of the most important data processing methods which has been wildly applied to machine learning, computer vision, pattern recognition and image processing. However, one of the main drawbacks of spectral clustering is the fact that the clustering model is defined only for primal data without clear extension to out-of-sample data. To improve its efficiency, in this paper, we proposed a new modularity-based method for spectral clustering with out-of-sample extension. First, kernel independent component analysis is used to solve the demixing matrix on Stiefel manifold in order to extract high-order irrelevant data feature. Then, a new modularity similarity measure-based spectral mapping algorithm is proposed, which allows the clustering model to be directly extended to out-of-sample data. Based on above analysis, we present a spectral clustering algorithm with out-of-sample extension. Experimental results show our method has better performance compared with other related algorithms in different datasets.

An empirical sequence to extract fetal electrocardiogram using the Kernel and wavelet optimization

Fetal electrocardiogram (ECG) monitoring from the mother’s abdomen during pregnancy provides electrophysiological statistics of fetus heart. To separate fetal ECG from mother ECG is a signal separation technique that has the potential to give blind source information. In this paper, an empirical sequence of Kernel Independent Component Analysis (KICA) and Dual-Tree Complex Wavelet Transform (DTCWT) is implemented for efficient ECGs separation and post enhancement of extracted fetal ECG. The kernel approach provides a non-linear transformation and works in building contrast function based on mutual information. Further to remove unwanted disturbances, shift-invariant DTCWT is used to reconstruct filtered extracted fetal ECG. The proposed work is validated on Abdominal and Direct Fetal ECG Database (ADFECGDB) from the physionet. The proposed method also compares the accuracy and running time by implementing the FastICA method on the same dataset simultaneously.

Retraction of “Fault Detection and Diagnosis of Nonlinear Processes Using Improved Kernel Independent Component Analysis (KICA) and Support Vector Machine (SVM)”

Retraction of “Fault Detection and Diagnosis of Nonlinear Processes Using Improved Kernel Independent Component Analysis (KICA) and Support Vector Machine (SVM)”

Study on Separation of Underwater Vehicle Noise Based on Blind Source Separation

Aiming at the study of underwater vehicle noise extraction in the measurement, a method based on blind source separation (BBS) is presented, and the kernel independent component analysis (KICA) is used in the separation of underwater vehicle noise. The principle and algorithm is introduced and the simulation is carried on to compare with the traditional ICA algorithm in BBS. The simulation results show that KICA not only separates the underwater vehicle noise effectively but also is more accurate than the traditional ICA algorithm.