Fast Independent Component Analysis Research Articles

Expanding the clinical application of OPM-MEG using an effective automatic suppression method for the dental brace metal artifact

Optically pumped magnetometer magnetoencephalography (OPM-MEG) holds significant promise for clinical functional brain imaging due to its superior spatiotemporal resolution. However, effectively suppressing metallic artifacts, particularly from devices such as orthodontic braces and vagal nerve stimulators remains a major challenge, hindering the wider clinical application of wearable OPM-MEG devices.A comprehensive analysis of metal artifact characteristics from time, frequency, and time–frequency perspectives was conducted for the first time using an OPM-MEG device in clinical medicine. This study focused on patients with metal orthodontics, examining the modulation of metal artifacts by breath and head movement, the incomplete regular sub-Gaussian distribution, and the high absolute power ratio in the 0.5–8 Hz band. The existing metal artifact suppression algorithms applied to SQUID-MEG, such as fast independent component analysis (FastICA), information maximization (Infomax), and algorithms for multiple unknown signal extraction (AMUSE), exhibit limited efficacy. Consequently, this study introduced the second-order blind identification (SOBI) algorithm, which utilized multiple time delays for the component separation of OPM-MEG measurement signals. We modified the time delays of the SOBI method to improve its efficacy in separating artifact components, particularly those in the ultralow frequency range. This approach employs the frequency-domain absolute power ratio, root mean square (RMS) value, and mutual information methods to automate the artifact component screening process.The effectiveness of this method was validated through simulation experiments involving four subjects in both resting and evoked experiments. In addition, the proposed method was also validated by the actual OPM-MEG evoked experiments of three subjects. Comparative analyses were conducted against the FastICA, Infomax, and AMUSE algorithms. Evaluation metrics included normalized mean square error, normalized delta band power error, RMS error, and signal-to-noise ratio, demonstrating that the proposed method provides optimal suppression of metal artifacts. This advancement holds promise for enhancing data quality and expanding the clinical applications of OPM-MEG.

Systemic Financial Risk Forecasting with Decomposition–Clustering-Ensemble Learning Approach: Evidence from China

Establishing a scientifically effective systemic financial risk early warning model is of great significance for prudently mitigating systemic financial risks and enhancing the efficiency of financial supervision. Based on the measurement of systemic financial risk and the network sentiment index of 47 financial institutions, this study adopted the “decomposition–reconstruction–integration” approach, utilizing techniques such as extreme-point symmetric empirical mode decomposition (ESMD), empirical mode decomposition (EMD), variational mode decomposition (VMD), hierarchical clustering, fast independent component analysis (FastICA), attention mechanism, bidirectional long short-term memory neural network (BiLSTM), support vector regression (SVR), and their combination, to construct a systemic financial risk prediction model. The empirical results demonstrate that decomposing and reconstructing relevant indicators before predicting systemic financial risks can enhance prediction accuracy. Among the proposed models, the ESMD-HFastICA-BiLSTM-Attention model exhibits superior performance in systemic financial risk early warning.

Orthogonal extended infomax algorithm.

Objective.The extended infomax algorithm for independent component analysis (ICA) can separate sub- and super-Gaussian signals but converges slowly as it uses stochastic gradient optimization. In this paper, an improved extended infomax algorithm is presented that converges much faster.Approach.Accelerated convergence is achieved by replacing the natural gradient learning rule of extended infomax by a fully-multiplicative orthogonal-group based update scheme of the ICA unmixing matrix, leading to an orthogonal extended infomax algorithm (OgExtInf). The computational performance of OgExtInf was compared with original extended infomax and with two fast ICA algorithms: the popular FastICA and Picard, a preconditioned limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) algorithm belonging to the family of quasi-Newton methods.Main results.OgExtInf converges much faster than original extended infomax. For small-size electroencephalogram (EEG) data segments, as used for example in online EEG processing, OgExtInf is also faster than FastICA and Picard.Significance.OgExtInf may be useful for fast and reliable ICA, e.g. in online systems for epileptic spike and seizure detection or brain-computer interfaces.

A concurrent fault diagnosis method for electric isolation valves in nuclear power plants based on rule-based reasoning and data-driven methods

In order to improve the fault diagnosis ability of electric isolation valves in nuclear power plants, especially for the diagnosis of concurrent faults, a novel concurrent fault diagnosis method based on rule reasoning and data-driven methods is proposed in this study. The concurrent fault diagnosis method is divided into two layers: the rule-based reasoning layer and data-driven layer. In order to realize the diagnosis of most concurrent faults, the rule-based reasoning layer is established by a rule inference model according to the failure mode and effects analysis (FMEA) of the electric isolation valve. In order to diagnose concurrent faults with mutual interference of fault features that cannot be diagnosed by rule-based reasoning layer, the data-driven layer is established by variational mode decomposition (VMD) and fast independent component analysis (Fast-ICA) method to separate concurrent fault signals and gate recurrent unit (GRU) method to identify fault patterns. After testing on the electric valve test bench and simulation data, multiple concurrent faults of the electric isolation valve are diagnosed accurately by the proposed concurrent fault diagnosis framework, including complex concurrent faults such as internal leakage and external leakage, and the framework can also work in a single fault diagnosis scenario without changing models. Compared with the concurrent fault diagnosis based on multi-label support vector machine, the accuracy of concurrent fault diagnosis is improved by about 25.3%. The research can provide a new idea for the concurrent fault diagnosis of electric isolation valves and other equipment.

Multiple ultrasonic partial discharge DOA estimation performance of KPCA Pseudo-Whitening mnc-FastICA

Empirical studies into partial discharge (PD) localization face the difficulty of signal contamination from external noise and interference. To extract relevant information from PD signals collected by acoustic sensor array, Kernel Principal Component Analysis (KPCA) pseudo-whitening with modified noncircular Fast Independent Component Analysis (mnc-FastICA) were used. By this approach, separated matrix and observed signals can be achieved. The reconstructed array manifold matrix created from the separated matrix generated by KPCA-mnc-FastICA may be used in the Direction of Arrival (DOA) estimation approach. An angle error correction matrix is designed to compensate for the sensor's phase inaccuracy. The simulation results show that angle identification accuracy is outstanding, with mistakes limited to a small margin of 2°. Furthermore, the results of trials show that this technique can efficiently isolate individual target signals even when they are polluted with significant noise and interference. The average errors in azimuth and pitch angle are less than 2° and 1.1°, respectively. These data support the effectiveness of the approach for effectively separating signals and estimating DOA of numerous signal sources.

Hybrid KuFaI: A novel secure key generation algorithm using fast independent component analysis for physical layer security techniques

AbstractMany real‐world applications, such as smart cities, industrial automation, health care, and so forth, utilize IoT‐enabled devices as a part of wireless networks. IoT devices must have low power and low computation complexity requirements with proper measures of security challenges. Since traditional cryptography techniques are not computationally efficient, other alternatives, such as physical layer key generation (PLKG), is one of the attractive means to achieve security. In this paper, we propose to use a fast independent component analysis (FICA) based KuFaI (Kurtosis and FICA) algorithm for a secured PLKG system. This method reduces data dimensions and improves system performance regarding Bit Disagreement Rate (BDR) and randomness. In KuFaI, we rearrange the received signal strength indicator (RSSI) data set using FICA and then select components based on the kurtosis function. Results demonstrate that the performance of the proposed algorithm is far better than the previously used PCA‐based algorithm.

Rolling bearing compound fault diagnosis based on spatiotemporal intrinsic mode decomposition

Aiming at the vibration signal characteristics of multi-channel rolling bearing complex faults containing various shock components, a rolling bearing complex fault diagnosis model based on spatiotemporal intrinsic mode decomposition (STIMD) method and fast spectral kurtosis method was proposed. The spatiotemporal intrinsic mode decomposition method combines the signal atomic decomposition method with the idea of signal blind source separation. Through the fast independent component analysis and the nonlinear matching pursuit method of the established overcomplete dictionary base, various fault mode components are separated. The initial phase function selected based on the high kurtosis fault frequency band obtained by the fast spectral kurtosis method can better fit the bearing fault frequency domain characteristics, so that the spatiotemporal intrinsic mode decomposition method can more accurately separate various impact components in the vibration signal. The simulation model of bearing compound fault was established and the data collected from fault diagnosis experiment platform were used to verify that the STIMD method was effective in solving the problem of rolling bearing compound fault diagnosis. By analyzing the kurtosis changes under different signal noise ratio (SNR) conditions and comparing the simulation results with the fast independent component analysis method, it shows that the kurtosis index decomposed by the proposed method is more able to prove the existence of faults under the condition of low SNR, that is, the impact is completely covered by noise. Therefore, a spatiotemporal intrinsic mode decomposition method with fast spectral kurtosis optimization can solve the problem of blind source separation in the field of composite faults of multi-channel rolling bearings and realize composite fault diagnosis.

Influence of sources with a spectral peak in the detection of Cosmic Dawn and Epoch of Reionization

ABSTRACT Foreground removal is one of the biggest challenges in the detection of the Cosmic Dawn (CD) and Epoch of Reionization (EoR). Various foreground subtraction techniques have been developed based on the spectral smoothness of foregrounds. However, the sources with a spectral peak (SP) at megahertz may break down the spectral smoothness at low frequencies (<1000 MHz). In this paper, we cross-match the GaLactic and Extragalactic All-sky Murchison Widefield Array (GLEAM) extragalactic source catalogue with three other radio source catalogues, covering the frequency range 72 MHz–1.4 GHz, to search for sources with spectral turnover. 4423 sources from the GLEAM catalogue are identified as SP sources, representing ≈3.2 per cent of the GLEAM radio source population. We utilize the properties of SP source candidates obtained from real observations to establish simulations and test the impact of SP sources on the extraction of CD/EoR signals. We statistically compare the differences introduced by SP sources in the residuals after removing the foregrounds with three methods, which are polynomial fitting, principal component analysis, and fast independent component analysis. Our results indicate that the presence of SP sources in the foregrounds has a negligible influence on extracting the CD/EoR signal. After foreground subtraction, the contribution from SP sources to the total power in the two-dimensional power spectrum within the EoR window is approximately 3–4 orders of magnitude lower than the CD/EoR signal.

The parameter identification of metro rail corrugation based on effective signal extraction and inertial reference method

Rail corrugation is a severe track damage and failure problem in metro lines. So, the accurate assessment of rail corrugation is significant for the safety and comfort of vehicles. It is an efficient means to detect rail corrugation through the acceleration signal. However, the acceleration signal contains the mixed signal caused by vehicle component noise and wheel polygonal wear, resulting in poor rail corrugation detection accuracy. Therefore, a new method is presented to extract the effective signal components and accurately identify the rail corrugation. Firstly, the Cubic mapping, modified sine algorithm, and Lévy flight are introduced into the dung beetle optimizer algorithm. A new improved dung beetle optimizer (IDBO) algorithm is presented to optimize the hyperparameters of the VMD algorithm, which can increase the signal decomposition performance of the VMD. Secondly, the fast independent component analysis method separates the independent components (ICs) from the VMD modes and original acceleration signal. Based on the selection criteria of ICs, the dominant signal components related to rail corrugation are determined. The rail corrugation amplitude can be obtained through the inertial reference method. The experimental results demonstrate that the presented method has better rail corrugation recognition accuracy, the root mean square error is smaller than the comparison method, and the corrugation wavelength of the straight track is larger than the curve track.

Joint Improved Fast Independent Component Analysis and Singular Value Decomposition for Fetal Electrocardiogram Extraction.

Combined the improved fast independent component analysis (FastICA) algorithm with the singular value decomposition algorithm, a single-channel fetal electrocardiogram (fECG) extraction method is proposed. First, the improved FastICA algorithm is used to estimate the maternal ECG component from a single-channel abdominal signal of pregnant women using an overrelaxation factor. Then, a preliminary estimate of the fECG signal is obtained by subtracting from the single-channel abdominal signal. Subsequently, the singular value decomposition algorithm is used to denoise the preliminarily estimated fECG signal to obtain a high signal-to-noise ratio. In addition, in the singular value decomposition algorithm for fetal arrhythmia, an improved method for constructing the ECG signal reconstruction matrix is proposed. Finally, the fECG extraction experiments on synthetic abdominal signals and actual abdominal signals (data from 49 abdominal channels sourced from DAISY database and the non-invasive fECG database in PhysioNet) are carried out. The experimental results show that the method in this paper can effectively improve the signal-to-noise ratio and the accuracy of fECG signal extraction, and is suitable for maternal or fetal arrhythmias. Compared with the FastICA algorithm, the signal-to-noise ratio of the fECG signal extracted by the method in this paper is improved by about 5 dB, and the accuracy of fECG extraction in the PhysioNet database can reach 96.54%.

Performance Evaluation of Matrix Factorization for fMRI Data.

A hypothesis in the study of the brain is that sparse coding is realized in information representation of external stimuli, which has been experimentally confirmed for visual stimulus recently. However, unlike the specific functional region in the brain, sparse coding in information processing in the whole brain has not been clarified sufficiently. In this study, we investigate the validity of sparse coding in the whole human brain by applying various matrix factorization methods to functional magnetic resonance imaging data of neural activities in the brain. The result suggests the sparse coding hypothesis in information representation in the whole human brain, because extracted features from the sparse matrix factorization (MF) method, sparse principal component analysis (SparsePCA), or method of optimal directions (MOD) under a high sparsity setting or an approximate sparse MF method, fast independent component analysis (FastICA), can classify external visual stimuli more accurately than the nonsparse MF method or sparse MF method under a low sparsity setting.

Extruder Machine Gear Fault Detection Using Autoencoder LSTM via Sensor Fusion Approach

In industrial settings, gears play a crucial role by assisting various machinery functions such as speed control, torque manipulation, and altering motion direction. The malfunction or failure of these gear components can have serious repercussions, resulting in production halts and financial losses. To address this need, research efforts have focused on early defect detection in gears in order to reduce the impact of possible failures. This study focused on analyzing vibration and thermal datasets from two extruder machine gearboxes using an autoencoder Long Short-Term Memory (AE-LSTM) model, to ensure that all important characteristics of the system are utilized. Fast independent component analysis (FastICA) is employed to fuse the data signals from both sensors while retaining their characteristics. The major goal is to implement an outlier detection approach to detect and classify defects. The results of this study highlighted the extraordinary performance of the AE-LSTM model, which achieved an impressive accuracy rate of 94.42% in recognizing malfunctioning gearboxes within the extruder machine system. The study used robust global metric evaluation techniques, such as accuracy, F1-score, and confusion metrics, to thoroughly evaluate the model’s dependability and efficiency. LSTM was additionally employed for anomaly detection to further emphasize the adaptability and interoperability of the methodology. This modification yielded a remarkable accuracy of 89.67%, offering additional validation of the model’s reliability and competence.

EEG-BCI Features Discrimination between Executed and Imagined Movements Based on FastICA, Hjorth Parameters, and SVM

Brain–Computer Interfaces (BCIs) communicate between a given user and their nearest environment through brain signals. In the case of device handling, an accurate control-based BCI depends essentially on how the user performs corresponding mental tasks. In the BCI illiteracy-related literature, one subject could perform a defined paradigm better than another. Therefore, this work aims to identify recorded Electroencephalogram (EEG) signal segments related to the executed and imagined motor tasks for BCI system applications. The proposed approach implements pass-band filters and the Fast Independent Component Analysis (FastICA) algorithm to separate independent sources from raw EEG signals. Next, EEG features of selected channels are extracted using Hjorth parameters. Finally, a Support Vector Machines (SVMs)-based classifier identifies executed and imagined motor features. Concretely, the Physionet dataset, related to executed and imagined motor EEG signals, provided training, testing, and validating data. The numerical results let us discriminate between executed and imagined motor tasks accurately. Therefore, the proposed method offers a reliable alternative to extract EEG features for BCI based on executed and imagined movements.

Efficient background subtraction method based on fast independent component analysis in video-surveillance

Modern video surveillance has now become an active area of research with a large set of requirements and various applications. In order to detect moving objects in video surveillance scenes, background subtraction techniques are the most used. In this paper, we developed and tested an efficient background subtraction technique in video surveillance based on the fast-independent component analysis (fast-ICA) method. The proposed technique initiated, first, on the use of a developed fast-ICA algorithm in order to estimate the de-mixing matrix and the denoising matrix parameters. Second, the estimated foreground can simply model by multiplying the data matrix with the de-mixing matrix. After that, the data matrix is multiplied by the denoising matrix for removing the noise. In addition, we propose a pre-processing and post-processing operations to effectively segment the true foreground objects and improve our results. The proposed method is evaluated on the publicly available change detection datasets CDnet 2012 and CDnet 2014 using performance parameters such as recall, precision and experimental results show that our algorithm can detect effectively and accurately the moving objects in several background and foreground conditions compared to other methods in literature with real-time frame rate.

Low Complex CORDIC-based Hand Movement Recognition Design Methodology for Rehabilitation and Prosthetic Applications.

Hand movement recognition using Electromyography (EMG) signals have gained much significance lately and is extensively used for rehabilitation and prosthetic applications including stroke-driven disability and other neuromuscular disorders. Herein, quantitative analysis of EMG signals is very crucial. However, such applications are constrained by power consumption limitations due to the battery backup necessitating low-complex system design and the on-chip area requirement. Existing hand movement recognition methodologies using single-channel EMG signal involve computationally intensive stages, including Ensemble Empirical Mode Decomposition (EEMD), Fast Independent Component Analysis (FastICA), feature extraction, and Linear Discriminant Analysis (LDA) classification, which can not be mapped onto the low-complex architecture directly from the algorithmic level. The high computational complexity of LDA classification makes it difficult to be used for low-complex applications. In this paper, we introduce a low-complex CORDIC-based hand movement recognition design methodology targeting resource-constrained rehabilitation applications. This work explores replacing LDA classification with K-Means clustering due to its reduced complexity and efficient clustering algorithm. CORDIC-based K-Means clustering is used to further reduce the overall computational complexity of the system. The proposed low complex, K-Means clustering-based hand movement recognition for classifying seven hand movements using single-channel EMG data is found to be 99.77 % less complex and 1.28% more accurate than the conventional LDA-based classification.

Topological Comparison of Some Dimension Reduction Methods Using Persistent Homology on EEG Data

In this paper, we explore how to use topological tools to compare dimension reduction methods. We first make a brief overview of some of the methods often used in dimension reduction such as isometric feature mapping, Laplacian Eigenmaps, fast independent component analysis, kernel ridge regression, and t-distributed stochastic neighbor embedding. We then give a brief overview of some of the topological notions used in topological data analysis, such as barcodes, persistent homology, and Wasserstein distance. Theoretically, when these methods are applied on a data set, they can be interpreted differently. From EEG data embedded into a manifold of high dimension, we discuss these methods and we compare them across persistent homologies of dimensions 0, 1, and 2, that is, across connected components, tunnels and holes, shells around voids, or cavities. We find that from three dimension clouds of points, it is not clear how distinct from each other the methods are, but Wasserstein and Bottleneck distances, topological tests of hypothesis, and various methods show that the methods qualitatively and significantly differ across homologies. We can infer from this analysis that topological persistent homologies do change dramatically at seizure, a finding already obtained in previous analyses. This suggests that looking at changes in homology landscapes could be a predictor of seizure.

Establishment of original liquor discrimination using fluorescence spectroscopy combined with chemometric analysis and its application in Chinese mild-flavor liquors

Original liquor quality control and grade identification are important for the quality improvement of finished liquor. For the purpose of this study, a meticulous collection of 209 samples of original Chinese mild-flavored liquors was conducted. The grading of these samples was determined through sensory tasting, which is the prevailing method used in major liquor factories. These samples were scanned by three-dimensional fluorescence spectroscopy to obtain the respective excitation-emission matrices (EEM). The suitability of EEM was evaluated for the classification of these samples using principal component analysis (PCA), Discrete Cosine Transform (DCT), Fast Independent Component Analysis (Fast-ICA) combined with linear discriminant analysis (LDA) and support vector machine (SVM). In general, it was found that a fast and labor-saving model for quality identification of original liquor was obtained, PCA was a more suitable algorithm for reducing the number of variables. The classification accuracy of the original liquor obtained by the SVM method after PCA dimensionality reduction was the highest, the training set accuracy was 89.81%. Therefore, the PCA-SVM model was selected, and after testing, its prediction accuracy was 84.62%. The model has undergone five-fold cross-validation (CV), and the CV accuracy is 81.53%, which proves that the model is sufficiently stable.

A high-precision and efficient algorithm for space-based ADS-B signal separation

AbstractSpace-based automatic dependent surveillance-broadcast (ADS-B) receivers can cover thousands of aircraft, each transmitting 6 ⋅ 2 signals per second. As a result, ADS-B signals are very prone to overlap. When the number of aircraft covered by a receiver reaches 3,000, about 90 % of the signals will be overlapping. Overlapped signals can reduce the decoding accuracy of receivers, so that aircraft information cannot be accurately transmitted to the air traffic control (ATC) surveillance system, hence threatening aviation flight safety. It is necessary to propose signal separation algorithms for space-based ADS-B systems. An orthogonal projection linear constrained minimum variance (OPLCMV) algorithm is proposed, which can separate two signals simultaneously based on the linearly constrained minimum variance algorithm by exploiting the characteristics of overlapped signals. Compared with the state-of-the-art extended projection algorithm and the fast independent component analysis algorithm, the OPLCMV method has a higher decoding accuracy for multiple overlapping signals with a small direction difference of arrival or frequency shift. Moreover, the OPLCMV algorithm has a low computational complexity when the number of overlapped signal sources is less than seven.

Rolling Bearing Composite Fault Diagnosis Method Based on Enhanced Harmonic Vector Analysis.

Composite fault diagnosis of rolling bearings is very challenging work, especially when the characteristic frequency ranges of different fault types overlap. To solve this problem, an enhanced harmonic vector analysis (EHVA) method was proposed. Firstly, the wavelet threshold (WT) denoising method is used to denoise the collected vibration signals to reduce the influence of noise. Next, harmonic vector analysis (HVA) is used to remove the convolution effect of the signal transmission path, and blind separation of fault signals is carried out. The cepstrum threshold is used in HVA to enhance the harmonic structure of the signal, and a Wiener-like mask will be constructed to make the separated signals more independent in each iteration. Then, the backward projection technique is used to align the frequency scale of the separated signals, and each fault signal can be obtained from composite fault diagnosis signals. Finally, to make the fault characteristics more prominent, a kurtogram was used to find the resonant frequency band of the separated signals by calculating its spectral kurtosis. Semi-physical simulation experiments are conducted using the rolling bearing fault experiment data to verify the effectiveness of the proposed method. The results show that the proposed method, EHVA, can effectively extract the composite faults of rolling bearings. Compared to fast independent component analysis (FICA) and traditional HVA, EHVA improves separation accuracy, enhances fault characteristics, and has higher accuracy and efficiency compared to fast multichannel blind deconvolution (FMBD).

An efficient and secure key management with the extended convolutional neural network for intrusion detection in cloud storage

SummaryCloud computing aids users for storing and recovering their information everywhere in the world. Security and efficiency are the two main issues in cloud service. Numerous intrusion detection techniques for the cloud computing environment were proposed, but those techniques do not effectively and accurately detect the attacks. Hence, an efficient and secure key management using extended convolutional neural network, that is, hybrid Enhanced Elman Spike convolutional Neural Network optimized with improved COOT optimization algorithm (Hyb EESCCNN) is proposed for intrusion detection in cloud system. Furthermore, the novel Adaptive Tangent Brakerski‐Gentry Vaikuntanathan Homomorphic Encryption (ATBGVHE) method is proposed for providing the security of the system. At first, SHA‐512 is used for authenticating cloud users to store its own information in to the cloud server. Then for Intrusion Detection (ID) the input data from the NSL‐KDD, UNSWNB15, CICIDS2018, and ToN‐IoT datasets are pre‐processed. The most relevant features are extracted using Fast Independent Component Analysis (Fast ICA) from the pre‐processed output. These extracted data are classified into malicious and non‐malicious data using Hyb EESCCNN. After classification, the non‐malicious data is secured using an ATBGVHE technique. The outcomes of the proposed methods shows that the NSL‐KDD datasets attains 99.9% higher accuracy, UNSW‐NB15 datasets offer 99.89% higher accuracy, CSE‐CIC‐IDS2018 datasets attains 99.8% higher accuracy, ToN‐IoT datasets attains 99.8% higher accuracy and 0.02 s lower encryption time compared with existing methods. Finally, case study with real time applications is also analyzed to prove the efficiency of the proposed method.