Search results

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.

In Part I, an intelligent acoustic emission (AE) locator is described while the Part II discusses a blind source separation, time delay estimation and location of two continuous AE sources. AE analysis is used for characterization and location of developing defects in materials. AE sources often generate a mixture of various statistically independent signals. A difficult problem of AE analysis is a separation and characterization of signal components when the signals from various sources and the mode of mixing are unknown. Recently, blind source separation (BSS) by independent component analysis (ICA) has been used to solve these problems. The purpose of this paper is to demonstrate the applicability of ICA to locate two independent simultaneously active AE sources on an aluminum band specimen. The method is promising for non‐destructive testing of aircraft frame structures by AE analysis.

Acoustic emission analysis (AE) is used for characterization and location of developing defects in materials. AE sources often generate a mixture of various statistically independent signals. One difficult problem of AE analysis is the separation and characterization of signal components when the signals from various sources and the way in which the signals were mixed are unknown. Recently, blind source separation (BSS) by independent component analysis (ICA) has been used to solve these problems. The main purpose of this paper is to demonstrate the applicability of ICA to time‐delay estimation of two independent continuous AE sources on an aluminum beam. It is shown that it is possible to estimate time delays by ICA, and thus to locate two independent simultaneously emitted sources.

To develop a new method for estimation of damage configuration in composite laminate structure using acoustic wave propagation signal and a reduction‐prediction neural network to deal with high dimensional spectral data.

A reduction‐prediction network, which is a combination of an independent component analysis (ICA) and a multi‐layer perceptron (MLP) neural network, is proposed to quantify the damage state related to transverse matrix cracking in composite laminates using acoustic wave propagation model. Given the Fourier spectral response of the damaged structure under frequency band‐selective excitation, the problem is posed as a parameter estimation problem. The parameters are the stiffness degradation factors, location and approximate size of the stiffness‐degraded zone. A micro‐mechanics model based on damage evolution criteria is incorporated in a spectral finite element model (SFEM) for beam type structure to study the effect of transverse matrix crack density on the acoustic wave response. Spectral data generated by using this model is used in training and testing the network. The ICA network called as the reduction network, reduces the dimensionality of the broad‐band spectral data for training and testing and sends its output as input to the MLP network. The MLP network, in turn, predicts the damage parameters.

Numerical demonstration shows that the developed network can efficiently handle high dimensional spectral data and estimate the damage state, damage location and size accurately.

Only numerical validation based on a damage model is reported in absence of experimental data. Uncertainties during actual online health monitoring may produce errors in the network output. Fault‐tolerance issues are not attempted. The method needs to be tested using measured spectral data using multiple sensors and wide variety of damages.

The developed network and estimation methodology can be employed in practical structural monitoring system, such as for monitoring critical composite structure components in aircrafts, spacecrafts and marine vehicles.

A new method is reported in the paper, which employs the previous works of the authors on SFEM and neural network. The paper addresses the important problem of high data dimensionality, which is of significant importance from practical engineering application viewpoint.

We present an approach for blind separation of acoustic sources produced from multiple speakers mixed in realistic room environments. We first transform recorded signals into the time‐frequency domain to make mixing become instantaneous. We then separate the sources in each frequency bin based on an independent component analysis (ICA) algorithm. For the present paper, we choose the complex version of fixedpoint iteration (CFPI), i.e. the complex version of FastICA, as the algorithm. From the separated signals in the time‐frequency domain, we reconstruct output‐separated signals in the time domain. To solve the so‐called permutation problem due to the indeterminacy of permutation in the standard ICA, we propose a method that applies a special property of the CFPI cost function. Generally, the cost function has several optimal points that correspond to the different permutations of the outputs. These optimal points are isolated by some non‐optimal regions of the cost function. In different but neighboring bins, optimal points with the same permutation are at almost the same position in the space of separation parameters. Based on this property, if an initial separation matrix for a learning process in a frequency bin is chosen equal to the final separation matrix of the learning process in the neighboring frequency bin, the learning process automatically leads us to separated signals with the same permutation as that of the neighbor frequency bin. In each bin, but except the starting one, by chosen the initial separation matrix in such a way, the permutation problem in the time domain reconstruction can be avoided. We present the results of some simulations and experiments on both artificially synthesized speech data and real‐world speech data, which show the effectiveness of our approach.

The purpose of this paper is to propose a robust correntropy assisted blind channel estimator for multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) for improved channel gains estimation and channel ordering and sign ambiguities resolution in non-Gaussian noise channel.

The correntropy independent component analysis with L₁-norm cost function is used for blind channel estimation. Then a correntropy-based method is formulated to resolve the sign and order ambiguities of the channel estimates.

Simulation study on Gaussian noise scenario shows that the proposed method achieves almost the same performance as the conventional L₂-norm based method. However, in non-Gaussian noise scenarios performance of the proposed method significantly outperforms the conventional and other popular estimators in terms of mean square error (MSE). To solve the ordering and sign ambiguities problems, an auto-correntropy-based method is proposed and compared with the extended cross-correlation-based method. Simulation study shows improved performance of the proposed method in terms of MSE.

This paper presents for the first time, a correntropy-based blind channel estimator for MIMO-OFDM as well as simulated comparison results with traditional correlation-based methods in non-Gaussian noise environment.

New approaches for non‐classical neural‐based computing are introduced. The developed approaches utilize new concepts in three‐dimensionality, invertibility and reversibility to perform the required neural computing. The various implementations of the new neural circuits using the introduced paradigms and architectures are presented, several applications are shown, and the extension for the utilization in neural‐systolic computing is also introduced.

The new neural paradigms utilize new findings in computational intelligence and advanced logic synthesis to perform the functionality of the basic neural network (NN). This includes the techniques of three‐dimensionality, invertibility and reversibility. The extension of implementation to neural‐systolic computing using the introduced reversible neural‐systolic architecture is also presented.

Novel NN paradigms are introduced in this paper. New 3D paradigm of NL circuits called three‐dimensional inverted neural logic (3DINL) circuits is introduced. The new 3D architecture inverts the inputs and weights in the standard neural architecture: inputs become bases on internal interconnects, and weights become leaves of the network. New reversible neural network (RevNN) architecture is also introduced, and a RevNN paradigm using supervised learning is presented. The applications of RevNN to multiple‐output feedforward discrete plant control and to reversible neural‐systolic computing are also shown. Reversible neural paradigm that includes reversible neural architecture utilizing the extended mapping technique with an application to the reversible solution of the maze problem using the reversible counterpropagation NN is introduced, and new neural paradigm of reversibility in both architecture and training using reversibility in independent component analysis is also presented.

Since the new 3D NNs can be useful as a possible optimal design choice for compacting a learning (trainable) circuit in 3D space, and because reversibility is essential in the minimal‐power computing as the reduction of power consumption is a main requirement for the circuit synthesis of several emerging technologies, the introduced methods for non‐classical neural computation are new and interesting for the design of several future technologies that require optimal design specifications such as three‐dimensionality, regularity, super‐high speed, minimum power consumption and minimum size such as in low‐power control, adiabatic signal processing, quantum computing, and nanotechnology.

The purpose of this paper is to propose a noise identification method for data without temporal structure, in which application of typical mathematical white or colored noise models is very limited due to observation order requirements. The method is used to identify the destructive elements and to eliminate them what finally brings prediction improvement.

The paper concerns noise detection problem presented in the framework of ensemble methods via blind signals separation. The authors utilize the Extended Generalized Lambda Distribution (EGLD) model to compare the signals with the target.

The authors proposed novel signals similarity measure which is based on the EGLD system. The authors showed that it can be applied for data with or without time structure, as well as for data which are mutually uncorrelated. It turned out that method is effective for noise identification and can be an alternative, in many cases, to correlation approach, particularly for noise identification problems.

In this method the improvement of prediction results is associated with elimination of the real physical factors rather than mathematical averaging in terms of arbitrary assumed distributions. In this approach, it does not matter what is the structure of aggregated models, what significantly distinct this approach from such techniques as boosting or bagging, in which the aggregation process applies to the models of similar structure. For this reason the methodology is focussed on physical noises elimination from predictions and it is complementary to the other ensemble approaches.

The main aim of this paper is to design a technique for improving the quality of EEG signal by removing artefacts which is obtained during acquisition. Initially, pre-processing is done on EEG signal for quality improvement. Then, by using wavelet transform (WT) feature extraction is done. The artefacts present in the EEG are removed using deep convLSTM. This deep convLSTM is trained by proposed fractional calculus based flower pollination optimisation algorithm.

Nowadays' EEG signals play vital role in the field of neurophysiologic research. Brain activities of human can be analysed by using EEG signals. These signals are frequently affected by noise during acquisition and other external disturbances, which lead to degrade the signal quality. Denoising of EEG signals is necessary for the effective usage of signals in any application. This paper proposes a new technique named as flower pollination fractional calculus optimisation (FPFCO) algorithm for the removal of artefacts from EEG signal through deep learning scheme. FPFCO algorithm is the integration of flower pollination optimisation and fractional calculus which takes the advantages of both the flower pollination optimisation and fractional calculus which is used to train the deep convLSTM. The existed FPO algorithm is used for solution update through global and local pollinations. In this case, the fractional calculus (FC) method attempts to include the past solution by including the second order derivative. As a result, the suggested FPFCO algorithm approaches the best solution faster than the existing flower pollination optimization (FPO) method. Initially, 5 EEG signals are contaminated by artefacts such as EMG, EOG, EEG and random noise. These contaminated EEG signals are pre-processed to remove baseline and power line noises. Further, feature extraction is done by using WT and extracted features are applied to deep convLSTM, which is trained by proposed fractional calculus based flower pollination optimisation algorithm. FPFCO is used for the effective removal of artefacts from EEG signal. The proposed technique is compared with existing techniques in terms of SNR and MSE.

The proposed technique is compared with existing techniques in terms of SNR, RMSE and MSE.

100%.