EMD与自适应滤波相结合的语音增强法

为了提高语音信号的信噪比,提出一种经验模态分解与自适应滤波相结合的语音增强法。对带噪语音进行经验模态分解,得到有限个固有模态函数,把所有的固有模态函数按顺序分成三组,将每一组所包含的固有模态函数叠加,得到三个子信号;对三个子信号进行自适应滤波,消除噪声;将降噪后的子信号重构得到增强后的语音。仿真实验表明,所提方法的语音增强效果优于自适应滤波。     

Closed-form unbiased frequency estimation of a noisy sinusoid using notch filters

In this note, the problem of the frequency estimation of a sinusoid embedded in white noise is considered. The approach used herein is the minimization of the sample variance of the output of constrained notch filters fed by the noisy sinusoid. In particular, this note focuses on closed-form expressions of the frequency estimate, which can be obtained using notch filters having an all-zeros finite-impulse response (FIR) structure. The results presented in this note are as follows: 1) it is shown that the FIR notch filters obtained from standard second-order infinite-impulse response (IIR) filters are inadequate; 2) a new second-order IIR notch filter is proposed, which provides an unbiased estimate of the frequency; 3) the FIR filter obtained from the new IIR filter provides a closed-form unbiased frequency estimate; and 4) the closed-form frequency estimate obtained using the new FIR notch filter asymptotically converges toward the Pisarenko harmonic decomposition estimator and the Yule-Walker estimator.     

Discrete time neural network synthesis using input and outputactivation functions

A new very fast algorithm for synthesis of a new structure of discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) combination of input and output activation functions, (ii) input time-varying signal distribution, (iii) time-discrete domain synthesis and (iv) one-step learning iteration approach. The problem of input-output mappings of time-varying vectors is solved. Simulation results based on the synthesis of a new structure of feedforward NN of an universal logical unit are presented. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems. In this sense a feedforward NN for an adaptive nonlinear robot control is designed. Finally, a new algorithm for the direct inverse modeling of input/output nonquadratic systems is discussed.     

A Simple Neural Network Pruning Algorithm with Application to Filter Synthesis

This paper describes an approach to synthesizing desired filters using a multilayer neural network (NN). In order to acquire the right function of the object filter, a simple method for reducing the structures of both the input and the hidden layers of the NN is proposed. In the proposed method, the units are removed from the NN on the basis of the influence of removing each unit on the error, and the NN is retrained to recover the damage of the removal. Each process is performed alternately, and then the structure is reduced. Experiments to synthesize a known filter were performed. By the analysis of the NN obtained by the proposed method, it has been shown that it acquires the right function of the object filter. By the experiment to synthesize the filter for solving real signal processing tasks, it has been shown that the NN obtained by the proposed method is superior to that obtained by the conventional method in terms of the filter performance and the computational cost.     

Linear dynamic filtering with noisy input and output

State estimation problems for linear time-invariant systems with noisy inputs and outputs are considered. An efficient recursive algorithm for the smoothing problem is presented. The equivalence between the optimal filter and an appropriately modified Kalman filter is established. The optimal estimate of the input signal is derived from the optimal state estimate. The result shows that the noisy input/output filtering problem is not fundamentally different from the classical Kalman filtering problem.     

The use of the Taguchi method with grey relational analysis and a neural network to optimize a novel GMA welding process

The objective of this paper is to present an integrated approach using the Taguchi method (TM), grey relational analysis (GRA) and a neural network (NN) to optimize the weld bead geometry in a novel gas metal arc (GMA) welding process. The TM is first used to construct a database for the NN. The GRA is adopted to solve the problem of multiple performance characteristics in a GMA welding process using activating flux. The grey relational grade obtained from the GRA is used as the output of the back-propagation (BP) NN. Then, a NN with the Levenberg-Marquardt BP (LMBP) algorithm is used to provide the nonlinear relationship between welding parameters and grey relational grade of each weldment. The optimal parameters of the novel GMA welding process were determined by simulating parameters using a well-trained BPNN model. Experimental results illustrate the proposed approach.     

Speech enhancement based on perceptual filter bank improvement

In this paper, a new denoising approach is presented based on perceptual analysis. The noisy signal is split by a gammatone filterbank with nonlinear frequency distributions according to ERB scale. The frequency masking threshold is calculated in each sub-band according to the Johnston model in the output of the Wiener filter. This threshold is then used in the gain function given by the perceptual filter. The evaluation tests are performed by using objective criterion including perceptual evaluation of speech quality as well as subjective criterion including mean opinion score. Obtained results show that the proposed method achieves best results in terms of quality and intelligibility of enhanced signal.     

Adaptive neural network output feedback control of stochastic nonlinear systems with dynamical uncertainties

In this paper, a robust adaptive neural network (NN) backstepping output feedback control approach is proposed for a class of uncertain stochastic nonlinear systems with unknown nonlinear functions, unmodeled dynamics, dynamical uncertainties and without requiring the measurements of the states. The NNs are used to approximate the unknown nonlinear functions, and a filter observer is designed for estimating the unmeasured states. To solve the problem of the dynamical uncertainties, the changing supply function is incorporated into the backstepping recursive design technique, and a new robust adaptive NN output feedback control approach is constructed. It is mathematically proved that the proposed control approach can guarantee that all the signals of the resulting closed-loop system are semi-globally uniformly ultimately bounded in probability, and the observer errors and the output of the system converge to a small neighborhood of the origin by choosing design parameters appropriately. The simulation example and comparison results further justify the effectiveness of the proposed approach.     

An enhanced empirical wavelet transform for noisy and non-stationary signal processing

As an alternative method of empirical mode decomposition (EMD), the empirical Wavelet transform (EWT) method was proposed to realize the signal decomposition by constructing an adaptive filter bank. Though the EWT method has been demonstrated its effectiveness in some applications, it becomes invalid in analyzing some noisy and non-stationary signals due to its improper segmentation in the frequency domain. In this paper, an enhanced empirical wavelet transform method is proposed. This method takes advantage of the waveform in the frequency domain of a signal to eliminate drawbacks of the EWT method in the spectrum segmentation. It modifies the segmentation algorithm by adopting the envelope approach based on the order statistics filter (OSF) and applying criteria to pick out useful peaks. With these measures, the proposed method obtains a perfect segmentation in decomposing noisy and non-stationary signals. Furthermore, simulated and experimental signals are used to verify the effectiveness of the proposed method.     

Learning neural networks with noisy inputs using theerrors-in-variables approach

Currently, most learning algorithms for neural-network modeling are based on the output error approach, using a least squares cost function. This method provides good results when the network is trained with noisy output data and known inputs. Special care must be taken, however, when training the network with noisy input data, or when both inputs and outputs contain noise. This paper proposes a novel cost function for learning NN with noisy inputs, based on the errors-in-variables stochastic framework. A learning scheme is presented and examples are given demonstrating the improved performance in neural-network curve fitting, at the cost of increased computation time.     

EMGdi signal enhancement based on ICA decomposition and wavelet transform

Diaphragmatic electromyogram (EMGdi) signal plays an important role in the diagnosis and analysis of respiratory diseases. However, EMGdi recordings are often contaminated by electrocardiographic (ECG) interference, which posing serious obstacle to traditional denoising approaches due to overlapped spectra of these signals. In this paper, a novel method based on wavelet transform and independent component analysis (ICA) is proposed to remove the ECG interference from noisy EMGdi signals. With the proposed method, the original independent components of contaminated EMGdi signal were first obtained with ICA. Then the ECG components contained were removed by a specially designed wavelet domain filter. After that, the purified independent components were reconstructed back to the original signal space by ICA to obtain clean EMGdi signals. Experimental results achieved on practical clinical data show that the proposed approach is better than several traditional methods include wavelet transform (WT), ICA, digital filter and adaptive filter in ECG interference removing.     

Novel L1 neural network adaptive control architecture with guaranteed transient performance.

In this paper, we present a novel neural network (NN) adaptive control architecture with guaranteed transient performance. With this new architecture, both input and output signals of an uncertain nonlinear system follow a desired linear system during the transient phase, in addition to stable tracking. This new architecture uses a low-pass filter in the feedback loop, which consequently enables to enforce the desired transient performance by increasing the adaptation gain. For the guaranteed transient performance of both input and output signals of the uncertain nonlinear system, the L1 gain of a cascaded system, comprised of the low-pass filter and the closed-loop desired reference model, is required to be less than the inverse of the Lipschitz constant of the unknown nonlinearities in the system. The tools from this paper can be used to develop a theoretically justified verification and validation framework for NN adaptive controllers. Simulation results illustrate the theoretical findings.     

Multiple model-based event-triggered adaptive control of a class of discrete-time nonlinear systems

In this study, the problem of event-triggered-based adaptive control (ETAC) for a class of discrete-time nonlinear systems with unknown parameters and nonlinear uncertainties is considered. Both neural network (NN) based and linear identifiers are used to approximate the unknown system dynamics. The feedback output signals are transmitted, and the parameters and the NN weights of the identifiers are tuned in an aperiodic manner at the event sample instants. A switching mechanism is provided to evaluate the approximate performance of each identifier and decide which estimated output is utilised for the event-triggered controller design, during any two events. The linear identifier with an auxiliary output and an improved adaptive law is introduced so that the nonlinear uncertainties are no longer assumed to be Lipschitz. The number of transmission times are significantly reduced by incorporating multiple model schemes into ETAC. The boundedness of both the parameters of identifiers and the system outputs is demonstrated though the Lyapunov approach. Simulation results demonstrate the effectiveness of the proposed method.     

Identification of stochastic linear systems in presence of input noise

Most identification methods rely on the assumption that the input is known exactly. However, when collecting data under an identification experiment it may not be possible to avoid noise when measuring the input signal. In the paper some different ways to identify systems from noisy data are discussed. Sufficient conditions for identifiability are given. Also accuracy properties and the computational requirements are discussed. A promising approach is to treat the measured input and output signals as outputs of a multivariable stochastic system. If a prediction error method is applied using this approach the system will be identifiable under mild conditions.     

Learning from hint for the conservative motion of the constrained industrial redundant manipulators

A neural network (NN)-based kinematic inversion of industrial redundant arms is developed in this paper to conserve the joint configuration in cyclic trajectories. In the developed approach, the Widrow–Hoff NN with an online adaptive learning algorithm derived by applying Lyapunov approach is introduced. Since this kinematic inversion has an infinite number of joint angle vectors, a fuzzy neural network system is designed to provide an approximate value for that vector. Feeding this vector as an additional hint input vector to the NN limits and guides the output of the NN within the self-motion of the manipulator. The derivation of the candidate Lyapunov function, which is designed to achieve the joint configurations conservation in addition to the joint limits avoidance, leads to a computationally efficient online learning algorithm of the NN. Simulations are conducted for the PA-10 redundant manipulator to bear out the efficacy of the developed approach for tracking closed trajectories.     

On the Importance of the Pearson Correlation Coefficient in Noise Reduction

Noise reduction, which aims at estimating a clean speech from noisy observations, has attracted a considerable amount of research and engineering attention over the past few decades. In the single-channel scenario, an estimate of the clean speech can be obtained by passing the noisy signal picked up by the microphone through a linear filter/transformation. The core issue, then, is how to find an optimal filter/transformation such that, after the filtering process, the signal-to-noise ratio (SNR) is improved but the desired speech signal is not noticeably distorted. Most of the existing optimal filters (such as the Wiener filter and subspace transformation) are formulated from the mean-square error (MSE) criterion. However, with the MSE formulation, many desired properties of the optimal noise-reduction filters such as the SNR behavior cannot be seen. In this paper, we present a new criterion based on the Pearson correlation coefficient (PCC). We show that in the context of noise reduction the squared PCC (SPCC) has many appealing properties and can be used as an optimization cost function to derive many optimal and suboptimal noise-reduction filters. The clear advantage of using the SPCC over the MSE is that the noise-reduction performance (in terms of the SNR improvement and speech distortion) of the resulting optimal filters can be easily analyzed. This shows that, as far as noise reduction is concerned, the SPCC-based cost function serves as a more natural criterion to optimize as compared to the MSE.     

Real-time torque control using discrete-time recurrent high-order neural networks

This paper presents a discrete-time direct current (DC) motor torque tracking controller, based on a recurrent high-order neural network to identify the plant model. In order to train the neural identifier, the extended Kalman filter (EKF) based training algorithm is used. The neural identifier is in series-parallel configuration that constitutes a well approximation method of the real plant by the neural identifier. Using the neural identifier structure that is in the nonlinear controllable form, the block control (BC) combined with sliding modes (SM) control techniques in discrete-time are applied. The BC technique is used to design a nonlinear sliding manifold such that the resulting sliding mode dynamics are described by a desired linear system. For the SM control technique, the equivalent control law is used in order to the plant output tracks a reference signal. For reducing the effect of unknown terms, it is proposed a specific desired dynamics for the sliding variables. The control problem is solved by the indirect approach, where an appropriate neural network (NN) identification model is selected; the NN parameters (synaptic weights) are adjusted according to a specific adaptive law (EKF), such that the response of the NN identifier approximates the response of the real plant for the same input. Then, based on the designed NN identifier a stabilizing or reference tracking controller is proposed (BC combined with SM). The proposed neural identifier and control applicability are illustrated by torque trajectory tracking for a DC motor with separate winding excitation via real-time implementation.     

Cuckoo search (CS)-NFC-based UPQC for compensating voltage sag of nonlinear load

In this paper, a cuckoo search (CS) algorithm-based neuro-fuzzy controller (NFC) is developed to improve the performance of unified power quality conditioner (UPQC). The CS algorithm is used for optimising the output of neural network (NN) so that the classification output of the NN is enhanced. The inputs of the networks are error and change of error voltage of the PQ issue signal of nonlinear load which are calculated by comparison with the reference signal. Next, the output of network, i.e. regulated (compensated) voltage, is optimised by the CS algorithm. From the output of CS, an optimum rule-based fuzzy interference system is developed and the PQ problem is compensated. The CS-NFC-based UPQC is implemented in MATLAB/Simulink and the PQ issue clearing performance is analysed. The PQ issue clearing performance of proposed UPQC is compared with traditional UPQC, NFC-UPQC, GA-NFC-UPQC and adaptive GA-NFC-UPQC. The CS-NFC-based UPQC controller has lesser error deviation of 2.8% with traditional UPQC, 2.12% with NFC, 1.7% with GA-NFC and 0.6% with adaptive GA-NFC.     

Intelligent methods for solving inverse problems of backscattering spectra with noise: a comparison between neural networks and simulated annealing

This paper investigates two different intelligent techniques—the neural network (NN) method and the simulated annealing (SA) algorithm for solving the inverse problem of Rutherford backscattering (RBS) with noisy data. The RBS inverse problem is to determine the sample structure information from measured spectra, which can be defined as either a function approximation or a non-linear optimization problem. Early studies emphasized on numerical methods and empirical fitting. In this work, we have applied intelligent techniques and compared their performance and effectiveness for spectral data analysis by solving the inverse problem. Since each RBS spectrum may contain up to 512 data points, principal component analysis is used to make the feature extraction so as to ease the complexity of constructing the network. The innovative aspects of our work include introducing dimensionality reduction and noise modeling. Experiments on RBS spectra from SiGe thin films on a silicon substrate show that the SA is more accurate but the NN is faster, though both methods produce satisfactory results. Both methods are resilient to 10% Poisson noise in the input. These new findings indicate that in RBS data analysis the NN approach should be preferred when fast processing is required; whereas the SA method becomes the first choice should the analysis accuracy be targeted.     

Optimizing the auto-brazing process quality of aluminum pipe and flange via a Taguchi-Neural-Genetic approach

This work describes an application of an integrated approach using the Taguchi method (TM), neural network (NN) and genetic algorithm (GA) for optimizing the lap joint quality of aluminum pipe and flange in automotive industry. The proposed approach (Taguchi-Neural-Genetic approach) consists of two phases. In first phase, the TM was adopted to collect training data samples for the NN. In second phase, a NN with a Levenberg-Marquardt back-propagation (LMBP) algorithm was adopted to develop the relationship between factors and the response. Then, a GA based on a well-trained NN model was applied to determine the optimal factor settings. Experimental results illustrated the Taguchi-Neural-Genetic approach.