A maximum noise fraction transform with improved noise estimation for hyperspectral images

Feature extraction is often performed to reduce spectral dimension of hyperspectral images before image classification. The maximum noise fraction （MNF） transform is one of the most commonly used spectral feature extraction methods. The spectral features in several bands of hyperspectral images are submerged by the noise. The MNF transform is advantageous over the principle component （PC） transform because it takes the noise information in the spatial domain into consideration. However, the experiments described in this paper demonstrate that classification accuracy is greatly influenced by the MNF transform when the ground objects are mixed together. The underlying mechanism of it is revealed and analyzed by mathematical theory. In order to improve the performance of classification after feature extraction when ground objects are mixed in hyperspectral images, a new MNF transform, with an improved method of estimating hyperspectral image noise covariance matrix （NCM）, is presented. This improved MNF transform is applied to both the simulated data and real data. The results show that compared with the classical MNF transform, this new method enhanced the ability of feature extraction and increased classification accuracy.

Carrier frequency offset and impulse noise estimation for underwater acoustic orthogonal frequency division multiplexing

The carrier frequency offset（CFO）and impulse noise always affect the performance of underwater acoustic communication_systems.The CFO and impulse noise could be estimated by using the null subcarriers to cancel the effects of the two types of interference.The null subcarriers estimation methods include optimal separate estimation and joint estimation.The separate estimation firstly estimates the CFO value and then estimates the impulse noise value.However,the CFO and impulse noise always affect each other when either of them is estimated separately.The performance could be improved by using the joint estimation.The results of simulations and experiments have showed that these two optimization methods have good performance and the joint estimation has better performance than the separate estimation method.There is 3 dB performance gain at the BER value of 10^（-2）when using the joint estimation method.Thus these methods could improve the system robustness by using the CFO compensation and impulse noise suppression.

Noise estimation for deep sub-micron integrated circuits

Noise analysis and avoidance are an increasingly critical step in the design of deep sub-micron (DSM) integrated circuits (ICs). The crosstalk between neighboring interconnects gradually becomes the main noise sources in DSM ICs. We introduce an efficient and accurate noise-evaluation method for capacitively coupled nets of ICs. The method holds for a victim net with arbitrary number of aggressive nets under ramp input excitation. For common RC nets extracted by electronic design au-tomation (EDA) tools, the deviation between our method and HSPICE is under 10% .

Automatic estimation and removal of noise on digital image

An spatially adaptive noise detection and removal algorithm is proposed.Under the assumption that an observed image and its additive noise have Gaussian distribution,the noise parameters are estimated with local statistics from an observed degraded image,and the parameters are used to define the constraints on the noise detection process.In addition,an adaptive low-pass filter having a variable filter window defined by the constraints on noise detection is used to control the degree of smoothness of the reconstructed image.Experimental results demonstrate the capability of the proposed algorithm.

Noise level estimation method with application to EMD-based signal denoising

This paper proposes a new signal noise level estimation approach by local regions. The estimated noise variance is applied as the threshold for an improved empirical mode decomposition（EMD） based signal denoising method. The proposed estimation method can effectively extract the candidate regions for the noise level estimation by measuring the correlation coefficient between noisy signal and a Gaussian filtered signal. For the improved EMD based method, the situation of decomposed intrinsic mode function（IMFs） which contains noise and signal simultaneously are taken into account. Experimental results from two simulated signals and an X-ray pulsar signal demonstrate that the proposed method can achieve better performance than the conventional EMD and wavelet transform（WT） based denoising methods.

Joint DOA and polarization estimation for unequal power sources based on reconstructed noise subspace

In most literature about joint direction of arrival（DOA） and polarization estimation, the case that sources possess different power levels is seldom discussed. However, this case exists widely in practical applications, especially in passive radar systems. In this paper, we propose a joint DOA and polarization estimation method for unequal power sources based on the reconstructed noise subspace. The invariance property of noise subspace（IPNS） to power of sources has been proved an effective method to estimate DOA of unequal power sources. We develop the IPNS method for joint DOA and polarization estimation based on a dual polarized array. Moreover, we propose an improved IPNS method based on the reconstructed noise subspace, which has higher resolution probability than the IPNS method. It is theoretically proved that the IPNS to power of sources is still valid when the eigenvalues of the noise subspace are changed artificially. Simulation results show that the resolution probability of the proposed method is enhanced compared with the methods based on the IPNS and the polarimetric multiple signal classification（MUSIC） method. Meanwhile, the proposed method has approximately the same estimation accuracy as the IPNS method for the weak source.

HMM-based noise estimator for speech enhancement

A noise estimator was presented in this paper by modeling the log-power sequence with hidden Markov model （HMM）. The smoothing factor of this estimator was motivated by the speech presence probability at each frequency band. This HMM had a speech state and a nonspeech state, and each state consisted of a unique Gaussian function. The mean of the nonspeech state was the estimation of the noise logarithmic power. To make this estimator run in an on-line manner, an HMM parameter updated method was used based on a first-order recursive process. The noise signal was tracked together with the HMM to be sequentially updated. For the sake of reliability, some constraints were introduced to the HMM. The proposed algorithm was compared with the conventional ones such as minimum statistics （MS） and improved minima controlled recursive averaging （IM- CRA）. The experimental results confirms its promising performance.

A new information fusion white noise deconvolution estimator

The white noise deconvolution or input white noise estimation problem has important applications in oil seismic exploration, communication and signal processing. By the modern time series analysis method, based on the autoregressive moving average （ARMA） innovation model, a new information fusion white noise deconvolution estimator is presented for the general multisensor systems with different local dynamic models and correlated noises. It can handle the input white noise fused filtering, prediction and smoothing problems, and it is applicable to systems with colored measurement noises. It is locally optimal, and is globally suboptimal. The accuracy of the fuser is higher than that of each local white noise estimator. In order to compute the optimal weights, the formula computing the local estimation error cross-covariances is given. A Monte Carlo simulation example for the system with Bernoulli-Gaussian input white noise shows the effectiveness and performances.

Influence of the environmental noise on determining the period of a torsion pendulum

The environmental noise can restrict the accuracy of period estimation since the torsion pendulum is sensitive to weak forces. Two typical models for the environmental noise are proposed to make an evaluation. Generally, the stationary environmental noise is modeled as a white noise, and contributes to the period uncertainty as a function of the initial amplitude, the quality factor, the variance of noise and the time length. As to a sudden sharp disturbance acting on the pendulum, a narrow impulse model is constructed. It results in a sharp jump in the phase difference, which can be excluded with the 3σ criterion for a correction. An experimental data analysis for the measurement of the gravitational constant G with the time-of-swing method shows that the period uncertainty due to the environmental noise is about one and a half times the fundamental thermal noise limit. Though this result is dependent on the ambient environment, the analysis is instructive to improve the measurement accuracy of experiments.

Self-tuning weighted measurement fusion Kalman filter and its convergence

For multisensor systems,when the model parameters and the noise variances are unknown,the consistent fused estimators of the model parameters and noise variances are obtained,based on the system identification algorithm,correlation method and least squares fusion criterion.Substituting these consistent estimators into the optimal weighted measurement fusion Kalman filter,a self-tuning weighted measurement fusion Kalman filter is presented.Using the dynamic error system analysis （DESA） method,the convergence of the self-tuning weighted measurement fusion Kalman filter is proved,i.e.,the self-tuning Kalman filter converges to the corresponding optimal Kalman filter in a realization.Therefore,the self-tuning weighted measurement fusion Kalman filter has asymptotic global optimality.One simulation example for a 4-sensor target tracking system verifies its effectiveness.

Decoupled Wiener state fuser for descriptor systems

By the modem time series analysis method, based on the autoregressive moving average （ARMA） innovation models and white noise estimation theory, using the optimal fusion rule weighted by diagonal matrices, a distributed descriptor Wiener state fuser is presented by weighting the local Wiener state estimators for the linear discrete stochastic descriptor systems with multisensor. It realizes a decoupled fusion estimation for state components. In order to compute the optimal weights, the formulas of computing the cross-covariances among local estimation errors are presented based on cross-covariances among the local innovation processes, input white noise, and measurement white noises. It can handle the fused filtering, smoothing, and prediction problems in a unified framework. Its accuracy is higher than that of each local estimator. A Monte Carlo simulation example shows its effectiveness and correctness.

The frequency estimation of harmonic signals embedded in multiplicative and additive noise

A method to separate a harmonic signal from multiplicative and additive noises is proposed. The method is to square the signal x(t), which consists of a harmonic signal embedded in multiplicative and additive noises, to form another signal y(t) = x2(t)-E[x2(t)]. After y(t) having been gotten, the Fourier transform is imposed on it. Because the information of x(t) (especially about frequency) is included in y(t), the frequency of x(t) can be estimated from the power spectrum of y(t). According to the simulation, under the condition where frequencies divided by resolution dω are integer, the maximum relative error of estimated frequencies is less than 0.4% when the signal-to-noise ratio (SNR) is greater than -23 dB. If frequencies divided by resolution dω are not integer, the maximum relative error will be less than 2.9%. But it is still small in terms of engineering.

A novel approach of noise statistics estimate using H_∞ filter in target tracking

Noise statistics are essential for estimation performance. In practical situations, however, a priori information of noise statistics is often imperfect. Previous work on noise statistics identification in linear systems still requires initial prior knowledge of the noise. A novel approach is presented in this paper to solve this paradox.First, we apply the H_∞ filter to obtain the system state estimates without the common assumptions about the noise in conventional adaptive filters. Then by applying state estimates obtained from the H_∞ filter, better estimates of the noise mean and covariance can be achieved, which can improve the performance of estimation. The proposed approach makes the best use of the system knowledge without a priori information with modest computation cost,which makes it possible to be applied online. Finally, numerical examples are presented to show the efficiency of this approach.

Distributed fusion white noise deconvolution estimators

The white noise deconvolution or input white noise estimation problem has important applications in oil seismic exploration,communication and signal processing.By combining the Kalman filtering method with the modern time series analysis method,based on the autoregressive moving average(ARMA)innovation model,new distributed fusion white noise deconvolution estimators are presented by weighting local input white noise estimators for general multisensor systems with different local dynamic models and correlated noises.The new estimators can handle input white noise fused filtering,prediction and smoothing problems,and are applicable to systems with colored measurement noise.Their accuracy is higher than that of local white noise deconvolution estimators.To compute the optimal weights,the new formula for local estimation error cross-covariances is given.A Monte Carlo simulation for the system with Bernoulli-Gaussian input white noise shows their effectiveness and performance.

Scanning paths for estimating sound power of noise sources by sound intensity scanning method

A mathematical model of deterndulng sound power by using the scanning method is developed. It is assumed that the scanning speed is constant and the noise source is stationary The accuracy of estimating sound power along some simple paths on the surfaces such as rectangle, disc and hemisphere is analyzed. It is argued that the accuracy of estimating sound power is strongly depended on a suitable selection of scan path. The accurate estdriation of sound power can be made by scanning along some simple paths.

No-reference noisy image quality assessment incorporating features of entropy, gradient, and kurtosis

Noise is the most common type of image distortion affecting human visual perception.In this paper,we propose a no-reference image quality assessment(IQA)method for noisy images incorporating the features of entropy,gradient,and kurtosis.Specifically,image noise estimation is conducted in the discrete cosine transform domain based on skewness invariance.In the principal component analysis domain,kurtosis feature is obtained by statistically counting the significant differences between images with and without noise.In addition,both the consistency between the entropy and kurtosis features and the subjective scores are improved by combining them with the gradient coefficient.Support vector regression is applied to map all extracted features into an integrated scoring system.The proposed method is evaluated in three mainstream databases(i.e.,LIVE,TID2013,and CSIQ),and the results demonstrate the superiority of the proposed method according to the Pearson linear correlation coefficient which is the most significant indicator in IQA.