Estimation Of Noise Statistics Research Articles

Adaptive UKF Filtering Algorithm Based on Maximum a Posterior Estimation and Exponential Weighting

摘要: 针对传统Unscented卡尔曼滤波器(Unscented Kalman filter, UKF)在噪声先验统计未知时变情况下非线性滤波精度下降甚至发散的问题, 设计了一种带噪声统计估计器的自适应UKF滤波算法. 首先根据极大后验(Maximum a posterior, MAP)估计原理, 推导出一种次优无偏MAP常值噪声统计估计器; 接着在此基础之上, 采用指数加权的方法, 给出了时变噪声统计估计器的递推公式; 最后对自适应UKF算法进行了性能分析. 相比于传统UKF, 该自适应UKF算法在噪声统计未知时变情况下不仅滤波依然收敛, 滤波精度及稳定性显著提高, 而且其具有应对噪声变化的自适应能力. 仿真实例验证了其有效性. 关键词: 非线性 / 自适应UKF滤波算法 / 常值噪声统计估计器 / 时变噪声统计估计器 / 极大后验估计 / 指数加权

Self-tuning measurement fusion white noise deconvolution estimator with correlated noises

For the multisensor linear discrete time-invariant stochastic systems with correlated noises and unknown noise statistics, an on-line noise statistics estimator is presented by using the correlation method. Substituting it into the steady-state Riccati equation, the self-tuning Riccati equation is obtained. Using the Kalman filtering method, based on the self-tuning Riccati equation, a self-tuning weighted measurement fusion white noise deconvolution estimator is presented. By the dynamic error system analysis (DESA) method, it is proved that the self-tuning fusion white noise deconvolution estimator converges to the optimal fusion steady-state white noise deconvolution estimator in a realization, so that it has the asymptotic global optimality. A simulation example for Bernoulli-Gaussian input white noise shows its effectiveness.

Adaptive Noise Mitigation in Impulsive Environment: Application to Power-Line Communications

In this paper, we address the general issue of asynchronous impulsive noise mitigation and its application over coded power-line communications (PLC). As is well known, PLC channels usually suffer from significant degradation due to impulsive interference generated by electrical appliances. The use of a level limiter is a simple and intuitive technique, widely used to mitigate the noxious effect of impulsive noise in these channels. However, the determination of the clipping threshold remains, most of the time, empirical, and the impulse statistics are usually assumed to be known. In a previous study, we proposed an original threshold determination based on signal detection theory, using the well-known false alarm and good detection tradeoff. Here, we further investigate the proposed optimization method in closed form. We compare two tradeoff criteria by means of a receiver operating curves analysis. We clearly show that the resulting decision fits well with encountered bit-error rate performances. We also evaluate the influence of impulsive noise statistics estimation on the performance of the proposed approach. To do so, we assess the robustness of the classical method of moments on Gaussian mixture estimation. It clearly appears that the estimation method is reliable for reasonable values of the impulse occurrence. As one of the main results of this paper, we make a proposal for impulse statistics estimation under ¿severe¿ conditions (i.e., for very rare impulse events, based on impulse detection over corrupted OFDM symbols). Subsequently, we propose a general scheme of automatic impulse mitigation, according to the disturbance ratio of the environment. Finally, the performance of the approach is evaluated over the Home-Plug AV (HPAV) physical layer.

Self-tuning weighted measurement fusion white noise deconvolution estimator

For the multi-sensor linear discrete time-invariant stochastic systems with correlated measurement noises and unknown noise statistics, an on-line noise statistics estimator is obtained using the correlation method. Substituting it into the optimal weighted fusion steady-state white noise deconvolution estimator based on the Kalman filtering, a self-tuning weighted measurement fusion white noise deconvolution estimator is presented. By the Dynamic Error System Analysis (DESA) method, it proved that the self-tuning fusion white noise deconvolution estimator converges to the steady-state optimal fusion white noise deconvolution estimator in a realization. Therefore, it has the asymptotically global optimality. A simulation example for the tracking system with 3 sensors and the Bernoulli-Gaussian input white noise shows its effectiveness.

Noise-Adaptive Soft Sensors in Mobile Robots through Particle Filtering

AbstractThe assumption of constant noise and requirement of prior calibration can limit the effectiveness of sensor fusion in mobile robot applications. This paper uses techniques from particle filtering parameter estimation research to construct a novel noise-adaptive particle filter which can provide on-line estimation of both robot state and noise statistics, in the presence of initially unknown and time-varying noise. The noise-adaptive particle filter augments its state with the noise relevant statistics and then artificially evolves these during on-line estimation to adapt to changing levels of noise. A simulated global localization problem is used to demonstrate the filter effectiveness against a traditional particle filter and results show it has comparable performance while requiring less initial calibration and fewer direct assumptions. Several techniques from parameter estimation literature are then considered, to reduce the filter computational complexity and inherent limitations.

Optimal sensor placement in highly variable noise fields to increase detection

Ambient noise (AN) is highly variable in littoral environments. AN predictions are often smoothed to produce mean estimates in support of signal detection. In a complex AN environment, the optimal placement of sensors for detection also depends on the spatial and temporal variance of AN. The recent development of the Dynamic Ambient Noise Model (DANM) allows accurate, detailed estimation of noise statistics. DANM was used to produce space- and time series of directional noise based on discrete ship tracks. This work describes a fast optimization scheme that exploits nonhomogeneous noise variability to select optimal locations that maximize detection. A standard, nonoptimal approach for choosing locations is sequential and myopic. A better approach is combinatorial; i.e., consider all possible sensor sets and choose the best. This optimal approach is often computationally prohibitive. Brown’s iterative algorithm combines elements of both algorithm types to achieve rapid results. Brown’s algorithm was modified and used to demonstrate the importance of nonhomogeneous noise statistics. The results show a significant improvement in probability of detection when DANM AN statistics are considered while choosing optimal sensor locations. This work has application to design of optimal sonobuoy field patterns. [Work sponsored by ONR under the LADC project.]

Negentropy based voice-activity detection for noise estimation in very low SNR condition

The spectral organization in a noisy speech is different during noise-only portions and speech portions. Such chaotic difference can be tracked by using negentropy as a measure. Accordingly, a Voice Activity Detector (VAD) based on the negentropy measure of magnitude of spectral components of the pseudo-stationary segments of speech is proposed and has been used for the estimation of noise statistics from the noisy speech signal in very low SNR conditions. The results show the effectiveness and usefulness of the proposed method under very noisy conditions.

CFAR adaptive threshold for ESM receiver with logarithmic amplification

An adaptive threshold with constant false alarm rate (CFAR) property is proposed to be used in a channelized electronic support measures (ESM) system with logarithmic video amplification. For this purpose, two CFAR processors are designed which are in fact modified excision (MEx) and adaptive MEx (AMEx) processors, previously presented by authors, but modified for the logarithmic amplification case. In the case of relatively small variations in the noise power, MEx-LOG/CFAR is proposed. This processor exhibits a good robustness against interfering pulses, which cause the major difficulty in the estimation of noise statistics. In the case of relatively large variations in the noise power, AMEx-LOG/CFAR processor is proposed. Thanks to a feedback loop in its structure, this processor can easily adapt itself with any change in the background noise power to assure the CFAR property and false alarm rate regulation. Furthermore, in the steady state (constant noise power), its detection performance is independent of the noise power. Methods to determine the design parameters of the proposed processors are discussed, and their performance analysis is studied using Monte Carlo simulations.

Systematic estimation of state noise statistics for extended Kalman filters

AbstractThe successful application of model‐based control depends on the information about the states of the dynamic system. State‐estimation methods, like extended Kalman filters (EKF), are useful for obtaining reliable estimates of the states from a limited number of measurements. They also can handle the model uncertainties and the effect of unmeasured disturbances. The main issue in applying EKF remains that one needs to specify the confidence in the model in terms of process noise covariance matrix. The information about the model uncertainties can effectively and systematically calculate the process noise covariance matrix for an EKF. Two systematic approaches are used for this calculation. The first is based on a Taylor series expansion of the nonlinear equations around the nominal parameter values, while the second accounts for the nonlinear dependence of the system on the fitted parameters by Monte Carlo simulations that can easily be performed on‐line. The value of the process noise covariance matrix obtained is not limited to a diagonal form and depends on the current state of the dynamic system. Thus the a‐priori information regarding the uncertainty in the model is utilized and the need for extensive tuning of the EKF is eliminated. The application of these techniques to example processes is also discussed. The accuracy of this methodology is compared very favorably with the traditional methods of trial‐and‐error tuning of EKF.

A DISTRIBUTION FUNCTION APPLICABLE TO OFFICE NOISE STUDY

Noise measurements were performed in 27 air-conditioned landscaped offices in the present investigation. From the measured equivalent sound pressure levels, percentile levels and noise level cumulative distributions, it is found that linear relationships exist between percentile levels and the equivalent sound pressure level. A new distribution function is proposed in the present study to describe the cumulative distribution as well as the probability density function of noise in air-conditioned landscaped offices. Higher order moments of the noise statistics can then be found. Results also enable the estimation of the above noise statistics from equivalent sound pressure levels and will be beneficial to the evaluation of existing offices and the setup of specifications for new commercial offices.

KALMAN FILTER ESTIMATION AND PREDICTION OF DAILY STREAM FLOWS: II. APPLICATION TO THE POTOMAC RIVER1

ABSTRACTResults are reported from an application of the state space formulation and the Kalman filter to real‐time forecasting of daily river flows. It is shown that the application of filtering techniques improves the overall forecasting performance of the model. As is true for most hydrologic systems, the model is not completely known. Therefore, the procedures pertaining to on‐line parameter and noise statistics estimation, as presented in the first paper, are implemented. The example in this paper shows that these techniques also perform satisfactorily when applied to a real‐world situation.