Showing papers on "Noise measurement published in 2018"

FFDNet: Toward a Fast and Flexible Solution for CNN-Based Image Denoising

Abstract: Due to the fast inference and good performance, discriminative learning methods have been widely studied in image denoising. However, these methods mostly learn a specific model for each noise level, and require multiple models for denoising images with different noise levels. They also lack flexibility to deal with spatially variant noise, limiting their applications in practical denoising. To address these issues, we present a fast and flexible denoising convolutional neural network, namely FFDNet, with a tunable noise level map as the input. The proposed FFDNet works on downsampled sub-images, achieving a good trade-off between inference speed and denoising performance. In contrast to the existing discriminative denoisers, FFDNet enjoys several desirable properties, including: 1) the ability to handle a wide range of noise levels (i.e., [0, 75]) effectively with a single network; 2) the ability to remove spatially variant noise by specifying a non-uniform noise level map; and 3) faster speed than benchmark BM3D even on CPU without sacrificing denoising performance. Extensive experiments on synthetic and real noisy images are conducted to evaluate FFDNet in comparison with state-of-the-art denoisers. The results show that FFDNet is effective and efficient, making it highly attractive for practical denoising applications.

Image Blind Denoising with Generative Adversarial Network Based Noise Modeling

Abstract: In this paper, we consider a typical image blind denoising problem, which is to remove unknown noise from noisy images. As we all know, discriminative learning based methods, such as DnCNN, can achieve state-of-the-art denoising results, but they are not applicable to this problem due to the lack of paired training data. To tackle the barrier, we propose a novel two-step framework. First, a Generative Adversarial Network (GAN) is trained to estimate the noise distribution over the input noisy images and to generate noise samples. Second, the noise patches sampled from the first step are utilized to construct a paired training dataset, which is used, in turn, to train a deep Convolutional Neural Network (CNN) for denoising. Extensive experiments have been done to demonstrate the superiority of our approach in image blind denoising.

A Novel Adaptive Kalman Filter With Inaccurate Process and Measurement Noise Covariance Matrices

Abstract: In this paper, a novel variational Bayesian (VB)-based adaptive Kalman filter (VBAKF) for linear Gaussian state-space models with inaccurate process and measurement noise covariance matrices is proposed. By choosing inverse Wishart priors, the state together with the predicted error and measurement noise covariance matrices are inferred based on the VB approach. Simulation results for a target tracking example illustrate that the proposed VBAKF has better robustness to resist the uncertainties of process and measurement noise covariance matrices than existing state-of-the-art filters.

Burst Denoising with Kernel Prediction Networks

Abstract: We present a technique for jointly denoising bursts of images taken from a handheld camera. In particular, we propose a convolutional neural network architecture for predicting spatially varying kernels that can both align and denoise frames, a synthetic data generation approach based on a realistic noise formation model, and an optimization guided by an annealed loss function to avoid undesirable local minima. Our model matches or outperforms the state-of-the-art across a wide range of noise levels on both real and synthetic data.

CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise

Abstract: In this paper, we study the problem of learning image classification models with label noise. Existing approaches depending on human supervision are generally not scalable as manually identifying correct or incorrect labels is time-consuming, whereas approaches not relying on human supervision are scalable but less effective. To reduce the amount of human supervision for label noise cleaning, we introduce CleanNet, a joint neural embedding network, which only requires a fraction of the classes being manually verified to provide the knowledge of label noise that can be transferred to other classes. We further integrate CleanNet and conventional convolutional neural network classifier into one framework for image classification learning. We demonstrate the effectiveness of the proposed algorithm on both of the label noise detection task and the image classification on noisy data task on several large-scale datasets. Experimental results show that CleanNet can reduce label noise detection error rate on held-out classes where no human supervision available by 41.5% compared to current weakly supervised methods. It also achieves 47% of the performance gain of verifying all images with only 3.2% images verified on an image classification task. Source code and dataset will be available at kuanghuei.github.io/CleanNetProject.

Hyperspectral Image Restoration Via Total Variation Regularized Low-Rank Tensor Decomposition

Abstract: Hyperspectral images (HSIs) are often corrupted by a mixture of several types of noise during the acquisition process, e.g., Gaussian noise, impulse noise, dead lines, stripes, etc. Such complex noise could degrade the quality of the acquired HSIs, limiting the precision of the subsequent processing. In this paper, we present a novel tensor-based HSI restoration approach by fully identifying the intrinsic structures of the clean HSI part and the mixed noise part. Specifically, for the clean HSI part, we use tensor Tucker decomposition to describe the global correlation among all bands, and an anisotropic spatial–spectral total variation regularization to characterize the piecewise smooth structure in both spatial and spectral domains. For the mixed noise part, we adopt the $\ell _1$ norm regularization to detect the sparse noise, including stripes, impulse noise, and dead pixels. Despite that TV regularization has the ability of removing Gaussian noise, the Frobenius norm term is further used to model heavy Gaussian noise for some real-world scenarios. Then, we develop an efficient algorithm for solving the resulting optimization problem by using the augmented Lagrange multiplier method. Finally, extensive experiments on simulated and real-world noisy HSIs are carried out to demonstrate the superiority of the proposed method over the existing state-of-the-art ones.

PhaseMax: Convex Phase Retrieval via Basis Pursuit

Abstract: We consider the recovery of a (real- or complex-valued) signal from magnitude-only measurements, known as phase retrieval. We formulate phase retrieval as a convex optimization problem, which we call PhaseMax. Unlike other convex methods that use semidefinite relaxation and lift the phase retrieval problem to a higher dimension, PhaseMax is a “non-lifting” relaxation that operates in the original signal dimension. We show that the dual problem to PhaseMax is basis pursuit, which implies that the phase retrieval can be performed using algorithms initially designed for sparse signal recovery. We develop sharp lower bounds on the success probability of PhaseMax for a broad range of random measurement ensembles, and we analyze the impact of measurement noise on the solution accuracy. We use numerical results to demonstrate the accuracy of our recovery guarantees, and we showcase the efficacy and limits of PhaseMax in practice.

Change Detection in Heterogenous Remote Sensing Images via Homogeneous Pixel Transformation

Abstract: The change detection in heterogeneous remote sensing images remains an important and open problem for damage assessment. We propose a new change detection method for heterogeneous images (i.e., SAR and optical images) based on homogeneous pixel transformation (HPT). HPT transfers one image from its original feature space (e.g., gray space) to another space (e.g., spectral space) in pixel-level to make the pre-event and post-event images represented in a common space for the convenience of change detection. HPT consists of two operations, i.e., the forward transformation and the backward transformation. In forward transformation, for each pixel of pre-event image in the first feature space, we will estimate its mapping pixel in the second space corresponding to post-event image based on the known unchanged pixels. A multi-value estimation method with noise tolerance is introduced to determine the mapping pixel using $K$ -nearest neighbors technique. Once the mapping pixels of pre-event image are available, the difference values between the mapping image and the post-event image can be directly calculated. After that, we will similarly do the backward transformation to associate the post-event image with the first space, and one more difference value for each pixel will be obtained. Then, the two difference values are combined to improve the robustness of detection with respect to the noise and heterogeneousness (modality difference) of images. Fuzzy-c means clustering algorithm is employed to divide the integrated difference values into two clusters: changed pixels and unchanged pixels. This detection results may contain some noisy regions (i.e., small error detections), and we develop a spatial-neighbor-based noise filter to further reduce the false alarms and missing detections using belief functions theory. The experiments for change detection with real images (e.g., SPOT, ERS, and NDVI) during a flood in U.K. are given to validate the effectiveness of the proposed method.

Exploring Speech Enhancement with Generative Adversarial Networks for Robust Speech Recognition

Abstract: We investigate the effectiveness of generative adversarial networks (GANs) for speech enhancement, in the context of improving noise robustness of automatic speech recognition (ASR) systems. Prior work [1] demonstrates that GANs can effectively suppress additive noise in raw waveform speech signals, improving perceptual quality metrics; however this technique was not justified in the context of ASR. In this work, we conduct a detailed study to measure the effectiveness of GANs in enhancing speech contaminated by both additive and reverberant noise. Motivated by recent advances in image processing [2], we propose operating GANs on log-Mel filterbank spectra instead of waveforms, which requires less computation and is more robust to reverberant noise. While GAN enhancement improves the performance of a clean-trained ASR system on noisy speech, it falls short of the performance achieved by conventional multi-style training (MTR). By appending the GAN-enhanced features to the noisy inputs and retraining, we achieve a 7% WER improvement relative to the MTR system.

Deep Shrinkage Convolutional Neural Network for Adaptive Noise Reduction

Abstract: The noise level of an image depends on settings of an imaging device. The settings can be used to select appropriate parameters for denoising methods. But denoising methods based on deep convolutional neural networks (deep-CNN) do not have such adjustable parameters. Therefore, a deep-CNN whose training data contain limited levels of noise does not effectively restore images whose noise level is different from the training data. If the range of noise levels of training data is extended to solve the problem, the maximum performance of a produced deep-CNN is limited. To solve the tradeoff, we propose a deep-CNN that is adjustable to the noise level of the input image immediately. We use soft shrinkage for activation functions of our deep-CNN. The soft shrinkage has thresholds proportional to the noise level given by the user. We also propose an optimization method for proportionality coefficients for the thresholds of soft shrinkage. Our method optimizes the coefficients for various noise levels simultaneously. In our experiment using a test set whose noise level is from 5 to 50, the proposed method showed higher PSNR than that in the case of the conventional method using only one deep-CNN, and PSNR comparable to that in the case of the conventional method using multiple noise-level-specific CNNs.

Bispectrum Inversion With Application to Multireference Alignment

Abstract: We consider the problem of estimating a signal from noisy circularly translated versions of itself, called multireference alignment (MRA). One natural approach to MRA could be to estimate the shifts of the observations first, and infer the signal by aligning and averaging the data. In contrast, we consider a method based on estimating the signal directly, using features of the signal that are invariant under translations. Specifically, we estimate the power spectrum and the bispectrum of the signal from the observations. Under mild assumptions, these invariant features contain enough information to infer the signal. In particular, the bispectrum can be used to estimate the Fourier phases. To this end, we propose and analyze a few algorithms. Our main methods consist of nonconvex optimization over the smooth manifold of phases. Empirically, in the absence of noise, these nonconvex algorithms appear to converge to the target signal with random initialization. The algorithms are also robust to noise. We then suggest three additional methods. These methods are based on frequency marching, semidefinite relaxation, and integer programming. The first two methods provably recover the phases exactly in the absence of noise. In the high noise level regime, the invariant features approach for MRA results in stable estimation if the number of measurements scales like the cube of the noise variance, which is the information-theoretic rate. Additionally, it requires only one pass over the data, which is important at low signal-to-noise ratio when the number of observations must be large.

Derivative-Free Kalman Filtering Based Approaches to Dynamic State Estimation for Power Systems With Unknown Inputs

Abstract: This paper proposes a decentralized derivative-free dynamic state estimation method in the context of a power system with unknown inputs, to address cases when system linearization is cumbersome or impossible. The suggested algorithm tackles situations when several inputs, such as the excitation voltage, are characterized by uncertainty in terms of their status. The technique engages one generation unit only and its associated measurements, and it remains totally independent of other system wide measurements and parameters, facilitating in this way the applicability of this process on a decentralized basis. The robustness of the method is validated against different contingencies. The impact of parameter errors, process, and measurement noise on the unknown input estimation performance is discussed. This understanding is further supported through detailed studies in a realistic power system model.

A Hybrid DSP/Deep Learning Approach to Real-Time Full-Band Speech Enhancement

Abstract: Despite noise suppression being a mature area in signal processing, it remains highly dependent on fine tuning of estimator algorithms and parameters. In this paper, we demonstrate a hybrid DSP/deep learning approach to noise suppression. We focus strongly on keeping the complexity as low as possible, while still achieving high-quality enhanced speech. A deep recurrent neural network with four hidden layers is used to estimate ideal critical band gains, while a more traditional pitch filter attenuates noise between pitch harmonics. The approach achieves significantly higher quality than a traditional minimum mean squared error spectral estimator, while keeping the complexity low enough for real-time operation at 48 kHz on a low-power CPU.

Noise-Tolerant Wireless Sensor Networks Localization via Multinorms Regularized Matrix Completion

Abstract: Accurate and sufficient location information is the prerequisite for most wireless sensor networks (WSNs) applications. Existing range-based localization approaches often suffer from incomplete and corrupted range measurements. Recently, some matrix completion-based localization approaches have been proposed, which only take into account Gaussian noise and outlier noise when modeling the range measurements. However, in some real-world applications, the inevitable structural noise usually degrades the localization accuracy and prevents the outlier recognition drastically. To address these challenges, we propose a noise-tolerant localization via multi-norms regularized matrix completion (LMRMC) approach in this paper. Leveraging the intrinsic low-rank property of euclidean distance matrix (EDM), the reconstruction problem of true underlying EDM is formulated as a multi-norms regularized matrix completion model, where the outlier noise and structural noise are explicitly sifted by $L_1$ -norm and $L_{1,2}$ -norm, respectively, while the Gaussian noise is implicitly smoothed by employing the well-known alternating direction method of multiplier optimization method. To the best of our knowledge, this is the first scheme being able to efficiently recover the unknown range measurements under the coexistence of Gaussian noise, outlier noise, and structural noise. Extensive experiments validate the superiority of our proposed LMRMC approach, outperforming the state-of-the-art localization approaches with regard to the localization accuracy. Besides, LMRMC can also achieve an accurate detection of both outlier noise and structural noise, making it promising for further nodes fault diagnosis and topology control in WSNs.

Improved Battery SOC Estimation Accuracy Using a Modified UKF With an Adaptive Cell Model Under Real EV Operating Conditions

Abstract: Electric vehicles (EVs) require reliable and very accurate battery state-of-charge (SOC) estimation to maximize their performance. A commonly used estimation technique, the extended Kalman filter (EKF), provides an accurate estimate of the SOC. However, EKF has some limitations, such as it assumes the knowledge of the statistics of the process noise and measurement noise is available, which practically cannot be guaranteed. In this paper, an adaptive equivalent-circuit model is proposed and used for SOC estimation. The proposed model is based on a common cell model with adaptive parameters tracking feature implemented using an artificial neural network controller embedded within the model. A variant of the EKF, namely the unscented Kalman filter (UKF), is used to achieve more accurate estimates of the SOC with a relatively fast convergence speed. The UKF uses the unscented transform to obtain the statistics of the process noise covariance. Furthermore, the autocovariance least-squares technique is used to estimate the measurement noise covariance by accounting for possible correlation in the measurement innovations, which enhances the accuracy of the estimate. Derivation of the proposed method followed by experimental verification is presented in this paper.

A Survey on Various Median Filtering Techniques For Removal of Impulse Noise From Digital Image

Abstract: The elimination of noise from images becomes a trending field in image processing. Imagesmay got corrupted by random change in pixel intensity, illumination, or due to poor contrast and can't be used directly. Therefore, it is necessary to get rid of impulse noise presented inan image. In order to remove such impulse noise, Median based filters are commonly used. However, we use various types of median filters such as recursive median filter, iterative median filter, directional median filter, weighted median filter, adaptive median filter progressive switching median filter and threshold median filter. This paper will survey various median filtering techniques for excluding noisy pixel from a digital image.

Bearing Fault Diagnosis Using Fully-Connected Winner-Take-All Autoencoder

Abstract: Intelligent fault diagnosis of bearings has been a heated research topic in the prognosis and health management of rotary machinery systems, due to the increasing amount of available data collected by sensors. This has given rise to more and more business desire to apply data-driven methods for health monitoring of machines. In recent years, various deep learning algorithms have been adapted to this field, including multi-layer perceptrons, autoencoders, convolutional neural networks, and so on. Among these methods, autoencoder is of particular interest for us because of its simple structure and its ability to learn useful features from data in an unsupervised fashion. Previous studies have exploited the use of autoencoders, such as denoising autoencoder, sparsity aotoencoder, and so on, either with one layer or with several layers stacked together, and they have achieved success to certain extent. In this paper, a bearing fault diagnosis method based on fully-connected winner-take-all autoencoder is proposed. The model explicitly imposes lifetime sparsity on the encoded features by keeping only $k$ % largest activations of each neuron across all samples in a mini-batch. A soft voting method is implemented to aggregate prediction results of signal segments sliced by a sliding window to increase accuracy and stability. A simulated data set is generated by adding white Gaussian noise to original signals to test the diagnosis performance under noisy environment. To evaluate the performance of the proposed method, we compare our methods with some state-of-the-art bearing fault diagnosis methods. The experiments result show that, with a simple two-layer network, the proposed method is not only capable of diagnosing with high precision under normal conditions, but also has better robustness to noise than some deeper and more complex models.

Rolling Bearing Fault Diagnosis Based on an Improved Denoising Method Using the Complete Ensemble Empirical Mode Decomposition and the Optimized Thresholding Operation

Abstract: Vibration signals are widely used in monitoring and diagnosing of rolling bearing faults. These signals are usually noisy and masked by other sources, which may therefore result in loss of information about the faults. This paper proposes an improved denoising method in order to enhance the sensitivity of kurtosis and the envelope spectrum for early detection of rolling bearing faults. The proposed method is based on a complete ensemble empirical mode decomposition with an adaptive noise (CEEMDAN) associated with an optimized thresholding operation. First, the CEEMDAN is applied to the vibration signals to obtain a series of functions called the intrinsic mode functions (IMFs). Second, an approach based on the energy content of each mode and the white noise characteristic is proposed to determine the trip point in order to select the relevant modes. By comparing the average energy of all the unselected IMFs with the energy of each selected IMFs, the singular IMFs are selected. Third, an optimized thresholding operation is applied to the singular IMFs. Finally, the kurtosis and the envelope spectrum are used to test the effectiveness of the proposed method. Different experimental data of the Case Western Reserve University Bearing Data Center are used to validate the effectiveness of the proposed method. The obtained experimental results illustrate well the merits of the proposed method for the diagnosis and detection of rolling bearing faults compared to those of the conventional method.

Improving Crowdsourced Label Quality Using Noise Correction

Abstract: Crowdsourcing systems provide a cost effective and convenient way to collect labels, but they often fail to guarantee the quality of the labels. This paper proposes a novel framework that introduces noise correction techniques to further improve the quality of integrated labels that are inferred from the multiple noisy labels of objects. In the proposed general framework, information about the qualities of labelers estimated by a front-end ground truth inference algorithm is utilized to supervise subsequent label noise filtering and correction. The framework uses a novel algorithm termed adaptive voting noise correction (AVNC) to precisely identify and correct the potential noisy labels. After filtering out the instances with noisy labels, the remaining cleansed data set is used to create multiple weak classifiers, based on which a powerful ensemble classifier is induced to correct these noises. Experimental results on eight simulated data sets with different kinds of features and two real-world crowdsourcing data sets in different domains consistently show that: 1) the proposed framework can improve label quality regardless of inference algorithms, especially under the circumstance that each instance has a few repeated labels and 2) since the proposed AVNC algorithm considers both the number of and the probability of potential label noises, it outperforms the state-of-the-art noise correction algorithms.

Convolutional-Recurrent Neural Networks for Speech Enhancement

Abstract: We propose an end-to-end model based on convolutional and recurrent neural networks for speech enhancement. Our model is purely data-driven and does not make any assumptions about the type or the stationarity of the noise. In contrast to existing methods that use multilayer perceptrons (MLPs), we employ both convolutional and recurrent neural network architectures. Thus, our approach allows us to exploit local structures in both the frequency and temporal domains. By incorporating prior knowledge of speech signals into the design of model structures, we build a model that is more data-efficient and achieves better generalization on both seen and unseen noise. Based on experiments with synthetic data, we demonstrate that our model outperforms existing methods, improving PESQ by up to 0.6 on seen noise and 0.64 on unseen noise.

Class-Aware Fully Convolutional Gaussian and Poisson Denoising

Abstract: We propose a fully convolutional neural-network architecture for image denoising which is simple yet powerful. Its structure allows to exploit the gradual nature of the denoising process, in which the shallow layers handle local noise statistics, while deeper layers recover edges and enhance textures. Our method advances the state of the art when trained for different noise levels and distributions (both Gaussian and Poisson). In addition, we show that making the denoiser class-aware by exploiting semantic class information boosts the performance, enhances the textures, and reduces the artifacts.

A Framework for Robust Hybrid State Estimation With Unknown Measurement Noise Statistics

Abstract: In practical applications like power systems, the distribution of the measurement noise is usually unknown and frequently deviates from the assumed Gaussian model, yielding outliers. Under these conditions, the performances of the existing state estimators that rely on Gaussian assumption can deteriorate significantly. In addition, the sampling rates of measurements from supervisory control and data acquisition (SCADA) system and phasor measurement unit (PMU) are quite different, causing time skewness problem. In this paper, we propose a robust state estimation framework to address the unknown non-Gaussian noise and the measurement time skewness issue. In the framework, robust Mahalanbis distances are proposed to detect system abnormalities and assign appropriate weights to each chosen buffered PMU measurements. Those weights are further utilized by the Schweppe-type Huber generalized maximum-likelihood (SHGM) estimator to filter out non-Gaussian PMU measurement noise and help suppress outliers. In the meantime, the SHGM estimator is used to handle unknown noise of the received SCADA measurements, yielding another set of state estimates. We show that the state estimates provided by the SHGM estimator follow an asymptotical Gaussian distribution. This nice property allows us to obtain the optimal state estimates by resorting to the data fusion theory for the fusion of the estimation results from two independent SHGM estimators. Extensive simulation results carried out on the IEEE 14, 30 and 118-bus test systems demonstrate the effectiveness and robustness of the proposed method.

Adaptive Very Deep Convolutional Residual Network for Noise Robust Speech Recognition

Abstract: Although great progress has been made in automatic speech recognition, significant performance degradation still exists in noisy environments. Our previous work has demonstrated the superior noise robustness of very deep convolutional neural networks (VDCNN). Based on our work on VDCNNs, this paper proposes a more advanced model referred to as the very deep convolutional residual network (VDCRN). This new model incorporates batch normalization and residual learning, showing more robustness than previous VDCNNs.Then, to alleviate the mismatch between the training and testing conditions, model adaptation and adaptive training are developed and compared for the new VDCRN. This paper focuses on factor aware training (FAT) and cluster adaptive training (CAT). For FAT, a unified framework is explored. For CAT, two schemes are first explored to construct the bases in the canonical model; furthermore, a factorized version of CAT is designed to address multiple nonspeech variabilities in one model. Finally, a complete multipass system is proposed to achieve the best system performance in the noisy scenarios. The proposed new approaches are evaluated on three different tasks: Aurora4 (simulated data with additive noise and channel distortion), CHiME4 (both simulated and real data with additive noise and reverberation), and the AMI meeting transcription task (real data with significant reverberation).The evaluation not only includes different noisy conditions, but also covers both simulated and real noisy data. The experiments show that the new VDCRN is more robust, and the adaptation on this model can further significantly reduce the word error rate (WER). The proposed best architecture obtains consistent and very large improvements on all tasks compared to the baseline VDCNN or long short-term memory. Particularly, on Aurora4 a new milestone 5.67% WER is achieved by only improving acoustic modeling.

Computerized Lung Sound Screening for Pediatric Auscultation in Noisy Field Environments

Abstract: Goal: Chest auscultations offer a non-invasive and low-cost tool for monitoring lung disease. However, they present many shortcomings, including inter-listener variability, subjectivity, and vulnerability to noise and distortions. This work proposes a computer-aided approach to process lung signals acquired in the field under adverse noisy conditions, by improving the signal quality and offering automated identification of abnormal auscultations indicative of respiratory pathologies. Methods: The developed noise-suppression scheme eliminates ambient sounds, heart sounds, sensor artifacts, and crying contamination. The improved high-quality signal is then mapped onto a rich spectrotemporal feature space before being classified using a trained support-vector machine classifier. Individual signal frame decisions are then combined using an evaluation scheme, providing an overall patient-level decision for unseen patient records. Results: All methods are evaluated on a large dataset with $>$ 1000 children enrolled, 1–59 months old. The noise suppression scheme is shown to significantly improve signal quality, and the classification system achieves an accuracy of 86.7% in distinguishing normal from pathological sounds, far surpassing other state-of-the-art methods. Conclusion: Computerized lung sound processing can benefit from the enforcement of advanced noise suppression. A fairly short processing window size ( $ s) combined with detailed spectrotemporal features is recommended, in order to capture transient adventitious events without highlighting sharp noise occurrences. Significance: Unlike existing methodologies in the literature, the proposed work is not limited in scope or confined to laboratory settings: This work validates a practical method for fully automated chest sound processing applicable to realistic and noisy auscultation settings.

A Deep Learning Approach to Anomaly Detection in Nuclear Reactors

Abstract: In this work, a novel deep learning approach to unfold nuclear power reactor signals is proposed. It includes a combination of convolutional neural networks (CNN), denoising autoencoders (DAE) and $k$-means clustering of representations. Monitoring nuclear reactors while running at nominal conditions is critical. Based on analysis of the core reactor neutron flux, it is possible to derive useful information for building fault/anomaly detection systems. By leveraging signal and image pre-processing techniques, the high and low energy spectra of the signals were appropriated into a compatible format for CNN training. Firstly, a CNN was employed to unfold the signal into either twelve or forty-eight perturbation location sources, followed by a $k$-means clustering and $k$-Nearest Neighbour coarse-to-fine procedure, which significantly increases the unfolding resolution. Secondly, a DAE was utilised to denoise and reconstruct power reactor signals at varying levels of noise and/or corruption. The reconstructed signals were evaluated w.r.t. their original counter parts, by way of normalised cross correlation and unfolding metrics. The results illustrate that the origin of perturbations can be localised with high accuracy, despite limited training data and obscured$/$noisy signals, across various levels of granularity.

Improved Algebraic Solution for Source Localization From TDOA and FDOA Measurements

Abstract: In this letter, an improved version of the popular two-stage weighted least squares (WLS) algorithm is presented to determine the position and velocity of a moving source using time difference of arrival and frequency difference of arrival measurements in a wireless sensor network. A closed-form solution is obtained from the minimization of the WLS criterion in each stage. The estimator accuracy is shown analytically to attain the Cramer–Rao lower bound under the small Gaussian noise assumption. Numerical simulations are included to support and corroborate the theoretical developments.

Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images

Abstract: Traditional algorithms for compressive sensing recovery are computationally expensive and are ineffective at low measurement rates. In this paper, we propose a data-driven noniterative algorithm to overcome the shortcomings of earlier iterative algorithms. Our solution, ReconNet , is a deep neural network, which is learned end-to-end to map block-wise compressive measurements of the scene to the desired image blocks. Reconstruction of an image becomes a simple forward pass through the network and can be done in real time. We show empirically that our algorithm yields reconstructions with higher peak signal-to-noise ratios (PSNRs) compared to iterative algorithms at low measurement rates and in presence of measurement noise. We also propose a variant of ReconNet, which uses adversarial loss in order to further improve reconstruction quality. We discuss how adding a fully connected layer to the existing ReconNet architecture allows for jointly learning the measurement matrix and the reconstruction algorithm in a single network. Experiments on real data obtained from a block compressive imager show that our networks are robust to unseen sensor noise.

Analysis and Design of Commutation-Based Circulator-Receivers for Integrated Full-Duplex Wireless

Abstract: Previously, we presented a non-magnetic, non-reciprocal N-path-filter-based circulator-receiver (circ.-RX) architecture for single-frequency full-duplex (SF-FD) wireless, which merges a commutation-based linear periodically time-varying (LPTV) non-magnetic circulator with a down-converting mixer and directly provides the baseband (BB) RX signals at its output, while suppressing the noise contribution of one set of the commutating switches. The architecture also incorporates an on-chip balance network to enhance the transmitter (TX)-RX isolation. In this paper, we present a detailed analysis of the architecture, including a noise analysis and an analysis of the effect of the balance network. The analyses are verified by the simulation and measurement results of a 65-nm CMOS 750-MHz circ.-RX prototype. The circ.-RX can handle up to +8 dBm of TX power with 8-dB noise figure (NF) and 40-dB average isolation over 20-MHz radio frequency (RF) bandwidth (BW). In conjunction with digital self-interference (SI) and its third-order intermodulation (IM3) cancellation, the SF-FD circ.-RX demonstrates 80-dB overall SI suppression for up to +8-dBm TX average output power. The claims are also verified through an SF-FD demonstration where a −50-dBm weak desired received signal is recovered while transmitting a 0-dBm average power orthogonal frequency-division multiplexing (OFDM)-like TX signal.

Multisensor Distributed Weighted Kalman Filter Fusion With Network Delays, Stochastic Uncertainties, Autocorrelated, and Cross-Correlated Noises

Abstract: This paper is concerned with the problem of distributed weighted Kalman filter fusion (DWKFF) for a class of multisensor unreliable networked systems (MUNSs) with correlated noises. The process noise and the measurement noises are assumed to be one-step, two-step cross-correlated, and one-step autocorrelated, and the measurement noises of each sensor are one-step cross-correlated. The stochastic uncertainties in the state and measurements are described by correlated multiplicative noises. The MUNSs suffer measurement delay or loss due to their unreliability. Buffers of finite length are proposed to deal with measurement delay or loss, and an optimal local Kalman filter estimator with a buffer of finite length is derived for each subsystem. Based on the new optimal local Kalman filter estimator, the DWKFF algorithm with finite length buffers has been developed which has stronger fault-tolerance ability. Simulation results illustrate the effectiveness of the proposed approaches.