Improve Estimation Accuracy Research Articles

Consensus-Based Distributed Target Tracking with False Data Injection Attacks over Radar Network

For target tracking in radar network, any anomaly in a part of the system can quickly spread over the network and lead to tracking failures. False data injection (FDI) attacks can damage the state estimation mechanism by modifying the radar measurements with unknown and time-varying attack variables, therefore making traditional filters inapplicable. To tackle this problem, we propose a novel consensus-based distributed state estimation (DSE) method for target tracking with FDI attacks, which is effective even when all radars are under FDI attacks. First, a real-time residual-based detector is introduced to the DSE framework, which can effectively detect FDI attacks by analyzing the statistical properties of the residual. Secondly, a simple yet effective attack parameter estimation method is proposed to provide attack parameter estimation based on a pseudo-measurement equation, which has the advantage of decoupled estimation of state and attack parameters compared with augmented state filters. Finally, for timely attack mitigation and global consistency achievement, a novel hybrid consensus method is proposed which can compensate for the estimation error caused by FDI attacks and provide estimation accuracy improvement. The simulation results show that the proposed solution is effective and superior to the traditional DSE method for target tracking in the presence of FDI attacks.

DART-PFLOTRAN: An ensemble-based data assimilation system for estimating subsurface flow and transport model parameters

Ensemble-based Data Assimilation (EDA) has been effectively applied to estimate model parameters through inverse modeling in subsurface flow and transport problems. To facilitate the management of EDA workflow and lower the barriers for adopting EDA-based parameter estimation in subsurface science, we develop a software framework linking the Data Assimilation Research Testbed (DART) with a massively parallel subsurface FLOw and TRANsport code PFLOTRAN. DART-PFLOTRAN enables an iterative EDA workflow based on the Ensemble Smoother for Multiple Data Assimilation method (ES-MDA) to improve estimation accuracy for nonlinear forward problems. We verify the implementation of ES-MDA in DART-PFLOTRAN using two synthetic cases designed to estimate static permeability and dynamic exchange fluxes across the riverbed from continuous temperature measurements. Both cases yield accurate estimations of the parameters compared to their synthetic truth. With a code base in Python and Fortran, DART-PFLOTRAN paves the way for large-scale inverse modeling using the sequential ES-MDA.

New data optimization framework for parameter estimation under uncertainties with application to lithium-ion battery

Data optimization, or optimal experiment design, is an effective way to improve and guarantee the accuracy of state and parameter estimation, as the quality of data has significant impact on the estimation accuracy. Such capability is especially critical for energy systems requiring high reliability. The common practice of data optimization is to design input excitation by maximizing the Fisher information, and hence minimizes the variance of the estimation error. However, such approach suffers from fundamental limitations, including negligence of estimation bias and system uncertainties in measurement, model, and parameter, which severely restrict the applicability and effectiveness of the method. This paper aims at establishing new criteria and a novel framework for data optimization and estimation error quantification to overcome the fundamental limitations. First, a generic formula is derived for quantifying the estimation error subject to sensor, model, and parameter uncertainties for the commonly used least-squares algorithm. Based on the formula, desirable data structures, which could minimize the errors caused by each uncertainty, are identified. These structures are then used as new criteria to formulate the novel data optimization framework. The proposed methodology is applied to the parameter estimation problem of a lithium-ion battery electrochemical model in simulation and experiments, showing up to two orders of magnitude improvement in estimation accuracy compared with the traditional Fisher-information-based approach and other baselines.

Phenology Effects on Physically Based Estimation of Paddy Rice Canopy Traits from UAV Hyperspectral Imagery

Radiation transform models such as PROSAIL are widely used for crop canopy reflectance simulation and biophysical parameter inversion. The PROSAIL model basically assumes that the canopy is turbid homogenous media with a bare soil background. However, the canopy structure changes when crop growth stages develop, which is more or less a departure from this assumption. In addition, a paddy rice field is inundated most of the time with flooded soil background. In this study, field-scale paddy rice leaf area index (LAI), leaf cholorphyll content (LCC), and canopy chlorophyll content (CCC) were retrieved from unmanned-aerial-vehicle-based hyperspectral images by the PROSAIL radiation transform model using a lookup table (LUT) strategy, with a special focus on the effects of growth-stage development and soil-background signature selection. Results show that involving flooded soil reflectance as background reflectance for PROSAIL could improve estimation accuracy. When using a LUT with the flooded soil reflectance signature (LUTflooded) the coefficients of determination (R2) between observed and estimation variables are 0.70, 0.11, and 0.79 for LAI, LCC, and CCC, respectively, for the entire growing season (from tillering to heading growth stages), and the corresponding mean absolute errors (MAEs) are 21.87%, 16.27%, and 12.52%. For LAI and LCC, high model bias mainly occurred in tillering growth stages. There is an obvious overestimation of LAI and underestimation of LCC for in the tillering growth stage. The estimation accuracy of CCC is relatively consistent from tillering to heading growth stages.

Blackman–Tukey spectral estimation and electric network frequency matching from power mains and speech recordings

Forensic applications exploit electric network frequency (ENF) as a fingerprint to determine multimedia content authenticity, as well as the time and region of multimedia recording. ENF is present at a nominal frequency of 50/60 Hz and its harmonics. Strong interference due to speech content deteriorates ENF estimation accuracy. Herein, the authors propose a non-parametric approach for ENF estimation, which incorporates a customised lag window design into the Blackman–Tukey spectral estimation method. Leakage reduction is formulated as a problem of energy maximisation within the main lobe of the spectral window. The proposed approach is compared to state-of-the-art methods for ENF estimation. Maximum correlation coefficient and minimum standard deviation of errors are employed to measure ENF estimation accuracy. Hypothesis testing is performed to determine whether the improvements in ENF estimation accuracy of the proposed approach over the state-of-the-art methods are statistically significant. Experimental results and statistical tests indicate that the proposed approach improves ENF estimation against many state-of-the-art methods.

Weak-lensing mass reconstruction using sparsity and a Gaussian random field

Aims. We introduce a novel approach to reconstructing dark matter mass maps from weak gravitational lensing measurements. The cornerstone of the proposed method lies in a new modelling of the matter density field in the Universe as a mixture of two components: (1) a sparsity-based component that captures the non-Gaussian structure of the field, such as peaks or halos at different spatial scales, and (2) a Gaussian random field, which is known to represent the linear characteristics of the field well. Methods. We propose an algorithm called MCALens that jointly estimates these two components. MCALens is based on an alternating minimisation incorporating both sparse recovery and a proximal iterative Wiener filtering. Results. Experimental results on simulated data show that the proposed method exhibits improved estimation accuracy compared to customised mass-map reconstruction methods.

Spatial–Temporal Convolutional Gated Recurrent Unit Network for Significant Wave Height Estimation From Shipborne Marine Radar Data

Spatial–temporal features are extracted from X-band marine radar backscatter image sequences via deep neural networks to estimate sea surface significant wave heights (SWHs). A convolutional neural network (CNN) is first constructed based on the pretrained GoogLeNet to estimate SWH using multiscale deep spatial features extracted from each radar image. Since the CNN-based model cannot analyze the temporal behavior of wave signatures in radar image sequences, a gated recurrent unit (GRU) network is concatenated after the deep convolutional layers from the CNN to build a convolutional GRU (CGRU)-based model, which generates spatial–temporal features for SWH estimation. Both the CNN and CGRU-based models are trained and tested using shipborne marine radar data collected during a sea trial off the East Coast of Canada, while simultaneous SWHs measured by nearby buoys are used as ground truths for model training and reference. Experimental results show that compared to the classic signal-to-noise ratio (SNR)-based method, both models improve estimation accuracy and computational efficiency significantly, with a reduction of RMSD by 0.32 m (CNN) and 0.35 m (CGRU), respectively. It is also found that under rainy conditions, CGRU outperforms SNR and CNN-based models by reducing the RMSD from around 0.90 to 0.54 m.

An Enhanced Equivalent Circuit Model With Real-Time Parameter Identification for Battery State-of-Charge Estimation

This article introduces an efficient modeling approach based on the Wiener structure to reinforce the capacity of classical equivalent circuit models (ECMs) in capturing the nonlinearities of lithium-ion (Li-ion) batteries. The proposed block-oriented modeling architecture is composed of a simple linear ECM followed by a static output nonlinearity block, which helps achieving a superior nonlinear mapping property while maintaining the real-time efficiency. The observability of the established battery model is analytically proven. This article also introduces an efficient parameter estimator based on extended-kernel iterative recursive least squares algorithm for real-time estimation of the parameters of the proposed Wiener model. The proposed approach is applied for state-of-charge (SoC) estimation of 3.4-Ah 3.6-V nickel-manganese-cobalt-based Li-ion cells using the extended Kalman filter (EKF). The results show about 1.5% improvement in SoC estimation accuracy compared with the EKF algorithm based on the second-order ECM. A series of real-time tests are also carried out to demonstrate the computational efficiency of the proposed method.

Analyst Optimism in the Automotive Industry: A Post-Bailout Boost and Methodological Insights

This paper empirically investigates the impact of the government bailout on analysts’ forecast optimism regardingfirms in the automotive industry. We compare the results from M- and MM-robust methodologies to the results from OLS regression in an event study context and find that inferences change. When M- and MM-robust estimation methods are used to estimate the same model, the results for key control variables fall directly in line with those of similar previous studies. Furthermore, an analysis of residuals indicates that the application of M- and MM estimation methods pulls the main prediction equation towards the main sample data, suggesting a more rigorous fit. Based on robust methods, we observe changes in analyst optimism during the announcement period of the bailout, as evidenced by the significantly positive variable of interest. We support our empirical results with simulations and confirm significant improvements in estimation accuracy when robust regression methods are applied to the samples contaminated by outliers.

Diffuse reflectance infrared spectroscopy estimates for soil properties using multiple partitions: Effects of the range of contents, sample size, and algorithms

AbstractThe RMSE of validation (RMSEV) and ratio of the interquartile range to RMSEV (RPIQV) are key quality parameters in diffuse reflectance infrared (IR) spectroscopy studies, but the effects of different factors on these parameters are often not sufficiently considered. Our objectives were to reveal the effects of range of contents, sample size, data pretreatment, wavenumber region selection, and algorithms on the evaluation of IR spectra in the wavenumber range from 1,000 to 7,000 cm−1 (mid‐ and long‐wave near IR) estimations. Contents of soil organic C (SOC), N, clay, and sand and pH values were determined for surface soils of an arable field in India, and IR spectra were recorded for four samples consisting of 71–263 soils. For each of the four samples, five random partitions into calibration and validation datasets were carried out, and partial least squares regression (PLSR) or support vector machine regression was performed. A plot of the RMSEV values against the interquartile ranges of measured values for the validation samples (IQRV) indicated that the IQRV was a key parameter for all soil properties: a sufficiently high IQRV—which is affected by sample size and random partitioning—resulted in generally good estimation accuracies (RPIQV ≥ 2.70). Optimized data pretreatment and wavenumber region selection improved estimation accuracy for SOC and pH. Support vector machine regression was superior to PLSR for the estimation of SOC, clay, and sand, but worse for pH. Overall, this study indicates that multiple partitioning of the data is essential in IR studies and suggests that RPIQV and RMSEV need to be interpreted in the context of the respective IQRV values.

Maximum-likelihood direction of arrival estimation under intermittent jamming

Multiple-snapshot maximum-likelihood (ML) direction of arrival (DOA) estimation problem is studied for the intermittent jamming scenario. The intermittent jamming modality is based on the assumption that only a subset of the collected snapshots are contaminated by the jammer while the others are jammer-free; but the receiver does not know which is which. This type of jamming is frequently encountered in practice either inadvertently, say due to the sporadic activity of a non-hostile system; or intentionally, say due to the activity of an adversary sweeping the operational bandwidth of the receiver. Exact maximum likelihood solution for the problem is analytically intractable and an expectation maximization (EM) method based solution is developed for coherent and non-coherent signal models. Coherent signal model assumes that the phase difference between the coefficients of two consecutive snapshots are known a-priori which is an assumption compatible with the Swerling-1/3 target models in the radar signal processing literature. Non-coherent signal model does not have such an assumption and it is suitable for Swerling-2/4 targets. The suggested EM based solution is shown to yield an important estimation accuracy improvement over conventional maximum-likelihood solution which ignores the intermittency of jammer and also over the atomic norm based high resolution estimation techniques. Cramer-Rao type performance lower bounds for the problem is also provided to illustrate the efficacy of the suggested estimator.

Analysis of current density in the electrode and electrolyte of lithium‐ion cells for ageing estimation applications

Lithium-ion battery is the commonly used energy storage technology in electric vehicles (EVs) because of its inexpensive manufacturing cost and high energy capacity. For optimal utilization of its capacity and lifetime, reliable state of health (SoH) monitoring solutions have to be included in the battery management system (BMS). SoH of a cell is affected by several reasons such as internal degradation or external damages that need to be estimated. This article analyses the current density in electrode and electrolyte of an EV lithium-ion cell using a simulation assisted method that leads to improvement in SoH estimation accuracy. The experimental results are analysed through the fusion of the magnetic field images captured by quantum fluxgate magnetometers, installed on the surface of the cell, together with the real-time simulation of the multi-physics model of the cell. The magnetic field sensors measure the magnetic field intensity with an accuracy of ±2 mT. The real-time simulation input data is updated from the measurements of both the magnetic field sensors and the battery cycler. The multi-physics model of the cell is developed in COMSOL modelling software, and real-time data fusion process is implemented on dSPACE Microlabbox real-time simulator. Results confirm that the proposed monitoring solution provides useful insight that can be employed in ageing estimation of EV batteries.

Influence of Roof Rock Thickness on the Failure Probability of Thermally Stable Diamond Composite Rock Cutting Tips

Thermally Stable Diamond Composite (TSDC) has been used to make rock cutting tips to tackle the challenges of high cutting temperature and high abrasiveness met in hard rock cutting. Various research has been conducted to investigate the failure behaviour and predict the failure risk of the TSDC tips in real rock cutting operations. Based on the scenario of roadway development in underground coal mines, a series studies have been carried out to estimate the probability of TSDC tip sudden failure suffered from randomly occurring excessive bending force, which is one of major failure modes of the TSDC tips. This study aims to improve estimation accuracy of the failure probability by removing the constraint on roof rock thickness that has been adopted in existing research.

Multi-task Learning-based All-in-one Collaboration Framework for Degraded Image Super-resolution

In this article, we address the degraded image super-resolution problem in a multi-task learning (MTL) manner. To better share representations between multiple tasks, we propose an all-in-one collaboration framework (ACF) with a learnable “junction” unit to handle two major problems that exist in MTL—“How to share” and “How much to share.” Specifically, ACF consists of a sharing phase and a reconstruction phase. Considering the intrinsic characteristic of multiple image degradations, we propose to first deal with the compression artifact, motion blur, and spatial structure information of the input image in parallel under a three-branch architecture in the sharing phase. Subsequently, in the reconstruction phase, we up-sample the previous features for high-resolution image reconstruction with a channel-wise and spatial attention mechanism. To coordinate two phases, we introduce a learnable “junction” unit with a dual-voting mechanism to selectively filter or preserve shared feature representations that come from sharing phase, learning an optimal combination for the following reconstruction phase. Finally, a curriculum learning-based training scheme is further proposed to improve the convergence of the whole framework. Extensive experimental results on synthetic and real-world low-resolution images show that the proposed all-in-one collaboration framework not only produces favorable high-resolution results while removing serious degradation, but also has high computational efficiency, outperforming state-of-the-art methods. We also have applied ACF to some image-quality sensitive practical task, such as pose estimation, to improve estimation accuracy of low-resolution images.

Improving Performance Estimation for Design Space Exploration for Convolutional Neural Network Accelerators

Contemporary advances in neural networks (NNs) have demonstrated their potential in different applications such as in image classification, object detection or natural language processing. In particular, reconfigurable accelerators have been widely used for the acceleration of NNs due to their reconfigurability and efficiency in specific application instances. To determine the configuration of the accelerator, it is necessary to conduct design space exploration to optimize the performance. However, the process of design space exploration is time consuming because of the slow performance evaluation for different configurations. Therefore, there is a demand for an accurate and fast performance prediction method to speed up design space exploration. This work introduces a novel method for fast and accurate estimation of different metrics that are of importance when performing design space exploration. The method is based on a Gaussian process regression model parametrised by the features of the accelerator and the target NN to be accelerated. We evaluate the proposed method together with other popular machine learning based methods in estimating the latency and energy consumption of our implemented accelerator on two different hardware platforms targeting convolutional neural networks. We demonstrate improvements in estimation accuracy, without the need for significant implementation effort or tuning.

Validation and estimation of spleen volume via computer-assisted segmentation on clinically acquired CT scans.

Purpose: Deep learning is a promising technique for spleen segmentation. Our study aims to validate the reproducibility of deep learning-based spleen volume estimation by performing spleen segmentation on clinically acquired computed tomography (CT) scans from patients with myeloproliferative neoplasms. Approach: As approved by the institutional review board, we obtained 138 de-identified abdominal CT scans. A sum of voxel volume on an expert annotator's segmentations establishes the ground truth (estimation 1). We used our deep convolutional neural network (estimation 2) alongside traditional linear estimations (estimation 3 and 4) to estimate spleen volumes independently. Dice coefficient, Hausdorff distance, coefficient, Pearson coefficient, the absolute difference in volume, and the relative difference in volume were calculated for 2 to 4 against the ground truth to compare and assess methods' performances. We re-labeled on scan-rescan on a subset of 40 studies to evaluate method reproducibility. Results: Calculated against the ground truth, the coefficients for our method (estimation 2) and linear method (estimation 3 and 4) are 0.998, 0.954, and 0.973, respectively. The Pearson coefficients for the estimations against the ground truth are 0.999, 0.963, and 0.978, respectively (paired -tests produced between 2 and 3, and 2 and 4). Conclusion: The deep convolutional neural network algorithm shows excellent potential in rendering more precise spleen volume estimations. Our computer-aided segmentation exhibits reasonable improvements in splenic volume estimation accuracy.

Vehicular trajectory estimation utilizing slip angle based on GNSS Doppler/IMU

Accurate vehicular trajectory estimation is important for the recently developed autonomous driving systems. As the accuracy of the vehicular trajectory estimation is reduced with the slippage that occurs during turning, we propose a method in this study to accurately estimate the trajectory of a vehicle, focusing on the slip angle estimation. Although the two-wheel model is used as a general concept slip angle estimation, the accurate estimation of the parameters was difficult using the conventional methods. Therefore, a global navigation satellite system (GNSS) Doppler was used for parameter estimation. In addition, the roll angle was estimated as it occurs during turning and affects the slip angle of the vehicle. Specifically, we verified the improvement in accuracy of the vehicular trajectory estimation using the cost-effective GNSS Doppler/IMU.

Transfer remaining useful life estimation of bearing using depth-wise separable convolution recurrent network

Rolling bearing is a vital part of the machinery, whose remaining useful life (RUL) estimation plays a critical role in ensuring the safety and maintenance decision-making. However, in most industrial applications, it is difficult to obtain run-to-failure data under complex operating conditions, which is inefficient for deep learning approaches. To solve the above problem, a new approach using transfer depth-wise separable convolution recurrent network (TDSCRN) for RUL estimation of bearing is presented. A novel prediction model so-called depth-wise separable convolution recurrent network (DSCRN) is designed and trained by the source-domain dataset. The parameters and model of DSCRN are transferred to the target-domain, and then TDSCRN is obtained for RUL estimation task. Two public run-to-failure datasets are used to validate the performance of the presented method. The results indicate that this framework can improve estimation accuracy and robustness in complex operating conditions.

A New Noninvasive System for Clinical Pulse Wave Velocity Assessment: The Athos Device.

This paper presents a low cost, noninvasive, clinical-grade Pulse Wave Velocity evaluation device. The proposed system relies on a simultaneous acquisition of femoral and carotid pulse waves to improve estimation accuracy and correctness. The sensors used are two high precision MEMS force sensors, encapsulated in two ergonomic probes, and connected to the main unit. Data are then wirelessly transmitted to a standard laptop, where a dedicated graphical user interface (GUI) runs for analysis and recording. Besides the interface, the Athos system provides a Matlab algorithm to process the signals quickly and achieve a reliable PWV assessment. To better compare the results at the end of each analysis, a detailed report is generated, including all the relevant examination information (subject data, mean PTT, and obtained PWV). A pre-clinical study was conducted to validate the system by realizing several Pulse Wave Velocity measurements on ten heterogeneous healthy subjects of different ages. The collected results were then compared with those measured by a well-established and largely more expensive clinical device (SphygmoCor).

Unsupervised Learning of Depth and Camera Pose with Feature Map Warping.

Estimating the depth of image and egomotion of agent are important for autonomous and robot in understanding the surrounding environment and avoiding collision. Most existing unsupervised methods estimate depth and camera egomotion by minimizing photometric error between adjacent frames. However, the photometric consistency sometimes does not meet the real situation, such as brightness change, moving objects and occlusion. To reduce the influence of brightness change, we propose a feature pyramid matching loss (FPML) which captures the trainable feature error between a current and the adjacent frames and therefore it is more robust than photometric error. In addition, we propose the occlusion-aware mask (OAM) network which can indicate occlusion according to change of masks to improve estimation accuracy of depth and camera pose. The experimental results verify that the proposed unsupervised approach is highly competitive against the state-of-the-art methods, both qualitatively and quantitatively. Specifically, our method reduces absolute relative error (Abs Rel) by 0.017–0.088.