Proposed Estimation Method Research Articles

An efficient state-of-health estimation method for lithium-ion batteries based on feature-importance ranking strategy and hybrid kernel extreme learning machine algorithm

The safe and reliable operation of battery systems depends critically on accurately and dependably estimating the state of health (SOH) of lithium-ion batteries (LIBs). However, accurate prediction of SOH still needs improvement due to the complex battery aging mechanism. This paper introduces a hybrid kernel extremum learning machine (HKELM) for estimating battery SOH. To improve estimation accuracy, we enhance the standard dung beetle optimization algorithm (DBO) with a new initialized population, adaptive weights method, and improved population diversification. We then use the enhanced IDBO algorithm to optimize the parameters of HKELM. This study examines two distinct anode types of LIBs from NASA and Oxford datasets. Fifty significant features are extracted from charging voltage, current, temperature, and incremental capacity (IC) curves. The importance indices of these features are then computed using statistical analyses, including Pearson's correlation coefficient and Spearman's rank correlation coefficient, followed by optimal ranking. The optimal number of final features is determined by comparing various combinations of high-level features, thus reducing model complexity and improving estimation accuracy. This paper proposes the IDBO-HKELM algorithm for SOH estimation. Compared to other methods, the algorithm shows superior estimation performance and anti-interference capability. Both B0007 and Cell8 estimate SOH with MAE < 0.15, RMSE <0.2, and R2 > 99.9 %. Experimental results demonstrate the robustness of the proposed method, achieving accurate and noise-immune SOH estimation.

Privately evaluating sensitive population record linkage without ground truth data

AbstractData containing personal information allow detailed studies in the health and social sciences, such as population-related analysis. However, such studies often require the linking of two or more databases because information about a person can be scattered across multiple data sources. To address this issue of data being scattered, researchers have been working on linking records across multiple data sources to identify records that refer to the same person, or the same group of individuals (known as group linkage) using quasi-identifiers such as names and addresses which can be missing, out of date or contain errors or variations, making record linkage a very challenging task. Record linkage applications often also lack ground truth data in the form of matching and non-matching record pairs, which challenges the assessment of the quality of linkage algorithms. Furthermore, when linkage is conducted on sensitive data, for example personal health records, due to privacy concerns ground truth can generally not be obtained using methods such as crowd sourcing. This study therefore aims to develop methods to assess the linkage quality of sensitive data by using publicly available data sets, such as census or voter data, in a privacy-preserving manner, with a focus on the group linkage problem. Assuming that distinct groups, such as siblings in a family, are identifiable in both the sensitive and public data sets, we develop a novel method to estimate linkage quality using public data by encoding information that is commonly available in both sensitive and public data sets into a common representation using Bloom filters. Comparing these Bloom filters then allows the estimation of linkage quality. An evaluation using a real sensitive birth data set and a public census data set from Scotland shows the effectiveness of our proposed method for quality estimation, which achieves a median correlation of 98% with linkage quality calculated based on ground truth data.

Probability density estimation of polynomial chaos and its application in structural reliability analysis

Polynomial chaos expansion (PCE) is a widely used approach for establishing the surrogate model of a time-consuming performance function for the convenience of uncertainty quantification of a stochastic structure. However, it remains difficult to calculate the probability density function (PDF) of the PCE accurately for general cases, though the PDF, as a complete representation of a random variable, is often required in some uncertainty problems. To address this problem, this paper proposes a semi-analytical method to compute the PDF of a PCE. This method derives the closed-form solutions of characteristic functions (CFs) of the first- and second-order PCEs, while an equivalent parabolization technique is proposed to provide the approximate solutions of CFs of higher-order PCEs. Then, the PDF of the PCE can be obtained by the Fourier transform of the resulting CF. Three numerical examples are investigated to demonstrate the accuracy, applicability, and efficiency of the proposed method for probability density estimation of PCE in structural reliability analysis.

Analyzing the permeability distribution of multilayered specimens using pulsed eddy-current testing with multi-scale 1D-ResNet

The mechanical properties of steel are determined by its microstructure, which is closely related to its permeability profile. In thermal processing, layered structures are formed in steel and different layers have different mechanical and magnetic properties. Therefore, it is crucial to propose a practical method to monitor the change of permeability profile along the depth, which can indicate the evolution of the microstructure of steel during thermal processing, such as hot rolling. This paper presents a method for determining the layered structure and permeability profile of the steel by using pulsed eddy current testing (PECT), which offers better penetration ability. An analytical model has been deduced for calculating the time-domain pulsed eddy current (PEC) response from a Hall sensor of a triple-layer conductor system based on the inverse Laplace transform. It is found the Tau (τ) curve is closely related to the permeability profile of the conductor. For the inverse solution, the Simultaneous Iterative Reconstruction Technique (SIRT) is utilized to determine the permeability profile of the multilayered specimens from the measured response. The approximate Jacobian matrix (sensitivity matrix) is obtained by the perturbation method based on the Tau curve. However, the permeability profile suffers from smoothing effect and sharp features are lost. Deep learning (DL) algorithm based on the Multi-Scale 1D-ResNet model is therefore introduced to address this issue. Numerical simulations and experiments have been performed to evaluate the proposed method for permeability profile estimation with various materials and thicknesses. The DL method can achieve an accurate estimation of the plate permeability profile with a relative error under 5%.

Fractal Characterization on Three-Dimensional Tortuosity of Fault Tectonic

Faults, as a kind of fracture tectonics, play a role in reservoir closure or provide oil and gas transportation channels. The accurate understanding of the distribution characteristics of faults is significant for oil and gas exploration. The traditional fractal dimension for fault number (Df3) cannot comprehensively characterize the complexity and heterogeneity of fault network distribution. In this paper, a fractal characterization method on three-dimensional (3D) tortuosity of fault tectonics is proposed based on 3D seismic exploration. The methodology is described in detail to establish the model on the fractal dimension for the 3D tortuosity of fault tectonics. The results show the proposed method of estimation of the DT3 displaying high accuracy and rationality. Compared with the traditional fractal dimension Df3, the proposed DT3 can comprehensively characterize the fractal characteristics of faults network systems in the 3D space. This study achieves a breakthrough in the fractal characterization of the 3D tortuosity of fault tectonics. It is worth further study for establishing an analytical fractal equation based on the DT3 and oil or gas transfer, which can provide the theoretical foundation and technical support for oil and gas exploration.

Incorporating Digital Footprints into Credit-Scoring Models through Model Averaging

Digital footprints provide crucial insights into individuals’ behaviors and preferences. Their role in credit scoring is becoming increasingly significant. Therefore, it is crucial to combine digital footprint data with traditional data for personal credit scoring. This paper proposes a novel credit-scoring model. First, lasso-logistic regression is used to select key variables that significantly impact the prediction results. Then, digital footprint variables are categorized based on business understanding, and candidate models are constructed from various combinations of these groups. Finally, the optimal weight is selected by minimizing the Kullback–Leibler loss. Subsequently, the final prediction model is constructed. Empirical analysis validates the advantages and feasibility of the proposed method in variable selection, coefficient estimation, and predictive accuracy. Furthermore, the model-averaging method provides the weights for each candidate model, providing managerial implications to identify beneficial variable combinations for credit scoring.

Dixon-based B0 self-navigation in radial stack-of-stars multi-echo gradient echo imaging.

To develop a Dixon-based self-navigation approach to estimate and correct temporal variations in radial stack-of-stars gradient echo imaging for quantitative body MRI. The proposed method estimates temporal variations using a self-navigator estimated by a graph-cut-based water-fat separation algorithm on the oversampled k-space center. The self-navigator was employed to correct for phase differences between radial spokes (one-dimensional [1D] correction) and to perform a motion-resolved reconstruction to correct spatiotemporal pseudo-periodic variations (three-dimensional [3D] correction). Numerical simulations, phantom experiments and in vivo neck scans were performed to evaluate the effects of temporal variations on the field-map, proton density fat fraction (PDFF) and map, and to validate the proposed method. Temporal variations were found to cause signal loss and phase shifts on the multi-echo images that lead to an underestimation of , while PDFF mapping was less affected. The self-navigator captured slowly varying temporal drifts and temporal variations caused by respiratory motion. While the 1D correction effectively corrected drifts in phantom studies, it was insufficient in vivo due to 3D spatially varying temporal variations with amplitudes of up to 25 Hz at 3 T near the lungs. The proposed 3D correction locally improved the correction of field-map and and reduced image artifacts. Temporal variations particularly affect mapping in radial stack-of-stars imaging. The self-navigation approach can be applied without modifying the MR acquisition to correct for drift and physiological motion-induced variations, especially in the presence of fat.

Bayesian Optimization for State and Parameter Estimation of Dynamic Networks with Binary Space.

This paper focuses on joint state and parameter estimation in partially observed Boolean dynamical systems (POBDS), a hidden Markov model tailored for modeling complex networks with binary state variables. The majority of current techniques for parameter estimation rely on computationally expensive gradient-based methods, which become intractable in most practical applications with large size of networks. We propose a gradient-free approach that uses Gaussian processes to model the expensive log-likelihood function and utilizes Bayesian optimization for efficient likelihood search over parameter space. Joint state estimation is also achieved alongside parameter estimation using the Boolean Kalman filter. The performance of the proposed method is demonstrated using gene regulatory networks observed through synthetic gene-expression data. The numerical results demonstrate the scalability and effectiveness of the proposed method in the joint estimation of the model parameters and genes' states.

Marginalized LASSO in the low-dimensional difference-based partially linear model for variable selection

The difference-based partially linear model is an appropriate regression model when both linear and nonlinear predictors are present in the data. However, when we want to optimize the weights using the difference-based method, the problem of variable selection can be difficult since low-variance predictors present a challenge. Therefore, this study aims to establish a novel methodology based on marginal theory to tackle such mixed relationships successfully, emphasizing variable selection in low dimensions. We suggest using a marginalized LASSO estimator with a penalty term that is not as severe and related to the difference order. As part of our numerical analysis of small sample performance, we undertake comprehensive simulation experiments to numerically demonstrate the strength of our proposed technique in estimation and prediction compared to the LASSO under a low-dimensional setup. This is done so that we can numerically demonstrate the strength of our proposed method in estimation and prediction. The bootstrapped method is utilized to evaluate how well our proposed prediction method performs when examining the King House dataset.

Stiffness-Based Evaluation of Hinge Joints in Prefabricated Assembled Multi-Girder Bridges under Operational Conditions.

Presently, the prevailing approaches to assessing hinge joint damage predominantly rely on predefined damage indicators or updating finite element models (FEMs). However, these methods possess certain limitations. The damage indicator method requires high-quality monitoring data and demonstrates variable sensitivities of distinct indicators to damage. On the other hand, the FEM approach mandates a convoluted FEM update procedure. Hinge joint damage represents a major kind of defect in prefabricated assembled multi-girder bridges (AMGBs). Therefore, effective damage detection methods are imperative to identify the damage state of hinge joints. To this end, a stiffness-based method for the performance evaluation of hinge joints of AMGBs is proposed in this paper. The proposed method estimates hinge joint stiffness by solving the characteristic equations of the multi-beam system. In addition, this study introduces a method for determining baseline joint stiffness using design data and FEM. Subsequently, a comprehensive evaluation framework for hinge joints is formulated, coupling a finite element model with the baseline stiffness, thereby introducing a damage indicator rooted in stiffness ratios. To verify the effectiveness of the proposed method, strain and displacement correlations are analyzed using actual bridge monitoring data, and articulation joint stiffness is identified. The results underscore the capability of the proposed method to accurately pinpoint the location and extent of hinge joint damage.

Low-rank tensor regression for selection of grouped variables

Low-rank tensor regression (LRTR) problems are widely studied in statistics and machine learning, in which the regressors are generally grouped by clustering strongly correlated variables or variables corresponding to different levels of the same predictive factor in many practical applications. By virtue of the idea of group selection in the classical linear regression framework, we propose an LRTR method for adaptive selection of grouped variables in this article, which is formulated as a group SLOPE penalized low-rank, orthogonally decomposable tensor optimization problem. Moreover, we introduce the notion of tensor group false discovery rate (TgFDR) to measure the group selection performance. The proposed regression method provably controls TgFDR and achieves the asymptotically minimax estimate under the assumption that variable groups are orthogonal to each other. Finally, an alternating minimization algorithm is developed for efficient problem resolution. We demonstrate the performance of our proposed method in group selection and low-rank estimation through simulation studies and real dataset analysis.

Sleep Stage Estimation by Introduction of Sleep Domain Knowledge to AI: Towards Personalized Sleep Counseling System with GenAI

As a first step towards realizing an AI sleep counselor capable of generating personalized advice, this paper proposes a method for monitoring daily sleep conditions with a mattress sensor. To improve the accuracy of sleep stage estimation and to get accurate sleep structure, this paper introduced sleep domain knowledge to machine learning for improving the accuracy of sleep stage estimation. Concretely, the proposed method estimates ultradian rhythm based on the body movement density, updates prediction probabilities of each sleep stage by ML model and applies WAKE/NR3 detection based on the large/small body movement. Through the human subject experiment, the following implications have been revealed: (1) the proposed method improved the percentage of Accuracy by 65.0% from 61.5% and the QWK score by 0.196 from 0.297 by the conventional machine learning method; (2) the proposed method prevents over-NR12 estimating and is useful for understanding sleep structure by estimating REM sleep and NR3 sleep correctly. (3) the correct estimation of ultradian rhythms significantly improved the sleep stage estimation, with an Accuracy of 77.6% and a QWK score of 0.52 when all subjects' ultradian rhythms were estimated correctly.

Physics-Constraint Variational Neural Network for Wear State Assessment of External Gear Pump.

Most current data-driven prognosis approaches suffer from their uncontrollable and unexplainable properties. To address this issue, this article proposes a physics-constraint variational neural network (PCVNN) for wear state assessment of the external gear pump. First, a response model of the pressure pulsation of the gear pump is constructed via a spectral method, and a compound neural network is utilized to extract features from the pressure pulsation signal. Then, the response model is formulated into an objective function to softly constrain the learning process of the neural network, forcing the learned features to have explicit physics meaning. Meanwhile, to characterize the system uncertainty, the variational inference is utilized to extend a Kullback-Leibler (KL) divergence into the objective function. Finally, the wear state is evaluated based on the distance of learned physics features. Experimental results on an external gear pump validate the merits of the proposed method in explainable representation learning and system uncertainty estimation. It also offers a controllable and explainable perspective to understand the dynamic behavior of the system.

DeepMesh: Mesh-Based Cardiac Motion Tracking Using Deep Learning.

3D motion estimation from cine cardiac magnetic resonance (CMR) images is important for the assessment of cardiac function and the diagnosis of cardiovascular diseases. Current state-of-the art methods focus on estimating dense pixel-/voxel-wise motion fields in image space, which ignores the fact that motion estimation is only relevant and useful within the anatomical objects of interest, e.g., the heart. In this work, we model the heart as a 3D mesh consisting of epi- and endocardial surfaces. We propose a novel learning framework, DeepMesh, which propagates a template heart mesh to a subject space and estimates the 3D motion of the heart mesh from CMR images for individual subjects. In DeepMesh, the heart mesh of the end-diastolic frame of an individual subject is first reconstructed from the template mesh. Mesh-based 3D motion fields with respect to the end-diastolic frame are then estimated from 2D short- and long-axis CMR images. By developing a differentiable mesh-to-image rasterizer, DeepMesh is able to leverage 2D shape information from multiple anatomical views for 3D mesh reconstruction and mesh motion estimation. The proposed method estimates vertex-wise displacement and thus maintains vertex correspondences between time frames, which is important for the quantitative assessment of cardiac function across different subjects and populations. We evaluate DeepMesh on CMR images acquired from the UK Biobank. We focus on 3D motion estimation of the left ventricle in this work. Experimental results show that the proposed method quantitatively and qualitatively outperforms other image-based and mesh-based cardiac motion tracking methods.

Self-administered questionnaires enhance emotion estimation of individuals with autism spectrum disorders in a robotic interview setting.

Robots offer many unique opportunities for helping individuals with autism spectrum disorders (ASD). Determining the optimal motion of robots when interacting with individuals with ASD is important for achieving more natural human-robot interactions and for exploiting the full potential of robotic interventions. Most prior studies have used supervised machine learning (ML) of user behavioral data to enable robot perception of affective states (i.e., arousal and valence) and engagement. It has previously been suggested that including personal demographic information in the identification of individuals with ASD is important for developing an automated system to perceive individual affective states and engagement. In this study, we hypothesized that assessing self-administered questionnaire data would contribute to the development of an automated estimation of the affective state and engagement when individuals with ASD are interviewed by an Android robot, which will be linked to implementing long-term interventions and maintaining the motivation of participants. Participants sat across a table from an android robot that played the role of the interviewer. Each participant underwent a mock job interview. Twenty-five participants with ASD (males 22, females 3, average chronological age = 22.8, average IQ = 94.04) completed the experiment. We collected multimodal data (i.e., audio, motion, gaze, and self-administered questionnaire data) to train a model to correctly classify the state of individuals with ASD when interviewed by an android robot. We demonstrated the technical feasibility of using ML to enable robot perception of affect and engagement of individuals with ASD based on multimodal data. For arousal and engagement, the area under the curve (AUC) values of the model estimates and expert coding were relatively high. Overall, the AUC values of arousal, valence, and engagement were improved by including self-administered questionnaire data in the classification. These findings support the hypothesis that assessing self-administered questionnaire data contributes to the development of an automated estimation of an individual's affective state and engagement. Given the efficacy of including self-administered questionnaire data, future studies should confirm the effectiveness of such long-term intervention with a robot to maintain participants' motivation based on the proposed method of emotion estimation.

Magnetic resonance imaging of blood perfusion rate based on Helmholtz decomposition of heat flux.

Objective.Thermal property (TP) maps of human tissues are useful for tumor treatment and diagnosis. In particular, the blood perfusion rate is significantly different for tumors and healthy tissues. Noninvasive techniques that reconstruct TPs from the temperature measured via magnetic resonance imaging (MRI) by solving an inverse bioheat transfer problem have been developed. A few conventional methods can reconstruct spatially varying TP distributions, but they have several limitations. First, most methods require the numerical Laplacian computation of the temperature, and hence they are sensitive to noise. In addition, some methods require the division of a region of interest (ROI) into sub-regions with homogeneous TPs using prior anatomical information, and they assume an unmeasurable initial temperature distribution. We propose a novel robust reconstruction method without the division of an ROI or the assumption of an initial temperature distribution.Approach.The proposed method estimates blood perfusion rate maps from relative temperature changes. This method avoids the computation of the Laplacian by using integral representations of the Helmholtz decomposition of the heat flux.Main Result.We compare the reconstruction results of the conventional and proposed methods using numerical simulations. The results indicate the robustness of the proposed method.Significance.This study suggests the feasibility of thermal property mapping with MRI using the robust proposed method.

An Efficient and Robust Estimation of Spatio‐Temporally Distributed Parameters in Dynamic Models by an Ensemble Kalman Filter

AbstractThe accuracy of Earth system models is compromised by unknown and/or unresolved dynamics, making the quantification of systematic model errors essential. While a model parameter estimation, which allows parameters to change spatio‐temporally, shows promise in quantifying and mitigating systematic model errors, the estimation of the spatio‐temporally distributed model parameters has been practically challenging. Here we present an efficient and practical method to estimate time‐varying parameters in high‐dimensional spaces. In our proposed method, Hybrid Offline and Online Parameter Estimation with ensemble Kalman filtering (HOOPE‐EnKF), model parameters estimated by EnKF are constrained by results of offline batch optimization, in which the posterior distribution of model parameters is obtained by comparing simulated and observed climatological variables. HOOPE‐EnKF outperforms the original EnKF in synthetic experiments using a two‐scale Lorenz96 model and a simple global general circulation model. One advantage of HOOPE‐EnKF over traditional EnKFs is that its performance is not greatly affected by inflation factors for model parameters, thus eliminating the need for extensive tuning of inflation factors. We thoroughly discuss the potential of HOOPE‐EnKF as a practical method for improving parameterizations of process‐based models and prediction in real‐world applications such as numerical weather prediction.

Coherent optical transmitter IQ imbalance mitigation with embedded carrier phase and frequency offset estimation.

We present a 4×4 real-valued channel equalizer with embedded phase estimator, designed for carrier phase and frequency offset estimation and compensation in coherent optical communications with in-phase/quadrature (IQ) impairments. These impairments include IQ timing skew, gain imbalance, and quadrature phase errors at the transmitter side. To achieve adaptive control of the equalizer's filter coefficients, we employ the decision-directed least mean square (DD-LMS) algorithm. This algorithm minimizes the error between the filter outputs and the desired signals in a symbol-by-symbol manner, resulting in faster channel coefficients adaptation speed. Simulation results for a 60 GBaud polarization-multiplexing 16 quadrature amplitude modulation (PM-16QAM) signal demonstrate that our proposed equalizer outperforms a 2×2 cascaded multi modulus algorithm-based (CMMA-based) equalizer, a 2×2 complex-valued method based on the DD-LMS algorithm, and the 4×4 real-valued equalizer without embedded frequency offset estimation (FOE), when the transmitter IQ impairments exist. Experimental validation is also conducted for the 60 GBaud PM-16QAM and 45 GBaud PM-64QAM signals. Similar to the simulation results, our experiments show that the proposed 4×4 real-valued equalizer with embedded FOE can achieve effective SNR penalties of less than 0.41 dB at 7 ps skew, 1.33 dB at 3.5 dB gain imbalance, and 1.64 dB at the bias voltage shift of 0.5 V for the 60 GBaud PM-16QAM signal. Finally, our experimental results confirm the effectiveness of our proposed method in carrier phase estimation as well as the frequency offset compensation, when compared with 4×4 real-valued equalizer without embedded FOE.

Optimizing photovoltaic models: A leader artificial ecosystem approach for accurate parameter estimation of dynamic and static three diode systems

AbstractThe utilization of accurate models is crucial in the various stages of development for photovoltaic (PV) systems. Modelling these systems effectively allows developers to assess new modifications prior to the manufacturing phase, resulting in cost and time savings. This research paper presents a viable approach to accurately estimate both static and dynamic PV models. The proposed estimation method relies on a novel and enhanced optimization algorithm called leader artificial ecosystem‐based optimization (LAEO), which improves upon the original artificial ecosystem‐based optimization (AEO). The proposed LAEO algorithm integrates the adaptive probability (AP) and leader‐based mutation‐selection strategies to enhance the search capability, improve the balance between exploration and exploitation, and overcome local optima. To evaluate the effectiveness of LAEO, it was tested on 23 different benchmark functions. Additionally, LAEO was applied to estimate the parameters of static three‐diode PV models, as well as integral‐order and fractional‐order dynamic models. This paper showcases practical implementations of photovoltaic (PV) parameter estimation in various scenarios, including the static three‐diode model, dynamic integral order model (IOM), and fractional order model (FOM). The results were assessed from various angles to examine the precision, performance, and stability of the LAEO algorithm.

A contact parameter estimation method for multi-modal robot locomotion on deformable granular terrains

AbstractIn this paper, we consider the problem of contact parameters (slippage and sinkage) estimation for multi-modal robot locomotion on granular terrains. To describe the contact events in the same framework for robots operated at different modes (e.g., wheel, leg), we propose a unified description of contact parameters for multi-modal robots. We also provide a parameter estimation method for multi-modal robots based on CNN and DWT (discrete wavelet transformation) techniques and verify its effectiveness over different types of granular terrains. Besides motion modes, this paper also considers the influence of slope angles and the robot’s handing angles over contact parameters. Through comparison and analysis of the prediction results, our method can not only effectively predict the contact parameters of multi-modal robot locomotion on a granular medium (better than $96\%$ accuracy) but also achieves the same or better performance when compared to other (direct) contact measurement methods designed for individual motion modes, that is, single-modal robots such as quadruped robots and mars rovers. Our proposed unified contact parameter estimation method can be useful for studying the interaction mechanics between multi-modal robots and granular terrains as well as terrain classification tasks due to its superior sensitivity which is analyzed in the experiments.