Model-based Method Research Articles

A Model-Free Deep Reinforcement Learning-Based Approach for Assessment of Real-Time PV Hosting Capacity

Assessments of the hosting capacity of electricity distribution networks are of paramount importance, as they facilitate the seamless integration of rooftop photovoltaic systems into the grid, accelerating the transition towards a more carbon neutral and sustainable system. This paper employs a deep reinforcement learning-based approach to evaluate the real-time hosting capacity of low voltage distribution networks in a model-free manner. The proposed approach only requires real-time customer voltage data and solar irradiation data to provide a fast and accurate estimate of real-time hosting capacity at each customer connection point. This study addresses the imperative for accurate electrical models, which are frequently unavailable, in evaluating the hosting capacity of electricity distribution networks. To meet this challenge, the proposed approach utilizes a deep neural network-based, data-driven model of a low-voltage electricity distribution network. This proposed methodology incorporates model-free elements, enhancing its adaptability and robustness. In addition, a comparative analysis between model-based and model-free hosting capacity assessment methods is presented, highlighting their respective strengths and weaknesses. The utilization of the proposed hosting capacity estimation model enables distribution network service providers to make well-informed decisions regarding grid planning, leading to cost minimization.

Electrothermal Model Based Remaining Charging Time Prediction of Lithium-Ion Batteries against Wide Temperature Range

Battery remaining charging time (RCT) prediction can facilitate charging management and alleviate mileage anxiety for electric vehicles (EVs). Also, it is of great significance to improve EV users' experience. However, the RCT for a lithium-ion battery pack in EVs changes with temperature and other battery parameters. This study proposes an electrothermal model-based method to accurately predict battery RCT. Firstly, a characteristic battery cell is adopted to represent the battery pack, thus an equivalent circuit model (ECM) of the characteristic battery cell is established to describe the electrical behaviors of a battery pack. Secondly, an equivalent thermal model (ETM) of the battery pack is developed by considering the influence of ambient temperature, thermal management, and battery connectors in the battery pack to calculate the temperature which is then fed back to the ECM to realize electrothermal coupling. Finally, the RCT prediction method is proposed based on the electrothermal model and validated in the wide temperature range from − 20 ℃ to 45 ℃. The experimental results show that the prediction error of the RCT in the whole temperature range is less than 1.5%.

Reconstruction method suitable for fast CT imaging

Reconstructing computed tomography (CT) images from an extremely limited set of projections is crucial in practical applications. As the available projections significantly decrease, traditional reconstruction and model-based iterative reconstruction methods become constrained. This work aims to seek a reconstruction method applicable to fast CT imaging when available projections are highly sparse. To minimize the time and cost associated with projections acquisition, we propose a deep learning model, X-CTReNet, which parameterizes a nonlinear mapping function from orthogonal projections to CT volumes for 3D reconstruction. The proposed model demonstrates effective capability in inferring CT volumes from two-view projections compared to baseline methods, highlighting the significant potential for drastically reducing projection acquisition in fast CT imaging.

DF-QSM: Data Fidelity based Hybrid Approach for Improved Quantitative Susceptibility Mapping of the Brain.

Quantitative Susceptibility Mapping (QSM) is an advanced magnetic resonance imaging (MRI) technique to quantify the magnetic susceptibility of the tissue under investigation. Deep learning methods have shown promising results in deconvolving the susceptibility distribution from the measured local field obtained from the MR phase. Although existing deep learning based QSM methods can produce high-quality reconstruction, they are highly biased toward training data distribution with less scope for generalizability. This work proposes a hybrid two-step reconstruction approach to improve deep learning based QSM reconstruction. The susceptibility map prediction obtained from the deep learning methods has been refined in the framework developed in this work to ensure consistency with the measured local field. The developed method was validated on existing deep learning and model-based deep learning methods for susceptibility mapping of the brain. The developed method resulted in improved reconstruction for MRI volumes obtained with different acquisition settings, including deep learning models trained on constrained (limited) data settings.

RobEns: Robust Ensemble Adversarial Machine Learning Framework for Securing IoT Traffic.

Recently, Machine Learning (ML)-based solutions have been widely adopted to tackle the wide range of security challenges that have affected the progress of the Internet of Things (IoT) in various domains. Despite the reported promising results, the ML-based Intrusion Detection System (IDS) proved to be vulnerable to adversarial examples, which pose an increasing threat. In fact, attackers employ Adversarial Machine Learning (AML) to cause severe performance degradation and thereby evade detection systems. This promoted the need for reliable defense strategies to handle performance and ensure secure networks. This work introduces RobEns, a robust ensemble framework that aims at: (i) exploiting state-of-the-art ML-based models alongside ensemble models for IDSs in the IoT network; (ii) investigating the impact of evasion AML attacks against the provided models within a black-box scenario; and (iii) evaluating the robustness of the considered models after deploying relevant defense methods. In particular, four typical AML attacks are considered to investigate six ML-based IDSs using three benchmarking datasets. Moreover, multi-class classification scenarios are designed to assess the performance of each attack type. The experiments indicated a drastic drop in detection accuracy for some attempts. To harden the IDS even further, two defense mechanisms were derived from both data-based and model-based methods. Specifically, these methods relied on feature squeezing as well as adversarial training defense strategies. They yielded promising results, enhanced robustness, and maintained standard accuracy in the presence or absence of adversaries. The obtained results proved the efficiency of the proposed framework in robustifying IDS performance within the IoT context. In particular, the accuracy reached 100% for black-box attack scenarios while preserving the accuracy in the absence of attacks as well.

Field-balancing alignment of the secondary mirror of space telescope using a self-calibrated model

In-orbit alignment of the secondary mirror (SM) of deployable space telescopes is crucial for high-resolution imaging. Traditional alignment methods, which typically involve dedicated wavefront sensors or numerous iterations to optimize a metric function, are not well-suited for space applications. In this paper, an improved model-based SM alignment method is proposed. The term model refers to the relationship between misalignments and a metric function. The improved method offers two advantages over the previous model-based method in [12]. Firstly, our method allows for self-calibration of the model without the need for an additional wavefront sensor, which greatly simplifies the calibration process. Secondly, our method enables field-balancing alignment of the SM with several correction cycles. The exposure number is only six in one correction cycle and is regardless of the number of FOV sampling points, making it highly efficient for telescopes with a large FOV. The feasibility and performance of our method are verified by simulation. A comparison with existing methods is also given to show the advantages of our method in convergence speed and accuracy.

Convex model-based regularization method for force reconstruction

In the process of reconstructing structural forces, the influence of measurement errors and inherent model inaccuracies cannot be ignored. These errors exhibit a degree of correlation, and the presence of such correlation inevitably affects the quantification of uncertainties in force reconstruction. Objectively, the inherent ill-posed nature of structural inverse problems makes it difficult to obtain the forces to be identified, subject to uncertainties and highly susceptible to perturbations. Consequently, this paper introduces a force reconstruction regularization approach that explicitly considers the correlation of uncertainty parameters based on the truncated singular value regularization method. The primary objective is to refine the influence of uncertainties on the reconstructed force bounds with greater precision. When determining robust regularization parameters, the generalized cross-validation method and convex modelling approach are introduced to consider the uncertainty and its correlation in solving inverse problems. The proposed approach is rigorously validated through a comprehensive numerical case study. Error indexes and dispersion indices are employed to analyze the impact of different levels of noise and correlation on force reconstruction results. The force bounds obtained using the proposed method are compared with Monte Carlo simulation results. Finally, the validity of the proposed method is verified by an experiment with a four-story shear frame.

A defect opening profile reconstruction method based on multidirectional magnetic flux leakage detection

Magnetic flux leakage (MFL) is a popular technique for detecting defects. The opening profile reconstruction is one of the most popular concerns. The commonly used unidirectional magnetization-based methods easily lead to incomplete MFL information to reconstruct the opening profile. The superimposition of MFL signals from different directions would cause information cancellation, making it difficult for the existing data processing methods to reconstruct. To solve the issues, this study constructs a model-based method to inverse defect opening profiles. It builds the forward equations from one magnetic permeability to multidirectional MFL fields. Then the pseudo-inversion with Tikhonov regularization is applied as the inversion algorithm. The algorithm associates the forward equations and finds the solution that can fulfill them simultaneously. Such a method can combine multidirectional MFL information without cancellation. It reduces the ill-posed problems that exist in unidirectional inversion and makes the reconstructed profile complete and accurate. The comparison experiments have been carried out, and the results have proved the high accuracy of the proposed method.

The 3 + 3 design in dose-finding studies with small sample sizes: Pitfalls and possible remedies.

In the last few years, numerous novel designs have been proposed to improve the efficiency and accuracy of phase I trials to identify the maximum-tolerated dose (MTD) or the optimal biological dose (OBD) for noncytotoxic agents. However, the conventional 3+3 approach, known for its and poor performance, continues to be an attractive choice for many trials despite these alternative suggestions. The article seeks to underscore the importance of moving beyond the 3+3 design by highlighting a different key element in trial design: the estimation of sample size and its crucial role in predicting toxicity and determining the MTD. We use simulation studies to compare the performance of the most used phase I approaches: 3+3, Continual Reassessment Method (CRM), Keyboard and Bayesian Optimal Interval (BOIN) designs regarding three key operating characteristics: the percentage of correct selection of the true MTD, the average number of patients allocated per dose level, and the average total sample size. The simulation results consistently show that the 3+3 algorithm underperforms in comparison to model-based and model-assisted designs across all scenarios and metrics. The 3+3 method yields significantly lower (up to three times) probabilities in identifying the correct MTD, often selecting doses one or even two levels below the actual MTD. The 3+3 design allocates significantly fewer patients at the true MTD, assigns higher numbers to lower dose levels, and rarely explores doses above the target dose-limiting toxicity (DLT) rate. The overall performance of the 3+3 method is suboptimal, with a high level of unexplained uncertainty and significant implications for accurately determining the MTD. While the primary focus of the article is to demonstrate the limitations of the 3+3 algorithm, the question remains about the preferred alternative approach. The intention is not to definitively recommend one model-based or model-assisted method over others, as their performance can vary based on parameters and model specifications. However, the presented results indicate that the CRM, Keyboard, and BOIN designs consistently outperform the 3+3 and offer improved efficiency and precision in determining the MTD, which is crucial in early-phase clinical trials.

3D cine-magnetic resonance imaging using spatial and temporal implicit neural representation learning (STINR-MR).

Objective. 3D cine-magnetic resonance imaging (cine-MRI) can capture images of the human body volume with high spatial and temporal resolutions to study anatomical dynamics. However, the reconstruction of 3D cine-MRI is challenged by highly under-sampled k-space data in each dynamic (cine) frame, due to the slow speed of MR signal acquisition. We proposed a machine learning-based framework, spatial and temporal implicit neural representation learning (STINR-MR), for accurate 3D cine-MRI reconstruction from highly under-sampled data.Approach. STINR-MR used a joint reconstruction and deformable registration approach to achieve a high acceleration factor for cine volumetric imaging. It addressed the ill-posed spatiotemporal reconstruction problem by solving a reference-frame 3D MR image and a corresponding motion model that deforms the reference frame to each cine frame. The reference-frame 3D MR image was reconstructed as a spatial implicit neural representation (INR) network, which learns the mapping from input 3D spatial coordinates to corresponding MR values. The dynamic motion model was constructed via a temporal INR, as well as basis deformation vector fields (DVFs) extracted from prior/onboard 4D-MRIs using principal component analysis. The learned temporal INR encodes input time points and outputs corresponding weighting factors to combine the basis DVFs into time-resolved motion fields that represent cine-frame-specific dynamics. STINR-MR was evaluated using MR data simulated from the 4D extended cardiac-torso (XCAT) digital phantom, as well as two MR datasets acquired clinically from human subjects. Its reconstruction accuracy was also compared with that of the model-based non-rigid motion estimation method (MR-MOTUS) and a deep learning-based method (TEMPEST).Main results. STINR-MR can reconstruct 3D cine-MR images with high temporal (<100 ms) and spatial (3 mm) resolutions. Compared with MR-MOTUS and TEMPEST, STINR-MR consistently reconstructed images with better image quality and fewer artifacts and achieved superior tumor localization accuracy via the solved dynamic DVFs. For the XCAT study, STINR reconstructed the tumors to a mean ± SD center-of-mass error of 0.9 ± 0.4 mm, compared to 3.4 ± 1.0 mm of the MR-MOTUS method. The high-frame-rate reconstruction capability of STINR-MR allows different irregular motion patterns to be accurately captured.Significance. STINR-MR provides a lightweight and efficient framework for accurate 3D cine-MRI reconstruction. It is a 'one-shot' method that does not require external data for pre-training, allowing it to avoid generalizability issues typically encountered in deep learning-based methods.

A machine learning approach for protected species bycatch estimation

IntroductionMonitoring bycatch of protected species is a fisheries management priority. In practice, protected species bycatch is difficult to precisely or accurately estimate with commonly used ratio estimators or parametric, linear model-based methods. Machine-learning algorithms have been proposed as means of overcoming some of the analytical hurdles in estimating protected species bycatch.MethodsUsing 17 years of set-specific bycatch data derived from 100% observer coverage of the Hawaii shallow-set longline fishery and 25 aligned environmental predictors, we evaluated a new approach for protected species bycatch estimation using Ensemble Random Forests (ERFs). We tested the ability of ERFs to predict interactions with five protected species with varying levels of bycatch in the fishery and methods for correcting these predictions using Type I and Type II error rates from the training data. We also assessed the amount of training data needed to inform a ERF approach by mimicking the sequential addition of new data in each subsequent fishing year.ResultsWe showed that ERF bycatch estimation was most effective for species with greater than 2% interaction rates and error correction improved bycatch estimates for all species but introduced a tendency to regress estimates towards mean rates in the training data. Training data needs differed among species but those above 2% interaction rates required 7-12 years of bycatch data.DiscussionOur machine learning approach can improve bycatch estimates for rare species but comparisons are needed to other approaches to assess which methods perform best for hyperrare species.

An Overview of Diagnosis Methods of Stator Winding Inter-Turn Short Faults in Permanent-Magnet Synchronous Motors for Electric Vehicles

This article provides a comprehensive overview of state-of-the-art techniques for detecting and diagnosing stator winding inter-turn short faults (ITSFs) in permanent-magnet synchronous motors (PMSMs) for electric vehicles (EVs). The review focuses on the following three main categories of diagnostic approaches: motor model-based, signal processing-based, and artificial intelligence (AI)-based fault detection and diagnosis methods. Motor model-based methods utilize motor state estimation and motor parameter estimation as the primary strategies for ITSF diagnosis. Signal processing-based techniques extract fault signatures from motor measured data across time, frequency, or time-frequency domains. In contrast, AI-based methods automatically extract higher-order fault signatures from large volumes of preprocessed data, thereby enhancing the effectiveness of fault diagnosis. The strengths and limitations of each approach are thoroughly examined, providing valuable insights into the advancements in ITSF detection and diagnosis techniques for PMSMs in EV applications. The emphasis is placed on the application of signal processing methods and deep learning techniques in the diagnosis of ITSF in PMSMs in EV applications.

A data-adaptive methods in detecting exogenous methyltransferase accessible chromatin in human genome using nanopore sequencing.

Identifying chromatin accessibility is one of the key steps in studying the regulation of eukaryotic genomes. The combination of exogenous methyltransferase and nanopore sequencing provides an strategy to identify open chromatin over long genomic ranges at the single-molecule scale. However, endogenous methylation, non-open-chromatin-specific exogenous methylation and base-calling errors limit the accuracy and hinders its application to complex genomes. We systematically evaluated the impact of these three influence factors, and developed a model-based computational method, methyltransferase accessible genome region finder (MAGNIFIER), to address the issues. By incorporating control data, MAGNIFIER attenuates the three influence factors with data-adaptive comparison strategy. We demonstrate that MAGNIFIER is not only sensitive to identify the open chromatin with much improved accuracy, but also able to detect the chromatin accessibility of repetitive regions that are missed by NGS-based methods. By incorporating long-read RNA-seq data, we revealed the association between the accessible Alu elements and non-classic gene isoforms. Freely available on web at https://github.com/Goatofmountain/MAGNIFIER.

Self-supervised enhanced denoising diffusion for anomaly detection

Generative models have significantly enhanced anomaly detection through their powerful ability to model data. However, many existing generative model-based anomaly detection methods prioritize refining the generative process while overlooking the importance of acquiring discriminative data representations, which is suboptimal. Furthermore, the intricate architectures of these methods contribute to poor model convergence, resulting in coarse data reconstructions and diminished performance. To address the above problems, we propose self-supervised enhanced denoising diffusion for anomaly detection (SDAD) to detect anomalies effectively. Specifically, SDAD acquires discriminative data representations through an auxiliary learning module with two pretext tasks, facilitating the distinction between normal data and abnormal data. Subsequently, a denoising diffusion module is used to accurately learn the normal data distribution, serving as a benchmark for anomaly detection. Extensive experiments on ten real-world datasets demonstrate the remarkable advantages of SDAD over nine state-of-the-art anomaly detection methods, as evidenced by significant improvements across various evaluation metrics.

Linewidth characterization of a self-traceable grating by SEM

To achieve high-precision nanometrology, a self-traceable grating reference material has been reported and prepared using atom lithography and soft x-ray interference techniques (Liu et al 2021 Nanotechnology 32 175 301). In this work, we employ a Monte Carlo simulation method to investigate the scanning electron microscopy (SEM) image contrast and linewidth characterization of the grating linewidth. The 3D structure of mushroom-shaped grating lines made of multilayers (Pt, SiO2 and Si) is modeled according to transmission electron microscopy (TEM) images, enabling the SEM linescan profiles of secondary electron signals to be obtained for different values of structural linewidth parameters from Monte Carlo simulations. Using the principle of the model-based library method, a model database of Monte Carlo-simulated SEM linescan profiles is thus constructed by varying the incident electron beam conditions and the grating linewidths; then, the grating linewidth is successfully characterized using experimental SEM images. The comparison with the TEM measurement reveals that the measurement accuracy is verified to within 0.3% for the linewidth of ∼25 nm.

An Instrumental Variable Approach to Learning the Causal Exposure–Response Relationship in a Randomized Dose Comparison Trial

We consider the problem of estimating the causal effect of drug exposure on clinical response in a randomized dose comparison trial where each group receives a different dose. Because exposure is not randomized, the exposure–response relationship is subject to confounding in this setting. Conventional statistical methods for confounding adjustment with a continuous exposure typically assume that there are no unmeasured confounders. This article provides an instrumental variable approach that does not require the assumption of no unmeasured confounders. Specifically, we use randomized dose assignment as an instrumental variable and characterize the causal exposure–response relationship using a control variable under a mild monotonicity assumption on individual dose–exposure profiles. Based on this characterization, we derive partial identification bounds for the causal exposure–response relationship, which are model-free but may be too wide to be useful in practice. For practicality, we further develop a simple estimation method based on a regression model for the mean response conditional on exposure and the control variable. Simulation results show that, in the presence of unmeasured confounding, the model-based estimation method reduces estimation bias effectively at the expense of increased variability, as compared to existing methods. The method is illustrated with real data from a study of chimeric antigen receptor T cell therapy for treating chronic lymphocytic leukemia.

Predicting cytogenetic risk in multiple myeloma using conventional whole-body MRI, spinal dynamic contrast-enhanced MRI, and spinal diffusion-weighted imaging

ObjectivesCytogenetic abnormalities are predictors of poor prognosis in multiple myeloma (MM). This paper aims to build and validate a multiparametric conventional and functional whole-body MRI-based prediction model for cytogenetic risk classification in newly diagnosed MM.MethodsPatients with newly diagnosed MM who underwent multiparametric conventional whole-body MRI, spinal dynamic contrast-enhanced (DCE-)MRI, spinal diffusion-weighted MRI (DWI) and had genetic analysis were retrospectively included (2011–2020/Ghent University Hospital/Belgium). Patients were stratified into standard versus intermediate/high cytogenetic risk groups. After segmentation, 303 MRI features were extracted. Univariate and model-based methods were evaluated for feature and model selection. Testing was performed using receiver operating characteristic (ROC) and precision-recall curves. Models comparing the performance for genetic risk classification of the entire MRI protocol and of all MRI sequences separately were evaluated, including all features. Four final models, including only the top three most predictive features, were evaluated.ResultsThirty-one patients were enrolled (mean age 66 ± 7 years, 15 men, 13 intermediate-/high-risk genetics). None of the univariate models and none of the models with all features included achieved good performance. The best performing model with only the three most predictive features and including all MRI sequences reached a ROC-area-under-the-curve of 0.80 and precision-recall-area-under-the-curve of 0.79. The highest statistical performance was reached when all three MRI sequences were combined (conventional whole-body MRI + DCE-MRI + DWI). Conventional MRI always outperformed the other sequences. DCE-MRI always outperformed DWI, except for specificity.ConclusionsA multiparametric MRI-based model has a better performance in the noninvasive prediction of high-risk cytogenetics in newly diagnosed MM than conventional MRI alone.Critical relevance statementAn elaborate multiparametric MRI-based model performs better than conventional MRI alone for the noninvasive prediction of high-risk cytogenetics in newly diagnosed multiple myeloma; this opens opportunities to assess genetic heterogeneity thus overcoming sampling bias.Key points• Standard genetic techniques in multiple myeloma patients suffer from sampling bias due to tumoral heterogeneity.• Multiparametric MRI noninvasively predicts genetic risk in multiple myeloma.• Combined conventional anatomical MRI, DCE-MRI, and DWI had the highest statistical performance to predict genetic risk.• Conventional MRI alone always outperformed DCE-MRI and DWI separately to predict genetic risk. DCE-MRI alone always outperformed DWI separately, except for the parameter specificity to predict genetic risk.• This multiparametric MRI-based genetic risk prediction model opens opportunities to noninvasively assess genetic heterogeneity thereby overcoming sampling bias in predicting genetic risk in multiple myeloma.Graphical

FusionDiff: A unified image fusion network based on diffusion probabilistic models

This paper introduces FusionDiff, a novel unified end-to-end image fusion network based on diffusion probabilistic models. The proposed method addresses the data dependency issue present in current unified image fusion approaches. Initially, the method pre-fuses the source images after diffusion. Subsequently, a noise prediction network forecasts the noise applied to the pre-fused image. During this stage, the Spatially-Adaptive Constraint layer is employed to restrict the fusion image, thereby maximizing the preservation of respective source image features. Finally, in the reverse process, skip-sampling is employed to effectively overcome the computational time drawback of traditional diffusion probabilistic models while maintaining high-quality image generation. Compared to other diffusion model-based image fusion methods, our approach stands out for its structural simplicity and ease of training, serving as a unified image fusion method. Furthermore, compared to other unified image fusion methods, our proposed network fully leverages the generalization of the diffusion probabilistic model, achieving adaptive feature extraction by constraining the inverse process of source images. Qualitative and quantitative experimental results across four classic image fusion tasks demonstrate the superiority of our method over state-of-the-art unified image fusion methods in recent years.

Fault-Tolerant Control for Aircraft with Structural Damage Using Sparse Online Gaussian Process Regression

This paper presents the design of data-driven fault-tolerant control using sparse online Gaussian process regression (SOGPR) to stabilize an aircraft with left-wing damage. The structural damage causes changes in mass, moment of inertia, center of gravity, and aerodynamic coefficients. These parameter variations deteriorate the performance of model-based nonlinear control methods. Hence, Gaussian process-based nonlinear dynamic inversion (GP-NDI) is proposed to compensate for uncertainties in situations of structural damage. Unlike parametric adaptive control approaches, Gaussian process regression is a non-parametric method that does not need prior information about uncertainties. And the proposed method implements SOGPR to reduce computational time and memory by incrementally updating the mean and variance. To compensate for the error in the estimated uncertainty, a robust control input is designed. In addition, a weighted delete score is used to improve the transient response. Numerical simulation results are compared with model reference adaptive control (MRAC) and nonlinear disturbance observer (NDO) to analyze a stabilizing and tracking performance in a structural damage situation.

A Deep Reinforcement Learning Model-based Optimization Method for Graphic Design

A Deep Reinforcement Learning Model-based Optimization Method for Graphic Design