Iterative Framework Research Articles

Sparse Inversion for the Iterative Marchenko Scheme of Irregularly Sampled Data

The Marchenko method is a data-driven way that makes it possible to calculate Green’s functions from virtual points in the subsurface using the reflection data at the surface and requiring only a macro velocity model. This method requires collocated sources and receivers. However, in practice, irregular sampling of sources or receivers will cause gaps and distortions in the obtained focusing functions and Green’s functions. To solve this problem, this paper proposes to integrate a sparse inversion into the iterative Marchenko scheme. Specifically, we add sparsity constraints to the Marchenko equations and apply the sparse inversion during the iterative process. To reduce the strict requirements on acquisition geometries, our work deals with the situation in which the sources are subsampled where the integrations are carried out over the receivers, while the existing point spread function method solves the situation where the receivers are subsampled. We make a step to handle both situations at the same time by integrating this method with our work because of the same iterative framework. Our new method is applied to a two-dimensional numerical example with irregularly sampled data. The result shows that it can effectively fill gaps in the obtained focusing functions and Green’s functions in the Marchenko method.

Global iterative optimization framework for predicting cognitive function statuses of patients with end‐stage renal disease

AbstractThe existing methods to determine the cognitive function level of end‐stage renal disease (ESRD) are not only inaccurate but also susceptible to the influence of the patient's education level, emotional state, and examination environment. We proposed a global iterative optimization framework (GIO) to accurately predict cognitive function statuses of ESRD patients without being affected by the above factors. First, the functional magnetic resonance imaging (fMRI) data preprocessed and the time series were extracted to construct brain functional networks. Secondly, the areas under curve (AUC) of topological attribute parameters in the brain functional networks were extracted as features. After statistical analysis, the global efficiency, the characteristic path length, and the shortest path length in the small‐world network were selected as features for linear fusion. Finally, the support vector regression (SVR) was used as the basis of GIO framework, and the global iterative search strategy was introduced to find out the most appropriate penalty factor and radial basis function parameters. Achieving the objective of accurately predicting the cognitive function status of patients with end‐stage renal disease. Since this framework uses SVR which has special advantages in processing small sample data, and introduces appropriate parameter selection method, the prediction ability of GIO framework has been significantly improved. Experimental results demonstrate that the final prediction accuracy of the proposed framework is significantly better than those of SVR, LSSVR, GMO‐SVR, GMO‐LSSVR, and PSO‐SVR. The mean absolute error (MAE) and the mean absolute percentage error (MAPE) of the proposed framework are 0.55% and 2.58%, respectively. It is suggested that this framework is more convenient to determine the current level of cognitive function in ESRD patients and is conducive to the early prevention of cognitive dysfunction in ESRD patients.

Using physical property surrogate models to perform accelerated multi-fidelity optimization of force field parameters.

Accurate representations of van der Waals dispersion-repulsion interactions play an important role in high-quality molecular dynamics simulations. Training the force field parameters used in the Lennard Jones (LJ) potential typically used to represent these interactions is challenging, generally requiring adjustment based on simulations of macroscopic physical properties. The large computational expense of these simulations, especially when many parameters must be trained simultaneously, limits the size of training data set and number of optimization steps that can be taken, often requiring modelers to perform optimizations within a local parameter region. To allow for more global LJ parameter optimization against large training sets, we introduce a multi-fidelity optimization technique which uses Gaussian process surrogate modeling to build inexpensive models of physical properties as a function of LJ parameters. This approach allows for fast evaluation of approximate objective functions, greatly accelerating searches over parameter space and enabling the use of optimization algorithms capable of searching more globally. In this study, we use an iterative framework which performs global optimization with differential evolution at the surrogate level, followed by validation at the simulation level and surrogate refinement. Using this technique on two previously studied training sets, containing up to 195 physical property targets, we refit a subset of the LJ parameters for the OpenFF 1.0.0 (Parsley) force field. We demonstrate that this multi-fidelity technique can find improved parameter sets compared to a purely simulation-based optimization by searching more broadly and escaping local minima. Additionally, this technique often finds significantly different parameter minima that have comparably accurate performance. In most cases, these parameter sets are transferable to other similar molecules in a test set. Our multi-fidelity technique provides a platform for rapid, more global optimization of molecular models against physical properties, as well as a number of opportunities for further refinement of the technique.

The evaluation of the Plan-Do-Study-Act cycles for a healthcare quality improvement intervention in primary care.

The Plan-Do-Study-Act (PDSA) cycle is an iterative framework that has been gaining traction in primary care for quality improvement. However, its implementation remains understudied. This study evaluated the completion, achievement of goal, content quality, and enablers and barriers associated with completion of high-quality PDSA cycles in cardiovascular disease management in general practices. This study analysed data from intervention practices of the QUality improvement in primary care to prevent hospitalisations and improve Effectiveness and efficiency of care for people Living people with coronary heart disease (QUEL) study. Content quality of cycles was assessed using a scoring system created based on established criteria of ideal PDSA cycles in the healthcare context. Practice-level factors associated with completion and cycles achieving the planned goal were explored through logistic regression models, and with content quality score through linear regression model. Enablers and barriers were assessed using thematic analysis of practices' responses to the PDSA sections. Ninety-seven cycles were reported by 18/26 (69%) practices. Seventy-seven percent of the cycles were completed and 68% achieved the planned goal. Content quality was low, with a median score of 56% (interquartile interval: 44%, 67%). Odds of cycles that were completed and achieved what was planned increased by 3.6- and 9.6-fold, respectively, with more general practitioners (GPs) within practices. Content quality was higher by 15% with more GPs. Lack of interprofessional engagement was a barrier to implementation. Cycles were well completed, but poor in content quality, with high variability between practices. Human or capital resources and organisational support may be critical for the completion and cycles achieving the planned goals.

DREAM-Net: Deep Residual Error Iterative Minimization Network for Sparse-View CT Reconstruction.

Sparse-view Computed Tomography (CT) has the ability to reduce radiation dose and shorten the scan time, while the severe streak artifacts will compromise anatomical information. How to reconstruct high-quality images from sparsely sampled projections is a challenging ill-posed problem. In this context, we propose the unrolled Deep Residual Error iterAtive Minimization Network (DREAM-Net) based on a novel iterative reconstruction framework to synergize the merits of deep learning and iterative reconstruction. DREAM-Net performs constraints using deep neural networks in the projection domain, residual space, and image domain simultaneously, which is different from the routine practice in deep iterative reconstruction frameworks. First, a projection inpainting module completes the missing views to fully explore the latent relationship between projection data and reconstructed images. Then, the residual awareness module attempts to estimate the accurate residual image after transforming the projection error into the image space. Finally, the image refinement module learns a non-standard regularizer to further fine-tune the intermediate image. There is no need to empirically adjust the weights of different terms in DREAM-Net because the hyper-parameters are embedded implicitly in network modules. Qualitative and quantitative results have demonstrated the promising performance of DREAM-Net in artifact removal and structural fidelity.

Discriminating Acute Respiratory Distress Syndrome from other forms of respiratory failure via iterative machine learning

Acute Respiratory Distress Syndrome (ARDS) is associated with high morbidity and mortality. Identification of ARDS enables lung protective strategies, quality improvement interventions, and clinical trial enrolment, but remains challenging particularly in the first 24 hours of mechanical ventilation. To address this we built an algorithm capable of discriminating ARDS from other similarly presenting disorders immediately following mechanical ventilation. Specifically, a clinical team examined medical records from 1263 ICU-admitted, mechanically ventilated patients, retrospectively assigning each patient a diagnosis of “ARDS” or “non-ARDS” (e.g., pulmonary edema). Exploiting data readily available in the clinical setting, including patient demographics, laboratory test results from before the initiation of mechanical ventilation, and features extracted by natural language processing of radiology reports, we applied an iterative pre-processing and machine learning framework. The resulting model successfully discriminated ARDS from non-ARDS causes of respiratory failure (AUC = 0.85) among patients meeting Berlin criteria for severe hypoxia. This analysis also highlighted novel patient variables that were informative for identifying ARDS in ICU settings.

Research on Power IoT System Based City Block Air Pollutant Emission Prediction

In order to constantly improve city environmental air quality, it is necessary to accurately control the major pollutants emissions such as air fine particulate matter. By adopting the proposed iterative update framework of air pollutant emission inventory, combined with block-level real-time electricity consumption data acquired by the smart city power IoT, and utilizing station-level and hourly environmental air quality monitoring data in specific areas of Yuxi and Dali in Yunnan Province from 2020 to 2021, the iterative update of emission inventory and prediction of air pollutant emission are studied. The experimental results shows that the prediction of the monthly average major air pollutants emissions such as NO2/PM10/PM2.5 in specific neighbourhoods of the two cities mentioned above reaches the same accuracy level as using numerical simulation prediction methods, but the prediction computational power requirements are greatly reduced, making it more suitable for the application requirements of the power IoT. This study provides a new idea for improving the regulatory capacity of intelligent environment and achieving higher urban air quality based on the smart city power IoT.

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

Iterative Retinex-Based Decomposition Framework for Low Light Visibility Restoration

Double-Iterative Gaussian Process Regression for Modeling Error Compensation in Autonomous Racing

Autonomous racing control is a challenging research problem as vehicles are pushed to their limits of handling to achieve an optimal lap time; therefore, vehicles exhibit highly nonlinear and complex dynamics. Difficult-to-model effects, such as drifting, aerodynamics, chassis weight transfer, and suspension can lead to infeasible and suboptimal trajectories. While offline planning allows optimizing a full reference trajectory for the minimum lap time objective, such modeling discrepancies are particularly detrimental when using offline planning, as planning model errors compound with controller modeling errors. Gaussian Process Regression (GPR) can compensate for modeling errors. However, previous works primarily focus on modeling error in real-time control without consideration for how the model used in offline planning can affect the overall performance. In this work, we propose a double-GPR error compensation algorithm to reduce model uncertainties; specifically, we compensate both the planner's model and controller's model with two respective GPR-based error compensation functions. Furthermore, we design an iterative framework to re-collect error-rich data using the racing control system. We test our method in the high-fidelity racing simulator Gran Turismo Sport (GTS); we find that our iterative, double-GPR compensation functions improve racing performance and iteration stability in comparison to a single compensation function applied merely for real-time control.

AI-dente: an open machine learning based tool to interpret nano-indentation data of soft tissues and materials.

Nano-indentation is a promising method to identify the constitutive parameters of soft materials, including soft tissues. Especially when materials are very small and heterogeneous, nano-indentation allows mechanical interrogation where traditional methods may fail. However, because nano-indentation does not yield a homogeneous deformation field, interpreting the resulting load-displacement curves is non-trivial and most investigators resort to simplified approaches based on the Hertzian solution. Unfortunately, for small samples and large indentation depths, these solutions are inaccurate. We set out to use machine learning to provide an alternative strategy. We first used the finite element method to create a large synthetic data set. We then used these data to train neural networks to inversely identify material parameters from load-displacement curves. To this end, we took two different approaches. First, we learned the indentation forward problem, which we then applied within an iterative framework to identify material parameters. Second, we learned the inverse problem of directly identifying material parameters. We show that both approaches are effective at identifying the parameters of the neo-Hookean and Gent models. Specifically, when applied to synthetic data, our approaches are accurate even for small sample sizes and at deep indentation. Additionally, our approaches are fast, especially compared to the inverse finite element approach. Finally, our approaches worked on unseen experimental data from thin mouse brain samples. Here, our approaches proved robust to experimental noise across over 1000 samples. By providing open access to our data and code, we hope to support others that conduct nano-indentation on soft materials.

Iterative framework for image registration and partial volume correction in brain positron emission tomography

Iterative framework for image registration and partial volume correction in brain positron emission tomography

Joint optimization of train scheduling and routing in a coupled multi-resolution space–time railway network

Train scheduling and routing are two critical and fundamental problems in the field of railway operations, especially under the large demand scenarios or complicated operation schemes. These problems are often solved separately and sequentially from the perspectives of different decision stages. To further make these two decision-making processes consistent, this paper develops a joint optimization model in a multi-resolution space–time network, by coupling the conflict-free routing constraints into the train scheduling process. To solve this model, a feedback iterative framework consisting of the Lagrangian relaxation and the branch-and-bound algorithm is developed, in which the Lagrangian relaxation aims to generate the train schedule and the branch-and-bound strategy with the constraint updating procedure resolves the potential micro conflicts. Compared with some existing approaches in the literature, the proposed model and solution algorithm have the merit of no requirement of optimization solvers. To test the performance of the proposed approach, we apply the algorithm to different small-scale operation scenarios and a real-life case with the INFORMS RAS 2016 (Railway Applications Section) dataset.

A framework for using real-time evaluative interview feedback for health promotion program and evaluation improvement: The Check It case study

Formative evaluation is a crucial strategy for health promotion program improvement. Early and ongoing formative evaluation can make a major impact on program outcomes; however, there are few frameworks that provide actual guidance on how programmatic or research teams can systematically perform this kind of important work. In this article we describe the use of an iterative real-time interview feedback framework we developed for Check It, a community-wide chlamydia screening and treatment program for young African American men in New Orleans, Louisiana. The framework considers the diverse and needed perspectives of multiple stakeholders, including participants, interviewers, transcribers, program staff, and lead researchers and/or administrators. Interviews were conducted with N = 15 Check It participants utilizing this approach. Employing the framework led to critical insights that resulted in several vital programmatic and evaluation improvements. Lessons learned, including strengths and challenges of utilizing the framework, are also shared so that this model can be replicated or adapted by program planning and evaluation professionals for other kinds of programs.

Development of a multi-objectives integer programming model for allocation of anti-fraud capacities during cyberfraud mitigation

PurposeThis study aims to investigate the feasibility of employing a multi-objectives integer-programming model for effective allocation of resources for cyberfraud mitigation. The formulated objectives are the minimisation of the total allocation cost of the anti-fraud capacities and the maximisation of the forensic accounting capacities in all cyberfraud incident prone spots.Design/methodology/approachFrom the literature survey conducted and primary qualitative data gathered from the 17 licenced banks in South Africa on fraud investigators, the suggested fraud investigators are the organisation’s finance department, the internal audit committee, the external risk manager, accountants and forensic accountants. These five human resource capacities were considered for the formulation of the multi-objectives integer programming (MOIP) model. The MOIP model is employed for the optimisation of the employed capacities for cyberfraud mitigation to ensure the effective allocation and utilisation of human resources. Thus, the MOIP model is validated by a genetic algorithm (GA) solver to obtain the Pareto-optimum solution without the violation of the identified constraints.FindingsThe formulated objective functions are optimised simultaneously. The Pareto front for the two objectives of the MOIP model comprises the set of optimal solutions, which are not dominated by any other feasible solution. These are the feasible choices, which indicate the suitability of the MOIP to achieve the set objectives.Practical implicationsThe results obtained indicate the feasibility of simultaneously achieving the minimisation of the total allocation cost of the anti-fraud capacities, or the maximisation of the forensic accounting capacities in all cyberfraud incident prone spots – or the trade-off between them, if they cannot be reached simultaneously. This study recommends the use of an iterative MOIP framework for decision-makers which may aid decision-making with respect to the allocation and utilisation of human resources.Originality/valueThe originality of this work lies in the development of multi-objectives integer-programming model for effective allocation of resources for cyberfraud mitigation.

Iterative optical diffraction tomography with embedded regularization.

Total-variation regularization is applied at each iteration of an iterative framework for optical diffraction tomography. Numerical and experimental tests are performed using various highly scattering objects, and significant improvement in reconstruction SNR are demonstrated.

X-ray CT image denoising with MINF: A modularized iterative network framework for data from multiple dose levels

In clinical applications, multi-dose scan protocols will cause the noise levels of computed tomography (CT) images to fluctuate widely. The popular low-dose CT (LDCT) denoising network outputs denoised images through an end-to-end mapping between an LDCT image and its corresponding ground truth. The limitation of this method is that the reduced noise level of the image may not meet the diagnostic needs of doctors. To establish a denoising model adapted to the multi-noise levels robustness, we proposed a novel and efficient modularized iterative network framework (MINF) to learn the feature of the original LDCT and the outputs of the previous modules, which can be reused in each following module. The proposed network can achieve the goal of gradual denoising, outputting clinical images with different denoising levels, and providing the reviewing physicians with increased confidence in their diagnosis. Moreover, a multi-scale convolutional neural network (MCNN) module is designed to extract as much feature information as possible during the network's training. Extensive experiments on public and private clinical datasets were carried out, and comparisons with several state-of-the-art methods show that the proposed method can achieve satisfactory results for noise suppression of LDCT images. In further comparisons with modularized adaptive processing neural network (MAP-NN), the proposed network shows superior step-by-step or gradual denoising performance. Considering the high quality of gradual denoising results, the proposed method can obtain satisfactory performance in terms of image contrast and detail protection as the level of denoising increases, which shows its potential to be suitable for a multi-dose levels denoising task.

End-to-End One-Shot Path-Planning Algorithm for an Autonomous Vehicle Based on a Convolutional Neural Network Considering Traversability Cost.

Path planning plays an important role in navigation and motion planning for robotics and automated driving applications. Most existing methods use iterative frameworks to calculate and plan the optimal path from the starting point to the endpoint. Iterative planning algorithms can be slow on large maps or long paths. This work introduces an end-to-end path-planning algorithm based on a fully convolutional neural network (FCNN) for grid maps with the concept of the traversability cost, and this trains a general path-planning model for 10 × 10 to 80 × 80 square and rectangular maps. The algorithm outputs the lowest-cost path while considering the cost and the shortest path without considering the cost. The FCNN model analyzes the grid map information and outputs two probability maps, which show the probability of each point in the lowest-cost path and the shortest path. Based on the probability maps, the actual optimal path is reconstructed by using the highest probability method. The proposed method has superior speed advantages over traditional algorithms. On test maps of different sizes and shapes, for the lowest-cost path and the shortest path, the average optimal rates were 72.7% and 78.2%, the average success rates were 95.1% and 92.5%, and the average length rates were 1.04 and 1.03, respectively.

New Aspects of Solution Feasibility in a Context of Personalized Therapy Optimization

In this work, the feasibility of a personalized therapy design is considered. We attempt to determine whether all of the obtained results of computer simulations should be presented to medical personnel. For this purpose, a two-drug displacement problem was used, which is the starting point of this research work. The relationships that can be used to characterize the progress as well as the efficiency of treatment in advanced cases can be modeled by a system of nonlinear dynamical equations with additional algebraic dependencies (differential-algebraic equations, DAEs). Then, to improve the efficiency of the therapy, an optimization task needs to be formulated and solved. The solution should meet all the assumed requirements and expectations. Therefore, a control vector parametrization (CVP) procedure for a DAE model is often suggested as an appropriate tool for solving the optimization-based therapy design tasks. In this work, a general iterative optimization framework is discussed in detail together with the proposed three levels of solution feasibility which try to decide if the iteratively obtained solution is trustworthy. The CVP optimization procedure with the designed levels of solution feasibility are implemented and tested. The obtained results are discussed from the perspective of their practical use in the treatment process. It is worth noting that solutions that are valuable from the perspective of creating new optimization algorithms may be rejected by the final recipient as devoid of application possibilities. Some of the presented solutions can be considered as a reference in further clinical research.

Iterative solution methods for 3D controlled-source electromagnetic forward modelling of geophysical exploration scenarios

We develop an efficient and robust iterative framework suitable for solving the linear system of equations resulting from the spectral element discretisation of the curl-curl equation of the total electric field encountered in geophysical controlled-source electromagnetic applications. We use the real-valued equivalent form of the original complex-valued system and solve this arising real-valued two-by-two block system (outer system) using the generalised conjugate residual method preconditioned with a highly efficient block-based PREconditioner for Square Blocks (PRESB). Applying this preconditioner equates to solving two smaller inner symmetric systems which are either solved using a direct solver or iterative methods, namely the generalised conjugate residual or the flexible generalised minimal residual methods preconditioned with the multigrid-based auxiliary-space preconditioner AMS. Our numerical experiments demonstrate the robustness of the outer solver with respect to spatially variable material parameters, for a wide frequency range of five orders of magnitude (0.1-10’000 Hz), with respect to the number of degrees of freedom, and for stretched structured and unstructured as well as locally refined meshes. For all the models considered, the outer solver reaches convergence in a small (typically < 20) number of iterations. Further, our numerical tests clearly show that solving the two inner systems iteratively using the indicated preconditioned iterative methods is computationally beneficial in terms of memory requirement and time spent as compared to a direct solver. On top of that, our iterative framework works for large-scale problems where direct solvers applied to the original complex-valued systems succumb due to their excessive memory consumption, thus making the iterative framework better suited for large-scale 3D problems. Comparison to a similar iterative framework based on a block-diagonal and the auxiliary-space preconditioners reveals that the PRESB preconditioner requires slightly fewer iterations to converge yielding a certain gain in time spent to obtain the solution of the two-by-two block system.

Dispositional Mindfulness and the Process of Mindfulness Cultivation: A Qualitative Synthesis and Critical Assessment of the Extant Literature on the Five Facet Mindfulness Questionnaire (FFMQ)

Background: Over the last decades, mindfulness has become an important concept and topic for many professions and interventional research. While the number of available self-report scales and empirical studies on the concept of mindfulness has increased in recent years, some questions regarding its theoretical underpinnings still remain. Objective: The goal of this systematic review and qualitative synthesis was to investigate the distinction of cultivated and dispositional mindfulness. We focused on research with the Five Facet Mindfulness Questionnaire (FFMQ) as it is both comprehensive (building on and incorporating other important mindfulness scales) and widely used. Data Sources: Journal articles and dissertations listed in Google Scholar, ProQuest, Scopus, Web of Science, and World Cat from January 2006 until January 2020. Review Methods: 172 studies were identified and systematically analyzed in a two-step iterative qualitative coding framework with three main categories of interest: FFMQ and its facets, dispositional mindfulness, cultivated mindfulness. Results: We offer a broad summary of the extant literature on the concepts of dispositional and cultivated mindfulness in terms of their definition, the practice of mindfulness, their state and trait aspects, and their assessment with self-report scales. Based on this evidence, inference on cultivated and dispositional aspects in the individual FFMQ facets is also presented and discussed. Conclusion: Mindfulness cultivation is a process induced by mindfulness practice. Dispositional mindfulness functions as a baseline for this process. We argue that each FFMQ facet mixes cultivation and disposition, which might limit their usability in intervention studies or when comparing meditators and non-meditators. Future research should pay more attention on the cultivated and dispositional aspects of mindfulness, for which we offer venues and recommendations.