检索结果-南通市图书馆

Prediction of Uncertainty estimation and Confidence Calibration Using Fully Convolutional Neural Network

在线全文

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2023年第5期75卷 2557-2573页

作者： Karim Gasmi Lassaad Ben Ammar Hmoud Elshammari Fadwa Yahya Department of Computer Science College of Arts and Sciences at TabarjalJouf UniversityJoufSaudi Arabia College of Sciences and Humanities Prince Sattam Bin Abdulaziz UniversityAl-KharjSaudi Arabia University of Sfax SfaxTunisia Department of Information Systems College of Computer and Information SciencesJouf UniversityJoufSaudi Arabia

Convolution neural networks(CNNs)have proven to be effective clinical imagingmethods.This study highlighted some of the key issues within these systems.It is difficult to train these systems in a limited clinical image databases,and many publications present strategies including such learning algorithm.Furthermore,these patterns are known formaking a highly reliable prognosis.In addition,normalization of volume and losses of dice have been used effectively to accelerate and stabilize the training.Furthermore,these systems are improperly regulated,resulting in more confident ratings for correct and incorrect classification,which are inaccurate and difficult to understand.This study examines the risk assessment of Fully Convolutional Neural Networks(FCNNs)for clinical image segmentation.Essential contributions have been made to this planned work:1)dice loss and cross-entropy loss are compared on the basis of segment quality and uncertain assessment of FCNNs;2)proposal for a group model for assurance measurement of full convolutional neural networks trained with dice loss and group normalization;And 3)the ability of the measured FCNs to evaluate the segment quality of the structures and to identify test examples outside the distribution.To evaluate the study’s contributions,it conducted a series of tests in three clinical image division applications such as heart,brain and prostate.The findings of the study provide significant insights into the predictive ambiguity assessment and a practical strategies for outside-distribution identification and reliable measurement in the clinical image segmentation.The approaches presented in this research significantly enhance the reliability and accuracy rating of CNNbased clinical imaging methods.

关键词： Medical image segmentation confidence calibration Uncertainty estimation fully convolutional neural network

Optimal Parameter and Uncertainty estimation of a Land Surface Model: Sensitivity to Parameter Ranges and Model Complexities

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Advances in Atmospheric Sciences 2005年第1期22卷 142-157页

作者： YoulongXIA Zong-LiangYANG PaulL.STOFFA MrinalK.SEN InstituteforGeophysics TheJohnA.andKatherineG.JacksonSchoolofGeosciencesUniversityofTexasatAustin4412SpicewoodSpringRoadAustinTX78759-8500USA DepartmentofGeologicalSciences TheJohnA.andKatherineG.JacksonSchoolofGeosciencesUniversityofTexasatAustinUSA

Most previous land-surface model calibration studies have defined globalranges for their parameters to search for optimal parameter sets. Little work has been conducted tostudy the impacts of realistic versus global ranges as well as model complexities on the calibrationand uncertainty estimates. The primary purpose of this paper is to investigate these impacts byemploying Bayesian Stochastic Inversion (BSI) to the Chameleon Surface Model (CHASM). The CHASM wasdesigned to explore the general aspects of land-surface energy balance representation within acommon modeling framework that can be run from a simple energy balance formulation to a complexmosaic type structure. The BSI is an Uncertainty estimation technique based on Bayes theorem,importance sampling, and very fast simulated annealing. The model forcing data and surface flux datawere collected at seven sites representing a wide range of climate and vegetation conditions. Foreach site, four experiments were performed with simple and complex CHASM formulations as well asrealistic and global parameter ranges. Twenty eight experiments were conducted and 50 000 parametersets were used for each run. The results show that the use of global and realistic ranges givessimilar simulations for both modes for most sites, but the global ranges tend to produce someunreasonable optimal parameter values. Comparison of simple and complex modes shows that the simplemode has more parameters with unreasonable optimal values. Use of parameter ranges and modelcomplexities have significant impacts on frequency distribution of parameters, marginal posteriorprobability density functions, and estimates of uncertainty of simulated sensible and latent heatfluxes. Comparison between model complexity and parameter ranges shows that the former has moresignificant impacts on parameter and Uncertainty estimations.

关键词： optimal parameters Uncertainty estimation CHASM model bayesian stochasticinversion parameter ranges model complexities

Trajectory prediction of ballistic missiles using Gaussian process error model

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Aeronautics 2022年第1期35卷 458-469页

作者： Ruiping JI Yan LIANG Linfeng XU Zhenwei WEI School of Automation Northwestern Polytcchnical UniversityXi'an 710129China Key Laboratory of Information Fusion Technology Ministry of EducationXi'an 710129China

Ballistic Missile Trajectory Prediction(BMTP)is critical to air defense systems.Most Trajectory Prediction(TP)methods focus on the coast and reentry phases,in which the Ballistic Missile(BM)trajectories are modeled as ellipses or the state components are propagated by the dynamic integral equations on time scales.In contrast,the boost-phase TP is more challenging because there are many unknown forces acting on the BM in this phase.To tackle this difficult problem,a novel BMTP method by using Gaussian Processes(GPs)is proposed in this paper.In particular,the GP is employed to train the prediction error model of the boost-phase trajectory database,in which the error refers to the difference between the true BM state at the prediction moment and the integral extrapolation of the BM state.And the final BMTP is a combination of the dynamic equation based numerical integration and the GP-based prediction error.Since the trained GP aims to capture the relationship between the numerical integration and the unknown error,the modified BM state prediction is closer to the true one compared with the original TP.Furthermore,the GP is able to output the uncertainty information of the TP,which is of great significance for determining the warning range centered on the predicted BM state.Simulation results show that the proposed method effectively improves the BMTP accuracy during the boost phase and provides reliable Uncertainty estimation boundaries.

关键词： Ballistic missile Boost-phase trajectory State prediction Gaussian processes Uncertainty estimation

Machine learning for recovery factor estimation of an oil reservoir:A tool for derisking at a hydrocarbon asset evaluation

在线全文

学校读者我要写书评

暂无评论

Petroleum 2022年第2期8卷 278-290页

作者： Ivan Makhotin Denis Orlov Dmitry Koroteev Evgeny Burnaev Aram Karapetyan Dmitry Antonenko Skolkovo Institute of Science and Technology MoscowRussia JSC Zarubezhneft MoscowRussia

Well-known oil recovery factor estimation techniques such as analogy,volumetric calculations,material balance,decline curve analysis,hydrodynamic simulations have certain limitations.Those techniques are time-consuming,and require specific data and expert knowledge.Besides,though Uncertainty estimation is highly desirable for this problem,the methods above do not include this by default.In this work,we present a data-driven technique for oil recovery factor(limited to water flooding)estimation using reservoir parameters and representative statistics.We apply advanced machine learning methods to historical worldwide oilfields datasets(more than 2000 oil reservoirs).The data-driven model might be used as a general tool for rapid and completely objective estimation of the oil recovery factor.In addition,it includes the ability to work with partial input data and to estimate the prediction interval of the oil recovery factor.We perform the evaluation in terms of accuracy and prediction intervals coverage for several tree-based machine learning techniques in application to the following two cases:(1)using parameters only related to geometry,geology,transport,storage and fluid properties,(2)using an extended set of parameters including development and production data.For both cases,the model proved itself to be robust and reliable.We conclude that the proposed data-driven approach overcomes several limitations of the traditional methods and is suitable for rapid,reliable and objective estimation of oil recovery factor for hydrocarbon reservoir.

关键词： Oil recovery factor Machine learning Regression Uncertainty estimation Conformal predictors Clustering Oilfield Oil reservoir

RGB Image‑ and Lidar‑Based 3D Object Detection Under Multiple Lighting Scenarios

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Automotive Innovation 2022年第3期5卷 251-259页

作者： Wentao Chen Wei Tian Xiang Xie Wilhelm Stork School of Automotive Studies Tongji UniversityShanghaiChina Karlsruhe Institute of Technology 76131 KarlsruheGermany

In recent years,camera-and lidar-based 3D object detection has achieved great progress.However,the related researches mainly focus on normal illumination conditions;the performance of their 3D detection algorithms will decrease under low lighting scenarios such as in the night.This work attempts to improve the fusion strategies on 3D vehicle detection accuracy in multiple lighting conditions.First,distance and uncertainty information is incorporated to guide the“painting”of semantic information onto point cloud during the data preprocessing.Moreover,a multitask framework is designed,which incorpo-rates uncertainty learning to improve detection accuracy under low-illumination scenarios.In the validation on KITTI and Dark-KITTI benchmark,the proposed method increases the vehicle detection accuracy on the KITTI benchmark by 1.35%and the generality of the model is validated on the proposed Dark-KITTI dataset,with a gain of 0.64%for vehicle detection.

关键词： 3D object detection Multi-sensor fusion Uncertainty estimation Semantic segmentation PointPainting

Robust Control of Robotic Manipulators in the Task-Space Using an Adaptive Observer Based on Chebyshev Polynomials

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2020年第5期33卷 1360-1382页

作者： GHOLIPOUR Reza FATEH Mohammad Mehdi Department of Electrical and Robotic Engineering Shahrood University of Technology*** ShahroodIran

In this paper,an adaptive observer for robust control of robotic manipulators is proposed.The lumped uncertainty is estimated using Chebyshev polynomials.Usually,the uncertainty upper bound is required in designing observer-controller structures.However,obtaining this bound is a challenging task.To solve this problem,many Uncertainty estimation techniques have been proposed in the literature based on neuro-fuzzy systems.As an alternative,in this paper,Chebyshev polynomials have been applied to Uncertainty estimation due to their simpler structure and less computational load.Based on strictly-positive-rea Lyapunov theory,the stability of the closed-loop system can be verified.The Chebyshev coefficients are tuned based on the adaptation rules obtained in the stability analysis.Also,to compensate the truncation error of the Chebyshev polynomials,a continuous robust control term is designed while in previous related works,usually a discontinuous term is used.An SCARA manipulator actuated by permanent magnet DC motors is used for computer simulations.Simulation results reveal the superiority of the designed method.

关键词： Adaptive observer Chebyshev polynomials electrically driven robot manipulators robust control Uncertainty estimation

Logit prototype learning with active multimodal representation for robust open-set recognition

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第6期67卷 297-312页

作者： Yimin FU Zhunga LIU Zicheng WANG School of Automation Northwestern Polytechnical University

Robust open-set recognition(OSR) performance has become a prerequisite for pattern recognition systems in real-world applications. However, the existing OSR methods are primarily implemented on the basis of single-modal perception, and their performance is limited when single-modal data fail to provide sufficient descriptions of the objects. Although multimodal data can provide more comprehensive information than single-modal data, the learning of decision boundaries can be affected by the feature representation gap between different modalities. To effectively integrate multimodal data for robust OSR performance, we propose logit prototype learning(LPL) with active multimodal representation. In LPL, the input multimodal data are transformed into the logit space, enabling a direct exploration of intermodal correlations without the impact of scale inconsistency. Then, the fusion weights of each modality are determined using an entropybased Uncertainty estimation method. This approach realizes adaptive adjustment of the fusion strategy to provide comprehensive descriptions in the presence of external disturbances. Moreover, the single-modal and multimodal representations are jointly optimized interactively to learn discriminative decision boundaries.Finally, a stepwise recognition rule is employed to reduce the misclassification risk and facilitate the distinction between known and unknown classes. Extensive experiments on three multimodal datasets have been done to demonstrate the effectiveness of the proposed method.

关键词： logit prototype learning multimodal perception open-set recognition Uncertainty estimation

Sliding mode disturbance observer-based backstepping control for a transport aircraft

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2014年第5期57卷 228-243页

作者： ZHANG Chao CHEN ZongJi WEI Chen Science and Technology on Aircraft Control Laboratory Beihang University School of Automation Science and Electrical Engineering Beihang University

This paper presents a novel control method by integrating the sliding mode disturbance observerbased control and the backstepping control technique,and successfully applies it to a flight control system for heavy cargo airdrop operations.The super-twisting second order sliding mode disturbance observer(SOSMDO)is employed to estimate bounded but otherwise arbitrary disturbances,thus ensuring asymptotic convergence of the estimation error to zero in a finite time.Besides,the integrated controller can significantly improve the robustness of the flight control system to modeling uncertainty and external disturbance in the presence of state/control constraints.The closed-loop stability is guaranteed in the sense of Lyapunov.In addition,the proposed approach can considerably reduce design cycles.The performance of the proposed control method is demonstrated in a very low altitude extraction airdrop simulation with a high-fidelity six-degree-of-freedom transport aircraft model.

关键词： backstepping sliding mode disturbance observer flight control heavy cargo airdrop Uncertainty estimation

Mapping aboveground biomass and its prediction uncertainty using LiDAR and field data, accounting for tree-level allometric and LiDAR model errors

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Forest Ecosystems 2020年第3期7卷 562-578页

作者： Svetlana Saarela AndréWästlund Emma Holmström Alex Appiah Mensah Sören Holm Mats Nilsson Jonas Fridman Göran Ståhl Faculty of Forest Sciences Swedish University of Agricultural SciencesSLU Skogsmarksgränd 17UmeåSE-90183Sweden

Background: The increasing availability of remotely sensed data has recently challenged the traditional way of performing forest inventories, and induced an interest in model-based inference. Like traditional design-based inference, model-based inference allows for regional estimates of totals and means, but in addition for wall-to-wall mapping of forest characteristics. Recently Light Detection and Ranging(LiDAR)-based maps of forest attributes have been developed in many countries and been well received by users due to their accurate spatial representation of forest resources. However, the correspondence between such mapping and model-based inference is seldom appreciated. In this study we applied hierarchical model-based inference to produce aboveground biomass maps as well as maps of the corresponding prediction uncertainties with the same spatial resolution. Further, an estimator of mean biomass at regional level, and its uncertainty, was developed to demonstrate how mapping and regional level assessment can be combined within the framework of model-based inference.Results: Through a new version of hierarchical model-based estimation, allowing models to be nonlinear, we accounted for uncertainties in both the individual tree-level biomass models and the models linking plot level biomass predictions with LiDAR metrics. In a 5005 km2 large study area in south-central Sweden the predicted aboveground biomass at the level of 18 m×18 m map units was found to range between 9 and 447 Mg·ha^-1. The corresponding root mean square errors ranged between 10 and 162 Mg·ha^-1. For the entire study region, the mean aboveground biomass was 55 Mg·ha^-1 and the corresponding relative root mean square error 8%. At this level 75%of the mean square error was due to the uncertainty associated with tree-level models.Conclusions: Through the proposed method it is possible to link mapping and estimation within the framework of model-based inference. Uncertainties in both tree-level biomass models and models linking plot level biomas

关键词： Aboveground biomass assessment Forest mapping Gauss-Newton Regression Hierarchical Model-Based inference LiDAR maps National Forest Inventory Uncertainty estimation uncertainty map