检索结果-内蒙古大学图书馆

Calibration and uncertainty quantification for deep learning-based drought detection

International Journal of Applied Earth Observation and Geoinformation 2025年 140卷

作者： Zhang, Mengxue Fernández-Torres, Miguel-Ángel Cohrs, Kai-Hendrik Camps-Valls, Gustau Image Processing Laboratory (IPL) Universitat de València Paterna València 46980 Spain Department of Signal Theory and Communications Universidad Carlos III de Madrid (UC3M) Madrid 28911 Spain

Droughts are hydrometeorological extreme events influenced by highly intricate land–atmosphere feedback mechanisms and climate variability. Deep learning models have recently succeeded in detecting extreme climate events and promise to uncover and understand droughts further. There are two main challenges of reliability and trustworthiness limiting their applications: miscalibration and inherent uncertainty. However, they remain rarely explored because deep learning models are overparameterized and seldom tractable. To address this shortcoming, we introduce methodologies for model calibration and entropy-based uncertainty quantification for deep learning-based drought detection. The calibration algorithm can deal with calibration errors by reducing distributional shifts and alleviating overconfident predictions. The uncertainty framework, in turn, decomposes and quantifies the total uncertainty according to several components: data uncertainty, procedural variability, parametric variability, and latent variability. Thus, our method identifies uncertain predictions and supports robust evaluations, benefiting the credibility of the decision-making process. Empirical evidence of performance in a wide range of European drought events is given, justifying the effectiveness of our approach. The calibration methodology yields the lowest expected calibration error (0.31%) and the precision of the uncertainty-based decision-making is improved from 72.27% to 74.06% and 76.59%, based on ensemble predictions and rejecting the predictions for the top 20% uncertain negative samples, respectively. In summary, our approach significantly enhances drought detection's reliability and classification accuracy, constituting a key step toward more trustworthy and actionable climate decision-making. © 2025 The Authors

关键词： Deep learning Drought detection Extreme climate events Model calibration Uncertainty quantification

来源：评论

学校读者我要写书评

暂无评论

Dynamics of Masked image Modeling in Hyperspectral image Classification

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Ma, Chen Li, Huayi Jiang, Junjun Aybar, Cesar Yao, Jiaqi Camps-Valls, Gustau Harbin Institute of Technology Research Center of Satellite Technology State Key Laboratory of Micro-Spacecraft Rapid Design and Intelligent Cluster School of Astronautics Harbin150001 China Harbin Institute of Technology School of Computer Science and Technology Harbin150001 China University of València Image Signal Processing Laboratory València46980 Spain Tianjin Normal University Tianjin300387 China

Masked image modeling (MIM), a common self-supervised learning (SSL) technique, has been extensively studied for remote sensing (RS) image processing. Nevertheless, its effectiveness for hyperspectral imagery (HSI) remains underexplored due to the distinct data structures and high dimensionality. This article aims to provide a detailed understanding of MIM from different perspectives of representation learning and statistical analysis for HSI classification tasks. Our study reveals that the MIM paradigm injects inductive bias in the attention mechanism of the transformer model, which is advantageous for capturing the local discrepancies between the spectra. We also show that MIM can increase the diversity of the attention heads in every layer, which is beneficial for the model in extracting more discriminative features from different spectral bands. The similarity of representations from various layers further proves this. Furthermore, our investigation highlights how MIM introduces a dynamic perspective to spectral representations, enabling the model to learn more robust and discriminative features. The final numerical experiments indicate that a moderate mask ratio can enhance the performance of downstream tasks. This suggests that designing a more targeted masking strategy might be necessary to achieve higher and more stable gains in downstream task performance. Without bells and whistles, the vanilla MIM improves the overall classification accuracy by an average of 2.69% over its supervised learning (SL) counterpart. We hope that our findings can advance the understanding of MIM in HSI and inspire the design of a more stable SSL paradigm for HSI processing. © 1980-2012 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Segmentation of Welding Defects using Level Set Methods

引用

JOURNAL OF ELECTRICAL ENGINEERING & TECHNOLOGY 2012年第6期7卷 1001-1008页

作者： Mohammed, Halimi Naim, Ramou Image and Signal Processing Laboratory. Welding and Control Research Center

Non-destructive testing (NDT) is a technique used in science and industry to evaluate the properties of a material without causing damage. In this paper we propose a method for segmenting radiographic images of welding in order to extract the welding defects which may occur during the welding process. We study different methods of level set and choose the model adapted to our application. The methods presented here take the property of local segmentation geodesic active contours and have the ability to change the topology automatically. The computation time is considerably reduced after taking into account a new level set function which eliminates the re-initialization procedure. Satisfactory results are obtained after applying this algorithm both on synthetic and real images.

关键词： image segmentation Level set Weld defects Radiographic image

来源：评论

学校读者我要写书评

暂无评论

EXTRAPOLATION ALGORITHMS FOR DISCRETE signalS WITH APPLICATION IN SPECTRAL ESTIMATION

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1981年第4期29卷 830-845页

作者： JAIN, AK RANGANATH, S Signal and Image Processing Laboratory University of California Davis CA USA

In this paper we present some new algorithms useful for extrapolation and spectral estimation of band-limited sequences in one and two dimensions. First we show that many of the existing extrapolation algorithms for noiseless observations are unified under the criterion of minimum norm least squares (MNLS) extrapolation. For example, the iterative algorithms proposed in [2] and [8]-[10] are shown to be special cases of a one-step gradient algorithm which has linear convergence. Convergence and other numerical properties are improved by going to a conjugate gradient algorithm. For noisy observations, these algorithms could be extended by considering a mean-square extrapolation criterion which gives rise to a mean-square extrapolation filter and also to a recursive extrapolation filter. Examples and application of these methods are given. Extension of these algorithms is made for problems where the signal is known to be periodic. A new set of functions called the periodic-discrete prolate spheroidal sequences (P-DPSS), analogous to DPSS [21], [22], are introduced and their properties are studied. Finally, several of these algorithms are generalized to two dimensions and the relevant equations are given.

关键词： Extrapolation Iterative algorithms Filters signal analysis Least squares methods Convergence of numerical methods Equations Fourier transforms signal processing image processing

来源：评论

学校读者我要写书评

暂无评论

Robust Optimization-based Neural Architectures Against Adversarial Attacks

Robust Optimization-based Neural Architectures Against Adver...

引用

IEEE SSD International Multi-Conference on Systems, signals and Devices

作者： Khaoula Ben Ali Seifeddine Messaoud Mohamed Ali Hajjaji Mohamed Atri Noureddine Liouane Laboratory of Automatic Signal Image Processing National Engineering School Monastir University Monastir Tunisia Faculty of Sciences of Monastir Monastir University Monastir Tunisia Higher Institute of Applied Sciences and Technology of Sousse Sousse University Sousse Tunisia Computer Engineering Department College of Computer Science King Khalid University Abha Saudi Arabia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

Recent years have seen a rapid development in Machine Learning, which has profoundly influenced many areas of science and engineering. Among them, computer vision takes the leading place, where important tasks are image classifications powered by CNNs. Despite the great performance of CNNs in complicated scenarios, they remain sensitive to so-called adversarial attacks, and deliberate perturbations leading them to incorrect predictions. Besides more innocuous consequences, this has serious security implications for critical applications, in-cluding medical diagnostics, where misclassifications might result in disastrous outcomes. This research work discusses adversarial attacks on CNNs and other DNNs in computer vision, studying a full range of the generation and detection methods with details while discussing intrinsic vulnerability and robustness. It also proposes a learning framework that will enhance the robustness and security of DNNs and CNNs against such adversarial perils. The ultimate goal is directed to an improvement in the reliability of such models in absolutely critical scenarios for safe deployment into applications where accuracy is crucial.

关键词： Computer vision Accuracy Perturbation methods Computer network reliability Machine learning Robustness Security Medical diagnosis Resilience image classification

来源：评论

学校读者我要写书评

暂无评论

Analyzing Cognitive Patterns in Gifted Children Using MRI and Morphometric Similarity Networks

Analyzing Cognitive Patterns in Gifted Children Using MRI an...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Han, Shuning Duan, Feng Vilaseca, Gemma Vilaró, Núria Caiafa, Cesar F. Sun, Zhe Solé-Casals, Jordi Data and Signal Processing Research Group University of Vic-Central University of Catalonia Vic Catalonia Spain Image Processing Research Group RIKEN Center for Advanced Photonics RIKEN Saitama Wako-Shi Japan Tianjin Key Laboratory of Brain Science and Intelligent Rehabilitation Nankai University Tianjin China Psychological Department Oms and Prat school Fundació Catalunya- La Pedrera Catalonia Manresa Spain Oms Foundation Catalonia Manresa Spain Instituto Argentino de Radioastronomıa-CCT La Plata CONICET / CIC-PBA / UNLP Argentina Faculty of Health Data Science Juntendo University Chiba Urayasu Japan Department of Psychiatry University of Cambridge Cambridge United Kingdom

Advances in non-invasive neuroimaging, such as structural magnetic resonance imaging (sMRI), have en abled the construction of structural brain networks (SBNs), allowing in vivo mapping of anatomical connec tions. This study investigates brain network structural differences linked to different intelligence levels in children by individual morphometric similarity networks (MSNs) derived from sMRI data. Through group and individual-level analyses, we aim to uncover key topological features associated with cognitive perfor mance and to identify a suitable connection density for SBN analysis. Connection density strongly affects global and nodal topological features, with a range of p = 0.05 to 0.15 recommended for stable and optimal results. Gifted individuals exhibit stronger intra-hemispheric and intra-modular connectivity, a more balanced distribution of left-to-right intra-hemispheric connections, and lower mean versatility, supporting efficient and stable cognitive processing. Moreover, anatomical modularity analyses based on von Economo indicate that higher cognitive performance is linked to enhanced connectivity in specific areas (such as secondary sensory area, motor to association area and secondary sensory to limbic area), alongside selective reduction in cer tain modular connections (such as motor to insular area, association to secondary sensory area and motor to secondary sensory area). Furthermore, topological features, including participation coefficient and local effi ciency, are linked to cognitive performance. These findings provide valuable insights into the SBNs underlying cognitive levels in children. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： Brain mapping

来源：评论

学校读者我要写书评

暂无评论

A NEW ALGORITHM FOR ADAPTIVE ARRAYS

引用

IEEE TRANSACTIONS ON ACOUSTICS SPEECH AND signal processing 1987年第9期35卷 1314-1319页

作者： GARDNER, WA BROWN, WA Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of California슠Davis Davis CA USA Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of California Davis Davis CA USA

A new deflected stochastic-gradient algorithm for adaptive sensor arrays is introduced. It is shown to have the capability of converging substantially faster than the nondeflected stochastic gradient (LMS) algorithm but slower than the recursive least squares (RLS) algorithm. Because of its amenability to reduction of computational complexity by data quantization, it has the potential for processing digital signals with bandwidths one to two orders of magnitude larger than the bandwidths manageable with the RLS algorithm for sensor arrays containing a number of adjustable weights in the approximate range of 10-50.

关键词： Adaptive arrays Sensor arrays Least squares approximation Resonance light scattering Bandwidth Stochastic processes Least squares methods Computational complexity Quantization signal processing

来源：评论

学校读者我要写书评

暂无评论

RECURSIVE BLOCK CODING - A NEW APPROACH TO TRANSFORM CODING

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1986年第2期34卷 161-179页

作者： FARRELLE, PM JAIN, AK Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of California Davis CA USA

The concept of fast KL transform coding introduced earlier [7], [8] for first-order Markov processes and certain random fields has been extended to higher order autoregressive (AR) sequences and practical images yielding what we call recursive block coding (RBC) algorithms. In general, the rate-distortion performance for these algorithms is significantly superior to that of the conventional block KL transform algorithm. Moreover, these algorithms permit the use of small size transforms, thereby removing the need for fast transforms and making the hardware implementation of such coders more appealing. This improved performance has been verified for practical image data and results in suppression of the block-boundary effect commonly observed in traditional transform coding techniques. This is illustrated by comparing RBC with cosine transform coding using both one- and twodimensional algorithms. Examples of RBC encoded images at various rates are given.

关键词： Transform coding Karhunen-Loeve transforms Block codes Data compression image coding signal processing image processing Bit rate Markov processes Rate-distortion

来源：评论

学校读者我要写书评

暂无评论

SPECTRAL CORRELATION OF MODULATED signalS - .1. ANALOG MODULATION

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1987年第6期35卷 584-594页

作者： GARDNER, WA Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of California Davis CA USA

The importance of the concept of cyclostationarity in design and analysis of signal detectors, synchronizers, and extractors in communication systems is briefly discussed, and the central role of spectral correlation, in the characterization of random processes that are cyclostationary in the wide sense, is explained. A spectral correlation function that is a generalization of the power spectral density function is described, and a corresponding generalization of the Wiener-Khinchine relation and several other fundamental spectral correlation relations also are described. Explicit formulas for the spectral correlation function for various types of analog-modulated signals are derived. This includes pulse and carrier amplitude modulation, quadrature amplitude carrier modulation, and phase and frequency carrier modulation. To illustrate the differing spectral correlation characteristics of different modulation types, the magnitudes of the spectral correlation functions are graphed or described in graphical terms as the heights of surfaces above a bifrequency plane.

关键词： Pulse modulation Amplitude modulation Phase modulation Quadrature amplitude modulation signal design signal analysis signal processing signal detection Detectors Frequency synchronization

来源：评论

学校读者我要写书评

暂无评论

SPECTRAL CORRELATION OF MODULATED signalS .2. DIGITAL MODULATION

引用

IEEE TRANSACTIONS ON COMMUNICATIONS 1987年第6期35卷 595-601页

作者： GARDNER, WA BROWN, WA CHEN, CK Signal and Image Processing Laboratory Department of Electrical and Computer Engineering University of California Davis CA USA

As a continuation of Part I, the spectral correlation function is presented for a variety of types of digitally modulated signals. These include digital pulse-amplitude, pulse-width, and pulse-position modulation, and various types of phase-shift keying and frequency-shift keying. The magnitudes of the spectral correlation functions are graphed as the heights of surfaces above a bifrequency plane, and these graphs are used as visual aids for comparison and contrast of the spectral correlation properties of different modulation types.

关键词： Digital modulation Space vector pulse width modulation signal processing Pulse modulation Phase shift keying Frequency shift keying Pulse width modulation Filters Matrices Parameter estimation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：