Skip to Content
You are currently on the new version of our website. Access the old version .

4,828 Results Found

  • Article
  • Open Access
4 Citations
3,682 Views
20 Pages

3 August 2019

The utilization of gradient information is a key issue in building Scale Invariant Feature Transform (SIFT)-like descriptors. In the literature, two types of gradient information, i.e., Gradient Magnitude (GM) and Gradient Occurrence (GO), are used f...

  • Article
  • Open Access
1 Citations
1,299 Views
21 Pages

9 May 2025

With the development of intelligent transportation systems (ITS), individual travel prediction has become a key technology for optimizing urban transportation. However, deep learning models are limited in decision-sensitive scenarios due to their lac...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Feature Paper
  • Article
  • Open Access
3 Citations
2,141 Views
20 Pages

30 June 2025

We consider Onsager’s non-equilibrium thermodynamics from the perspective of the gradient flow in information geometry. Assuming Onsager’s reciprocal relations, we can regard his phenomenological equations as gradient-flow equations and d...

(This article belongs to the Section Non-equilibrium Phenomena)
  • Article
  • Open Access
3 Citations
2,098 Views
17 Pages

27 March 2025

Serious information loss often occurs when the input data undergoes the layer-by-layer feature extraction process through deep neural networks. In small-target detection tasks, this problem becomes more serious. The existing theory holds that the inf...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
1 Citations
1,643 Views
13 Pages

18 October 2024

Traffic sensors are vital to the development and operation of Intelligent Transportation Systems, providing essential data for traffic monitoring, management, and transportation infrastructure planning. However, optimizing the placement of these sens...

(This article belongs to the Section Information Applications)
  • Article
  • Open Access
6 Citations
2,284 Views
31 Pages

Dim and Small Target Detection Based on Energy Sensing of Local Multi-Directional Gradient Information

  • Xiangsuo Fan,
  • Juliu Li,
  • Lei Min,
  • Linping Feng and ,
  • Ling Yu and
  • Zhiyong Xu
  • + 1 author+ 0 author

25 June 2023

It is difficult for traditional algorithms to remove cloud edge contours in multi-cloud scenarios. In order to improve the detection ability of dim and small targets in complex edge contour scenes, this paper proposes a new dim and small target detec...

(This article belongs to the Special Issue Machine Vision and Advanced Image Processing in Remote Sensing II)
  • Article
  • Open Access
2 Citations
4,437 Views
21 Pages

Line Segment Matching Fusing Local Gradient Order and Non-Local Structure Information

  • Weibo Cai,
  • Jintao Cheng,
  • Juncan Deng,
  • Yubin Zhou and ,
  • Hua Xiao,
  • Jian Zhang and
  • Kaiqing Luo
  • + 2 authors+ 0 author

23 December 2021

Line segment matching is essential for industrial applications such as scene reconstruction, pattern recognition, and VSLAM. To achieve good performance under the scene with illumination changes, we propose a line segment matching method fusing local...

(This article belongs to the Special Issue Computational Sensing and Imaging)
  • Article
  • Open Access
1 Citations
2,022 Views
21 Pages

Single-Lens Imaging Spectral Restoration Method Based on Gradient Prior Information Optimization

  • Peidong He,
  • Zekun Li,
  • Jianwei Wang,
  • Yinhui Tang and ,
  • Yang Bai and
  • Qunbo Lv
  • + 1 author+ 0 author

24 September 2023

Single-lens imaging systems can capture spectral information, but they are affected by aberrations, defocusing, and other factors, leading to spectral data overlap. It is then necessary to perform restoration on overlapped spectral data. The restorat...

(This article belongs to the Section Optics and Lasers)
  • Article
  • Open Access
4 Citations
2,831 Views
11 Pages

22 September 2021

Traditional smooth stitching method for the texture seams of remote sensing images is affected by gradient structure information, leading to poor stitching effect. Therefore, a smooth stitching method for the texture seams of remote sensing images ba...

(This article belongs to the Special Issue Advance in Machine Learning)
  • Article
  • Open Access
3 Citations
1,723 Views
17 Pages

7 November 2025

Background: In China, a paradox has emerged: while the digital access gap narrows, a pronounced digital gradient—a sequential decline in outcomes from urban to county to township students—persists in innovation and entrepreneurship. This...

  • Article
  • Open Access
4 Citations
2,863 Views
20 Pages

29 December 2023

Disability management in information systems refers to the process of ensuring that digital technologies and applications are designed to be accessible and usable by individuals with disabilities. Traditional methods face several challenges such as p...

(This article belongs to the Special Issue Fuzzy Logic and Computational Intelligence)
  • Article
  • Open Access
17 Citations
4,982 Views
20 Pages

5 August 2018

The automatic image registration serves as a technical prerequisite for multimodal remote sensing image fusion. Meanwhile, it is also the technical basis for change detection, image stitching and target recognition. The demands of subpixel level regi...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
12 Citations
5,923 Views
15 Pages

17 May 2020

This paper demonstrates a novel approach to training deep neural networks using a Mutual Information (MI)-driven, decaying Learning Rate (LR), Stochastic Gradient Descent (SGD) algorithm. MI between the output of the neural network and true outcomes...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Article
  • Open Access
1,231 Views
11 Pages

Information Entropy and Its Periodic Features in Hermite–Gaussian Correlated Schell-Model Beams in a Gradient-Index Fiber

  • Jiayi Yu,
  • Jifei Huang,
  • Ruilin Liu,
  • Jidong Wu and ,
  • Xiaofeng Peng,
  • Yangjian Cai and
  • Xinlei Zhu
  • + 2 authors+ 0 author

26 February 2025

This paper investigates the evolution of information entropy (IE) in Hermite–Gaussian correlated Schell-model (HGcSM) beams propagating through a gradient-index (GRIN) fiber using Shannon information theory. Our results reveal that the IE of su...

(This article belongs to the Section Optical Interaction Science)
  • Article
  • Open Access
15 Citations
2,491 Views
19 Pages

The assessment of landscape ecological risk (LER) in different terrain gradients is beneficial to ecological environmental protection and risk management in different terrain gradients. Due to the impact of urban expansion, the landscape pattern of t...

  • Article
  • Open Access
48 Citations
6,019 Views
17 Pages

25 July 2019

Accurate and timely misfire fault diagnosis is of vital significance for diesel engines. However, existing algorithms are prone to fall into model over-fitting and adopt low energy-concentrated features. This paper presents a novel extreme gradient b...

(This article belongs to the Special Issue Advanced Signal Processing in Intelligent Systems for Health Monitoring)
  • Article
  • Open Access
5 Citations
3,752 Views
35 Pages

13 May 2022

This work proposes a unifying framework for extending PDE-constrained Large Deformation Diffeomorphic Metric Mapping (PDE-LDDMM) with the sum of squared differences (SSD) to PDE-LDDMM with different image similarity metrics. We focused on the two bes...

(This article belongs to the Section Sensing and Imaging)
  • Article
  • Open Access
2 Citations
2,227 Views
20 Pages

12 April 2023

Currently, automatic optical zoom setups are being extensively explored for their applications in search, detection, recognition, and tracking. In visible and infrared fusion imaging systems with continuous zoom, dual-channel multi-sensor field-of-vi...

(This article belongs to the Section Intelligent Sensors)
  • Letter
  • Open Access
5 Citations
3,162 Views
12 Pages

Suppressing False Alarm in VideoSAR viaGradient-Weighted Edge Information

  • Zihan Li,
  • Anxi Yu,
  • Zhen Dong,
  • Zhihua He and
  • Tianzhu Yi

15 November 2019

VideoSAR (Video Synthetic Aperture Radar) technology provides an important mean for real-time and continuous earth observation, whereas the ever-changing scattering characteristics may destroy the accuracy of target motion perception and bring in mas...

(This article belongs to the Special Issue Airborne SAR: Data Processing, Calibration and Applications)
  • Article
  • Open Access
1,542 Views
18 Pages

22 December 2025

Understanding how the brain encodes and decodes dynamic neural responses to visual stimuli is crucial for revealing visual information representation. Currently, most methods (including deep neural networks, DNNs) often overlook the dynamic generatio...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
9 Citations
2,929 Views
24 Pages

28 April 2021

Quality control is of great significance for the economical manufacturing and reliable application of medium voltage insulators. With the increasingly stringent quality control requirement, traditional quality control methods in this field face a gro...

(This article belongs to the Special Issue Learning for Process Optimization and Control)
  • Article
  • Open Access
18 Citations
3,735 Views
20 Pages

23 January 2020

Medium voltage insulators are essential and versatile components in electrical engineering. Quality control of the manufacturing process for the insulators has a significant role in their economic production and reliable operation. As the quality of...

(This article belongs to the Special Issue Process Optimization and Control)
  • Article
  • Open Access
5 Citations
2,065 Views
16 Pages

17 October 2025

Physics-Informed Neural Networks (PINNs) have emerged as a promising paradigm for solving partial differential equations (PDEs) by embedding physical laws into the learning process. However, standard PINNs often suffer from training instabilities and...

  • Article
  • Open Access
17 Citations
4,321 Views
20 Pages

18 June 2021

Hyperspectral image (HSI) super-resolution has gained great attention in remote sensing, due to its effectiveness in enhancing the spatial information of the HSI while preserving the high spectral discriminative ability, without modifying the imagery...

(This article belongs to the Special Issue Machine Learning and Pattern Analysis in Hyperspectral Remote Sensing)
  • Article
  • Open Access
1 Citations
1,098 Views
27 Pages

11 May 2026

The operating status of chillers in data centers critically affects temperature stability and energy efficiency, imposing stringent requirements on the accuracy, robustness, and adaptability of sensor fault detection systems. Existing Physics-Informe...

(This article belongs to the Section Fault Diagnosis & Sensors)
  • Article
  • Open Access
657 Views
38 Pages

Physics-informed neural networks (PINNs) are difficult to train on strongly coupled, multi-objective systems: with fixed loss weights an otherwise identical run succeeds or diverges with the random seed, and a leading explanation attributes the failu...

  • Review
  • Open Access
2 Citations
4,917 Views
20 Pages

30 November 2022

Many real-life problems that involve decisions under uncertainty are often sequentially repeated and can be approached iteratively. Knowledge Gradient (KG) formulates the decision-under-uncertainty problem into repeatedly estimating the value of info...

  • Article
  • Open Access
3 Citations
3,244 Views
24 Pages

Hyperspectral Reconstruction Method Based on Global Gradient Information and Local Low-Rank Priors

  • Chipeng Cao,
  • Jie Li,
  • Pan Wang,
  • Weiqiang Jin and ,
  • Runrun Zou and
  • Chun Qi
  • + 1 author+ 0 author

20 December 2024

Hyperspectral compressed imaging is a novel imaging detection technology based on compressed sensing theory that can quickly acquire spectral information of terrestrial objects in a single exposure. It combines reconstruction algorithms to recover hy...

(This article belongs to the Special Issue 3D Information Recovery and 2D Image Processing for Remotely Sensed Optical Images II)
  • Article
  • Open Access
3 Citations
1,521 Views
20 Pages

28 July 2025

The structural units with different characteristic scales in gradient nanostructured (GS) 316L stainless steel act synergistically to achieve the matching of strength and plasticity, and the intrinsic plasticity of nanoscale and ultrafine grains is f...

(This article belongs to the Section Mechanics of Materials)
  • Article
  • Open Access
5 Citations
1,814 Views
19 Pages

BDNet: A Real-Time Biomedical Image Denoising Network with Gradient Information Enhancement Loss

  • Lemin Shi,
  • Xin Feng,
  • Ping Gong,
  • Dianxin Song and ,
  • Hao Zhang,
  • Langxi Liu,
  • Yuqiang Zhang and
  • Mingye Li
  • + 3 authors+ 0 author

1 January 2026

Biomedical imaging plays a critical role in medical diagnostics and research, yet image noise remains a significant challenge that hinders accurate analysis. To address this issue, we propose BDNet, a real-time biomedical image denoising network opti...

(This article belongs to the Section Biosensors and Healthcare)
  • Article
  • Open Access
6 Citations
4,958 Views
15 Pages

Nonrigid Medical Image Registration Using an Information Theoretic Measure Based on Arimoto Entropy with Gradient Distributions

  • Bicao Li,
  • Huazhong Shu,
  • Zhoufeng Liu,
  • Zhuhong Shao and ,
  • Chunlei Li,
  • Min Huang and
  • Jie Huang
  • + 2 authors+ 0 author

18 February 2019

This paper introduces a new nonrigid registration approach for medical images applying an information theoretic measure based on Arimoto entropy with gradient distributions. A normalized dissimilarity measure based on Arimoto entropy is presented, wh...

(This article belongs to the Special Issue Entropy in Image Analysis)
  • Article
  • Open Access
3 Citations
3,496 Views
20 Pages

Gradient Structure Information-Guided Attention Generative Adversarial Networks for Remote Sensing Image Generation

  • Baoyu Zhu,
  • Qunbo Lv,
  • Yuanbo Yang,
  • Kai Zhang and ,
  • Xuefu Sui,
  • Yinhui Tang and
  • Zheng Tan
  • + 2 authors+ 0 author

29 May 2023

A rich and effective dataset is an important foundation for the development of AI algorithms, and the quantity and quality of the dataset determine the upper limit level of the algorithms. For aerospace remote sensing datasets, due to the high cost o...

(This article belongs to the Topic Deep Learning and Transformers’ Methods Applied to Remotely Captured Data)
  • Article
  • Open Access
32 Citations
4,223 Views
19 Pages

22 November 2019

The prediction of protein–ligand binding sites is important in drug discovery and drug design. Protein–ligand binding site prediction computational methods are inexpensive and fast compared with experimental methods. This paper proposes a...

(This article belongs to the Section Technologies and Resources for Genetics)
  • Article
  • Open Access
189 Views
41 Pages

8 October 2026

Long-term monitoring can test whether pile-design assumptions remain appropriate as consolidation and soil-pile load transfer develop after construction. This study combines records from three Ontario transportation projects: Ramsayville, Locha Creek...

(This article belongs to the Special Issue Scientific Computing and Machine Learning in Engineering)
  • Article
  • Open Access
7 Citations
5,767 Views
23 Pages

25 November 2014

Cultivated land resources are an important basis of regional sustainability; thus, it is important to determine the distribution of the cultivated land in the Northeast Asia trans-boundary area of China, Russia and Mongolia, which has a continuous g...

  • Article
  • Open Access
29 Citations
6,058 Views
14 Pages

The present study aimed to observe the effect of socio-economic status on health information literacy and to identify whether there is a social gradient for health information literacy among urban older adults in Western China. This study employed a...

(This article belongs to the Collection Global Health Literacy)
  • Article
  • Open Access
5 Citations
3,831 Views
16 Pages

Defect Detection and Depth Estimation in Composite Materials for Pulsed Thermography Images by Nonuniform Heating Correction and Oriented Gradient Information

  • Jorge Erazo-Aux,
  • Humberto Loaiza-Correa,
  • Andrés David Restrepo-Girón,
  • Clemente Ibarra-Castanedo and
  • Xavier Maldague

10 April 2023

Pulsed thermography is a nondestructive method commonly used to explore anomalies in composite materials. This paper presents a procedure for the automated detection of defects in thermal images of composite materials obtained with pulsed thermograph...

(This article belongs to the Special Issue Application of Emerging Materials for Advanced Imaging and Sensing)
  • Article
  • Open Access
33 Citations
9,942 Views
20 Pages

Neural Dynamics under Active Inference: Plausibility and Efficiency of Information Processing

  • Lancelot Da Costa,
  • Thomas Parr,
  • Biswa Sengupta and
  • Karl Friston

12 April 2021

Active inference is a normative framework for explaining behaviour under the free energy principle—a theory of self-organisation originating in neuroscience. It specifies neuronal dynamics for state-estimation in terms of a descent on (variational) f...

(This article belongs to the Section Information Theory, Probability and Statistics)
  • Feature Paper
  • Article
  • Open Access
2 Citations
2,228 Views
25 Pages

Mirror Descent and Exponentiated Gradient Algorithms Using Trace-Form Entropies

  • Andrzej Cichocki,
  • Toshihisa Tanaka,
  • Frank Nielsen and
  • Sergio Cruces

8 December 2025

This paper introduces a broad class of Mirror Descent (MD) and Generalized Exponentiated Gradient (GEG) algorithms derived from trace-form entropies defined via deformed logarithms. Leveraging these generalized entropies yields MD and GEG algorithms...

(This article belongs to the Special Issue SUURI of Information Geometry: Dedicated to SUURI Engineer Professor Shun’ichi Amari on the Occasion of His 90th Birthday)
  • Article
  • Open Access
1,275 Views
22 Pages

Deep neural networks are vulnerable and susceptible to adversarial examples, which can induce erroneous predictions by injecting imperceptible perturbations. Transferability is a crucial property of adversarial examples, enabling effective attacks un...

(This article belongs to the Special Issue Internet Intelligence for Cybersecurity)
  • Article
  • Open Access
2 Citations
3,129 Views
24 Pages

29 October 2024

Color transfer, an essential technique in image editing, has recently received significant attention. However, achieving a balance between holistic color style transfer and local detail refinement remains a challenging task. This paper proposes an in...

(This article belongs to the Topic Color Image Processing: Models and Methods (CIP: MM))
  • Article
  • Open Access
7 Citations
5,610 Views
8 Pages

22 September 2016

The present study was carried out to compute the straightforward formulations of information entropy for ecological sites and to arrange their locations along the ordination axes using the values of those entropic measures. The data of plant communit...

(This article belongs to the Special Issue Applications of Information Theory in the Geosciences)
  • Feature Paper
  • Article
  • Open Access
1 Citations
1,375 Views
14 Pages

Non-Metricity in Information Geometry

  • Tatsuaki Wada and
  • Antonio Maria Scarfone

14 April 2026

The importance of non-metricity in information geometry is described through studies on gradient flow from the perspective of Weyl geometry. The Amari–Centsov tensor Ckij is the non-metricity tensor with respect to the α connection &nabla...

(This article belongs to the Special Issue SUURI of Information Geometry: Dedicated to SUURI Engineer Professor Shun’ichi Amari on the Occasion of His 90th Birthday)
  • Article
  • Open Access
1 Citations
2,957 Views
21 Pages

Communication-Efficient Zeroth-Order Adaptive Optimization for Federated Learning

  • Ping Xie,
  • Xiangrui Gao,
  • Fan Li,
  • Ling Xing and ,
  • Yu Zhang and
  • Hanxiao Sun
  • + 1 author+ 0 author

11 April 2024

Federated learning has become a prevalent distributed training paradigm, in which local devices collaboratively train learning models without exchanging local data. One of the most dominant frameworks of federated learning (FL) is FedAvg, since it is...

(This article belongs to the Section E1: Mathematics and Computer Science)
  • Article
  • Open Access
9 Citations
6,442 Views
17 Pages

28 June 2017

Information geometry enables a deeper understanding of the methods of statistical inference. In this paper, the problem of nonlinear parameter estimation is considered from a geometric viewpoint using a natural gradient descent on statistical manifol...

(This article belongs to the Special Issue Information Geometry II)
  • Article
  • Open Access
3 Citations
5,192 Views
20 Pages

Speed-First: An Aggressive Gradient-Based Local Planner for Quadrotor Faster Flight

  • Jiajie Yu,
  • Jiaqi Li,
  • Tong Zhang,
  • Binbin Yan and ,
  • Shaoyi Li and
  • Zhongjie Meng
  • + 1 author+ 0 author

11 March 2023

Autonomous flight for quadrotors is maturing with the development of real-time local trajectory planning. However, the current local planning method is too conservative to waste the agility of the quadrotors. So in this paper, we have focused on aggr...

  • Article
  • Open Access
39 Citations
6,823 Views
25 Pages

Change Detection Based on Multi-Grained Cascade Forest and Multi-Scale Fusion for SAR Images

  • Wenping Ma,
  • Hui Yang,
  • Yue Wu,
  • Yunta Xiong and ,
  • Tao Hu,
  • Licheng Jiao and
  • Biao Hou
  • + 2 authors+ 0 author

12 January 2019

In this paper, a novel change detection approach based on multi-grained cascade forest (gcForest) and multi-scale fusion for synthetic aperture radar (SAR) images is proposed. It detects the changed and unchanged areas of the images by using the well...

  • Article
  • Open Access
22 Citations
5,503 Views
13 Pages

14 November 2019

Super-resolution (SR) technology is essential for improving image quality in magnetic resonance imaging (MRI). The main challenge of MRI SR is to reconstruct high-frequency (HR) details from a low-resolution (LR) image. To address this challenge, we...

(This article belongs to the Special Issue Signal Processing and Machine Learning for Biomedical Data)
  • Article
  • Open Access
2 Citations
3,117 Views
20 Pages

2 September 2022

In this paper, we investigate the bifurcations of solutions to a class of degenerate constrained optimization problems. This study was motivated by the Information Bottleneck and Information Distortion problems, which have been used to successfully c...

(This article belongs to the Special Issue Theory and Application of the Information Bottleneck Method)
  • Feature Paper
  • Article
  • Open Access
727 Views
12 Pages

Gradient Systems and Asymmetric Relaxations in View of Riemannian Geometry

  • Alessandro Bravetti,
  • Miguel Ángel García Ariza and
  • José Roberto Romero-Arias

2 May 2026

In dually flat manifolds, there is a deep connection between gradient flows and pregeodesics. This was one of the many important contributions of Amari to information geometry. In this paper, we extend the study of this relationship to general Rieman...

(This article belongs to the Special Issue SUURI of Information Geometry: Dedicated to SUURI Engineer Professor Shun’ichi Amari on the Occasion of His 90th Birthday)

of 97