Skip to Content

909 Results Found

  • Article
  • Open Access
2 Citations
1,853 Views
24 Pages

5 November 2022

In this paper, we show that the local distribution class Lloc∩OSloc is not closed under infinitely divisible distribution roots, i.e., there is an infinitely divisible distribution which belongs to the class, while the corresponding Lévy d...

(This article belongs to the Special Issue Distribution Theory and Application)
  • Article
  • Open Access
22 Citations
6,859 Views
16 Pages

19 January 2023

Due to the distributed data collection and learning in federated learnings, many clients conduct local training with non-independent and identically distributed (non-IID) datasets. Accordingly, the training from these datasets results in severe perfo...

(This article belongs to the Topic Machine Learning in Communication Systems and Networks)
  • Article
  • Open Access
7 Citations
3,056 Views
12 Pages

23 March 2022

Visible thermal person re-identification (VT Re-ID) is the task of matching pedestrian images collected by thermal and visible light cameras. The two main challenges presented by VT Re-ID are the intra-class variation between pedestrian images and th...

  • Article
  • Open Access
300 Views
25 Pages

23 September 2026

Federated learning under label skew aggregates models trained with different local class distributions. Local logit adjustment can reduce class-dependent bias, but the adjusted loss updates both the encoder and classifier in client-specific direction...

(This article belongs to the Special Issue Green Deep Learning Techniques for Sensing and Experimental Multimodal Signal Processing)
  • Article
  • Open Access
7 Citations
6,806 Views
14 Pages

Extreme Value Laws for Superstatistics

  • Pau Rabassa and
  • Christian Beck

20 October 2014

We study the extreme value distribution of stochastic processes modeled by superstatistics. Classical extreme value theory asserts that (under mild asymptotic independence assumptions) only three possible limit distributions are possible, namely: Gum...

(This article belongs to the Collection Advances in Applied Statistical Mechanics)
  • Article
  • Open Access
2 Citations
3,687 Views
23 Pages

Class-Hidden Client-Side Watermarking in Federated Learning

  • Weitong Chen,
  • Chi Zhang,
  • Wei Zhang and
  • Jie Cai

27 January 2025

Federated learning consists of a central aggregator and multiple clients, forming a distributed structure that effectively protects data privacy. However, since all participants can access the global model, the risk of model leakage increases, especi...

(This article belongs to the Special Issue Applications of Information Theory to Machine Learning)
  • Article
  • Open Access
2 Citations
2,248 Views
18 Pages

Saliency-Guided Local Semantic Mixing for Long-Tailed Image Classification

  • Jiahui Lv,
  • Jun Lei,
  • Jun Zhang,
  • Chao Chen and
  • Shuohao Li

In real-world visual recognition tasks, long-tailed distributions pose a widespread challenge, with extreme class imbalance severely limiting the representational learning capability of deep models. In practice, due to this imbalance, deep models oft...

  • Article
  • Open Access
2 Citations
1,464 Views
15 Pages

Resistance of Steel Sections (Classes 1 to 4) Including Bimoment Effects

  • Antonio Aguero,
  • Robert Glauz,
  • Ana Almerich-Chulia,
  • Yvona Kolekova and
  • Pedro Martin-Concepcion

28 October 2025

This article investigates the structural resistance of thin-walled steel sections classified as Classes 1 to 4 under Eurocode 3. The study focuses on flexural capacity, and takes into consideration the effects of local buckling and the bimoment. Alth...

(This article belongs to the Special Issue Advanced Studies in Steel Structure)
  • Article
  • Open Access
36 Citations
6,775 Views
19 Pages

Entanglement of Three-Qubit Random Pure States

  • Marco Enríquez,
  • Francisco Delgado and
  • Karol Życzkowski

29 September 2018

We study entanglement properties of generic three-qubit pure states. First, we obtain the distributions of both the coefficients and the only phase in the five-term decomposition of Acín et al. for an ensemble of random pure states generated b...

(This article belongs to the Special Issue Quantum Probability and Randomness)
  • Article
  • Open Access
3 Citations
3,374 Views
21 Pages

In this paper, we propose a new dimensionality reduction method named Discriminative Sparsity Graph Embedding (DSGE) which considers the local structure information and the global distribution information simultaneously. Firstly, we adopt the intra-c...

(This article belongs to the Special Issue Energy-Efficient and Reliable Information Processing: Computing and Storage)
  • Article
  • Open Access
1 Citations
7,849 Views
12 Pages

5 October 2012

We present evidence that one can calculate generically combinatorially expensive Lp and lp averages, 0 < p < 1, in polynomial time by restricting the data to come from a wide class of statistical distributions. Our approach differs from the approache...

  • Article
  • Open Access
5 Citations
2,487 Views
14 Pages

Bidirectional Decoupled Distillation for Heterogeneous Federated Learning

  • Wenshuai Song,
  • Mengwei Yan,
  • Xinze Li and
  • Longfei Han

5 September 2024

Federated learning enables multiple devices to collaboratively train a high-performance model on the central server while keeping their data on the devices themselves. However, due to the significant variability in data distribution across devices, t...

(This article belongs to the Section Signal and Data Analysis)
  • Article
  • Open Access
34 Citations
4,021 Views
14 Pages

1 April 2021

Domain adaptation-based models for fault classification under variable working conditions have become a research focus in recent years. Previous domain adaptation approaches generally assume identical label spaces in the source and target domains, ho...

(This article belongs to the Special Issue Information Theory and Its Application in Machine Condition Monitoring)
  • Article
  • Open Access
5 Citations
2,740 Views
23 Pages

19 August 2025

Federated learning (FL) has emerged as a powerful framework for decentralized model training, preserving data privacy by keeping datasets localized on distributed devices. However, data heterogeneity, characterized by significant variations in size,...

  • Article
  • Open Access
508 Views
20 Pages

To address the challenges of classifying known categories and rejecting unknown categories in the radio-frequency fingerprinting of uncooperative UAVs in open, low-altitude environments, this paper proposes PASM-Net, an open-set recognition method ba...

  • Review
  • Open Access
564 Views
46 Pages

17 October 2026

Class imbalance remains a central problem in machine learning because the rare class is often the event of scientific, clinical, financial, or operational interest. Yet the literature is fragmented across sampling, cost-sensitive learning, ensembles,...

(This article belongs to the Special Issue Feature Review Papers in "Computing and Artificial Intelligence")
  • Article
  • Open Access
8 Citations
5,044 Views
21 Pages

The Control of the Crossover Localization in Allium

  • Natalia Kudryavtseva,
  • Aleksey Ermolaev,
  • Anton Pivovarov,
  • Sergey Simanovsky and ,
  • Sergey Odintsov and
  • Ludmila Khrustaleva
  • + 1 author+ 0 author

Meiotic crossovers/chiasmata are not randomly distributed and strictly controlled. The mechanisms behind crossover (CO) patterning remain largely unknown. In Allium cepa, as in the vast majority of plants and animals, COs predominantly occur in the d...

(This article belongs to the Special Issue Genetics and Multi-Omics for Crop Breeding)
  • Article
  • Open Access
13 Citations
4,549 Views
13 Pages

Entropic Divergence and Entropy Related to Nonlinear Master Equations

  • Tamás Sándor Biró,
  • Zoltán Néda and
  • András Telcs

11 October 2019

We reverse engineer entropy formulas from entropic divergence, optimized to given classes of probability distribution function (PDF) evolution dynamical equation. For linear dynamics of the distribution function, the traditional Kullback–Leible...

(This article belongs to the Special Issue Selected Papers from 15th Joint European Thermodynamics Conference)
  • Article
  • Open Access
1,090 Views
27 Pages

7 July 2026

Federated learning (FL) is a promising paradigm for privacy-preserving IoT intrusion detection, but its effectiveness can be substantially degraded by the combination of heterogeneous non-IID client distributions and severe multi-class imbalance. Und...

  • Article
  • Open Access
36 Citations
8,994 Views
19 Pages

Spectral-Spatial Classification of Hyperspectral Images: Three Tricks and a New Learning Setting

  • Jacopo Acquarelli,
  • Elena Marchiori,
  • Lutgarde M.C. Buydens,
  • Thanh Tran and
  • Twan Van Laarhoven

21 July 2018

Spectral-spatial classification of hyperspectral images has been the subject of many studies in recent years. When there are only a few labeled pixels for training and a skewed class label distribution, this task becomes very challenging because of t...

(This article belongs to the Section Remote Sensing Image Processing)
  • Article
  • Open Access
13 Citations
3,321 Views
22 Pages

Fine-Grained Aircraft Recognition Based on Dynamic Feature Synthesis and Contrastive Learning

  • Huiyao Wan,
  • Pazlat Nurmamat,
  • Jie Chen,
  • Yice Cao and ,
  • Shuai Wang,
  • Yan Zhang and
  • Zhixiang Huang
  • + 2 authors+ 0 author

23 February 2025

With the rapid development of deep learning, significant progress has been made in remote sensing image target detection. However, methods based on deep learning are confronted with several challenges: (1) the inherent limitations of activation funct...

(This article belongs to the Special Issue Efficient Object Detection Based on Remote Sensing Images)
  • Article
  • Open Access
1 Citations
1,189 Views
17 Pages

30 November 2025

When trained on long-tailed distributions, deep neural networks often suffer performance degradation and model bias due to the dominance of head classes. Existing reweighting and sampling strategies have significant limitations, such as reliance on f...

(This article belongs to the Topic Applications of Machine Learning in Large-Scale Optimization and High-Dimensional Learning)
  • Review
  • Open Access
2 Citations
2,621 Views
20 Pages

9 February 2026

Background/Objectives: The efficacy of antidiabetic drugs is determined by intracellular target exposure rather than solely by plasma concentrations. This review synthesizes current evidence regarding subcellular drug distribution and its clinical si...

  • Article
  • Open Access
636 Views
19 Pages

In few-shot action recognition (FSAR), limited annotated data and large scene variations make it difficult for models to learn stable spatial semantics and reliable temporal dynamics. As a result, spatiotemporal representations tend to be weak, and m...

(This article belongs to the Section Artificial Intelligence)
  • Article
  • Open Access
2 Citations
1,199 Views
23 Pages

8 January 2026

Federated learning with data free knowledge distillation enables effective and privacy-preserving knowledge aggregation by employing generators to produce local pseudo samples during client-side model migration. However, in practical applications, da...

(This article belongs to the Special Issue Information and Future Internet Security, Trust and Privacy—4th Edition)
  • Article
  • Open Access
13 Citations
3,939 Views
20 Pages

29 May 2020

As the performance of supervised classification using convolutional neural networks (CNNs) are affected significantly by training patches, it is necessary to analyze the effects of the information content of training patches in patch-based classifica...

(This article belongs to the Special Issue Remote Sensing and Geoscience Information Systems in Applied Sciences)
  • Article
  • Open Access
5 Citations
2,033 Views
24 Pages

Class-Discrepancy Dynamic Weighting for Cross-Domain Few-Shot Hyperspectral Image Classification

  • Chen Ding,
  • Jiahao Yue,
  • Sirui Zheng,
  • Yizhuo Dong and ,
  • Wenqiang Hua,
  • Xueling Chen,
  • Yu Xie,
  • Song Yan,
  • Wei Wei and
  • Lei Zhang
  • + 5 authors+ 0 author

27 July 2025

In recent years, cross-domain few-shot learning (CDFSL) has demonstrated remarkable performance in hyperspectral image classification (HSIC), partially alleviating the distribution shift problem. However, most domain adaptation methods rely on simila...

  • Article
  • Open Access
2 Citations
5,848 Views
11 Pages

Feature extraction methods have been used to extract location features for indoor positioning in wireless local area networks. However, existing methods, such as linear discriminant analysis and principal component analysis, all suffer from the multi...

  • Article
  • Open Access
363 Views
33 Pages

2 October 2026

Lorenz curves are a socioeconomic method of coding the statistics of positive-valued random variables. Standing at the confluence of fractals, wealth distributions, and non-Euclidean geometry, this paper presents quadrant Lorenz curves (QLCs): Lorenz...

(This article belongs to the Section Statistical Physics)
  • Article
  • Open Access
3 Citations
2,142 Views
17 Pages

30 June 2023

Sea ice plays an important role in climate change research and maritime shipping safety, and SAR imaging technology provides important technical support for sea ice extraction. However, traditional methods have limitations such as low efficiency, mod...

  • Article
  • Open Access
290 Views
26 Pages

31 August 2026

To address the decline in insulation fault localization accuracy of urban rail DC traction return systems under varying operating conditions and missing target-domain classes, this study proposes a two-stage multi-source unilateral alignment network...

(This article belongs to the Section Fault Diagnosis & Sensors)
  • Article
  • Open Access
4 Citations
2,775 Views
20 Pages

Personalized Federated Learning Based on Dynamic Parameter Fusion and Prototype Alignment

  • Ying Chen,
  • Jing Wen,
  • Shaoling Liang,
  • Zhaofa Chen and
  • Baohua Huang

15 August 2025

To address the limitation of generalization of federated learning under non-independent and identically distributed (Non-IID) data, we propose FedDFPA, a personalized federated learning framework that integrates dynamic parameter fusion and prototype...

(This article belongs to the Section Intelligent Sensors)
  • Article
  • Open Access
1 Citations
960 Views
31 Pages

Communication-Efficient Federated Class-Incremental Intrusion Detection for Edge IoT Networks

  • Ziang Wu,
  • Buzhen He,
  • Zhiwei Si,
  • Chen Qiu and ,
  • Xiuheng Liao and
  • Chunhua Su
  • + 1 author+ 0 author

21 July 2026

The continuous emergence of new attack classes challenges intrusion detection in edge Internet of Things (IoT) networks. Although federated learning enables distributed devices to collaboratively train a shared detector without exchanging raw traffic...

(This article belongs to the Special Issue Trusted and Secure Edge Intelligence for Large AI Models in IoT Sensor Networks)
  • Article
  • Open Access
7 Citations
2,731 Views
27 Pages

12 May 2025

Imbalanced data are a non-trivial problem in deep learning. The high variability in the number of samples composing each category might force learning procedures to become biased towards classes with major cardinality and disregard classes with low i...

(This article belongs to the Section Agricultural Science and Technology)
  • Article
  • Open Access
4 Citations
4,467 Views
27 Pages

Few-Shot Object Detection for SAR Images via Context-Aware and Robust Gaussian Flow Representation

  • Po Zhao,
  • Jie Chen,
  • Huiyao Wan,
  • Yice Cao and ,
  • Shuai Wang,
  • Yan Zhang,
  • Yingsong Li,
  • Zhixiang Huang and
  • Bocai Wu
  • + 4 authors+ 0 author

23 January 2025

In recent decades, few-shot object detection in SAR imagery has gained prominence as a major research focus. The unique imaging mechanism of SAR causes the model to suffer from foreground–background imbalance and inaccurate extraction of class...

(This article belongs to the Special Issue SAR Image Object Detection and Information Extraction: Methods and Applications)
  • Article
  • Open Access
76 Citations
9,667 Views
25 Pages

A Remote Sensing Approach to Estimate Vertical Profile Classes of Phytoplankton in a Eutrophic Lake

  • Kun Xue,
  • Yuchao Zhang,
  • Hongtao Duan,
  • Ronghua Ma and ,
  • Steven Loiselle and
  • Minwei Zhang
  • + 1 author+ 0 author

30 October 2015

The extension and frequency of algal blooms in surface waters can be monitored using remote sensing techniques, yet knowledge of their vertical distribution is fundamental to determine total phytoplankton biomass and understanding temporal variabilit...

(This article belongs to the Special Issue Remote Sensing of Water Resources)
  • Article
  • Open Access
3 Citations
1,636 Views
27 Pages

9 April 2026

Class imbalance is a persistent challenge in supervised machine learning, particularly in biological datasets where minority classes represent functionally critical categories. Synthetic data generation has emerged as a principal strategy for mitigat...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
273 Views
38 Pages

An Exploratory Evaluation of Targeted Label Poisoning in a Client-Local Feature Federated Ensemble for Chest X-Ray Classification

  • Abdulaziz A. Alsulami,
  • Qasem Abu Al-Haija,
  • Ahmad J. Tayeb,
  • Rayed Alakhtar and ,
  • Badraddin Alturki,
  • Huda Alsobhi and
  • Afnan Abdulrahman Bukhari
  • + 2 authors+ 0 author

Local label manipulation can threaten federated medical-image classification. We evaluated Pneumonia-to-Normal poisoning in a client-local feature-federated ensemble using 20,795 chest X-rays from three sources. Three of 10 simulated clients with dif...

(This article belongs to the Section Biosignal Processing)
  • Article
  • Open Access
2 Citations
5,927 Views
18 Pages

The aim of this paper is to estimate the influence of the dimensions of the torsion box (height and width), of a 2400 TEU feeder-class container ship, on local stress distribution and assessment of local fatigue strength by using a numerical approach...

(This article belongs to the Special Issue Strength of Ship Structures)
  • Article
  • Open Access
156 Views
20 Pages

22 October 2026

Open-set hyperspectral classification requires accurate recognition of known land-cover classes and detection of samples from unseen classes. We propose GRDOSR, which extends representative-discriminative open-set recognition (RDOSR) by combining sec...

(This article belongs to the Section Computing and Artificial Intelligence)
  • Article
  • Open Access
4 Citations
3,679 Views
19 Pages

Mixing Global and Local Features for Long-Tailed Expression Recognition

  • Jiaxiong Zhou,
  • Jian Li,
  • Yubo Yan,
  • Lei Wu and
  • Hao Xu

1 February 2023

Large-scale facial expression datasets are primarily composed of real-world facial expressions. Expression occlusion and large-angle faces are two important problems affecting the accuracy of expression recognition. Moreover, because facial expressio...

  • Article
  • Open Access
16 Citations
3,633 Views
21 Pages

22 October 2024

Accurate and timely fault diagnosis is of great significance for the stable operation of a distribution network. Traditional artificial intelligence-based localization methods rely heavily on large-scale labeled datasets, making them prone to being a...

(This article belongs to the Section Process Control, Modeling and Optimization)
  • Article
  • Open Access
27 Citations
4,289 Views
21 Pages

3 September 2020

As an important part of farmland, the slope farmland is widely distributed in the central and western plateau mountain region in China. It is necessary to scientifically evaluate the slope farmland quality (SFQ) and analyze the spatial structure char...

(This article belongs to the Special Issue Impacts of Land Tenure Systems on Land Use Sustainability)
  • Article
  • Open Access
1 Citations
831 Views
23 Pages

27 May 2026

Accurate and efficient semantic segmentation of point cloud data is critical in many application areas involving indoor scene understanding. In particular, fine-grained object categories, high data density, and class imbalance in high-resolution indo...

(This article belongs to the Special Issue Advances in Point Clouds for Sensing Applications)
  • Article
  • Open Access
2 Citations
1,639 Views
31 Pages

29 August 2025

With the growing emphasis on healthy eating and nutrition management in modern society, food image recognition has become increasingly important. However, it faces challenges such as large intra-class differences and high inter-class similarities. To...

  • Feature Paper
  • Article
  • Open Access
2 Citations
2,748 Views
11 Pages

16 April 2021

In this research, we continue studying limit theorems for combinatorial numbers satisfying a class of triangular arrays. Using the general results of Hwang and Bender, we obtain a constructive proof of the central limit theorem, specifying the rate o...

  • Article
  • Open Access
445 Views
22 Pages

Spatiotemporal and Vehicle-Class Modeling of Urban Speed Distributions

  • Mahmoud Owais,
  • Abdou S. Ahmed and
  • Mohamed A. El Sayed

25 September 2026

Urban speed management requires distributional rather than mean-only assessment because averages can conceal upper-tail speeding, vehicle-class differences, and multiple operating regimes. This study applies an integrated sensor-based analytical fram...

(This article belongs to the Topic Mobility Engineering and Sustainability)
  • Article
  • Open Access
1 Citations
2,502 Views
7 Pages

30 May 2020

The methods of statistical physics are exemplified in the classical perfect gas—each atom is a single dynamical entity. Such methods can be applied in ecology to the distribution of cosmopolitan species over many sites. The analogue of an atom...

(This article belongs to the Section Thermodynamics)
  • Article
  • Open Access
1,272 Views
26 Pages

MetaGAN: Metamorphic GAN-Based Augmentation for Improving Deep Learning-Based Multiple-Fault Localization Without Test Oracles

  • Anlin Hu,
  • Wenjiang Feng,
  • Xudong Zhu,
  • Junjie Wang and ,
  • Yiping Ao and
  • Hao Feng
  • + 1 author+ 0 author

Modern electronic information system software is becoming increasingly complex, making manual debugging prohibitively expensive and necessitating automated fault localization (FL) methods to prioritize suspicious code segments. While Single-Fault Loc...

(This article belongs to the Special Issue Software Analysis, Quality, and Security)
  • Article
  • Open Access
1,443 Views
9 Pages

2 June 2024

This paper aims to discuss the de Rham cohomology of hemi-slant submanifolds in locally product Riemannian manifolds. The integrability and geodesical invariance conditions of the distributions derived from the definition of a hemi-slant submanifold...

(This article belongs to the Special Issue Differentiable Manifolds and Geometric Structures)

of 19