- Article
In this paper, we show that the local distribution class
In this paper, we show that the local distribution class
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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,...
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...
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,...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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...
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 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...
of 19