Search Results

Traditional information theory-based feature selection methods are designed for discrete features, which require additional discretization steps when working with continuous features. In contrast, fuzzy information theory-based feature selection ...

As a new federated learning(FL) paradigm, clustered federated learning (CFL) could effectively address the issue of model training accuracy loss due to different data distribution in FL. However, the introduction of the clustering process also brings new ...

Motivation: Large-scale pre-trained models (PTMs) such as BERT and GPT have recently achieved great success in Natural Language Processing and Computer Vision domains. However, the development of PTMs on healthcare time-series data is lagging behind. ...

Gamut compression emerges as a key technology in digital printing, ensuring minimal visual loss and color distortion from the design phase on monitors to the final print output. Monitors usually operate in a wide gamut (sRGB), and this color-rich ...

Current existing image enhancement methods do not consider the importance of semantic information, and ignore the local feature consistency within semantic regions. In this paper, we incorporate semantic-aware information into lookup tables (LUTs) ...

Current unsupervised deformable medical image registration methods rely on image similarity measures. However, these methods are inherently limited by the difficulty of integrating important anatomy knowledge into registration. The development of ...

Fuzzy information-theoretic metrics have been demonstrated to be effective in evaluating feature relevance and redundancy in both categorical and numerical feature selection tasks. Most existing feature selection methods based on fuzzy ...

• Introduce several class-specific fuzzy information-theoretic metrics.
• Develop a class-specific fuzzy information-theoretic feature selection algorithm.
• Design a class-specific ensemble classification framework.
• Perform ...

This paper investigates the achievable region of a K-user discrete memoryless (DM) multiple access wiretap (MAC-WT) channel, where each user transmits both secret and open (i.e., non-confidential) messages. All these messages are intended for the ...

Compressing a set of unordered points is far more challenging than compressing images/videos of regular sample grids, because of the difficulties in characterizing neighboring relations in an irregular layout of points. Many researchers resort to ...

In this paper, we investigate the use of diffusion models which are pre-trained on large-scale image-caption pairs for open-vocabulary 3D semantic understanding. We propose a novel method, namely Diff2Scene, which leverages frozen representations ...$\mathrm{}$

Data plays a crucial role in training learning-based methods for 3D point cloud registration. However, the real-world dataset is expensive to build, while rendering-based synthetic data suffers from domain gaps. In this work, we present ...

• Eliminate the need for tedious analysis and derivation of intermediate variables.
• Simplify the establishment of constraint equations and require constructing fewer equations.
• The proposed method is more straightforward to establish ...

The wheel-ground unilateral constraint is essential in establishing the complete mobile multi-axis system dynamics. To reduce the calculation complexity and improve the dynamic performance, an innovative joint-space dynamic theory for mobile ...

Anchor link prediction (ALP) aims to align the accounts of the same natural person on different social networks, which is essential for cross-platform recommendations and comprehensive characterization of user characteristics. In recent years, the ...

Large-scale Pre-trained Language Models (PLMs) have become the backbones of text classification due to their exceptional performance. However, they treat input documents as independent and uniformly distributed, thereby disregarding potential ...

Due to the explosion of mobile users and the ever-increasing heterogeneity and scale of wireless networks, traditional communication protocols and optimizing methods can not satisfy future wireless network (FWN) requirements. As promising technologies, ...

In energy-constrained scenarios such as IoT applications, the primary requirement for System-on-Chips (SoCs) is to increase battery life. However, when performing the sub/near-threshold operations, the relatively large leakage current hinders ...

• Development of an 8T SRAM with leakage detection for sub-threshold operation at 0.25V.
• Presenting a model to describe the relationship between read and leakage current.
• Implementation of a digitized timing module for accurate read ...

• Propose a rough integrated asymmetric cloud (RIAC) model.
• Put forward a new AC score function, distance, and similarity.
• Expert weights are measured from the perspective of cooperative game.
• Establish a trust propagation model ...

Large group decision-making often contains strong uncertainty and randomness due to the complexity of decision-making problems. Moreover, existing methods about large group decision-making usually assume that the relationships among decision-...

Blood vessel segmentation is a crucial stage in extracting morphological characteristics of vessels for the clinical diagnosis of fundus and coronary artery disease. However, traditional convolutional neural networks (CNNs) are confined to ...

This study addresses the bipartite graph weight maximum matching problem with a focus on achieving fairness. We introduce a deterministic truthful mechanism and a universal truthful mechanism tailored for fair matching, striving for an ...

Recent works have demonstrated the efficacy of Chain-of-Thought (CoT), which comprises multimodal information, in multiple complex reasoning tasks. CoT, involving multiple stages of reasoning, has also been applied to Visual Question Answering (...

• We propose a novel visual question answering model for science curricula.
• This method guides the mining of information according to the constructed prompts.
• This method also enhances the fusion of information by contrastive ...