计算机科学最新文献

英文中文

IF： -

From Local to Global: Semantic Communication-Driven Remote 3D Scene Reconstruction Using Low-Altitude Platforms 从局部到全局：语义通信驱动的低空平台远程三维场景重建

IF 8.6 1区计算机科学 Q1 TELECOMMUNICATIONS

IEEE Transactions on Cognitive Communications and Networking

Pub Date : 2026-02-09 DOI: 10.1109/tccn.2026.3662333

Tianle Mai, Haipeng Yao, Gepeng Zhu, Chenlang Jin, Xiangjun Xin

引用次数: 0

Generalized Decoupled Control and Capacitor Voltage Balancing for Current Scalable Modular Multilevel Converter 电流可扩展模块化多电平变换器的广义解耦控制与电容电压平衡

IF 7.7 1区工程技术 Q1 AUTOMATION & CONTROL SYSTEMS

IEEE Transactions on Industrial Electronics

Pub Date : 2026-02-09 DOI: 10.1109/tie.2026.3651339

Diego Verdugo, Félix Rojas, Javier Pereda, Jonathan Lillo, Alan Watson

引用次数: 0

Adversarial Augmentation With Maximum Discrepancy for Graph Contrastive Learning. 图对比学习的最大差异对抗增强。

IF 8.9 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE transactions on neural networks and learning systems

Pub Date : 2026-02-09 DOI: 10.1109/TNNLS.2026.3650798

Chunchun Chen, Xing Wei, Yuxing Zhang, Wei Ye

Graph contrastive learning (GCL) has achieved remarkable success in graph self-supervised learning (SSL) through an augmenting-contrasting paradigm. Existing augmentation strategies typically generate augmentations independently, ignoring the explicit modeling of the underlying relationship between augmentations, i.e., augmentation discrepancy. In addition, previous discrete augmentations (e.g., edge dropping and feature masking) also hinder the path toward joint optimization. These limit the diversity and complementarity of augmentations, leading to the suboptimal contrastive learning. In this article, we propose a novel adversarial augmentation method, called adversarial augmentation with maximum discrepancy for GCL (AMD-GCL), to jointly optimize pairwise augmentations. The core of AMD-GCL is an adversarial augmentation constraint module that maximizes the discrepancy between pairwise augmentations. Specifically, we establish a theoretical analysis indicating that maximizing graph reconstruction error in a continuous space serves as a surrogate for minimizing mutual information (MI), laying the basis for the differentiable constraint of augmentation discrepancy. Based on this, AMD-GCL designs a min-max problem. We directly add continuous adversarial perturbations to the original graph structure and features to maximize the reconstruction error. Meanwhile, we maximize the reconstruction error between pairwise augmentations to amplify the discrepancy. This leads to a maximization problem. After obtaining augmentations, AMD-GCL optimizes both the contrastive loss and reconstruction objectives, deriving a unified minimization problem. The adversarial augmentations are iteratively updated during the training process. Comprehensive experiments on 18 datasets demonstrate the superiority and robustness of AMD-GCL on several downstream tasks and various adversarial scenarios.

图对比学习（GCL）通过增强-对比范式在图自监督学习（SSL）中取得了显著的成功。现有的增强策略通常是独立地生成增强，而忽略了对增强之间潜在关系（即增强差异）的显式建模。此外，先前的离散增强（例如，边下降和特征屏蔽）也阻碍了联合优化的路径。这些限制了增强的多样性和互补性，导致了次优对比学习。在本文中，我们提出了一种新的对抗增强方法，称为GCL的最大差异对抗增强（AMD-GCL），用于联合优化成对增强。AMD-GCL的核心是一个对抗性增强约束模块，该模块可以最大化两两增强之间的差异。具体而言，我们建立了一个理论分析，表明在连续空间中最大化图重构误差可以作为最小化互信息（MI）的代理，为增强差异的可微约束奠定了基础。在此基础上，AMD-GCL设计了一个最小-最大问题。我们直接在原始图的结构和特征上加入连续的对抗性扰动，使重建误差最大化。同时，我们最大化了两两增强之间的重构误差来放大差异。这就导致了最大化问题。在得到增强后，AMD-GCL对对比损失目标和重建目标进行优化，得到统一的最小化问题。对抗性增强在训练过程中迭代更新。在18个数据集上的综合实验证明了AMD-GCL在多个下游任务和各种对抗场景中的优越性和鲁棒性。

{"title":"Adversarial Augmentation With Maximum Discrepancy for Graph Contrastive Learning.","authors":"Chunchun Chen, Xing Wei, Yuxing Zhang, Wei Ye","doi":"10.1109/TNNLS.2026.3650798","DOIUrl":"https://doi.org/10.1109/TNNLS.2026.3650798","url":null,"abstract":"Graph contrastive learning (GCL) has achieved remarkable success in graph self-supervised learning (SSL) through an augmenting-contrasting paradigm. Existing augmentation strategies typically generate augmentations independently, ignoring the explicit modeling of the underlying relationship between augmentations, i.e., augmentation discrepancy. In addition, previous discrete augmentations (e.g., edge dropping and feature masking) also hinder the path toward joint optimization. These limit the diversity and complementarity of augmentations, leading to the suboptimal contrastive learning. In this article, we propose a novel adversarial augmentation method, called adversarial augmentation with maximum discrepancy for GCL (AMD-GCL), to jointly optimize pairwise augmentations. The core of AMD-GCL is an adversarial augmentation constraint module that maximizes the discrepancy between pairwise augmentations. Specifically, we establish a theoretical analysis indicating that maximizing graph reconstruction error in a continuous space serves as a surrogate for minimizing mutual information (MI), laying the basis for the differentiable constraint of augmentation discrepancy. Based on this, AMD-GCL designs a min-max problem. We directly add continuous adversarial perturbations to the original graph structure and features to maximize the reconstruction error. Meanwhile, we maximize the reconstruction error between pairwise augmentations to amplify the discrepancy. This leads to a maximization problem. After obtaining augmentations, AMD-GCL optimizes both the contrastive loss and reconstruction objectives, deriving a unified minimization problem. The adversarial augmentations are iteratively updated during the training process. Comprehensive experiments on 18 datasets demonstrate the superiority and robustness of AMD-GCL on several downstream tasks and various adversarial scenarios.","PeriodicalId":13303,"journal":{"name":"IEEE transactions on neural networks and learning systems","volume":"PP ","pages":""},"PeriodicalIF":8.9,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146149469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Ninth IEEE RADIO International Conference, 27–30 October 2025, Mauritius [AP-S Committees & Activities] 第九届IEEE无线电国际会议，2025年10月27-30日，毛里求斯[AP-S委员会和活动]

IF 5.7 4区计算机科学 Q2 ENGINEERING, ELECTRICAL & ELECTRONIC

IEEE Antennas and Propagation Magazine

Pub Date : 2026-02-09 DOI: 10.1109/MAP.2025.3638524

Vikass Monebhurrun

Provides society information that may include news, reviews or technical notes that should be of interest to practitioners and researchers.

提供社会信息，可能包括新闻，评论或技术笔记，从业者和研究人员应该感兴趣。

引用次数: 0

Advancing Dysarthric Speech-to-Text Recognition with LATTE: A Low-Latency Acoustic Modeling Approach for Real-Time Communication. 用LATTE推进困难语音到文本识别：用于实时通信的低延迟声学建模方法。

IF 2.6 4区计算机科学 Q2 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Big Data

Pub Date : 2026-02-09 DOI: 10.1177/2167647X251411174

Qurat Ul Ain, Hammad Afzal, Fazli Subhan, Mazliham Mohd Suud, Younhyun Jung

Dysarthria, a motor speech disorder characterized by slurred and often unintelligible speech, presents substantial challenges for effective communication. Conventional automatic speech recognition systems frequently underperform on dysarthric speech, particularly in severe cases. To address this gap, we introduce low-latency acoustic transcription and textual encoding (LATTE), an advanced framework designed for real-time dysarthric speech recognition. LATTE integrates preprocessing, acoustic processing, and transcription mapping into a unified pipeline, with its core powered by a hybrid architecture that combines convolutional layers for acoustic feature extraction with bidirectional temporal layers for modeling temporal dependencies. Evaluated on the UA-Speech dataset, LATTE achieves a word error rate of 12.5%, phoneme error rate of 8.3%, and a character error rate of 1%. By enabling accurate, low-latency transcription of impaired speech, LATTE provides a robust foundation for enhancing communication and accessibility in both digital applications and real-time interactive environments.

构音障碍是一种运动语言障碍，其特征是说话含糊不清，常常难以理解，对有效的沟通提出了重大挑战。传统的自动语音识别系统经常表现不佳，特别是在严重的情况下。为了解决这一差距，我们引入了低延迟声学转录和文本编码（LATTE），这是一种专为实时困难语音识别而设计的高级框架。LATTE将预处理、声学处理和转录映射集成到一个统一的管道中，其核心由混合架构提供动力，该架构结合了用于声学特征提取的卷积层和用于建模时间依赖性的双向时间层。在UA-Speech数据集上进行评估，LATTE的单词错误率为12.5%，音素错误率为8.3%，字符错误率为1%。通过实现对受损语言的准确、低延迟转录，LATTE为增强数字应用程序和实时交互环境中的通信和可访问性提供了坚实的基础。

{"title":"Advancing Dysarthric Speech-to-Text Recognition with LATTE: A Low-Latency Acoustic Modeling Approach for Real-Time Communication.","authors":"Qurat Ul Ain, Hammad Afzal, Fazli Subhan, Mazliham Mohd Suud, Younhyun Jung","doi":"10.1177/2167647X251411174","DOIUrl":"https://doi.org/10.1177/2167647X251411174","url":null,"abstract":"Dysarthria, a motor speech disorder characterized by slurred and often unintelligible speech, presents substantial challenges for effective communication. Conventional automatic speech recognition systems frequently underperform on dysarthric speech, particularly in severe cases. To address this gap, we introduce low-latency acoustic transcription and textual encoding (LATTE), an advanced framework designed for real-time dysarthric speech recognition. LATTE integrates preprocessing, acoustic processing, and transcription mapping into a unified pipeline, with its core powered by a hybrid architecture that combines convolutional layers for acoustic feature extraction with bidirectional temporal layers for modeling temporal dependencies. Evaluated on the UA-Speech dataset, LATTE achieves a word error rate of 12.5%, phoneme error rate of 8.3%, and a character error rate of 1%. By enabling accurate, low-latency transcription of impaired speech, LATTE provides a robust foundation for enhancing communication and accessibility in both digital applications and real-time interactive environments.","PeriodicalId":51314,"journal":{"name":"Big Data","volume":" ","pages":"2167647X251411174"},"PeriodicalIF":2.6,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146143844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SKDAN: A Signal Knowledge-enhanced Domain Adaptation Network for remaining useful life prediction and uncertainty quantification of rolling bearings SKDAN：一种用于滚动轴承剩余使用寿命预测和不确定性量化的信号知识增强域自适应网络

IF 1 1区计算机科学 Q1 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS

Computers in Industry

Pub Date : 2026-02-09 DOI: 10.1016/j.compind.2026.104447

Bin Liu, Changfeng Yan, Ming Lv, Yuan Huang, Lixiao Wu

Domain adaptation-based methods are extensively applied to predict the Remaining Useful Life (RUL) of rolling bearings under complex operating conditions. However, the nonlinear degradation process of bearings gives rise to markedly non-stationary characteristics in vibration signals throughout the full life cycle. Although significant differences in fault features arise across different degradation stages, clearly identifying the critical degradation information remains a challenge. In this paper, a Signal Knowledge-enhanced Domain Adaptation Network (SKDAN) is proposed to learn domain-invariant features from non-stationary degradation processes, thereby improving cross-domain RUL prediction. Specifically, an adaptive short-time Fourier transform layer with a variable window is introduced to analyze the raw vibration signals in the time domain. This differentiable layer extracts time–frequency physical information with high energy concentration, which enhances the representation of degradation features. Subsequently, a novel discrepancy metric, termed Multi-Stage Maximum Mean Discrepancy (MSMMD), is proposed to replace the global average discrepancy with multiple local discrepancies. The MSMMD metric effectively increases the inter-class distance between cluster centers, which enables cross-domain feature alignment. Finally, an uncertainty measurement mechanism is constructed via a step-by-step training strategy, with the objective of quantifying the uncertainty in RUL results by calculating confidence intervals for prediction points. Comparative tests with other methods are conducted on two different bearing datasets, and the results demonstrate that SKDAN achieves superior performance and reliability in cross-domain RUL prediction.

基于域自适应的方法被广泛应用于复杂工况下滚动轴承剩余使用寿命的预测。然而，轴承的非线性退化过程导致振动信号在整个生命周期中具有明显的非平稳特征。尽管不同退化阶段的断层特征存在显著差异，但清晰识别关键退化信息仍然是一个挑战。本文提出了一种信号知识增强的域自适应网络（SKDAN），从非平稳退化过程中学习域不变特征，从而提高了跨域RUL预测能力。具体来说，引入了一种带可变窗口的自适应短时傅里叶变换层，对原始振动信号进行时域分析。该可微层提取能量浓度高的时频物理信息，增强了退化特征的表征。随后，提出了一种新的差异度量，称为多阶段最大平均差异（MSMMD），用多个局部差异代替全球平均差异。MSMMD度量有效地增加了聚类中心之间的类间距离，从而实现了跨域特征对齐。最后，通过逐步训练策略构建不确定性度量机制，通过计算预测点的置信区间来量化规则学习结果中的不确定性。在两个不同的轴承数据集上与其他方法进行了对比测试，结果表明，SKDAN在跨域RUL预测中取得了优异的性能和可靠性。

{"title":"SKDAN: A Signal Knowledge-enhanced Domain Adaptation Network for remaining useful life prediction and uncertainty quantification of rolling bearings","authors":"Bin Liu, Changfeng Yan, Ming Lv, Yuan Huang, Lixiao Wu","doi":"10.1016/j.compind.2026.104447","DOIUrl":"https://doi.org/10.1016/j.compind.2026.104447","url":null,"abstract":"Domain adaptation-based methods are extensively applied to predict the Remaining Useful Life (RUL) of rolling bearings under complex operating conditions. However, the nonlinear degradation process of bearings gives rise to markedly non-stationary characteristics in vibration signals throughout the full life cycle. Although significant differences in fault features arise across different degradation stages, clearly identifying the critical degradation information remains a challenge. In this paper, a Signal Knowledge-enhanced Domain Adaptation Network (SKDAN) is proposed to learn domain-invariant features from non-stationary degradation processes, thereby improving cross-domain RUL prediction. Specifically, an adaptive short-time Fourier transform layer with a variable window is introduced to analyze the raw vibration signals in the time domain. This differentiable layer extracts time–frequency physical information with high energy concentration, which enhances the representation of degradation features. Subsequently, a novel discrepancy metric, termed Multi-Stage Maximum Mean Discrepancy (MSMMD), is proposed to replace the global average discrepancy with multiple local discrepancies. The MSMMD metric effectively increases the inter-class distance between cluster centers, which enables cross-domain feature alignment. Finally, an uncertainty measurement mechanism is constructed via a step-by-step training strategy, with the objective of quantifying the uncertainty in RUL results by calculating confidence intervals for prediction points. Comparative tests with other methods are conducted on two different bearing datasets, and the results demonstrate that SKDAN achieves superior performance and reliability in cross-domain RUL prediction.","PeriodicalId":55219,"journal":{"name":"Computers in Industry","volume":"24 1","pages":""},"PeriodicalIF":10.0,"publicationDate":"2026-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146507","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Survey on Learning Motion Planning and Control for Mobile Robots: Toward Embodied Intelligence 移动机器人运动规划与控制学习综述：面向具身智能

IF 10.4 1区计算机科学 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

IEEE transactions on neural networks and learning systems

Pub Date : 2026-02-09 DOI: 10.1109/tnnls.2026.3656889

Mengyun Wang, Yifeng Niu, Bo Wang, Wei Zhang, Chang Wang

引用次数: 0

NOMA and Hybrid Beamforming Aided Secure Computation Offloading for MmWave VEC Networks with Multi-Agent DRL 基于多agent DRL的毫米波VEC网络的NOMA和混合波束形成辅助安全计算卸载

IF 8.6 1区计算机科学 Q1 TELECOMMUNICATIONS

IEEE Transactions on Cognitive Communications and Networking

Pub Date : 2026-02-09 DOI: 10.1109/tccn.2026.3662303

Ying Ju, Zhiwei Cao, Mingdong Li, Lei Liu, Qingqi Pei, Mianxiong Dong, Shahid Mumtaz, Mohsen Guizani