检索结果-内蒙古大学图书馆

Self-Supervised Reflective Learning Through Self-Distillation and Online Clustering for Speaker Representation Learning

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 1535-1550页

作者： Danwei Cai Zexin Cai Ze Li Ming Li Department of Electrical and Computer Engineering Duke University Durham NC USA Suzhou Municipal Key Laboratory of Multimodal Intelligent Systems Digital Innovation Research Center Duke Kunshan University Kunshan China School of Computer Science Wuhan University Wuhan China

Speaker representation learning is crucial for voice recognition systems, with recent advances in self-supervised approaches reducing dependency on labeled data. Current two-stage iterative frameworks, while effective, suffer from significant computational overhead due to repeated rounds of clustering and training. They also struggle with noisy pseudo labels that can impair model learning. This paper introduces self-supervised reflective learning (SSRL), an improved framework that addresses these limitations by enabling continuous refinement of pseudo labels during training. Through a teacher-student architecture and online clustering mechanism, SSRL eliminates the need for iterative training rounds. To handle label noise, we incorporate noisy label modeling and pseudo label queues that maintain temporal consistency. Experiments on VoxCeleb show SSRL's superiority over current two-stage iterative approaches, surpassing the performance of a 5-round method in just a single training round. Ablation studies validate the contributions of key components like noisy label modeling and pseudo label queues. Moreover, consistent improvements in pseudo labeling and the convergence of cluster counts demonstrate SSRL's effectiveness in deciphering unlabeled data. This work marks an important advancement in efficient and accurate self-supervised speaker representation learning through the novel reflective learning paradigm.

关键词： Training Representation learning Iterative methods Noise Adaptation models Noise measurement Predictive models Speech processing Robustness Convergence

来源：评论

学校读者我要写书评

暂无评论

Goal-Oriented Communication, Estimation, and Control Over Bidirectional Wireless Links

引用

IEEE Transactions on Communications 2025年第5期73卷 3031-3045页

作者： Cao, Jie Kurniawan, Ernest Boonkajay, Amnart Pappas, Nikolaos Sun, Sumei Popovski, Petar School of Electronic and Information Engineering Guangdong Provincial Key Laboratory of Aerospace Communication and Networking Technology Shenzhen518055 China Institute of Infocomm Research Agency for Science Technology and Research Fusionopolis 138632 Singapore Linköping University Department of Computer and Information Science Linköping58183 Sweden Aalborg University Department of Electronic Systems Aalborg9220 Denmark

We consider a wireless networked control system (WNCS) with imperfect bidirectional links for real-time applications such as smart grids. To maintain the stability of WNCS, captured by the probability that plant state violates preset values, at minimal cost, heterogeneous physical processes are monitored by multiple sensors. This status information, such as dynamic plant state and Markov Process-based context information, is then received/estimated by the controller for remote control. However, scheduling multiple sensors and designing the controller with limited resources is challenging due to their coupling, delay, and transmission loss. We formulate a Constrained Markov Decision Problem (CMDP) to minimize violation probability with cost constraints. We reveal the relationship between the goal and different updating actions by analyzing the significance of information that incorporates goal-related usefulness and contextual importance. Subsequently, a goal-oriented deterministic scheduling policy is proposed. Two sensing-assisted control strategies and a control-aware estimation policy are proposed to improve the violation probability-cost tradeoff, integrated with the scheduling policy to form a goal-oriented co-design framework. Additionally, we explore retransmission in downlink transmission and qualitatively analyze its preference scenario. Simulation results demonstrate that the proposed goal-oriented co-design policy outperforms previous work in simultaneously reducing violation probability and cost. © 1972-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Improving the quality of diffuse optical tomography reconstruction with APU-Net: an attention-based physical U-Net model 16

Improving the quality of diffuse optical tomography reconstr...

引用

Optical Tomography and Spectroscopy of Tissue XVI 2025

作者： Xue, Minghao Li, Shuying Zhu, Quing Biomedical Engineering Department Washington University in St. Louis St. LouisMO63130 United States Electrical and Computer Engineering Department Boston University BostonMA02215 United States Electrical and Systems Engineering Department Washington University in St. Louis St. LouisMO63130 United States

ISBN: (纸本)9781510683761

Traditional diffuse optical tomography (DOT) reconstructions suffer from image artifacts due to various factors such as the proximity of DOT sources to shallow lesions, poor optode-tissue coupling, tissue heterogeneity, and large high-contrast lesions causing shadowing effects. This study introduces an attention-based U-Net (APU-Net) model with Contextual Transformer (CoT) attention modules to enhance DOT image quality and improve lesion diagnostic accuracy. Trained on simulation and phantom data, and evaluated on clinical data, the APU-Net model effectively reduced artifacts by 26.83% on average and significantly improved image contrast in deeper regions, with increases of 20.28% and 45.31% for the second and third target layers, respectively. These improvements demonstrate the potential of the APU-Net model in enhancing DOT reconstructions for better breast cancer diagnosis. © 2025 SPIE.

关键词： Tumor growth modeling Data modeling Image restoration systems modeling Diffuse optical tomography Image enhancement Image quality Medical image reconstruction Commercial off the shelf technology Transformers

来源：评论

学校读者我要写书评

暂无评论

Secure and Reliable 6G Communications with BCH-Based GLDPC and Kyber

Secure and Reliable 6G Communications with BCH-Based GLDPC a...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Linh Nguyen Cheol-Hong Min Hanho Lee Tuy Tan Nguyen School of Informatics Computing and Cyber Systems Northern Arizona University USA Department of Electrical. and Computer Engineering University of St. Thomas USA Department of Electrical and Computer Engineering Inha University Republic of Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Channel coding in sixth-generation (6G) networks must attain exceptionally low bit error rate (BER), typically in the range of 10– 6 to 10– 9 , to ensure the requisite level of reliability. While fifth-generation (5G) New Radio (NR) coding techniques have made substantial progress, the inherent limitations of the low error floor impede the attainment of such stringent BER targets. Compared to the low-density parity check (LDPC) codes employed in 5G communications, generalized low-density parity check (GLDPC) codes offer a more advantageous tradeoff between computational complexity and error correction performance in 6G networks. GLDPC codes enhance traditional LDPC structures by incorporating more complex local decoding units within their check nodes. When coupled with cryptographic techniques, GLDPC codes can establish a robust information security framework. In this paper, we propose a new security-based GLDPC that uses a number of BCH matrices for the GLDPC decoding process combined with the Kyber algorithm (BCH-based KyGLDPC) before transmitting data to increase reli-ability and solve the security problem against quantum computer attacks. The system's performance is assessed using both image data and data encrypted prior to transmission in a white additive Gaussian noise environment. The results indicate that the system provides strong error correction and data security.

关键词： 6G mobile communication Quantum computing computer network reliability System performance Bit error rate Parity check codes Error correction codes Decoding Reliability Channel coding

来源：评论

学校读者我要写书评

暂无评论

Learning for predictive control: A Dual Gaussian Process approach

引用

Automatica 2025年 177卷

作者： Liu, Yuhan Wang, Pengyu Tóth, Roland Control Systems Group Department of Electrical Engineering Eindhoven University of Technology Eindhoven Netherlands Flight Dynamics and Control Laboratory Department of Aerospace Engineering Korea Advanced Institute of Science and Technology Daejeon Korea Republic of Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

An important issue in model-based control design is that an accurate dynamic model of the system is generally nonlinear, complex, and costly to obtain. This limits achievable control performance in practice. Gaussian Process (GP) based estimation of system models is an effective tool to learn unknown dynamics directly from input/output data. However, conventional GP-based control methods often ignore the computational cost associated with accumulating data during the operation of the system and how to handle forgetting in continuous adaption. In this paper, we present a novel Dual Gaussian Process (DGP) based Model Predictive Control (MPC) strategy that enables efficient use of online learning based predictive control without the danger of catastrophic forgetting. The bio-inspired DGP structure is a combination of a long-term GP and a short-term GP, where the long-term GP is used to keep the learnt knowledge in memory and the short-term GP is employed to rapidly compensate unknown dynamics during online operation. A novel recursive online update strategy for the short-term GP is proposed to successively improve the learnt model during online operation without a "dictionary" update and re-computation of the Gram matrix at each time step. Effectiveness of the proposed strategy is demonstrated via numerical simulations. © 2025

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Detection of Perfect Stealthy Attacks on Cyber-Physical systems Subject to Measurement Quantizations: A Watermark-Based Strategy

引用

IEEE/CAA Journal of Automatica Sinica 2025年第1期12卷 114-125页

作者： Yu-Ang Wang Zidong Wang Lei Zou Bo Shen Hongli Dong the College of Information Science and Technology Donghua University the Engineering Research Center of Digitalized Textile and Fashion Technology Ministry of Education IEEE the College of Electrical Engineering and Automation Shandong University of Science and Technology the Department of Computer Science Brunel University London Uxbridge the Sanya Offshore Oil and Gas Research Institute Northeast Petroleum University the Artificial Intelligence Energy Research Institute Northeast Petroleum University Heilongjiang Provincial Key Laboratory of Networking and Intelligent Control Northeast Petroleum University

In this paper, the attack detection problem is investigated for a class of closed-loop systems subjected to unknownbutbounded noises in the presence of stealthy attacks. The measurement outputs from the sensors are quantized before transmission.A specific type of perfect stealthy attack, which meets certain rather stringent conditions, is taken into account. Such attacks could be injected by adversaries into both the sensor-toestimator and controller-to-actuator channels, with the aim of disrupting the normal data flow. For the purpose of defending against these perfect stealthy attacks, a novel scheme based on watermarks is developed. This scheme includes the injection of watermarks(applied to data prior to quantization) and the recovery of data(implemented before the data reaches the estimator).The watermark-based scheme is designed to be both timevarying and hidden from adversaries through incorporating a time-varying and bounded watermark signal. Subsequently, a watermark-based attack detection strategy is proposed which thoroughly considers the characteristics of perfect stealthy attacks,thereby ensuring that an alarm is activated upon the occurrence of such attacks. An example is provided to demonstrate the efficacy of the proposed mechanism for detecting attacks.

关键词： Attack detection cyber-physical systems (CPSs) perfect stealthy attacks watermark-based strategy

来源：评论

学校读者我要写书评

暂无评论

OPTIMAL MULTI-OBJECTIVE BEST ARM IDENTIFICATION WITH FIXED CONFIDENCE

arXiv

引用

arXiv 2025年

作者： Chen, Zhirui Karthik, P.N. Chee, Yeow Meng Tan, Vincent Y.F. Department of Electrical and Computer Engineering Department of Industrial Systems Engineering and Management National University of Singapore Singapore Department of Industrial Systems Engineering and Management National University of Singapore Singapore Department of Mathematics Department of Electrical and Computer Engineering National University of Singapore Singapore Department of Artificial Intelligence Indian Institute of Technology Hyderabad India

We consider a multi-armed bandit setting with finitely many arms, in which each arm yields an M-dimensional vector reward upon selection. We assume that the reward of each dimension (a.k.a. objective) is generated independently of the others. The best arm of any given objective is the arm with the largest component of mean corresponding to the objective. The end goal is to identify the best arm of every objective in the shortest (expected) time subject to an upper bound on the probability of error (i.e., fixed-confidence regime). We establish a problem-dependent lower bound on the limiting growth rate of the expected stopping time, in the limit of vanishing error probabilities. This lower bound, we show, is characterised by a max-min optimisation problem that is computationally expensive to solve at each time step. We propose an algorithm that uses the novel idea of surrogate proportions to sample the arms at each time step, eliminating the need to solve the max-min optimisation problem at each step. We demonstrate theoretically that our algorithm is asymptotically optimal. In addition, we provide extensive empirical studies to substantiate the efficiency of our algorithm. While existing works on pure exploration with multi-objective multi-armed bandits predominantly focus on Pareto frontier identification, our work fills the gap in the literature by conducting a formal investigation of the multi-objective best arm identification problem. Copyright © 2025, The Authors. All rights reserved.

关键词： Pareto principle

来源：评论

学校读者我要写书评

暂无评论

Identifying candidate biomarkers for detecting bronchogenic carcinoma stages using metaheuristic algorithms based on information fusion theory

引用

Discover Oncology 2025年第1期16卷 1-27页

作者： Khalvati, Bagher Kavousi, Kaveh Keyhanipour, Amir Hosein Arabfard, Masoud Department of Bioinformatics Kish International Campus University of Tehran Kish Iran Laboratory of Complex Biological Systems and Bioinformatics (CBB) Department of Bioinformatics Institute of Biochemistry and Biophysics (IBB) University of Tehran Tehran Iran Computer Engineering Department Faculty of Engineering College of Farabi University of Tehran Tehran Iran Chemical Injuries Research Center Systems Biology and Poisonings Institute Baqiyatallah University of Medical Sciences Tehran Iran

Objective: Invasive lung cancer staging poses significant challenges, often requiring painful and costly biopsy procedures. This study aims to identify non-invasive biomarkers for detecting bronchogenic carcinoma and its various stages by analyzing gene expression data using bioinformatics and machine learning techniques. By leveraging these advanced computational methods, we seek to eliminate the need for surgical intervention in the diagnostic process. Methods: We utilized the TCGA-LUAD dataset, including gene expression data from healthy and cancerous samples. To identify robust biomarkers, we applied eight metaheuristic algorithms for feature selection, combined with four classification methods and two data fusion techniques to optimize performance. Results: Our approach achieved 100% accuracy in distinguishing healthy samples from cancerous ones, outperforming existing methods that reported 97% accuracy. Notably, while prior methods have struggled to separate bronchogenic carcinoma stages effectively, our research achieved an approximate accuracy of 77% in stage classification. Furthermore, using gene enrichment methods, we identified 5, 7, and 16 diagnostic biomarker candidates for stages I, II, III, and IV, respectively. Conclusion: This study demonstrates that integrating bioinformatics, gene set enrichment, and biological pathway analysis can enable non-invasive diagnostics for bronchogenic carcinoma stages. These findings hold promise for developing alternatives to traditional, invasive staging systems, potentially improving patient outcomes and reducing healthcare costs. © The Author(s) 2025.

关键词： Biomarker Bronchogenic carcinoma Feature selection algorithms Information fusion Machine learning

来源：评论

学校读者我要写书评

暂无评论

Strategic Planning of Stealthy Backdoor Attacks in Markov Decision Processes

arXiv

引用

arXiv 2025年

作者： Wei, Xinyi Han, Shuo Hemida, Ahmed H. Kamhoua, Charles A. Fu, Jie Department of Electrical and Computer Engineering University of Florida GainesvilleFL United States Department of Electrical and Computer Engineering University of Illinois Chicago United States DE-VCOM Army Research Laboratory United States

This paper investigates backdoor attack planning in stochastic control systems modeled as Markov Decision Processes (MDPs). In a backdoor attack, the adversary provides a control policy that behaves well in the original MDP to pass the testing phase. However, when such a policy is deployed with a trigger policy, which perturbs the system dynamics at runtime, it optimizes the attacker’s objective instead. To solve jointly the control policy and its trigger, we formulate the attack planning problem as a constrained optimal planning problem in an MDP with augmented state space, with the objective to maximize the attacker’s total rewards in the system with an activated trigger, subject to the constraint that the control policy is near optimal in the original MDP. We then introduce a gradient-based optimization method to solve the optimal backdoor attack policy as a pair of coordinated control and trigger policies. Experimental results from a case study validate the effectiveness of our approach in achieving stealthy backdoor attacks. Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic control systems

来源：评论

学校读者我要写书评

暂无评论

ACDV: Adaptive Content Delivery for Vehicular Digital Twin Networks

引用

IEEE Transactions on Vehicular Technology 2025年第5期74卷 7084-7098页

作者： Zheng, Jinkai Luan, Tom H. Li, Guanjie Yin, Zhisheng Wu, Yuan Dong, Mianxiong Dongguan University of Technology School of Electrical Engineering and Intelligentization Dongguan523808 China Xi'an Jiaotong University School of Cyber Science and Engineering Xi'an710049 China Xidian University School of Cyber Engineering Xi'an710071 China Singapore University of Technology and Design Information Systems Technology and Design Pillar 487372 Singapore Xidian University State Key Laboratory of Isn Xi'an710071 China University of Macau State Key Laboratory of Internet of Things for Smart City 999078 China University of Macau Department of Computer Information Science 999078 China Muroran Institute of Technology Department of Sciences and Informatics Muroran05-08585 Japan

Digital Twins (DTs), serving personalized cloud-based digital assistants, hold great promise for supporting infotainment applications of the Internet of Vehicles (IoVs), in which personalized content such as high-definition maps, system updates, and social video streaming can be delivered from individualized DTs to vehicular users (VUEs) to enhance the intelligence of IoV services and improve their driving experience. This paper proposes a novel content caching framework tailored to DT-enabled IoVs, where DTs selectively cache on-demand contents on edge devices (i.e., cellular base stations and roadside units) managed by the edge service manager (ESM) along the VUE's trip to avoid backbone congestion yet save download time. However, ESMs are inherently selfish and reluctant to contribute resources to cache contents without benefits. Furthermore, considering the diverse trajectories of vehicles, it is inefficient to cache data along a single path. To address these challenges, we propose ACDV, which first models the interactions between the ESMs and DTs as a Stackelberg game to incentivize ESMs to actively participate in the content caching process. We then deploy a Markov model to predict the VUE distribution, which enables DTs to cache contents with a focus on predicted trajectories. To save storage costs, we derive an upper bound of content sizes that the VUE can download within a limited network connection time. Considering the lack of network information and users' private utility model in practical scenarios, we further develop a learning-based algorithm to find the optimal pricing scheme and content size strategies of ESMs and DTs. Through extensive simulations, we show that our proposal can effectively find the optimal strategy and achieve a fast convergence speed and high-level performance compared to the baselines. © 1967-2012 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：