检索结果-内蒙古大学图书馆

Heterogeneous Domain Adaptation via Correlative and Discriminative Feature Learning

IEEE Transactions on Multimedia 2025年

作者： Lu, Yuwu Lin, Dewei Shen, Linlin Zhou, Yicong Pan, Jiahui South China Normal University School of Artificial Intelligence Foshan528225 China Shenzhen University College of Computer Science and Software Engineering Shenzhen518055 China Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen518060 China University of Nottingham Ningbo China Department of Computer Science Ningbo315100 China University of Macau Department of Computer and Information Science China

Heterogeneous domain adaptation seeks to learn an effective classifier or regression model for unlabeled target samples by using the well-labeled source samples but residing in different feature spaces and lying different distributions. Most recent works have concentrated on learning domain-invariant feature representations to minimize the distribution divergence via target pseudo-labels. However, two critical issues need to be further explored: 1) new feature representations should be not only domain-invariant but also category-correlative and discriminative, and 2) alleviating the negative transfer caused by the incorrect pseudo-labeling target samples could boost the adaptation performance during the iterative learning process. To address these issues, in this paper, we put forward a novel heterogeneous domain adaptation method to learn category-correlative and discriminative representations, referred to as correlative and discriminative feature learning (CDFL). Specifically, CDFL aims to learn a feature space where class-specific feature correlations between the source and target domains are maximized, the divergences of marginal and conditional distribution between the source and target domains are minimized, and the distances of inter-class distribution are forced to be maximized to ensure the discriminative ability. Meanwhile, a selective pseudo-labeling procedure based on the correlation coefficient and classifier prediction is introduced to boost class-specific feature correlation and discriminative distribution alignment in an iteration way. Extensive experiments certify that CDFL outperforms the state-of-the-art algorithms on five standard benchmarks. © 1999-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Multimedia Services Problems in Hybrid Network 23

Multimedia Services Problems in Hybrid Network

引用

23rd Slovak-Czech-Polish Optical Conference on Wave and Quantum Aspects of Contemporary Optics

作者： Štípal, Jiří Trubák, Kamil Látal, Jan Šiška, Petr Vojtěch, Josef Hristov, Hristo Department of Telecommunications Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17. listopadu 2172/15 Ostrava-Poruba708 00 Czech Republic CESNET a. l. e. Zikova 1903/4 Prague160 00 6 Czech Republic Department of Software Technologies Plovdiv University "Paisii Hilendarski" Plovdiv4000 Bulgaria

ISBN: (数字)9781510688094

ISBN: (纸本)9781510688087

This work is dealing with actual topic in the field of internet service providers that are solving the question of metallic and optical networks convergence. The aim was to construct an experimental network topology in the form of WAN or LAN topology consisting of GPON network with VDSL2 technology, which led to the creation of a hybrid access network, on which the parameters of multimedia services were then measured. In particular, focusing on the distribution of video streams through SDTV & HDTV (MPEG-2) + HDTV (MPEG-4). As part of the network integrity measurements, tests are performed according to the recommendations of RFC 6349 and ITU-T Y.1564 standard. © 2025 SPIE.

关键词： Multimedia services

来源：评论

学校读者我要写书评

暂无评论

Iterative Optimal Attention and Local Model for Single Image Rain Streak Removal

arXiv

引用

arXiv 2025年

作者： Li, Xiangyu Fan, Wanshu Shen, Yue Wang, Cong Wang, Wei Yang, Xin Zhang, Qiang Zhou, Dongsheng National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University Dalian China Department of Computing The Hong Kong Polytechnic University Hong Kong School of Cyber Science and Technology Sun Yat-Sen University Shenzhen China School of Computer Science and Technology Dalian University of Technology Dalian China National and Local Joint Engineering Laboratory of Computer Aided Design School of Software Engineering Dalian University School of Computer Science and Technology Dalian University of Technology Dalian China

High-fidelity imaging is crucial for the successful safety supervision and intelligent deployment of vision-based measurement systems (VBMS). It ensures high-quality imaging in VBMS, which is fundamental for reliable visual measurement and analysis. However, imaging quality can be significantly impaired by adverse weather conditions, particularly rain, leading to blurred images and reduced contrast. Such impairments increase the risk of inaccurate evaluations and misinterpretations in VBMS. To address these limitations, we propose an Expectation Maximization Reconstruction Transformer (EMResformer) for single image rain streak removal. The EMResformer retains the key self-attention values for feature aggregation, enhancing local features to produce superior image reconstruction. Specifically, we propose an Expectation Maximization Block seamlessly integrated into the single image rain streak removal network, enhancing its ability to eliminate superfluous information and restore a cleaner background image. Additionally, to further enhance local information for improved detail rendition, we introduce a Local Model Residual Block, which integrates two local model blocks along with a sequence of convolutions and activation functions. This integration synergistically facilitates the extraction of more pertinent features for enhanced single image rain streak removal. Extensive experiments validate that our proposed EMResformer surpasses current state-of-the-art single image rain streak removal methods on both synthetic and real-world datasets, achieving an improved balance between model complexity and single image deraining performance. Furthermore, we evaluate the effectiveness of our method in VBMS scenarios, demonstrating that high-quality imaging significantly improves the accuracy and reliability of VBMS tasks. Codes are at https://***/ghfkahfk/EMResformer. Copyright © 2025, The Authors. All rights reserved.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tong Liu Dongyang Xu Tiantian Zhang Shilong Zhang Jinhua Chen Keping Yu Victor C. M. Leung Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The accelerated development of the Industrial Internet of Things (IoT) has significantly enhanced the computational efficiency and processing capabilities of Wireless Consumer Application Networks (WCAN). Despite these advancements, the performance of WCAN remains constrained by the inherent limitations in computational capacity and energy resources of wireless devices. To address these issues, this paper proposes a wireless powered-mobile edge computing system with Reconfigurable Intelligent Surface (RIS) assistance for WCAN, where wireless consumer devices can not only harvest energy from access point, but also offload computing tasks to edge server with the help of RIS. Aiming to maximize the system computation rate, a non-convex problem is developed and a block optimization with deep reinforcement learning (BO-DRL) scheme is proposed. First, the RIS phase shifts in the Wireless Power Transfer (WPT) stage and offloading stage are optimized using closed-form solutions and the gradient ascent algorithm, respectively. Subsequently, the offloading strategies are optimized using deep reinforcement learning, and a convex optimization algorithm is employed to obtain the time allocation for the WPT and offloading stages. Numerical results illustrate that the BO-DRL algorithm greatly enhances computation rate by 20% compared to without RIS.

关键词： Wireless communication Training Performance evaluation Wireless power transfer Reconfigurable intelligent surfaces Deep reinforcement learning Convex functions Resource management Servers Uplink

来源：评论

学校读者我要写书评

暂无评论

Adaptive Deep Reinforcement Learning-based Resource Management for Complex Decision Making in Industry Internet of Things Applications

引用

Procedia computer science 2025年 252卷 231-240页

作者： Niharika Karne Chandra Shekar Ramagundam Ranga Rao Patnala Shashishekhar Ramagundam Sai Nitisha Tadiboina Sr. Principal Systems Engineer in C&RS Platform services DT Amtrak USA University of south alabama Department of electrical engineering Masters in electrical engineering Senior Software Engineer in Cloud platform services City Of Philadelphia Pennsylvania USA Vice president Neuberger Berman US Software Development & Engineering in Content Discovery & AI Comcast USA Troy University Montgomery Campus AL. Department of computer Science Masters In Computer Science Department of Information Technology GEICO - Chevy Chase Chevy Chase MD 20815 United States

An independent industrial system may transform into a connected network through the assistance of Industrial Internet of Things (IIoT). The deployed sensors in the IIoT maintain surveillance of the industrial machinery and equipment. As a result, safety and reliability emerge as the primary concerns in IIoT. This presents a variety of well-known and increasing issues related to the industrial system. The IIoT devices are exposed to a wide range of malware, threats, and assaults. To prevent the IIoT devices from malware effects, effective protection plans must be implemented. But adequate security mechanisms are not be incorporated in IIoT devices with limited resources. It is essential to ensure the accuracy and dependability of information gathered by IIoT devices. Decisions taken with incomplete or inaccurate data might be devastating. To overcome these difficulties deep learning with reinforcement learning for complex decision-making in industry applications is developed in this research work. In this developed model, an Adaptive Deep Reinforcement learning (ADRL)-based resource management is performed to reduce the operation cost associated with IIoT deployments. Energy efficiency is essential in IIoT ecosystem, particularly for the devices that run on batteries. Through dynamic resource allocation based on workload needs and energy limits, ADRL-based resource management optimizes the usage of energy. The reliability of the designed model is enhanced by fine-tuning the parameters from DRL using the Ship Rescue Optimization (SRO) algorithm. Thus, ADRL-based resource management systems make real-time decisions based on current environmental conditions and system requirements. This helps the IIoT systems to react quickly to change demands and optimize resource allocation. Finally, the experimental analysis is performed to find the success rate of the developed resource management system via various metrics. Throughout the validation, the statistical analysis of the

关键词： Resource Management Industrial Internet of Things Applications Complex Decision Making Adaptive Deep Reinforcement Learning Ship Rescue Optimization

来源：评论

学校读者我要写书评

暂无评论

Causal Discovery from Shifted Multiple Environments 25

Causal Discovery from Shifted Multiple Environments

引用

Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1

作者： Dezhi Yang Guoxian Yu Jun Wang Jinglin Zhang Carlotta Domeniconi School of Software Shandong University Jinan Shandong China School of Control Science and Engineering Shandong University Jinan Shandong China Department of Computer Science George Mason University Fairfax VA USA

ISBN: (纸本)9798400712456

A fundamental problem in many science domains is learning the causal structure of a system from observed data. The observed data canonically come from multiple environments (i.e. different times, locations, and measurements), and causal models may have unobserved shifts. Although the causal graphs can be identified by modeling the distribution changes among different environments, existing solutions can only learn causal structures when given environmental information. In contrast, we propose a causal discovery approach (CausalSME) which automatically identifies pseudo environments and unobserved distribution shifts. Specifically, CausalSME learns a causal model containing unobserved variables, which can correct the distribution shifts with mixed environments. The heart of CausalSME is a variational autoencoder that infers shifted causal effects of unobserved variables and guides the identification of environment information. It further divides the shifted samples by the identified environments to jointly learn an invariant causal model. We prove the structure identifiability of CausalSME with the causal additive model. In our extensive experiments we show that CausalSME achieves state-of-the-art performance.

关键词： adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Student Stress Prediction in Higher Education Using a TriBranch CNN Framework

Enhanced Student Stress Prediction in Higher Education Using...

引用

Integrated Circuits and Communication Systems (ICICACS), IEEE International Conference on

作者： Fateh Bahadur Kunwar Satyajee Srivastava R Dhivya Monika Gulati K. Amudha D Antony Arul Raj Department of Computer Science and Engineering Geetanjali Institute of Technical Studies Udaipur India Department of Computer Science and Engineering School of Engineering and Technology Manav Rachna International Institute of Research and Studies Faridabad India Department of Information Technology M.Kumarasamy College of Engineering Karur India MMIM Maharishi Markandeshwar (Deemed to be University) Mullana Ambala India Department of Electronics and Communication Engineering Kongunadu College of Engineering and Technology Trichy India Department of Software Systems PSG College of Arts & Science Coimbatore India

ISBN: (数字)9798331508456

ISBN: (纸本)9798331508463

Students' stress levels have a significant impact on their academic performance in higher education, thus it's important to identify signs of stress early on and intervene to improve academic performance. Machine learning has evolved into a powerful tool for stress prediction, allowing for proactive support of at-risk youngsters. In order to better anticipate college students' stress levels, this study presents an enhanced TriBranch CNN framework. In order to provide the best possible performance, the technique includes data preparation, feature extraction, and model training. The dimensionality and redundancy are reduced using Principal Component Analysis (PCA). After being trained and tested against other models, the Fully Conditional Temporal Bayesian Network (Fully CTBN) outperformed them all with an accuracy of 93.29%, beating both traditional CNN and FCN approaches. These findings demonstrate that the Fully CTBN approach is useful for identifying students who may be struggling academically and providing schools with the information they need to implement data-driven interventions that boost student well-being and performance.

关键词： Training Accuracy Redundancy Human factors Machine learning Mental health Convolutional neural networks Integrated circuit modeling Stress Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

State-Aware Perturbation Optimization for Robust Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Zhang, Zongyuan Duan, Tianyang Lin, Zheng Huang, Dong Fang, Zihan Sun, Zekai Xiong, Ling Liang, Hongbin Cui, Heming Cui, Yong Department of Computer Science The University of Hong Kong Hong Kong Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Department of Computer Science City University of Hong Kong Hong Kong School of Computer and Software Engineering Xihua University Chengdu610039 China National United Engineering Laboratory of Integrated and Intelligent Transportation The National Engineering Laboratory of Integrated Transportation Big Data Application Technology Southwest Jiaotong University Chengdu611756 China Department of Computer Science and Technology Ts-inghua University Beijing100084 China

Recently, deep reinforcement learning (DRL) has emerged as a promising approach for robotic control. However, the deployment of DRL in real-world robots is hindered by its sensitivity to environmental perturbations. While existing white-box adversarial attacks rely on local gradient information and apply uniform perturbations across all states to evaluate DRL robustness, they fail to account for temporal dynamics and state-specific vulnerabilities. To combat the above challenge, we first conduct a theoretical analysis of white-box attacks in DRL by establishing the adversarial victim-dynamics Markov decision process (AVD-MDP), to derive the necessary and sufficient conditions for a successful attack. Based on this, we propose a selective state-aware reinforcement adversarial attack method, named STAR, to optimize perturbation stealthiness and state visitation dispersion. STAR first employs a soft mask-based state-targeting mechanism to minimize redundant perturbations, enhancing stealthiness and attack effectiveness. Then, it incorporates an information-theoretic optimization objective to maximize mutual information between perturbations, environmental states, and victim actions, ensuring a dispersed state-visitation distribution that steers the victim agent into vulnerable states for maximum return reduction. Extensive experiments demonstrate that STAR outperforms state-of-the-art benchmarks. Copyright © 2025, The Authors. All rights reserved.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Camouflaged Variational Graph AutoEncoder against Attribute Inference Attacks for Cross-Domain Recommendation

引用

IEEE Transactions on Knowledge and Data engineering 2025年

作者： Xiong, Yudi Guo, Yongxin Pan, Weike Yang, Qiang Ming, Zhong Zhang, Xiaojin Yu, Han Lin, Tao Tang, Xiaoying Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China School of Science and Engineering Shenzhen518172 China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong WeBank Shenzhen China Huazhong University of Science and Technology School of Computer Science and Technology Wuhan430074 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore Westlake University School of Engineering Hangzhou China

Cross-domain recommendation (CDR) aims to alleviate the data sparsity problem by leveraging the benefits of modeling two domains. However, existing research often focuses on the recommendation performance while ignores the privacy leakage issue. We find that an attacker can infer user attribute information from the knowledge (e.g., user preferences) transferred between the source and target domains. For example, in our experiments, the average inference accuracies of attack models on gender and age attributes are 0.8323 and 0.3897. The best-performing attack model achieves accuracies of 0.8847 and 0.4634, exceeding a random inference by 25.10% and 64.04%. We can see that the leakage of user attribute information may significantly exceed what would be expected from random inference. In this paper, we propose a novel recommendation framework named CVGAE (short for camouflaged variational graph autoencoder), which effectively models user behaviors and mitigates the risk of user attribute information leakage at the same time. Specifically, our CVGAE combines the strengths of VAEs in capturing latent features and variability with the ability of GCNs in exploiting high-order relational information. Moreover, to ensure against attribute inference attacks without sacrificing the recommendation performance, we design a user attribute protection module that fuses user attribute-camouflaged information with knowledge transfer during cross-domain processes. We then conduct extensive experiments on three real-world datasets, and find our CVGAE is able to achieve strong privacy protection while making little sacrifices in recommendation accuracy. © 1989-2012 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Intrusion Detection System Approach Using PCA and SMOTE with Advanced Ensemble Models

A Hybrid Intrusion Detection System Approach Using PCA and S...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Khaled Mahmud Sujon Nusrat Jahan Someyo Kamal Utsho Mahadi Hasan Shuvo Md Najmus Sakib Razin Department of Software Engineering Universiti Teknologi Malaysia (UTM) Johor Bahru Johor Malaysia Department of Computer Science and Engineering Chittagong University of Engineering & Technology Chittagong Bangladesh Department of Software Engineering Universiti Teknologi Malaysia Johor Bahru Johor Malaysia Department of Architecture American International University-Bangladesh Dhaka Bangladesh Department of Electrical & Electronics Engineering Universiti Teknologi Malaysia Johor Bahru Johor Malaysia

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

A persistent issue of class imbalance in intrusion detection systems (IDS) is addressed in this research, particularly in the context of cyber-physical systems and IoT devices. Current IDS approaches often struggle to detect rare attack patterns due to the dominance of normal traffic in imbalanced datasets. To address this, we present a unique strategy that combines Principal Component Analysis (PCA) for selecting features with the Synthetic Minority Oversampling Technique (SMOTE) to deal with class imbalance, applied to four powerful classifiers: Random Forest (RF), Decision Trees (DT), XGBoost (XGB), and AdaBoost. By reducing the feature space with PCA and balancing the dataset with SMOTE, our methodology significantly enhances model performance. Evaluating on the KDDCup ’99 dataset, we observe notable improvements: for instance, Random Forest achieves 96.42% accuracy, 98.52% precision, 94.68% recall 96.55% F1-score, and 93.87% MCC. Similarly, XGBoost achieves 94.78% accuracy, 96.72% precision, 92.94% recall, 94.81% F1-score, and 92.36% MCC. These results demonstrate that the integration of SMOTE and PCA effectively addresses class imbalance and enhances the detection of minority class attacks. Our findings contribute to the advancement of machine learning techniques in IDS and provide a foundation for further research into combining oversampling methods and dimensionality reduction for robust cybersecurity solutions. Future work will focus on exploring alternative oversampling methods, incorporating deep learning models, and assessing the practical deployment of the proposed methodology in real-time network environments.

关键词： Dimensionality reduction Deep learning Accuracy Computational modeling Intrusion detection Real-time systems Decision trees Random forests Principal component analysis Testing

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：