检索结果-内蒙古大学图书馆

T3 Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839.0页

作者： Hao, Yijun Yang, Shusen Li, Fang Zhang, Yifan Zhao, Cong Ren, Xuebin Zhao, Peng Xu, Chenren Wang, Shibo Xi'an Jiaotong University National Engineering Laboratory for Big Data Analytics China National Engineering Laboratory for Big Data Analytics Ministry of Education Key Lab for Intelligent Networks and Network Security Xi'an Jiaotong University China Peking University China Chinese University of HongKong Xi'an Jiaotong University China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46:6% cost, and supports 3:12× more demand when compared to related existing approaches. © 1983-2012 IEEE.

关键词： Network topology

来源：评论

学校读者我要写书评

暂无评论

Effi-CNN: real-time vision-based system for interpretation of sign language using CNN and transfer learning

引用

Multimedia Tools and Applications 2025年第6期84卷 3137-3159页

作者： Pranav Katarya, Rahul Big Data Analytics and Web Intelligence Laboratory Computer Science & Engineering Department Delhi Technological University New Delhi India

The deaf and mute population has difficulty conveying their thoughts and ideas to others. Sign language is their most expressive mode of communication, but the general public is callow of sign language;therefore, the mute and deaf have difficulty communicating with others. A system that can correctly translate sign language motions to speech and vice versa in real time is required to overcome this communication barrier. Effi-CNN, a vision-based Sign Language Recognition (SLR) system employing transfer learning with EfficientNetB2, is proposed in this paper. We have also developed a system covering sign gestures to text in real time. Our approach was evaluated on eight publicly available datasets, including the Massey University gesture dataset, the ArSL2018 dataset, the MNIST-ASL dataset, and others. When comparing our results to state-of-the-art algorithms, the experimental findings showed that our proposed work is more successful than existing models. Our proposed model delivered an accuracy of 99.90 on MNIST dataset. The results show that our Effi-CNN surpasses most currently existing solutions and can categorize many gestures with a low error rate. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Toward Throughput Optimization: A Congestion Control Scheme for CAM Delivery via NR Sidelink

引用

IEEE Internet of Things Journal 2025年第9期12卷 12206-12218页

作者： Fu, Qiang Liu, Jiajia Wang, Jiadai Kong, Jun Northwestern Polytechnical University National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology The School of Cybersecurity Shaanxi Xi’an710072 China

In the new radio (NR) vehicle-to-everything (V2X),congestion control (CC) is adopted to reduce channel occupancy and improve delivery performance. However, most existing CC schemes decide to adjust the number of messages while ignoring the throughput requirements, which may lead to serious traffic accidents due to the loss of information. In light of this, we investigate the performance of cooperative awareness messages (CAMs) delivery via NR sidelink under different CC configurations, including the modulation and coding scheme, the semi-persistent scheduling-based resource allocation, as well as the CAM transmission period. Specifically, taking into account these configurations, we develop a theoretical framework to capture two metrics of CAM delivery, namely the effective throughput and the channel busy ratio, based on the stochastic geometry approach. With the help of this framework, we propose the CC-(m,n,τ ) scheme, which is able to optimize the two metrics simultaneously by properly tuning the parameters m, n, and τ . Extensive numerical results show that the proposed scheme is highly beneficial for efficient and reliable CAM delivery via NR sidelink, particularly in scenarios with high vehicle densities. © 2014 IEEE.

关键词： Congestion control (communication)

来源：评论

学校读者我要写书评

暂无评论

T³Planner: Multi-Phase Planning Across Structure-Constrained Optical, IP, and Routing Topologies

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1823-1839页

作者： Yijun Hao Shusen Yang Fang Li Yifan Zhang Cong Zhao Xuebin Ren Peng Zhao Chenren Xu Shibo Wang National Engineering Laboratory for Big Data Analytics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and the Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China School of Computer Science Peking University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong Hong Kong China National Engineering Laboratory for Big Data Analytics XiÃan Jiaotong University XiÃan China

Network topology planning is an essential multi-phase process to build and jointly optimize the multi-layer network topologies in wide-area networks (WANs). Most existing practices target single-phase/layer planning, and are incapable of satisfying all rigorous topological structure constraints (e.g., dual-homing rings) defined by network standards and operators, especially in large-scale networks. These significantly limit their usability and performance in production networks. We consider a general topology planning problem with typical structure constraints over three essential phases (greenfield, reconfiguration, and site expansion) and topological layers (optical, IP, and routing topologies). We present, T3Planner, a novel practical solver to this problem in production. Specifically, we develop a structure-driven encoder based on graph neural network (GNN) for concise structure encoding, and design a new learning framework with optical-centric layer compression/reconstruction and rule-aided reinforcement learning (RL) for fast convergence and high performance. Extensive experiments on nine real topologies demonstrate that T3Planner scales to large optical networks with hundreds of sites, saves 46.6% cost, and supports $3.12\times $ more demand when compared to related existing approaches.

关键词： Topology Network topology Planning IP networks Optical fiber networks Routing Optical fibers Optical feedback Production Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Semantic and Sentiment Dual-Enhanced Generative Model for Script Event Prediction 31

Semantic and Sentiment Dual-Enhanced Generative Model for Sc...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Wu, Feiyang Huang, Peixin Hu, Yanli Tan, Zhen Zhao, Xiang Laboratory for Big Data and Decision National University of Defense Technology China National Key Laboratory of Information Systems Engineering National University of Defense Technology China

ISBN: (纸本)9798891761964

Script Event Prediction (SEP) aims to forecast the next event in a sequence from a list of candidates. Traditional methods often use pre-trained language models to model event associations but struggle with semantic ambiguity and embedding bias. Semantic ambiguity arises from the multiple meanings of identical words and insufficient consideration of event arguments, while embedding bias results from assigning similar word embeddings to event pairs with similar lexical features, despite their different meanings. To address above issues, we propose a the Semantic and Sentiment Dual-enhanced Generative Model (SSD-GM). SSD-GM leverages two types of script event information to enhance the generative model. Specifically, it employs a GNN-based semantic structure aggregator to integrate the event-centric structure information, thereby mitigating the impact of semantic ambiguity. Furthermore, we find that local sentiment variability effectively reduces biases in event embeddings, while maintaining global sentiment consistency enhances predictive accuracy. As a result, SSD-GM adeptly captures both global and local sentiment of events through its sentiment information awareness mechanism. Extensive experiments on the Multi-Choice Narrative Cloze (MCNC) task demonstrate that our approach achieves better results than other state-of-the-art baselines. © 2025 Association for Computational Linguistics.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Dynamic-prototype Contrastive Fine-tuning for Continual Few-shot Relation Extraction with Unseen Relation Detection 31

Dynamic-prototype Contrastive Fine-tuning for Continual Few-...

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhao, Simiao Tan, Zhen Pang, Ning Xiao, Weidong Zhao, Xiang National Key Laboratory of Information Systems Engineering National University of Defense Technology China Laboratory for Big Data and Decision National University of Defense Technology China

ISBN: (纸本)9798891761964

Continual Few-shot Relation Extraction (CFRE) aims to continually learn new relations from limited labeled data while preserving knowledge about previously learned relations. Facing the inherent issue of catastrophic forgetting, previous approaches predominantly rely on memory replay strategies. However, they often overlook task interference in continual learning and the varying memory requirements for different relations. To address these shortcomings, we propose a novel framework, DPC-FT, which features: 1) a lightweight relation encoder for each task to mitigate negative knowledge transfer across tasks;2) a dynamic prototype module to allocate less memory for easier relations and more memory for harder relations. Additionally, we introduce the None-Of-The-Above (NOTA) detection in CFRE and propose a threshold criterion to identify relations that have never been learned. Extensive experiments demonstrate the effectiveness and efficiency of our method in CFRE, making our approach more practical and comprehensive for real-world scenarios. © 2025 Association for Computational Linguistics.

关键词： Knowledge transfer

来源：评论

学校读者我要写书评

暂无评论

OSE: On-Site State of Health Estimation for Li-ion Battery using Real-Time Field data

引用

IEEE Transactions on Transportation Electrification 2025年

作者： Chen, Yanwen Zhao, Cong Yang, Shusen Zhao, Peng Ren, Xuebin Han, Qing Yang, Yuqian Wu, Shuaijun Xi'an Jiaotong University National Engineering Laboratory for Big Data Analytics Shaanxi Xi'an710049 China Xi'an Jiaotong University National Engineering Laboratory for Big Data Analytics The Ministry of Education Key Lab for Intelligent Networks and Network Security Shaanxi Xi'an710049 China

On-site lithium-ion battery state of health (SoH) estimation is of crucial importance for reliable operations of electric vehicles (EVs). Yet, due to the low-quality of unlabeled real-time field data, diverse operating environments of in-service EVs, and limited computational capability of onboard devices, existing techniques established on data from well-controlled experimental environments are not practical for real world EVs' SoH estimation. Accurate and rapid SoH estimation based on field data of in-service EVs still remains quite challenging. To tackle this challenge, we present an on-site SoH estimation (OSE) method using in-service EV field data through a new knowledge embedded deep transfer learning (DTL) model. Initially, an universal data preprocessing approach integrating mechanism knowledge is designed to process low-quality data under diverse operating environments. Then, we develop a domain adaptive hybrid deep neural network (DAHDNN) model suitable for unlabeled field data, which can be deployed via edge cloud collaborative framework to meet actual computational capability. We demonstrate the superiority of our method across four real datasets, where, OSE's estimation error is decreased by up to 78.5% compared with the state-of-the-art methods. The results indicate that the proposed method has good generalizability and reliability for SoH estimation on real-time field data. © 2015 IEEE.

关键词： State of charge

来源：评论

学校读者我要写书评

暂无评论

DRL-Enabled Computation Offloading for AIGC Services in IIoT-Assisted Edge Computing Networks

引用

IEEE Internet of Things Journal 2025年第9期12卷 12829-12844页

作者： Zhang, Xingxing Li, Shaobo Tang, Jianhang Zhu, Keyu Zhang, Yang Guizhou University State Key Laboratory of Public Big Data Guiyang550025 China National University of Singapore Department of Electrical and Computer Engineering Queenstown Singapore Guizhou Institute of Technology School of Big Data Guiyang550003 China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing210016 China

The widespread application of AI-generated content (AIGC) services has driven demand for efficient computational resources, making effective task scheduling and computation offloading in edge computing (EC) environments a critical research topic. However, the high computational requirements and low latency demands of AIGC services, combined with the limitations of EC, present challenges for existing offloading methods, such as unstable decision making in dynamic task environments and resource overloading. Here, we propose a decentralized AIGC task offloading architecture within an IoT-assisted EC network to optimize the quality of AIGC services. In this architecture, we define a multiobjective joint optimization problem for AIGC task offloading, aiming to simultaneously optimize key performance metrics, such as task latency, energy efficiency, and load balancing. To address this problem, we introduce an improved proximal policy optimization (PPO)-based deep reinforcement learning (DRL) algorithm, named TOPPO. By incorporating a policy update step size constraint and a clipping mechanism, TOPPO significantly enhances the stability of the training process and reduces fluctuations during policy updates. Additionally, the algorithm integrates an LSTM model to improve its ability to handle temporal dependencies. Through continuous interaction between the model and the environment, the offloading strategy is iteratively updated to ensure that diverse AIGC tasks are efficiently executed on IoT devices or edge servers. Extensive simulations and performance evaluations demonstrate that the proposed method achieves significant improvements in task latency, energy consumption, and load management during AIGC task processing. © 2014 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Multi-Label MambaOut for Quality Assessment of Low-Field Pediatric Brain MR Images 1st

Multi-Label MambaOut for Quality Assessment of Low-Field P...

引用

1st MICCAI Challenge on Low Field Pediatric Brain Magnetic Resonance Image Segmentation and Quality Assurance, LISA 2024, held in Conjunction with Medical Image Computing and Computer Assisted Intervention Conference, MICCAI 2024

作者： Zhu, Yueyue Jiang, Haotian Cai, Rongqing Chen, Geng National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science and Engineering Northwestern Polytechnical University Xi’an China

ISBN: (纸本)9783031830105

Magnetic Resonance Imaging (MRI) can be utilized to study the structure of pediatric brains non-invasively. In practice, low-field MRI scanners are widely adopted for pediatric brain imaging. However, the corresponding acquired MRI data usually suffers from severe artifacts, such as noise and motion. Therefore, an effective Quality Assessment (QA) method is essential. To this end, we design a Multi-Label MambaOut (MLMambaOut) model for the low-field pediatric brain MRI QA challenge. Specifically, we view this challenge as a multi-label classification task, utilizing four stages of gated convolution neural network blocks and ML-Decoder to finish the classification with class balance loss. Furthermore, we explore the performance of Mamba and some advanced models for this challenge. We performed extensive experiments on the challenge data, which is low-field and corrupted with seven kinds of artifacts. The results show that our MLMambaOut achieves superior classification results compared with other methods. © The Author(s) 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

FBI-Net: Frequency Band Integration Network for Infrared Small Target Segmentation

FBI-Net: Frequency Band Integration Network for Infrared Sma...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xin, Biqiao Li, Qiang Mao, Qianchen Wang, Jinbao Wang, Bingshu School of Software Northwestern Polytechnical University Xi'an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (纸本)9798350368741

Small targets in infrared imagery exhibit challenging characteristics due to their minimal semantic information and the extremely imbalanced distribution between the targets and the background. In this paper, we propose a frequency band integration network to extract salient features of infrared small targets in both the spatial and frequency domains. To excavate the high-frequency features of the small targets, we propose a frequency decoupling-fusion module. To decrease the semantic loss that occurs in deep networks, we propose a semantic injection mechanism to assist in retaining critical information from shallow layers. Experimental results show that our proposed method reaches higher prediction accuracy and robustness in the infrared small target segmentation task compared with other state-of-the-art approaches. © 2025 IEEE.

关键词： Feature Fusion Infrared Small Target Segmentation Semantic Injection Wavelet Transformation

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：