检索结果-内蒙古大学图书馆

International Conference on Networking and Network Applications (NaNA)

作者： Hui Tian Haibao Chen Yuyan Zhao Pinchang Zhang Yan Xu Yangyang Liu School of Computer Science and Technology Anhui University Hefei China School of Computer and Information Engineering Chuzhou University Chuzhou China School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China State Key Laboratory of Integrated Services Networks (Xidian University) Xi’an China School of Computer Science and Technology Xidian University Xi’an China

ISBN: (数字)9798350376777

ISBN: (纸本)9798350376784

Source camera identification method is crucial in digital image forensics for determining the authentic source of an image. In this paper, we propose a new source camera identification method by combining the intrinsic features of the camera with a carefully designed tag. Our method establishes a hybrid fingerprint model involving two parameters as the unique camera fingerprints of a digital image. Utilizing hypothesis testing theory, we develop a generalized likelihood ratio test (GLRT) to identify the source camera of digital images. Finally, we provide numerical results to validate the performance of the proposed method and demonstrate its effectiveness in identifying source camera devices.

关键词： Performance evaluation Digital images Forensics Fingerprint recognition Cameras Numerical models Object recognition

来源：评论

学校读者我要写书评

暂无评论

Split Fine-Tuning for Large Language Models in Wireless networks

arXiv

引用

arXiv 2025年

作者： Zhang, Songge Cheng, Guoliang Huang, Xinyu Li, Zuguang Wu, Wen Song, Lingyang Shen, Xuemin School of Electronic and Computer Engineering Peking University Shenzhen518000 China Frontier Research Center Pengcheng Laboratory Shenzhen518055 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China School of Electronic and Computer Engineering Peking University Shenzhen Graduate School Shenzhen518055 China Department of Electrical and Computer Engineering University of Waterloo WaterlooN2L 3G1 Canada

Fine-tuning is the process of adapting the pre-trained large language models (LLMs) for downstream tasks. Due to substantial parameters, fine-tuning LLMs on mobile devices demands considerable memory resources, and suffers from high communication overhead and long fine-tuning delay. In this paper, we propose an efficient LLM fine-tuning scheme in wireless networks, named Split Fine-Tuning (SFT), which can accommodate LLM fine-tuning on mobile devices. Specifically, an LLM is split into a server-side part on the edge server and a device-side part on the mobile device to satisfy the device-side memory constraint. All devices share a server-side model and perform parallel fine-tuning to reduce fine-tuning delay. In addition, to reduce significant communication overhead incurred by data exchange between devices and the edge server, we propose a data compression scheme by jointly leveraging sparsification, stochastic quantization, and lossless encoding methods. Furthermore, we formulate a fine-tuning delay minimization problem under accuracy and memory constraints, taking device heterogeneity and channel dynamics into account. To solve the problem, the nonlinear mixed-integer problem is decoupled into two subproblems in different timescales. The two-timescale resource management algorithm is proposed to jointly optimize the compression rate and transformer block allocation in the large timescale using the augmented Lagrangian method, and determine spectrum resource allocation in the small timescale via sequential quadratic programming. Extensive simulation results demonstrate that the proposed scheme can reduce the fine-tuning delay by up to 80.2% and communication overhead by 93.6% compared to state-of-the-art benchmarks, while satisfying device-side memory and model accuracy constraints. Copyright © 2025, The Authors. All rights reserved.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Service Function Chains Mapping With Multi-Task Deep Reinforcement Learning

引用

IEEE Transactions on Network Science and engineering 2025年

作者： Wei, Wenting Wang, Qingyi Gu, Huaxi Zheng, Danyang Zhang, Ning Wu, Celimuge Xidian University State Key Laboratory of Integrated Service Networks Xi'an710071 China Southwest Jiaotong University School of Computing and Artificial Intelligence China University of Windsor Department of Electrical and Computer Engineering Canada University of Electro-Communications Meta-Networking Research Center Japan

Network function virtualization (NFV) facilitates different virtual network functions (VNF) to be dynamically chained in sequence to offer new services in a flexible, scalable, and cost-effective manner. Recent years have witnessed the increasing diverse service demands from the ever-increasing new applications, which has posed significant challenges to the efficient and sequential execution of VNFs to achieve specific objectives, especially under conditions of shared resources. To address these challenges, substantial efforts have been dedicated to enhancing resource utilization and minimizing the costs associated with service function chains (SFCs), while maintaining high quality of service. However, an overemphasis on cost reduction can sometimes result in network congestion, which ultimately degrades both network performance and service quality. Given the time-varying and unpredictable characteristics of SFCs, it is essential to leverage their temporal features, along with those of network states, for adaptive SFC mapping. In this paper, we introduce an adaptive online SFC mapping algorithm to reduce operational costs and alleviate network congestion. This is achieved through the adaptive allocation of VNFs and the control of traffic routing between them. Our approach incorporates multi-task deep reinforcement learning to manage the coexistence of multiple SFC requests with varying resource requirements. Specifically, we integrate a long short-term memory (LSTM) layer into our model to capture the temporal dynamics of network states and resource demands, thereby enabling more effective long-term planning. To address the issue of reward sparsity, we implement a hierarchical reward mechanism and reward shaping techniques. Experimental results demonstrate that our algorithm achieves near-optimal performance in optimizing service delay, bandwidth consumption, and network congestion, while also ensuring a high acceptance rate for user requests. © 2013 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

An Effective CU Depth Decision Method for HEVC Using Machine Learning

引用

computer Systems Science & engineering 2021年第11期39卷 275-286页

作者： Xuan Sun Pengyu Liu Xiaowei Jia Kebin Jia Shanji Chen Yueying Wu Beijing University of Technology Beijing100124China Beijing Laboratory of Advanced Information Networks Beijing100124China Beijing Key Laboratory of Computational Intelligence and Intelligent System Beijing100124China Department of Computer Science University of PittsburghPittsburgh15260USA School of Physics and Electronic Information Engineering Qinghai Nationalities University810007QinghaiChina

This paper presents an effective machine learning-based depth selection algorithm for CTU(Coding Tree Unit)in HEVC(High Efficiency Video Coding).Existing machine learning methods are limited in their ability in handling the initial depth decision of CU(Coding Unit)and selecting the proper set of input features for the depth selection *** this paper,we first propose a new classification approach for the initial division depth *** particular,we study the correlation of the texture complexity,QPs(quantization parameters)and the depth decision of the CUs to forecast the original partition depth of the current ***,we further aim to determine the input features of the classifier by analysing the correlation between depth decision of the CUs,picture distortion and the *** the found relationships,we also study a decision method for the end partition depth of the current CUs using bit-rate and picture distortion as ***,we formulate the depth division of the CUs as a binary classification problem and use the nearest neighbor classifier to conduct *** proposed method can significantly improve the efficiency of interframe coding by circumventing the traversing cost of the division *** shows that the mentioned method can reduce the time spent by 34.56%compared to HM-16.9 while keeping the partition depth of the CUs correct.

关键词： HEVC inter-frame coding CU depth

来源：评论

学校读者我要写书评

暂无评论

A New Design of RIS-Aided Hybrid NOMA Offloading in Wireless Powered MEC networks

A New Design of RIS-Aided Hybrid NOMA Offloading in Wireless...

引用

IEEE Conference on Vehicular Technology (VTC)

作者： Lu Lv Hao Luo Long Yang Zhiguo Ding Arumugam Nallanathan Naofal Al-Dhahir Jian Chen State Key Laboratory of Integrated Services Networks Xidian University Xi'an China Department of Electrical Engineering and Computer Science Khalifa University Abu Dhabi UAE School of Electronic Engineering and Computer Science Queen Mary University of London UK Department of Electrical and Computer Engineering The University of Texas at Dallas Richardson TX USA

We investigate a reconfigurable intelligent surface (RIS)-aided wireless powered mobile edge computing (MEC) network, where a new RIS-aided hybrid non-orthogonal multiple access (NOMA) offloading scheme is proposed to improve the efficiency of both MEC offloading and energy harvesting. A joint optimization framework for the transmit power, time allocation, and RIS phase shifts is developed to minimize the overall energy consumption of the network, subject to the energy causality and MEC offloading constraints. Despite of the optimization problem's non-convexity with highly coupled optimization variables, we devise a computationally-efficient algorithm to solve it iteratively. Simulation results are also provided to facilitate the performance evaluation of the RIS-aided wireless powered MEC, quantify the value of the RIS for energy efficient MEC offloading, and validate the performance gains of the proposed hybrid NOMA offloading over various baseline schemes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Demonstration of 16D Voronoi Constellation with Two-Level Coding over 50km Four-Core Fiber

arXiv

引用

arXiv 2024年

作者： Zhao, Can Chen, Bin Cai, Jiaqi Liang, Zhiwei Lei, Yi Xiong, Junjie Ma, Lin Hu, Daohui Sun, Lin Shen, Gangxiang School of Computer Science and Information Engineering Hefei University of Technology Hefei China School of Electronic and Information Engineering Soochow University Suzhou China State Key Laboratory of Advanced Optical Communication Systems and Networks Shanghai Jiao Tong University Shanghai China

A 16-dimensional Voronoi constellation concatenated with multilevel coding is experimentally demonstrated over a 50 km four-core fiber transmission system. The proposed scheme reduces the required launch power by 6 dB and provides a 17 dB larger operating range than 16QAM with BICM at the outer HD-FEC BER threshold. © 2024, CC BY-NC-SA.

关键词： Digital television

来源：评论

学校读者我要写书评

暂无评论

Parallel chaotic sources based on microcombs

Parallel chaotic sources based on microcombs

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Shen, Bitao Shu, Haowen Xie, Weiqiang Chen, Ruixuan Liu, Zhi Zhang, Xuguang Wang, Yimeng Zhang, Yunhao Cheng, Buwen Yu, Shaohua Bowers, John E. Chang, Lin Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Frontiers Science Center for Nano-Optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China State Key Laboratory on Integrated Optoelectronics Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of Sciences Beijing100049 China

Massively parallel optical chaotic sources with large bandwidth are demonstrated based on chaotic microcombs in the AlGaAsOI platform. 30-channel parallel random bit generation with 30 Gbit/s per channel is realized b... 详细信息

ISBN: (纸本)9781957171258

关键词： Gallium compounds

来源：评论

学校读者我要写书评

暂无评论

A SUPERVISED INFORMATION ENHANCED MULTI-GRANULARITY CONTRASTIVE LEARNING FRAMEWORK FOR EEG BASED EMOTION RECOGNITION

arXiv

引用

arXiv 2024年

作者： Li, Xiang Song, Jian Zhao, Zhigang Wang, Chunxiao Song, Dawei Hu, Bin Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Institute of Engineering Medicine Beijing Institute of Technology Beijing China

This study introduces a novel Supervised Info-enhanced Contrastive Learning framework for EEG based Emotion Recognition (SI-CLEER). SI-CLEER employs multi-granularity contrastive learning to create robust EEG contextual representations, potentially improving emotion recognition effectiveness. Unlike existing methods solely guided by classification loss, we propose a joint learning model combining self-supervised contrastive learning loss and supervised classification loss. This model optimizes both loss functions, capturing subtle EEG signal differences specific to emotion detection. Extensive experiments demonstrate SI-CLEER's robustness and superior accuracy on the SEED dataset compared to state-of-the-art methods. Furthermore, we analyze electrode performance, highlighting the significance of central frontal and temporal brain region EEGs in emotion detection. This study offers an universally applicable approach with potential benefits for diverse EEG classification tasks. © 2024, CC0.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

A novel and highly stable 840 MHz repetition rate femtosecond fiber laser

A novel and highly stable 840 MHz repetition rate femtosecon...

引用

2022 Conference on Lasers and Electro-Optics Pacific Rim, CLEO-PR 2022

作者： Yang, Ruoao Zhao, Minghe Jin, Xingang Li, Qian Chen, Zhangyuan Wang, Aimin Zhang, Zhigang State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing100871 China School of Electronic and Computer Engineering Peking University Shenzhen518055 China Jiaxing Xurui Electronics Tech Co Ltd Jiaxing314001 China

ISBN: (纸本)9798350350012

We demonstrate a novel and highly stable femtosecond fiber laser at a repetition rate of 840 MHz. Because the laser components are bonded on a silica glass, the repetition rate of the free running laser drifts within 1 kHz over 12 hrs. The timing jitter of the pulses measured by the balanced optical cross-correlation is 130 as for the integration range of 10 kHz to 1 MHz. © 2022 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel and highly stable 840 MHz repetition rate femtosecond fiber laser

A novel and highly stable 840 MHz repetition rate femtosecon...

引用

2022 Conference on Lasers and Electro-Optics Pacific Rim, CLEO/PR 2022

关键词： Silica

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：