检索结果-内蒙古大学图书馆

4th International Conference on Computing, Networks and Internet of Things, CNIOT 2023

作者： Zhang, Dongyan Xu, Yuanjun School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798400700705

Network impairment simulation is designed to simulate different Internet network environments on a local area network(LAN) and provide testing environments for different services under various network conditions (latency, bandwidth limitations, network conflicts, etc.). This verifies the application in a real network environment. In this paper, we implement a system based on the Linux platform which communicate with the Linux kernel through netlink to achieve network damage simulation using the traffic control mechanism in Linux. In this simulation system, it also implements simulation according to certain network loss policies in besides implementing network delay, packet loss, speed limit, repetition, chaos, jitter, etc. For network delay simulation, we proposed to use sparrow search algorithm-optimized long short-Term memory(SSA-LSTM) algorithm to predict future delays using past network delay data. And to perform accurate simulation in the network impairment simulation system based on the results obtained from the prediction, which makes the network impairment simulation about delay more consistent with the real WAN environment. Finally, the experiment verifies the function of the network impairment simulation system. © 2023 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Federated Learning Scheme Based on Gradient Compression and Local Differential Privacy

Federated Learning Scheme Based on Gradient Compression and ...

引用

2023 IEEE International Conference on Control, Electronics and computer technology, ICCECT 2023

作者： Zhao, Lun Hu, Siquan Shi, Zhiguo University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798350399028

As a deep learning framework for distributed deployment, federated learning allows users to complete model training while retaining the original data, which meets the local data privacy protection needs of each user. Differential privacy, as a classic data desensitization technology, is often used to improve privacy protection. Many studies have applied it to machine learning, but it is accompanied by the problem of model utility. In addition, in the traditional federated learning model training, there are frequent gradient exchanges between the user and the central server, which poses a huge challenge to the communication overhead of the model and affects the training efficiency of the model. In order to solve these problems, we propose a new federated learning scheme, firstly propose a StaComp compression algorithm to compress the gradient parameters before the user uploads them, use the local differential privacy mechanism to add noise to protect the user's local data. Finally, we evaluate our scheme on the MNIST dataset. Experiments show that the scheme of this article is close to the classic FedAvg algorithm in the aspect of model accuracy, and is better than other methods based on differential privacy. At the same time, it significantly reduces the training time, improves the convergence speed of the model, and saves communication costs. © 2023 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Teacher Probability Reconstruction based knowledge distillation within intelligent network compression

引用

International Journal of Intelligent Networks 2025年 6卷 47-56页

作者： Chen, Han Teng, Xuyang Su, Jiajie Li, Chunhao Hu, Chang Han, Meng School of Communication Engineering Hangzhou Dianzi University Hangzhou China Department of Computer Science National University of Singapore Singapore College of Computer Science and Technology Zhejiang University Hangzhou China

In the optimization of intelligent network architecture, limited resources at each node, including edge computing devices, have posed challenges for deploying large models in performance-demanding scenarios. Knowledge distillation serves as a model compression method that extracts knowledge from a large-scale teacher model and transfers it to a more lightweight student model. Previous knowledge distillation methods mainly focus on the intermediate layers of the network. However, due to privacy protection regulations that limit data sharing and access as well as computational efficiency requirements in practical scenarios, feature-based distillation encounters challenges in practical applications. We start with logit-based distillation to address these issues, enabling students to learn more representative knowledge from the teacher's output probability distribution. Due to the structural limitations of the teacher network such as insufficient depth or width, and potential issues in the training data like noise and imbalance, the output probability distribution contains many errors. Therefore, we propose a knowledge distillation method that improves the student by correcting errors in the teacher model. Nevertheless, teacher's errors not only bring mistakes to students but also give students greater subjectivity, enabling them to break free from the limitations of the teacher. We also retain the teacher's thinking to prevent students from becoming biased on the remaining (non-target) categories while correcting teacher errors for students. Extensive experiments demonstrate that our method achieves competitive performance on multiple benchmarks without extra parameters. © 2025 The Authors

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

FMNet: Semantic Segmentation of Small Targets in Food Factories by Fusing Multi-Scale Features 2

FMNet: Semantic Segmentation of Small Targets in Food Factor...

引用

2nd International Conference on Artificial Intelligence, Human-computer Interaction and Robotics, AIHCIR 2023

作者： Li, Botao Zhang, Taohong Yang, Huguang Xia, Chenglong Ma, Yuejia School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9798350360363

How to better integrate features of different scales is an important research direction in the field of semantic segmentation. In the task of semantic segmentation of small objects, there is often a problem of incorrect object boundary segmentation, which is caused by the model's inability to effectively integrate multi-scale information and obtain sufficient features. To solve this problem, we designed a fusing multi-scale features *** is included by multi scale pyramid pooling(MSPP) module and atrous convolution fusion(ACF) *** module is designed to extract multi-scale features based on spatial pyramid pooling with different *** module has different rates of dilated convolution. These two modules together form an overall fusing multi-scale module. We created a dataset for online detection in a food workshop and our model outperforms other semantic segmentation models on this dataset, with an accuracy of up to 97%. In addition, the computational and parameter costs of our model only slightly increase. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A DE-LGCA Personalized Recommendation Algorithm Study

A DE-LGCA Personalized Recommendation Algorithm Study

引用

2023 International Conference on Cloud Computing, Performance Computing, and Deep Learning, CCPCDL 2023

作者： Zhang, Qingda Shi, Zhiguo School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China

ISBN: (纸本)9781510666474

A graph convolutional neural network is a special type of neural network that GCN can use to extract features from graphs and use these features for classification or regression. The current lightweight graph convolutional neural network in the recommendation field only considers the case of fixed neighborhood weights, with the increase in the number of training layers of the network recommendation effect will rapidly decline resulting in the problem of oversmoothing and overfitting. In this paper, in order to solve the above problem, this paper will introduce a DE-LGCA personalized recommendation algorithm that uses a random wandering strategy for data enhancement based on a lightweight graph convolutional neural, while introducing an attention mechanism to increase the node neighborhood weights, and show how to use this algorithm to achieve personalized recommendations. Experiments were conducted on three publicly available datasets, and three performance metrics, Precision, Recall, and Normalized Discounted Cumulative Gain (NDCG), were used to evaluate the performance of DE-LGCA, which not only outperformed the comparison method in terms of performance metrics, but also improved the efficiency of the algorithm. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Computational Experiments of Signal Detection Algorithms in VANETs based on Parallel Intelligence 3

Computational Experiments of Signal Detection Algorithms in ...

引用

3rd IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2023

作者： Li, Yi Han, Shuangshuang Chen, Yueyun Du, Liping University of Science and Technology Beijing School of Computer & Communication Engineering Beijing China

ISBN: (纸本)9798350318470

With the rapid growth of connected vehicles in Internet of Vehicle (IoV), ensuring reliable and secure communication is significant. This paper presents a parallel intelligence-based signal detection method for vehicular networks. The proposed method exploits the main idea of parallel intelligent to analyze wireless communication signal in real-time, achieving efficient and accurate algorithm options for difference IoV environment and different requirements. Experimental results demonstrate that the comparison and analysis of the proposed method based on the detection accuracy and computational complexity, while also contributing to enhanced security in vehicular networks. This approach offers a promising solution for timely, reliable and secure communication in the era of connected vehicles. © 2023 IEEE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

A Unified Model Fusing Region of Interest Detection and Super Resolution for Video Compression

引用

computers, Materials & Continua 2024年第6期79卷 3955-3975页

作者： Xinkun Tang Feng Ouyang Ying Xu Ligu Zhu Bo Peng School of Computer and Cyber Sciences Communication University of ChinaBeijing100024China Cable Television Technology Research Institute Academy of Broadcasting ScienceBeijing100866China

High-resolution video transmission requires a substantial amount of *** this paper,we present a novel video processing methodology that innovatively integrates region of interest(ROI)identification and super-resolution *** method commences with the accurate detection of ROIs within video sequences,followed by the application of advanced super-resolution techniques to these areas,thereby preserving visual quality while economizing on data *** validate and benchmark our approach,we have curated a new gaming dataset tailored to evaluate the effectiveness of ROI-based super-resolution in practical *** proposed model architecture leverages the transformer network framework,guided by a carefully designed multi-task loss function,which facilitates concurrent learning and execution of both ROI identification and resolution enhancement *** unified deep learning model exhibits remarkable performance in achieving super-resolution on our custom *** implications of this research extend to optimizing low-bitrate video streaming *** selectively enhancing the resolution of critical regions in videos,our solution enables high-quality video delivery under constrained bandwidth *** results demonstrate a 15%reduction in transmission bandwidth compared to traditional super-resolution based compression methods,without any perceivable decline in visual *** work thus contributes to the advancement of video compression and enhancement technologies,offering an effective strategy for improving digital media delivery efficiency and user experience,especially in bandwidth-limited *** innovative integration of ROI identification and super-resolution presents promising avenues for future research and development in adaptive and intelligent video communication systems.

关键词： Super resolution region of interest detection video compression

来源：评论

学校读者我要写书评

暂无评论

>Student Expression Recognition Algorithm Based on TransConv 2

>Student Expression Recognition Algorithm Based on TransConv

引用

2nd International Conference on Machine Learning, Control, and Robotics, MLCR 2023

作者： Hu, Siquan Zhang, Xiaoxia Shi, Zhiguo University of Science and Technology Beijing School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798350381245

Human facial expression is one of the expressions of inner emotion, which is an important means of emotional communication between people. With the development of artificial intelligence, human facial expression recognition has been widely studied as an important topic in the field of computer vision, especially in the context of teaching scenarios with important applications. Therefore, adopting more novel facial expression feature extraction methods and improving models with higher accuracy of expression recognition are crucial for the task of human facial expression recognition. In this paper, we carry out the research on student expression recognition algorithms in the context of teaching scenarios, in order to improve the accuracy of facial expression recognition, the experiments are based on the JAFFE dataset and the CK+ dataset to construct a caricatured expression dataset consisting solely of locally populated key points of facial expressions, and improve the expression recognition method based on the traditional convolutional neural network, and put forward an expression recognition method based on the TransConv algorithm. The expression recognition method is trained and compared under the same dataset. The experimental results show that the training accuracy of the method proposed in this paper is higher, with an accuracy of up to 90%, and the processing speed is faster. The method described in this paper is feasible and effective, and can play a good role in assisting teachers to grasp the teaching process. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Land Cover Classification for Polarimetric SAR Images Based on Global Membership Tensor 2

Land Cover Classification for Polarimetric SAR Images Based ...

引用

2nd IEEE International Conference on Signal, Information and Data Processing, ICSIDP 2024

作者： Ren, Dawei Han, Songli Gao, Fan Yin, Junjun Yang, Jian Tsinghua University Department of Electronic Engineering Beijing China University of Science and Technology School of Computer and Communication Engineering Beijing China

ISBN: (纸本)9798331515669

The increasing resolution of PolSAR images makes it challenging to achieve satisfactory land cover classification performance with a single feature. Existing research considers combining multiple features to integrate polarimetric and multi-modal information from images, thereby better representing the diversity of land cover. Nevertheless, in the process of extracting multimodal information, the challenges of dimensionality disaster and dynamic range discrepancies persist, and how to effectively eliminate redundant information while preserving higher-order correlations among features remains a significant research challenge. This paper proposes a PolSAR land cover classification framework based on a global membership tensor, which avoids the dimensionality disaster and dynamic range difference issues by concatenating the pre-classified membership matrices, and utilizes Tucker decomposition to extract higher-order correlation information embedded in the tensor structure of the global membership tensor for final land cover classification. Experiments are carried out on the multi-frequency Hainan dataset acquired by the Aerospace Information Research Institute Chinese Academy of sciences (AIRCAS). The experimental results indicate that the proposed classification framework based on global membership tensors successfully integrates polarimetric and texture features for effective land cover classification. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Online Learning-Based Offloading Decision and Resource Allocation in Mobile Edge Computing-Enabled Satellite-Terrestrial Networks

引用

China communications 2024年第3期21卷 230-246页

作者： Tong Minglei Li Song Han Wanjiang Wang Xiaoxiang School of Information and Communication Engineering Beijing University of Posts and TelecommunicationsBeijing 100876China Key Laboratory of Universal Wireless Communications Ministry of EducationBeijing University of Posts and TelecommunicationsBeijing 100876China School of Information and Control Engineering China University of Mining and TechnologyXuzhou 221116China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China

Mobile edge computing(MEC)-enabled satellite-terrestrial networks(STNs)can provide Internet of Things(IoT)devices with global computing ***,the network state information is uncertain or *** deal with this situation,we investigate online learning-based offloading decision and resource allocation in MEC-enabled STNs in this *** problem of minimizing the average sum task completion delay of all IoT devices over all time periods is *** decompose this optimization problem into a task offloading decision problem and a computing resource allocation problem.A joint optimization scheme of offloading decision and resource allocation is then proposed,which consists of a task offloading decision algorithm based on the devices cooperation aided upper confidence bound(UCB)algorithm and a computing resource allocation algorithm based on the Lagrange multiplier *** results validate that the proposed scheme performs better than other baseline schemes.

关键词： computing resource allocation mobile edge computing satellite-terrestrial networks task offloading decision

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：