检索结果-内蒙古大学图书馆

FedCLCC:A personalized federated learning algorithm for edge cloud collaboration based on contrastive learning and conditional computing

引用

Defence technology(防务技术) 2025年第1期43卷 80-93页

作者： Kangning Yin Xinhui Ji Yan Wang Zhiguo Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Federated learning(FL)is a distributed machine learning paradigm for edge cloud *** can facilitate data-driven decision-making in tactical scenarios,effectively addressing both data volume and infrastructure challenges in edge ***,the diversity of clients in edge cloud computing presents significant challenges for *** federated learning(pFL)received considerable attention in recent *** example of pFL involves exploiting the global and local information in the local *** pFL algorithms experience limitations such as slow convergence speed,catastrophic forgetting,and poor performance in complex tasks,which still have significant shortcomings compared to the centralized *** achieve high pFL performance,we propose FedCLCC:Federated Contrastive Learning and Conditional *** core of FedCLCC is the use of contrastive learning and conditional *** learning determines the feature representation similarity to adjust the local *** computing separates the global and local information and feeds it to their corresponding heads for global and local *** comprehensive experiments demonstrate that FedCLCC outperforms other state-of-the-art FL algorithms.

关键词： Federated learning Statistical heterogeneity Personalized model Conditional computing Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Brain Tumor Diagnosis: A Cutting-Edge Ensemble Deep Learning Approach 24

Enhancing Brain Tumor Diagnosis: A Cutting-Edge Ensemble Dee...

引用

8th International Conference on Algorithms, Computing and Systems, ICACS 2024

作者： Chen, Zixuan Wu, Keliang Feng, Xiang Nneji, Grace Ugochi Monday, Happy Nkanta Peng, Jincheng Computers Science and Software Engineering Chengdu University of Technology Sichuan Chengdu China

ISBN: (纸本)9798400718304

Brain cancer is a severe and intricate neurological condition that is expected to impact 13.2 million individuals worldwide by 2030. Brain tumors pose a significant challenge among the different types of cancer, primarily because of their complex characteristics and profound effects on health. Existing detection techniques, such as Magnetic Resonance Imaging (MRI), are efficient but primarily depend on human experience, resulting in a time-consuming and subjective procedure. This study utilizes advanced deep learning techniques, notably convolutional neural networks (CNNs), to improve the diagnostic process for brain tumors and overcome the difficulties associated with it. The proposed ensemble model combines a VGG Residual Learning Network with CBAM attention and an Inception convolutional filters block. The purpose model aims to enhance the efficacy of feature extraction and classification by leveraging the capabilities of both components. The model is trained and validated using the brain tumor dataset consisting of 2,513 images of tumor and 2,087 healthy images, obtained from Kaggle. The results indicate that the ensemble model attains improved performance measured in accuracy of 98.04%, recall of 96.81%, precision of 97.43%, F1-score of 97.11%, and AUC of 100.00%. These metrics clearly demonstrate its superiority over traditional models such as InceptionV3, ResNet50, and VGG16. Grad-CAM visuals validate the model's attention towards pertinent brain regions, hence improving the comprehensibility. The proposed ensemble model provides a strong, effective, and understandable strategy for identifying brain tumors, greatly improving the capacities of existing diagnostic techniques. © 2024 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Towards Selection and Transition Between Behavior-Based Neural Networks for Automated Driving 24

Towards Selection and Transition Between Behavior-Based Neur...

引用

8th International Conference on Computer Science and Artificial Intelligence, CSAI 2024

作者： Aslam, Iqra Anpilogov, Igor Rausch, Andreas Institute for Software and System Engineering Clausthal University of Technology Clausthal Zellerfeld Germany

ISBN: (纸本)9798400718182

Autonomous driving technology is progressing rapidly, largely due to complex End-To-End systems based on deep neural networks. While these systems are effective, their complexity can make it difficult to understand their behavior, which raises safety concerns. This paper presents a new solution: a Behavior Selector that uses multiple smaller artificial neural networks (ANNs) to manage different driving tasks, such as lane following and turning. Rather than relying on a single large network, which can be burdensome, require extensive training data and is hard to understand. The developed approach allows the system to dynamically select the appropriate neural network for each specific behaviour (i.e. turns) in real time. We focus on ensuring smooth transitions between behaviors and taking into account the vehicle’s current speed and orientation to improve stability and safety. The proposed system has been tested using the AirSim simulation environment, demonstrating its effectiveness. © 2024 Copyright held by the owner/author(s).

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Event-Driven Attention Network:A Cross-Modal Framework for Efficient Image-Text Retrieval in Mass Gathering Events

引用

Computers, Materials & Continua 2025年第5期83卷 3277-3301页

作者： Kamil Yasen Heyan Jin Sijie Yang Li Zhan Xuyang Zhang Ke Qin Ye Li School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu611731China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Kashi Institute of Electronics and Information Industry Kashi844508China

Research on mass gathering events is critical for ensuring public security and maintaining social ***,most of the existing works focus on crowd behavior analysis areas such as anomaly detection and crowd counting,and there is a relative lack of research on mass gathering *** believe real-time detection and monitoring of mass gathering behaviors are essential formigrating potential security risks and ***,it is imperative to develop a method capable of accurately identifying and localizing mass gatherings before disasters occur,enabling prompt and effective *** address this problem,we propose an innovative Event-Driven Attention Network(EDAN),which achieves image-text matching in the scenario of mass gathering events with good results for the first *** image-text retrieval methods based on global alignment are difficult to capture the local details within complex scenes,limiting retrieval *** local alignment-based methods aremore effective at extracting detailed features,they frequently process raw textual features directly,which often contain ambiguities and redundant information that can diminish retrieval efficiency and degrade model *** overcome these challenges,EDAN introduces an Event-Driven AttentionModule that adaptively focuses attention on image regions or textual words relevant to the event *** calculating the semantic distance between event labels and textual content,this module effectively significantly reduces computational complexity and enhances retrieval *** validate the effectiveness of EDAN,we construct a dedicated multimodal dataset tailored for the analysis of mass gathering events,providing a reliable foundation for subsequent *** conduct comparative experiments with other methods on our dataset,the experimental results demonstrate the effectiveness of *** the image-to-text retrieval task,EDAN achieved the best performance on the R@5 metric,w

关键词： Mass gathering events image-text retrieval attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Heterologous Image Matching Based on Salience Region

IAENG International Journal of Computer Science

引用

IAENG International Journal of Computer Science 2025年第4期52卷 894-900页

作者： Zhai, Jinlong Xu, Yang Yan, Xiaohu Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen518055 China

To address the matching problem caused by the significant differences in spatial features, spectrum and contrast between heterologous images, a heterologous image matching method based on salience region is proposed in this paper. Firstly, texture features and corner features are detected. Secondly, the epanechnikov kernel function is used to calculate the point with the maximum kernel function value among all feature points, which is then defined as E-point. Thirdly, the salience region is defined and extracted according to the position of the E-point. Finally, six groups of heterologous images are used as data sources, and compared with HAPCG, HOWP, SIFT, and PSO_SIFT algorithms respectively. The results show that the comprehensive matching performance of the proposed method is better than the original algorithm without salience region processing. The root mean square error and the matching time are less than the original method while ensuring a similar number of matching points, which greatly improves the accuracy and speed of heterologous image matching. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

A Novel Lightweight IoT Intrusion Detection Model Based on Self-knowledge Distillation

引用

IEEE Internet of Things Journal 2025年第11期12卷 16912-16930页

作者： Wang, Zhendong Zhou, Renqiang Yang, Shuxin He, Daojing Chan, Sammy Jiangxi University of Science and Technology School of Information Engineering Ganzhou341000 China Nanchang University Software Engineering Institute Nanchang330047 China Harbin Institute of Technology School of Computer Science and Technology Shenzhen518055 China City University of Hong Kong Department of Electrical Engineering Hong Kong

The Internet of Things (IoT) environment contains many different types of devices, each with different functionalities, communication protocols, and security capabilities, which makes the IoT a complex challenge for security protection. Therefore, network intrusion detection (NID) is needed to detect intrusions in the network to secure the IoT. In recent years, deep learning-based intrusion detection systems have achieved excellent results, but they tend to require high computational resources and storage space, which is not feasible for most IoT devices. In this paper, we propose a lightweight intrusion detection model based on self-knowledge distillation, namely TBCLNN, which improves the detection accuracy while also reducing the number of model parameters and computational cost. Specifically, we use the binary Harris Hawk optimization algorithm for dimensionality reduction of traffic features. We use lightweight convolution, such as Tied Block Convolution (TBC), to design lightweight neural network models with residual and inverse residual structures. Moreover, we propose an improved self-knowledge distillation loss function to solve the sample imbalance problem and compensate for the performance degradation caused by lightweight neural networks. The multiclassification accuracy of our proposed method exceeds 99% on all three publicly available IoT datasets. The experimental results show that our method has a small model size and requires only low computational resources, making it suitable for resource-constrained IoT intrusion detection. © 2014 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

ENHANCING E-HEALTH CYBERSECURITY AND RESILIENCE: SHIFTING FROM MONOLITHIC TO MICROSERVICES ARCHITECTURE

UPB Scientific Bulletin, Series C: Electrical Engineering an...

引用

UPB Scientific Bulletin, Series C: Electrical engineering and Computer Science 2025年第1期87卷 21-34页

作者： Contașel, Cristian Rughiniș, Răzvan Trancă, Dumitru Cristian Țurcanu, Dinu Dept. of Computer Science and Engineering National University of Science and Technology POLITEHNICA Bucharest Romania Dep. of Software Engineering and Automatics Technical University of Moldova Chișinău Moldova

This study provides an innovative architectural model for e-Health systems that aims to improve cyber resilience while maintaining high availability under fluctuating traffic loads. We examined typical cybersecurity incidents in the field of e-Health, their correlations with architectural defects, and frequent design patterns in currently operational systems. A testing approach based on our research finds those weaknesses and proposes viable fixes. In this paper, a comprehensive support strategy for transitioning from conventional monolithic architectures to microservices is presented. This change makes use of cloud computing's vertical and horizontal scalability to maximize resource utilization while ensuring system reliability. We also discuss deployment ideas for the new microservices, focusing on operational resilience and cybersecurity in e-Health environments. © 2025, Politechnica University of Bucharest. All rights reserved.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Network Traffic Anomaly Detection Based on DGBi-SA Model

引用

engineering Letters 2025年第3期33卷 612-619页

作者： Wang, Xin Dai, Hong Huang, Zheng Han, Yue University of Science and Technology Liaoning Liaoning CO Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology Liaoning Liaoning CO Anshan114051 China

Network traffic anomaly detection plays a crucial role in today's network security and performance management. In response to the challenges in current network traffic data processing, such as insufficient structuring and dynamics, the paper proposes a network traffic anomaly detection approach based on DGBi-SA model, which integrates Dynamic Graph Convolutional Networks (DyGCN), Bi-directional Long Short-Term Memory (Bi-LSTM), and the Self-Attention mechanism. To solve the problem of insufficient structuring, the model employs DyGCN to capture network traffic's dynamic graph structural characteristics proficiently. Simultaneously, combining Bi-LSTM and the Self-Attention mechanism enhances the model's ability to capture temporal and spatial dependencies. The main objective of the research in the paper is to improve the accuracy and detection efficiency of network traffic prediction, thereby achieving effective detection and timely response to abnormal behaviors in complex network environments. Through a sequence of experiments conducted on the CICIDS-2017 dataset, the paper verifies that the DGBi-SA model can effectively solve the above problems. The experimental results indicate that the model outperforms existing methods in key performance indicators such as AUC, precision, recall, and F1 score, thereby proving that the DGBi-SA model has important application value and scientific significance in network traffic anomaly detection. © 2025, International Association of Engineers. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Enhancing Large Language Model Inference Efficiency via Lookahead Cache Filtering

Enhancing Large Language Model Inference Efficiency via Look...

引用

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

作者： Ou, Jie Chen, Yueming Jiang, Shuaihong Tian, Wenhong School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China

ISBN: (纸本)9798350368741

The large Key-Value (KV) cache is a significant challenge in deploying Large Language Models (LLMs). Current research addressing these issues employs cache compression techniques, which we find suffer from information loss and the "lost-in-the-middle" problem. We propose the Lookahead Cache Filtering (LCF), which retains the full cache in host memory to keep complete details, using the Important Key-Value Lookahead Prediction by Approximate Sorting and the Gather-based Matrix Multiplication on CPU, to filter important KV cache to reduce the overhead of loading cache to GPU and improve the throughput of inference. Finally, we use the Multi-Scale Pyramid Information Fusion mechanism to enhance information fusion to further improve the effectiveness of inference results. Experiments demonstrate that LCF effectively maintains accuracy without introducing additional latency while reducing memory requirements. Our code will be available on GitHub. © 2025 IEEE.

关键词： Approximate Sorting Important Key-Value Lookahead Information Fusion Lost-in-the-Middle Operator Fusion on CPU

来源：评论

学校读者我要写书评

暂无评论

Spatial analysis application research of 3D geological point cloud data 2

Spatial analysis application research of 3D geological point...

引用

2nd International Conference on Big Data, Computational Intelligence, and Applications, BDCIA 2024

作者： Yang, Hao Bi, Xiaojia School of Software Engineering Chengdu University of Information Technology Sichuan Chengdu610000 China

ISBN: (纸本)9781510689053

The application of computer 3D visualization and real-time measurement technology in geological exploration has significant advantages over traditional geological exploration methods, especially in the context of the high altitude, significant elevation differences, variable climatic conditions, and complex terrain of the Tibetan Plateau in China. We have utilized cutting-edge technologies such as Cesium, Vue, and Springboot to develop a three-dimensional visualization and spatial data analysis platform for geological point cloud data. The platform is built using technology frameworks such as Vue and Springboot, and through the powerful 3D rendering capabilities of Cesium, it realizes the efficient loading, rendering, and visualization of geological point cloud data. In terms of computer implementation methods, the platform uses advanced point cloud processing algorithms to preprocess and optimize the geological point cloud data, improving the accuracy and visualization effect of the data. By spatially analyzing a series of geological issues along the tunnel route, aided by large point cloud data obtained via LiDAR technology, we have been able to assist in addressing the primary engineering geological problems in selecting railway routes, such as the hazardous rock falls and landslides near tunnel entrances and exits. © 2025 SPIE.

关键词： Radioactive prospecting

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：