检索结果-内蒙古大学图书馆

FSD-Net: a fuzzy semi-supervised distillation network for noise-resistant classification of medical images

Multimedia Tools and Applications 2024年第36期83卷 83661-83676页

作者： Du, Xiangtong Shen, Ao Wang, Ximing Li, Zongsheng Deng, Hai School of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing211106 China School of Information Science and Engineering Hohai University Changzhou213022 China Department of Radiology First Affiliated Hospital of Soochou University Suzhou215006 China Department of Electrical and Computer Engineering Florida International University MiamiFL33174 United States

Deep Learning (DL)-based models have been successfully applied for medical image classifications. However, the performance of traditional medical image classifiers is limited by insufficient training samples and inaccurate annotations due to labeling noise. Numerous methods were proposed to address the issues, to no avail. To fill this gap, we propose a Fuzzy Semi-supervised Distillation Network (FSD-Net) to improve the noise-resistant classification performance. Firstly, with the aid of semi-supervised training based on the pseudo-labels, the problem of insufficient training samples can be alleviated by using unlabeled data to a certain extent. Then, a Confidence Filtering model (CF-model) is designed to improve the quality of the pseudo-labels and filter the noisy labeling data by combining the soft labels generated from the classification model and the improved Soft Fuzzy C-Means (SFCM) model. Compared with the setting thresholds, the data with low confidence are reclassified as unlabeled to participate in training, while the labeled and unlabeled data (generating pseudo-labels) with high confidences are added into the mixed dataset. Finally, the mixed data are fed to train a multi-model online distillation module consisting of the SFCM and two other student models. The weighted average value of the three student models is used as teacher knowledge to train the students and obtain the final classification results. Experimental results on multiple medical datasets show that the proposed FSD-Net can solve the problems of insufficient labeled samples and labeling noise simultaneously to some extent. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

End-to-End Secure Video Streaming Using Homomorphic Encryption Techniques 2

End-to-End Secure Video Streaming Using Homomorphic Encrypti...

引用

2nd International Conference on Artificial Intelligence, Blockchain, and Internet of Things, AIBThings 2024

作者： Darwich, Mahmoud Khalil, Kasem Bayoumi, Magdy University of Mount Union Department of Mathematics and Computer Science AllianceOH44601 United States University of Mississippi University Department of Electrical and Computer Engineering MS38677 United States University of Louisiana Department of Electrical and Computer Engineering LafayetteLA70504 United States

ISBN: (纸本)9798331529529

In the rapidly evolving landscape of digital media, video streaming has become a ubiquitous method of content delivery. However, the increasing sophistication of cyber threats poses significant risks to the security and privacy of streamed content. Traditional encryption methods, while effective in many scenarios, often fall short in providing comprehensive protection without compromising performance and user experience. This paper introduces a novel approach to achieving end-to-end secure video streaming by leveraging homomorphic encryption techniques. Homomorphic encryption allows for computations to be performed on encrypted data without needing to decrypt it first, thereby maintaining data privacy and security throughout the streaming process. Our proposed method integrates homomorphic encryption into the video streaming pipeline, ensuring that video data remains secure from the point of origin to the end user. We discuss the theoretical foundations of homomorphic encryption, detail the implementation of our approach, and evaluate its performance against conventional encryption methods. Experimental results demonstrate that our technique provides robust security with minimal impact on streaming quality and latency, making it a viable solution for secure video streaming in various applications. © 2024 IEEE.

关键词： Video streaming

来源：评论

学校读者我要写书评

暂无评论

Black Hole Search in Dynamic Rings: The Scattered Case 27

Black Hole Search in Dynamic Rings: The Scattered Case

引用

27th International Conference on Principles of Distributed Systems, OPODIS 2023

作者： Di Luna, Giuseppe A. Flocchini, Paola Prencipe, Giuseppe Santoro, Nicola DIAG Sapienza University of Rome Italy School of Electrical Engineering and Computer Science University of Ottawa Canada Department of Computer Science University of Pisa Italy School of Computer Science Carleton University Ottawa Canada

ISBN: (纸本)9783959773089

In this paper we investigate the problem of searching for a black hole in a dynamic graph by a set of scattered agents (i.e., the agents start from arbitrary locations of the graph). The black hole is a node that silently destroys any agent visiting it. This kind of malicious node nicely models network failures such as a crashed host or a virus that erases the visiting agents. The black hole search problem is solved when at least one agent survives, and it has the entire map of the graph with the location of the black hole. We consider the case in which the underlining graph is a dynamic 1-interval connected ring: a ring graph in which at each round at most one edge can be missing. We first show that the problem cannot be solved if the agents can only communicate by using a face-to-face mechanism: this holds for any set of agents of constant size, with respect to the size n of the ring. To circumvent this impossibility we consider agents equipped with movable pebbles that can be left on nodes as a form of communication with other agents. When pebbles are available, three agents can localize the black hole in O(n2) moves. We show that such a number of agents is optimal. We also show that the complexity is tight, that is Ω(n2) moves are required for any algorithm solving the problem with three agents, even with stronger communication mechanisms (e.g., a whiteboard on each node on which agents can write messages of unlimited size). To the best of our knowledge this is the first paper examining the problem of searching a black hole in a dynamic environment with scattered agents. © Giuseppe A. Di Luna, Paola Flocchini, Giuseppe Prencipe, and Nicola Santoro

关键词： Mobile agents

来源：评论

学校读者我要写书评

暂无评论

AutoColor: learned light power control for multi-color holograms 5

AutoColor: learned light power control for multi-color holog...

引用

Optical Architectures for Displays and Sensing in Augmented, Virtual, and Mixed Reality (AR, VR, MR) V 2024

作者： Zhan, Yicheng Kavakll, Koray Urey, Hakan Sun, Qi Akşit, Kaan University College London Department of Computer Science London United Kingdom Koç University Department of Electrical and Electronics Engineering Istanbul Turkey New York University Department of Computer Science and Engineering New YorkNY United States

ISBN: (纸本)9781510670860

Multi-color holograms rely on simultaneous illumination from multiple light sources. These multi-color holograms could utilize light sources better than conventional single-color holograms and can improve the dynamic range of holographic displays. In this letter, we introduce AutoColor, the first learned method for estimating the optimal light source powers required for illuminating multi-color holograms. For this purpose, we establish the first multi-color hologram dataset using synthetic images and their depth information. We generate these synthetic images using a trending pipeline combining generative, large language, and monocular depth estimation models. Finally, we train our learned model using our dataset and experimentally demonstrate that AutoColor significantly decreases the number of steps required to optimize multi-color holograms from > 1000 to 70 iteration steps without compromising image quality. © 2024 SPIE.

关键词： Holograms

来源：评论

学校读者我要写书评

暂无评论

Random hyperbolic graphs in d+1 dimensions

引用

Physical Review E 2024年第5期109卷 054131-054131页

作者： Gabriel Budel Maksim Kitsak Rodrigo Aldecoa Konstantin Zuev Dmitri Krioukov Faculty of Electrical Engineering Mathematics and Computer Science Department of Physics Network Science Institute Department of Computing and Mathematical Sciences Department of Physics Department of Mathematics Department of Electrical & Computer Engineering

We consider random hyperbolic graphs in hyperbolic spaces of any dimension d+1≥2. We present a rescaling of model parameters that casts the random hyperbolic graph model of any dimension to a unified mathematical framework, leaving the degree distribution invariant with respect to the dimension. Unlike the degree distribution, clustering does depend on the dimension, decreasing to 0 at d→∞. We analyze all of the other limiting regimes of the model, and we release a software package that generates random hyperbolic graphs and their limits in hyperbolic spaces of any dimension.

关键词： Network formation & growth Network structure

来源：评论

学校读者我要写书评

暂无评论

Design and Development of an Intelligent Energy Management System for a Smart Grid to Enhance the Power Quality

引用

Energy engineering 2023年第8期120卷 1747-1761页

作者： Nisha Vasudevan Vasudevan Venkatraman A.Ramkumar T.Muthukumar A.Sheela M.Vetrivel R.J.Vijaya Saraswathi F.T.Josh Department of Electrical and Electronics Engineering Kalasalingam Academy of Research and EducationTamil NaduIndia Department of Computer Science Engineering Kalasalingam Academy of Research and EducationTamil NaduIndia Department of Electrical and Electronics Engineering Kongunadu College of Engineering and TechnologyTamil NaduIndia Department of Electrical and Electronics Engineering Kongu Engineering CollegeTamil NaduIndia Department of Electrical and Electronics Engineering Narasu’s Sarathy Institute of TechnologyTamil NaduIndia Department of Electrical and Electronics Engineering Panimalar Engineering CollegeTamil NaduIndia Department of Electrical and Electronics Engineering Karunya Institute of Technology&SciencesTamil NaduIndia

MigroGrid(MG)has emerged to resolve the growing demand for *** because of its inconsistent output,it can result in various power quality(PQ)*** is a problem that is becoming more and more important for the reliability of power systems that use renewable energy ***,the employment of nonlinear loads will introduce harmonics into the system and,as a result,cause distortions in the current and voltage waveforms as well as low power quality issues in the supply ***,this research focuses on power quality enhancement in the MG using hybrid shunt ***,the performance of the filter mainly depends upon the design,and stability of the *** efficiency of the proposed filter is enhanced by incorporating an enhanced adaptive fuzzy neural network(AFNN)*** performance of the proposed topology is examined in a MATLAB/Simulink environment,and experimental findings are provided to validate the effectiveness of this ***,the results of the proposed controller are compared with Adaptive Fuzzy Back-Stepping(AFBS)and Adaptive Fuzzy Sliding(AFS)to prove its superiority over power quality improvement in *** the analysis,it can be observed that the proposed system reduces the total harmonic distortion by about 1.8%,which is less than the acceptable limit standard.

关键词： Artificial intelligence resistive inductive load shunt hybrid filter smart grid adaptive fuzzy back-stepping power factor

来源：评论

学校读者我要写书评

暂无评论

Evaluating Large Language Models for Enhanced Intrusion Detection in Internet of Things Networks

Evaluating Large Language Models for Enhanced Intrusion Dete...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Nwafor, Ebelechukwu Baskota, Ujjwal Parwez, Md Salik Blackstone, Jeremy Olufowobi, Habeeb Villanova University Department of Computing Sciences PA United States University of Texas at Arlington Department of Computer Science & Engineering TX United States Howard University Department of Electrical Engineering & Computer Science WashingtonDC United States

ISBN: (纸本)9798350351255

The Internet of Things (IoT) landscape has grown exponentially in recent years, making robust and efficient intrusion detection systems (IDS) even more critical. While Large Language Models (LLMs) have gained significant traction, their effectiveness in network intrusion detection remains largely unexplored. This paper proposes an LLM-based framework for enhanced threat detection and analysis in IoT networks. We explore using advanced LLMs like OpenAI's Generative Pre-trained Transformer (GPT) model, focusing on techniques such as fine-tuning and embedding similarity. Using real-world intrusion datasets, we evaluate the proposed LLM's performance in detecting common network attacks and compare it with ensemble-based IDS solutions. We assess the efficiency of the LLM in binary class and multiclass classification task using standard metrics, such as accuracy, recall, precision, and F1 scores. While the fine-tuning approach does not produce comparable results to the current baseline ensemble-based IDS models, the embedding approach, however, yields comparable results. This analysis represents a starting point for exploring the utilization of advanced large language models for intrusion detection within an IoT ecosystem. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Design of a Magneto-Electric Monopole Antenna

Design of a Magneto-Electric Monopole Antenna

引用

2024 International Symposium on Antennas and Propagation, ISAP 2024

作者： Nakamura, Shunta Sano, Makoto Kuse, Ryuji Fukusako, Takeshi Department of Computer Science and Electrical Engineering Kumamoto University Kumamoto Japan Faculty of Advanced Science and Technology Kumamoto University Kumamoto Japan

ISBN: (纸本)9798350364774

This paper presents a compact magneto-electric (ME) monopole antenna. Based on the image theory, the lateral size of the conventional ME dipole antenna is reduced by half, by placing a vertical ground plane. The ME monopole antenna was designed at 2.5 GHz. High front-to-back ratio of 20 dB and low cross polarization are observed. © 2024 IEEE.

关键词： Monopole antennas

来源：评论

学校读者我要写书评

暂无评论

A Comparative of Classification Models for Predicting of Heart Diseases

A Comparative of Classification Models for Predicting of Hea...

引用

2023 International Conference on science, engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Arowolo, Micheal Olaolu Adesina, Ruth Omorinsola Adebiyi, Marion Olubunmi Adebiyi, Ayodele Ariyo University of Missouri Department of Electrical Engineering and Computer Science Columbia United States Landmark University Department of Computer Science Omu-Aran Nigeria

ISBN: (纸本)9798350324785

To slow the rising mortality toll, early detection of heart illness is essential, as it is one crucial organ in human;if it stops beating, life ends. To put it simply, cardiovascular diseases (CVDs) are the important global killer. In 2019, CVDs were responsible for the deaths of 17.9 million individuals worldwide. The medical field has benefited greatly from technological advancements, but there are still some challenges associated with machine learning, such as data that is noisy, error-prone, or contains outliers. Due to their often-late diagnosis, these diseases are principal reason of bereavement in heart patients, making it imperative to learn more about effective algorithms for disease prognosis. Accurate predictions of such results with Machine Learning algorithms can support in the initial diagnosis of diseases, mitigation of their effects, and even prevention of their occurrence by providing crucial information to both medical professionals and patients. This study proposes a model that can rapidly and cheaply diagnose cardiac problems. Therefore, this research employs SVM, Naive Bayes, and Random Forest to detect cardiac illnesses using a data set from Kaggle, with 93%, 85%, and 95% accuracy, respectively;however, the Random Forest attained the best accuracy of 96.9%. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Enhanced Self-Deployment in IoT Sensor Networks through Leveraging 3D-Voronoi Diagrams with an Advanced Genetic Algorithm

Enhanced Self-Deployment in IoT Sensor Networks through Leve...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Andreas, Andreou Mavromoustakis, Constandinos X. Markakis, Evangelos Bourdena, Athina Mastorakis, George University of Nicosia Department of Computer Science Nicosia Cyprus Hellenic Mediterranean University Department of Electrical and Computer Engineering Crete Greece Hellenic Mediterranean University Department of Management Science and Technology Crete Greece

ISBN: (纸本)9798350351255

Smart spaces integrate advanced technologies like the Internet of Things (IoT), Machine Learning, and Artificial Intelligence (AI) to enhance automation and control within various environments. Effective deployment of IoT nodes is crucial for maximizing coverage, minimizing costs, and ensuring network stability in these spaces. This paper presents a novel approach combining 3D Voronoi diagrams with a modified Genetic Algorithm (GA) to optimize IoT node placement in three-dimensional environments. The proposed method starts with node placement using a homogeneous Poisson Point Process (PPP) and partitions the space into Voronoi cells, followed by iterative adjustments using the modified GA. The method achieves a 15% improvement in coverage ratio, a 10% reduction in deployment effort, and a 20% increase in network stability compared to existing algorithms, with results statistically significant at 5%. Moreover, optimising sensor placements indirectly enhances network security by reducing redundant data paths and strengthening network resilience. This study provides a scalable, efficient solution for IoT network deployment in complex environments, addressing key challenges in smart space optimization and paving the way for more secure and robust IoT infrastructures. © 2024 IEEE.

关键词： Genetic algorithms

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：