检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Shubhi Shukla Subhadeep Dalui Manaar Alam Shubhajit Datta Arijit Mondal Debdeep Mukhopadhyay Partha Pratim Chakrabarti Centre for Computational and Data Sciences IIT Kharagpur India Computer Science and Engineering Department IIT Kharagpur India Center for Cyber Security New York University Abu Dhabi UAE Department of Artificial Intelligence IIT Kharagpur India Computer Science and Engineering Department IIT Patna India

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Adversarial attacks rely on transferability, where an adversarial example (AE) crafted on a surrogate classifier tends to mislead a target classifier. Recent ensemble methods demonstrate that AEs are less likely to mislead multiple classifiers in an ensemble. This paper proposes a new ensemble training using a Pairwise Adversarially Robust Loss (PARL) that by construction produces an ensemble of classifiers with diverse decision boundaries. PARL utilizes outputs and gradients of each layer with respect to network parameters in every classifier within the ensemble simultaneously. PARL is demonstrated to achieve higher robustness against black-box transfer attacks than previous ensemble methods as well as adversarial training without adversely affecting clean example accuracy. Extensive experiments using standard Resnet20, WideResnet28-10 classifiers demonstrate the robustness of PARL against state-of-the-art adversarial attacks. While maintaining similar clean accuracy and lesser training time, the proposed architecture has a 24.8% increase in robust accuracy (∊= 0.07) from the state-of-the art method. Code is available at: https://***/shubhishukla10/PARL

关键词： Training computer vision Accuracy Perturbation methods Neural networks Closed box computer architecture Robustness Ensemble learning Standards

来源：评论

学校读者我要写书评

暂无评论

Optimized Transfer Learning Model for Lung Cancer Stage Classification Using Computed Tomography Images

Optimized Transfer Learning Model for Lung Cancer Stage Clas...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： R Deepika P. Shanmugam K. Moorthi P. K. Manoj Kumar S. L. Swarna Ramnath. K Department of Artificial Intelligence and Data Science B V Raju Institute of Technology Narsapur Telangana India Department of Computer Science and Engineering Rajalakshmi Engineering College Chennai India Department of Electronics and Communication Engineering Sri Sairam Engineering College Chennai India School of Computational Intelligence Joy University Tirunelveli India Department of Computer Science and Engineering Sona college of Technology Salem Tamilnadu India Department of Computer Science and Engineering K.L.N College of Information Technology Madurai Tamilnadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Lung cancer has become one of the primary causes of death worldwide due to cancer, which indicates the necessity of early diagnosis. In this regard, the present work proposes an optimized model of transfer learning based on characterizing different stages of lung cancer by using computed tomography images acquired from the IQ-OTH/NCCD lung cancer database downloadable from Kaggle. It makes use of a two-step process: first, a U-Net model is used on the patient's CT images to reconstruct anatomical features and reduce noise; second, a ShuffleNet architecture is used to predict the patient's CT stage using the reconstructed image. In addition, to enhance classification, PSO was incorporated into the model so that it can optimize the hyperparameters. The accuracy of the model was at 97.85 percent, and it suggests that the model can become a very useful tool for clinicians to bring about earliest identification and staging for lung cancer.

关键词： Accuracy databases computational modeling Computed tomography Transfer learning Noise Lung cancer Predictive models Image reconstruction Optimization

来源：评论

学校读者我要写书评

暂无评论

Fed-GAN: Federated Generative Adversarial Network with Privacy-Preserving for Cross-Device Scenarios

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Han, Song Ding, Hongxin Zhao, Shuai Ren, Siqi Zeng, Shengke Xue, Mengqi Wang, Ruili Hangzhou City University School of Computer and Computing Science Hangzhou China Zhejiang Gongshang University School of Computer Science and Technology China Zhejiang Key Laboratory of Big Data and Future E-Commerce Technology Hangzhou China Xihua University School of Computer and Software Engineering Chengdu China Massey University School of Mathematical and Computational Science Auckland New Zealand

Huge amounts of data from various sources are substantial to dependable distributed machine learning, especially for trustworthy federated learning (FL). However, existing FL methods are difficult to collect enough data for training the global model more accurately, especially in cross-device scenarios. In this paper, we propose a new federated generative adversarial network empowered by differential privacy and knowledge transfer named Fed-GAN, which can be used to address the problem of data shortage and prevent generator leakage from resource-constrained devices, as well as generate high-quality synthetic data while ensuring strict DP guarantees. Different from other generative model methods, our Fed-GAN framework can achieve efficient and secure generative model training and limited permission for resource-constrained devices to prevent them from leaking or misusing the generator. In addition, we propose a pHash-KT method for our Fed-GAN framework, which selects potentially high-quality data through the knowledge of each client for improving the utility of synthetic data. Our FedGAN framework satisfies (Formula presented)-DP, and also has high resistance when number of adversaries is 10%-70% of the total number of clients. Extensive experiments demonstrate that our Fed-GAN framework not only generates high-quality synthetic data, but also provides strict DP guarantees, compared with other generative model methods. © 2004-2012 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Reliable Optical Wireless Communication in Underwater Sensor Networks Using GRO Based DCO-OFDM

引用

Wireless Personal Communications 2025年 1-28页

作者： Selvin Pradeep Kumar, S. Gummadi, Annapurna Hariharan, U. Muthukumaran, N. Goyal, Vishal Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences SIMATS Chennai India Department of CSE (Data Science) CVR College of Engineering Hyderabad India Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab India Centre for Computational Imaging and Machine Vision Department of ECE Sri Eshwar College of Engineering Coimbatore India Department of Electronics and Communication Engineering Chandigarh Engineering College Chandigarh Group of Colleges-Jhanjeri Mohali India

Developing an acceptable routing strategy for underwater sensor networks (UWSNs) is a challenging task due to the rigorous testing settings of underwater scenarios. Energy confinement is the primary problem in UWSNs. To decrease the energy consumption during data transfer from the source to the base station and increase the lifespan of the network, an energy-efficient strategy must be planned. Turbulence-induced fading is a significant deteriorating factor connected to the underwater channel. Spatial multipath diversity techniques can be applied using UWOC networks to decrease this aging and extend the practical connection distance. In this paper, Gold Rush Optimization based DC biased Optical Orthogonal Frequency Division Multiplexing (GRO-DCO-OFDM) is developed for effective data gathering from Underwater seas. The sensor nodes are initially deployed in the underwater region for sensing various information. The deployed nodes are clustered and cluster head (CH) are selected using the rank based algorithm. Then the data from the best cluster head is transferred to the base station. GRO-DCO-OFDM is utilized for data transmission from CH to the base station in this proposed approach. Geographical Location (GL) and Existing Energy Level (EEL) are utilized to prioritize the sensor nodes. After that, the stored data in on-shore BS are given to the off shore station using bandwidth allocation based Dynamic power Ad hoc On-Demand Distance Vector (DP-AODV) protocol. The Wild Geese Migration Optimization algorithm (GMO) is utilized as a bandwidth allocation approach in this proposed method. The proposed method achieves 0.32 ms of latency, 0.35 ms of propagation delay, and 6.3 J of energy consumption. Thus the proposed approach is the best choice for effective data transmission in UWSN.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automated Assignment Management System: Integrating Email Inbox Parsing, database Updates, and Notification

Automated Assignment Management System: Integrating Email In...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： P Varun R.S. Rashika S Kayalvizhi D Preetha P Naveen T A Mohanaprakash Department of Data Science and Business Systems School of Computing SRM Institute of Science and Technology Kattankulathur Department of CSE Panimalar Engineering College Chennai Department of Computer Science and Engineering Velammal Engineering College Department of Information Technology Alpha College of Engineering Department of Computational Intelligence SRM Institute of Science and Technology Kattankulathur Chennai Department of CSE School of Engineering & Technology CMR University Bengalunu Karnataka

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

This paper presents the design and implementation of an automated assignment management system utilizing a bot interface. The system’ s primary objective is to streamline the process of collecting and tracking student assignments, ensuring timely updates to a central database, and facilitating communication between students and teachers. The bot employs email inbox parsing techniques to identify incoming assignment submissions, extracting relevant data such as student names, assignment details, and submission timestamps. Upon receiving a submission, the bot updates an Excel database with the pertinent information, maintaining an organized record of completed ***, the system incorporates a notification feature to promptly alert students who have not yet submitted their assignments by the deadline. Leveraging email integration, the bot sends personalized notifications reminding students of impending deadlines and urging them to submit their work promptly. Additionally, the bot generates a list of incomplete assignments and forwards it to the respective teacher, providing a consolidated overview of students who require *** automating the assignment management process, this system reduces manual intervention, minimizes administrative burden, and enhances efficiency in monitoring student progress. The integration of email parsing, database updates, and notification functionalities ensures seamless communication and facilitates timely submission of assignments, contributing to improved academic outcomes and instructor-student engagement

关键词： Automation databases Manuals Chatbots Feature extraction data mining Informatics

来源：评论

学校读者我要写书评

暂无评论

Version Innovation Age and Age of Incorrect Version for Monitoring Markovian Sources

Version Innovation Age and Age of Incorrect Version for Moni...

引用

International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOpt)

作者： Mehrdad Salimnejad Marios Kountouris Anthony Ephremides Nikolaos Pappas Department of Computer and Information Science Linköping University Linköping Sweden Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence (DaSCI) University of Granada Spain Electrical and Computer Engineering University of Maryland College Park MD USA

ISBN: (数字)9783903176652

ISBN: (纸本)9798331508722

In this paper, we study the problem of real-time remote tracking of a two-state Markov process. We introduce a modified randomized stationary sampling and transmission policy where the decision to perform sampling occurs probabilistically depending on the current state of the source and whether the system was in a sync state during the previous time slot or not. We then propose two new performance metrics, coined the Version Innovation Age (VIA) and the Age of Incorrect Version (AoIV), and analyze their performance under the modified randomized stationary and other state-of-the-art sampling and transmission policies. Specifically, we derive closed-form expressions for the distribution and the average of VIA and AoIV under these policies. Furthermore, we formulate and solve two constrained optimization problems. The first optimization problem aims to minimize the average VIA subject to constraints on the time-averaged sampling cost and time-averaged reconstruction error. In the second problem, the objective is to minimize the average AoIV while considering a constraint on the time-averaged sampling cost. Finally, we compare the performance of various sampling and transmission policies and identify the conditions under which each policy outperforms the others in optimizing the proposed metrics.

关键词： Measurement Technological innovation Costs Transmitters Wireless networks System performance Receivers Synchronization Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

A consensus model for linguistic group decision making considering emotion analysis 10

A consensus model for linguistic group decision making consi...

引用

10th International Conference on Information Technology and Quantitative Management, ITQM 2023

作者： Xu, Mengru Jing, Fuying Chao, Xiangrui Herrera-Viedma, Enrique School of Management Science and Engineering Chongqing Technology and Business University Chongqing400067 China National Research Base of Intelligent Manufacturing Service Chongqing Technology and Business University Chongqing400067 China School of Business Sichuan University Chengdu610065 China Andalusian Research Institute in Data Science and Computational Intelligence Department of Computer Science and Artificial Intelligence University of Granada Granada18071 Spain

In a problem of linguistic group decision-making (GDM), various emotional characteristics of decision-makers' (DMs) behind their preference series, which is defined as emotion factor, can impact consensus reaching process. As words mean different things to different people, this study comprehensively proposes a novel consensus model with emotion factors based on personalized individual semantics. An improved grey clustering method facilitates to obtain emotion factors. Finally, the proposal model can provide more accurate judgments for moderator's management and further promote consensus. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0) Peer-review under responsibility of the scientific committee of the Tenth International Conference on Information Technology and Quantitative Management.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A GNN-based Spectral Filtering Mechanism for Imbalance Classification in Network Digital Twin

arXiv

引用

arXiv 2025年

作者： Isah, Abubakar Aliyu, Ibrahim Rashid, Sulaiman Muhammad Park, Jaehyung Hahn, Minsoo Kim, Jinsul Department of Intelligent Electronics and Computer Engineering Chonnam National University Buk-gu Gwangju61186 Korea Republic of Department of Computer Science Ahmadu Bello University Zaria810241 Nigeria Department of Computational and Data Science Astana IT University Astana Kazakhstan

Graph Neural Networks are gaining attention in Fifth-Generation (5G) core network digital twins, which are data-driven complex systems with numerous components. Analyzing these data can be challenging due to rare failure types, leading to imbalanced classification in multiclass settings. Digital twins of 5G networks increasingly employ graph classification as the main method for identifying failure types. However, the skewed distribution of failure occurrences is a major class imbalance issue that prevents effective graph data mining. Previous studies have not sufficiently tackled this complex problem. In this paper, we propose Class-Fourier Graph Neural Network (CF-GNN) introduces a class-oriented spectral filtering mechanism that ensures precise classification by estimating a unique spectral filter for each class. We employ eigenvalue and eigenvector spectral filtering to capture and adapt to variations in the minority classes, ensuring accurate class-specific feature discrimination, and adept at graph representation learning for complex local structures among neighbors in an end-to-end setting. Extensive experiments have demonstrated that the proposed CF-GNN could help with both the creation of new techniques for enhancing classifiers and the investigation of the characteristics of the multi-class imbalanced data in network digital twin Copyright © 2025, The Authors. All rights reserved.

关键词： Wiener filtering

来源：评论

学校读者我要写书评

暂无评论

Invertibility of Discrete-Time Linear Systems with Sparse Inputs

arXiv

引用

arXiv 2024年

作者： Poe, Kyle Mallada, Enrique Vidal, René Applied Mathematics and Computational Science Group University of Pennsylvania PA19104 United States Department of Electrical and Computer Engineering Johns Hopkins University MD21218 United States Departments of Electrical and Systems Engineering Radiology Computer and Information Science Statistics and Data Science University of Pennsylvania PA19104 United States

One of the fundamental problems of interest for discrete-time linear systems is whether its input sequence may be recovered given its output sequence, a.k.a. the left inversion problem. Many conditions on the state space geometry, dynamics, and spectral structure of a system have been used to characterize the well-posedness of this problem, without assumptions on the inputs. However, certain structural assumptions, such as input sparsity, have been shown to translate to practical gains in the performance of inversion algorithms, surpassing classical guarantees. Establishing necessary and sufficient conditions for left invertibility of systems with sparse inputs is therefore a crucial step toward understanding the performance limits of system inversion under structured input assumptions. In this work, we provide the first necessary and sufficient characterizations of left invertibility for linear systems with sparse inputs, echoing classic characterizations for standard linear systems. The key insight in deriving these results is in establishing the existence of two novel geometric invariants unique to the sparse-input setting, the weakly unobservable and strongly reachable subspace arrangements. By means of a concrete example, we demonstrate the utility of these characterizations. We conclude by discussing extensions and applications of this framework to several related problems in sparse control. © 2024, CC BY.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Analysis and Classification of Network Security Attacks Using Domain Generation Algorithm

Analysis and Classification of Network Security Attacks Usin...

引用

Sustainable Communication Networks and Application (ICSCNA), International Conference on

作者： S. Gomathi S. Samundeeswari S. Ponmanirai S. Nanthini Department of Computer Science and Engineering Vandayar Engineering College Thanjavur India Department of Computational Intelligence Saveetha School of Engineering SIMATS University Thandalam India Department of Department of Data Science Saveetha School of Engineering SIMATS University Thandalam India

In the realm of cybersecurity, the evolution of network attacks necessitates innovative approaches for threat prediction and mitigation. Traditional methods often fall short in identifying novel attack patterns or adapting swiftly to emerging threats. This study explores the application of Domain Generative Algorithms (DGAs) in the context of network attack prediction. DGAs leverage advanced machine learning techniques to generate synthetic data samples representing various network attack scenarios. By training generative models on diverse and large-scale datasets comprising both historical attack data and benign network traffic, the algorithms learn intricate patterns intrinsic to different types of attacks. Through, systematic analysis of these synthetic attack instances, IDS and IPS algorithms can be fine-tuned to recognize subtle attack patterns that might elude conventional signature-based detection methods. This research underscores the pivotal role of DGAs in revolutionizing the landscape of network attack prediction. By harnessing the power of generative algorithms, organizations can proactively strengthen their cybersecurity posture, effectively mitigating the risks posed by an ever-evolving spectrum of network attacks.

关键词：

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：