检索结果-内蒙古大学图书馆

FedDAD: Federated Domain Adaptation for Object Detection

IEEE Access 2023年 11卷 51320-51330页

作者： Lu, Peggy Joy Jui, Chia-Yung Chuang, Jen-Hui National Yang Ming Chiao Tung University Department of Computer Science Hsinchu30010 Taiwan National Center for High-Performance Computing Data Science and Technology Division Taichung40763 Taiwan

Training an object detection model often requires numerous annotated images on a centralized host, which may violate user privacy and data confidentiality. Federated learning (FL) resolves this issue by allowing multiple clients, e.g., cameras, to collaboratively train a model while protecting user privacy. However, models trained with FL may fail to be generalized for new target domain due to domain shift when the data between source and target domains are statistically different. In this work, we formulate a real-world object detection problem as a source-free multi-domain adaptation problem in FL architecture. Moreover, we propose an adaptive FL algorithm, called FedDAD (Federated Domain Adaptive Detector), which aggregates models with dynamic attention targeting the unsupervised domain on server, and utilize instance-level alignment to alleviate the effects of scene variation on clients. Experimental results show that FedDAD improves the average precision (AP) by up to 10.05% and 19.15% compared to the popular FedAvg for specific object classes in the KAIST and MI3 datasets, respectively. © 2013 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

On some properties of the bibasic Humbert hypergeometric functions Ξ_(1) and Ξ_(2)

引用

Applied Mathematics(A Journal of Chinese Universities) 2023年第4期38卷 614-630页

作者： CAI Qing-bo Ghazi S.Khammash Shimaa I.Moustafa Ayman Shehata Provincial Key Laboratory of Data-Intensive Computing Key Laboratory of Intelligent Computing and Information ProcessingSchool of Mathematics and Computer ScienceQuanzhou Normal UniversityQuanzhou 362000China Department of Mathematics Al-Aqsa UniversityGazaGaza StripPalestine Department of Mathematics Faculty of ScienceAssiut UniversityAssiut 71516Egypt Department of Mathematics Unaizah College of Science and ArtsUnaizah 56264Qassim UniversityBuraydah 52571QassimSaudi Arabia

The main object of this paper is to deduce the bibasic Humbert functions Ξ_(1) and Ξ_(2)Some interesting results and elementary summations technique that was successfully employed,q-recursion,q-derivatives relations,the q-differential recursion relations,the q-integral representations for Ξ_(1) and Ξ_(2)are *** summation formula derives a list of p-analogues of transformation formulas for bibasic Humbert functions that have been studied,also some hypergeometric functions properties of some new interesting special cases have been given.

关键词： q-calculus bibasic Humbert hypergeometric functions q-derivative

来源：评论

学校读者我要写书评

暂无评论

A Conceptual Evaluation of the data as Partner (DAP) Framework 9

A Conceptual Evaluation of the Data as Partner (DAP) Framewo...

引用

9th IEEE International Smart Cities Conference, ISC2 2023

作者： Hassan, Sonia Sobnath, Drishty Snell, Esther Isiaq, Olufemi Solent University Department of Science and Engineering Southampton United Kingdom Creative Computing Institute Universiy of Arts Department of Computer and Data Science and Ai United Kingdom

ISBN: (纸本)9798350397758

This paper explores the innovative data As Partner (DAP) philosophy as a transformative approach to organisational data strategy, drawing upon established concepts of information value, technology acceptance, and inclusivity for people with disabilities (PwD) in smart cities. The study conducted a comprehensive systematic review, after meticulous screening, 20 eligible papers were selected, forming the foundation for deriving the key components of the DAP framework. Subsequently, a qualitative focus group study engaged 18 participants from diverse sectors to evaluate the practical applicability of the DAP conceptual framework. Thematic analysis of the focus group sessions revealed five key themes: practical value, pragmatic performance, ethical perspective, clarity of the framework, and enhancement tools. These findings offer valuable insights for refining the DAP framework and optimising its integration into real-world scenarios, in empowering individuals in smart cities, especially those with disabilities. Future research should explore larger and more diverse samples to generalise findings and assess the framework's long-term impact through longitudinal evaluations. By adopting user-centred methodologies, the DAP framework can be further enhanced as a strategic tool, empowering data to actively participate in organisational decision-making processes. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Augmenting IoT Intrusion Detection System Performance Using Deep Neural Network

引用

Computers, Materials & Continua 2023年第1期74卷 1351-1374页

作者： Nasir Sayed Muhammad Shoaib Waqas Ahmed Sultan Noman Qasem Abdullah M.Albarrak Faisal Saeed Department of Computer Science Islamia College PeshawarPeshawar25120Pakistan Department of Computer Science CECOS University of IT and Emerging SciencesPeshawar25000Pakistan Department of Electrical Engineering HITEC University TaxilaTaxila47080Pakistan Computer Science Department College of Computer and Information SciencesImam Mohammad Ibn Saud Islamic University(IMSIU)Riyadh11432Saudi Arabia DAAI Research Group Department of Computing and Data ScienceSchool of Computing and Digital TechnologyBirmingham City UniversityBirminghamB47XGUK

Due to their low power consumption and limited computing power,Internet of Things(IoT)devices are difficult to ***,the rapid growth of IoT devices in homes increases the risk of *** detection systems(IDS)are commonly employed to prevent *** systems detect incoming attacks and instantly notify users to allow for the implementation of appropriate *** have been made in the past to detect new attacks using machine learning and deep learning techniques,however,these efforts have been *** this paper,we propose two deep learning models to automatically detect various types of intrusion attacks in IoT ***,we experimentally evaluate the use of two Convolutional Neural Networks(CNN)to detect nine distinct types of attacks listed in the NF-UNSW-NB15-v2 *** accomplish this goal,the network stream data were initially converted to twodimensional images,which were then used to train the neural network *** also propose two baseline models to demonstrate the performance of the proposed ***,both models achieve high accuracy in detecting the majority of these nine attacks.

关键词： Internet of things intrusion detection system deep learning convolutional neural network supervised learning

来源：评论

学校读者我要写书评

暂无评论

Gradient Descent Robustly Learns the Intrinsic Dimension of data in Training Convolutional Neural Networks

arXiv

引用

arXiv 2025年

作者： Zhang, Chenyang Gao, Peifeng Zou, Difan Cao, Yuan Department of Statistics and Actuarial Science School of Computing and Data Science The University of Hong Kong Hong Kong Department of Computer Science School of Computing and Data Science The University of Hong Kong Hong Kong Department of Computer Science School of Computing and Data Science & Institute of Data Science The University of Hong Kong Hong Kong

Modern neural networks are usually highly over-parameterized. Behind the wide usage of over-parameterized networks is the belief that, if the data are simple, then the trained network will be automatically equivalent to a simple predictor. Following this intuition, many existing works have studied different notions of "ranks" of neural networks and their relation to the rank of data. In this work, we study the rank of convolutional neural networks (CNNs) trained by gradient descent, with a specific focus on the robustness of the rank to image background noises. Specifically, we point out that, when adding background noises to images, the rank of the CNN trained with gradient descent is affected far less compared with the rank of the data. We support our claim with a theoretical case study, where we consider a particular data model to characterize low-rank clean images with added background noises. We prove that CNNs trained by gradient descent can learn the intrinsic dimension of clean images, despite the presence of relatively large background noises. We also conduct experiments on synthetic and real datasets to further validate our claim. © 2025, CC BY-SA.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enabled Quality Assurance and Traceability in the Indian Confectionery Market

Blockchain-Enabled Quality Assurance and Traceability in the...

引用

2024 International Conference on Innovative computing, Intelligent Communication and Smart Electrical Systems, ICSES 2024

作者： Subashini, B. Shanthi, P. Venkatesh, K. School of Computing Srm Institute of Science and Technology Department of Data Science and Business Systems Tamilnadu kattankulathur India St. Joseph's Institute of Technology Department of Information Technology OMR Chennai119 India School of Computing Srm Institute of Science and Technology Department of Networking and Communications Tamilnadu kattankulathur India

ISBN: (纸本)9798331543617

India, whose population growth is its greatest asset cannot afford to let its people eat confectionery that is either tainted or somehow polluted, since this would lead to extensive malnutrition. Traditional food supply chains are characterized by centralization and the problems associated with it such as having a single point of failure and producing inconsistent products while compromising the quality, along with data loss. With the need for daily reports in all regions of India regarding food fraud, contamination, and adulteration, a clearly advanced decentralized model is sought after for the creation of a supply chain. This paper introduces the supply chain network for the Indian confectionery market based on blockchain to better address quality claims, contamination, and transparency. This enables real-time traceability within the ecosystem, by using IoT strategies along with the Ethereum blockchain leading to better product authentication and resulting in higher consumer confidence. Blockchain creates a secure data tracking function, while smart contracts can be used to define the process - such as IoT monitoring of temperature. The united method enables verified data to be available to the consumer, energy efficiency, and trust across the supply chain. © 2024 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

FVCap: An Approach to Understand Scanned Floor Plan Images Using Deep Learning and its Applications

引用

SN Computer science 2024年第4期5卷 383页

作者： Goyal, Shreya Chattopadhyay, Chiranjoy Bhatnagar, Gaurav AI Labs American Express Bengaluru India School of Computing and Data Science FLAME University Pune India Department of Mathematics Indian Institute of Technology Jodhpur Jodhpur India

Understanding the layouts and features of indoor scenes necessitates graphic recognition in scanned floor plan images. Scanning floor plans usually results in obvious and unanticipated interruptions. Accurately identifying symbols in such a scenario has long been a contentious issue in the document image analysis field. The task was performed with respectable efficiency using classic machine learning approaches such as hand-crafted features and deep neural networks. The strengths of the previously proposed Capsule network and VGG19 are combined in this research to create a hybrid network. The proposed network FVCap employs the VGG19 network for feature encoding and the Capsule network for classification and decoding from floor plan region images. The proposed approach can recognise and identify region elements in scanned floor plan images, as well as perform end-to-end room labeling with significantly more accuracy than other hybrid networks and conventional machine learning models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd 2024.

关键词： Application Capsule Floor plans Graphic recognition Room labelling

来源：评论

学校读者我要写书评

暂无评论

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

XGBD: Explanation-Guided Graph Backdoor Detection 26

XGBD: Explanation-Guided Graph Backdoor Detection

引用

26th European Conference on Artificial Intelligence, ECAI 2023

作者： Guan, Zihan Du, Mengnan Liu, Ninghao School of Computing University of Georgia United States Department of Data Science New Jersey Institute of Technology United States

ISBN: (纸本)9781643684369

Backdoor attacks pose a significant security risk to graph learning models. Backdoors can be embedded into the target model by inserting backdoor triggers into the training dataset, causing the model to make incorrect predictions when the trigger is present. To counter backdoor attacks, backdoor detection has been proposed. An emerging detection strategy in the vision and NLP domains is based on an intriguing phenomenon: when training models on a mixture of backdoor and clean samples, the loss on backdoor samples drops significantly faster than on clean samples, allowing backdoor samples to be easily detected by selecting samples with the lowest loss values. However, the ignorance of topological feature information on graph data limits its detection effectiveness when applied directly to the graph domain. To this end, we propose an explanation-guided backdoor detection method to take advantage of the topological information. Specifically, we train a helper model on the graph dataset, feed graph samples into the model, and then adopt explanation methods to attribute model prediction to an important subgraph. We observe that backdoor samples have distinct attribution distribution than clean samples, so the explanatory subgraph could serve as more discriminative features for detecting backdoor samples. Comprehensive experiments on multiple popular datasets and attack methods demonstrate the effectiveness and explainability of our method. Our code is available: https://***/GuanZihan/GNN-backdoor-detection. © 2023 The Authors.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchronous Graph Neural Network 24

CDA-GNN: A Chain-driven Accelerator for Efficient Asynchrono...

引用

61st ACM/IEEE Design Automation Conference, DAC 2024

作者： Yu, Hui Zhang, Yu He, Ligang He, Donghao Li, Qikun Zhao, Jin Liao, Xiaofei Jin, Hai Gu, Lin Liu, Haikun National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China Department of Computer Science University of Warwick United Kingdom

ISBN: (纸本)9798400706011

Asynchronous Graph Neural Network (AGNN) has attracted much research attention because it enables faster convergence speed than the synchronous GNN. However, existing software/hardware solutions suffer from redundant computation overhead and excessive off-chip communications for AGNN due to irregular state propagations along the dependency chains between vertices. This paper proposes a chain-driven asynchronous accelerator, CDA-GNN, for efficient AGNN inference. Specifically, CDA-GNN proposes a chain-driven asynchronous execution approach into novel accelerator design to regularize the vertex state propagations for fewer redundant computations and off-chip communications and also designs a chain-aware data caching method to improve data locality for AGNN. We have implemented and evaluated CDA-GNN on a Xilinx Alveo U280 FPGA card. Compared with the cutting-edge software solutions (i.e., Dorylus and AMP) and hardware solutions (i.e., BlockGNN and FlowGNN), CDA-GNN improves the performance of AGNN inference by an average of 1,173x, 182.4x, 10.2x, and 7.9x and saves energy by 2,241x, 242.2x, 12.4x, and 8.9x, respectively. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Graph neural networks

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：