检索结果-内蒙古大学图书馆

10th International Conference on Internet of Things, Big Data and Security, IoTBDS 2025

作者： Mthethwa, Sthembile Dlamini, Moses Jembere, Edgar School of Mathematics Statistics and Computer Science University of KwaZulu-Natal Westville Durban South Africa Pretoria South Africa

ISBN: (纸本)9789897587504

Distributed Ledger Technologies (DLTs) are advancing various fields such as the financial sector, supply chain management, Internet of Things (IoTs), etc. Through its characteristics, DLTs have the potential to solve some of the challenges encountered by IoT devices as the number of connected devices continues to grow tremendously. These characteristics includes but not limited to decentralisation, traceability, security, transparency, immutability, non-repudiation, etc. There has been an increase in the body of knowledge in relation to the convergence of DLTs and IoTs. This paper examines how DLTs can enhance the security of resource-constrained IoT devices, which have limitations that prevent the implementation of traditional security measures like encryption due to size and computational power. This paper consolidates existing research by comparing techniques, technologies used, and results achieved over the years. Finally, the research identifies knowledge gaps for future exploration. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Supply chain management

来源：评论

学校读者我要写书评

暂无评论

Enabling Secure Data Aggregation Scheme for Smart Grids based on Local Differential Privacy 24

Enabling Secure Data Aggregation Scheme for Smart Grids base...

引用

2nd International Conference on Electronics, computers and Communication Technology, CECCT 2024

作者： He, Yixuan Mei, Lin Liu, Jianghua Xu, Lei Xu, Chungen School of Mathematics and Statistics Nanjing University of Science and Technology Jiangsu Nanjing China School of Computer Science and Engineering Nanjing University of Science and Technology Jiangsu Nanjing China

ISBN: (纸本)9798400710193

Existing data aggregation schemes for privacy protection in smart grids face limitations in efficiency and application, often relying on trusted third parties or incurring significant overhead. To address these issues, this paper introduces a multidimensional and multisubset data aggregation scheme leveraging local differential privacy, aimed at enabling fine-grained data analysis while safeguarding privacy. The scheme effectively protects user privacy by locally perturbing data from randomly selected dimensions while utilizing the Chinese Remainder Theorem to compress multidimensional data, thereby optimizing the transmission. Theoretical and experimental results demonstrate that our scheme offers strong privacy, flexibility, and utility, achieving a relative error of aggregation results no more than 0.05 under optimal conditions. Additionally, it outperforms existing approaches in terms of both computational and communication overhead. © 2024 Copyright held by the owner/author(s).

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Enhancing Missing Data Imputation for Migrants Data: A Neutrosophic Set-Based Machine Learning Approach

引用

Neutrosophic Sets and Systems 2025年 81卷 479-502页

作者： Abdo, Doaa A. Salama, A.A. Abdelmegaly, Alaa A. Mahmoud, Hanan Khadari Mahdi Applied statistics and insurance department faculty of commerce Mansoura university Mansoura Egypt Dept. of Math and Computer Sci. Faculty of Science Port Said Univ. Egypt Higher Institute of Advanced Management Sciences and Computers Al-Buhayrah Egypt Depatrment of applied statistics at the Nile Higher Institute of commercial sciences and Computer Technology in Mansoura Egypt

This study tackles the problem of missing data in migrant datasets by introducing a new framework that combines machine learning techniques with neutrosophic sets. These sets, which can represent uncertainty and ambiguity, are well-suited for managing the complex nature of missing information in sensitive fields like migration research. We test the effectiveness of KNN, SVM, decision tree, random forest, and Ada Boost algorithms on a migrant dataset, comparing their results using different imputation methods (mean/mode, model-based imputer (simple tree), and random values). Our research showed that our proposed approach, which used neutrosophic sets, improved imputation accuracy and strengthened model reliability. Our results underscored the potential of neutrosophic set-based machine learning for addressing missing data issues across various fields. © 2025, University of New Mexico. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent classification of flue-cured tobacco based on improved network model of six channel ResNet

Journal of Biotech Research

引用

Journal of Biotech Research 2025年 20卷 98-110页

作者： Wang, Shiyu Zhuang, Runjie Lv, Wanping Lin, Tianzhen Wen, Yongxian College of Computer and information Science Fujian Agriculture and Forestry University Fujian Fuzhou China Institute of Statistics and Applications Fujian Agriculture and Forestry University Fujian Fuzhou China

Flue-cured tobacco is the most important raw material for cigarette production, and efficient and accurate intelligent grading of flue-cured tobacco leaves is of great significance to the acquisition and correct use of tobacco. Currently, there are few studies on the classification of flue-cured tobacco by using both front and back images of tobacco leaves, while the back image of flue-cured tobacco leaves has enriched information. To harness the back information of these leaves and enhance grading accuracy, a revolution ResNet network model, Evo-ResNet, was proposed in this study based on front and back images of flue-cured tobacco leaves. Evo-ResNet had six channel with added Squeeze-and-Excitation (SE) attention mechanism. Six grades pictures of Cuibi 1 and Yunyan 87 tobacco species were collected using mobile phone, respectively. Evo-ResNet was compared with three-channel models of ResNet, GoogLeNet, VGGNet, and AlexNet with only front images of flue-cured tobacco leaves and both front and back images of flue-cured tobacco leaves. The results showed that the loss of train set and the accuracy of validation set had better results while the front and back pictures of flue-cured tobacco leaves were used meantime. For the test set, the accuracy, recall, precision, and F1-score of Evo-ResNet were better than that of other three-channel network models, expect for GoogleNet. The accuracy, recall, precision, and F1-score value of Cuibi 1 were 95.83%, 95.83%, 96.16%, and 95.78%, respectively, while those of Yunyan 87 were 99.07%, 99.07%, 99.10% and 99.08%, respectively. There was better generalization ability for Evo-ResNet. Because of the convenience for obtaining image of flue-cured tobacco by mobile phone, the proposed Evo-ResNet network model had better applicability in practice, which provided a new idea for the application of intelligent classification of flue-cured tobacco leaves in purchasing practice of flue-cured tobacco. © (2025), (Bio Tech System). All rights

关键词： Flues

来源：评论

学校读者我要写书评

暂无评论

Assessing the impact of Covid-19 on the Italian comic book industry: a panel vector autoregressive analysis of financial ratios

引用

Quality and Quantity 2025年 1-29页

作者： Magrini, Alessandro Rimediotti, Luca Department of Statistics Computer Science Applications “G. Parenti” University of Florence Florence 50134 Italy Independent Researcher Prato 59100 Italy

The comic book market is a niche that has significantly benefited from the more time spent at home by people during the outbreak of Covid-19. This is particularly true in Italy, where sales of comics have met an unprecedented expansion during the two decades before the pandemic. It is therefore important for policy makers to understand the impact of Covid-19 on the economic performance of the Italian comic book industry. To this purpose, yearly data on 10 financial ratios are collected for a panel of 13 Italian comic publishers in the period 2011-2022, and an interrupted time series (ITS) design based on panel vector autoregressive (PVAR) models is applied. In order to maximize the statistical power of the design given the small number of both time points (T=9) and cross-sectional units (n=13), we correct least squares estimates based on the half panel jackknife and perform model reduction through system sequential elimination. The results highlight a worsened performance for small publishers used to base most of their business on comic fairs (Round Robin, Magic Press Edizioni), while companies able to renew their business by launching new products and re-editions (the historic Astorina and Sergio Bonelli Editore, but also the young Tunué) experienced a significant growth compared to the pre-pandemic period. Publishers that dedicated most of their activity to the publication of manga (Bao Publishing, Coconino, Edizioni BD, Edizioni Star Comics, and also Panini with the label Planet Manga) received even more benefits from the pandemic. © The Author(s) 2025.

关键词： Comics Firm performance Half panel jackknife Interrupted time series Panel VAR models

来源：评论

学校读者我要写书评

暂无评论

Routing and Spectrum Allocation in Broadband Quantum Entanglement Distribution

引用

IEEE Journal on Selected Areas in Communications 2025年第5期43卷 1856-1870页

作者： Bali, Rohan Tittelbaugh, Ashley N. Jenkins, Shelbi L. Agrawal, Anuj Horgan, Jerry Ruffini, Marco Kilper, Daniel C. Bash, Boulat A. The Department of Electrical and Computer Engineering Department University of Arizona TucsonAZ United States The School of Computer Science and Statistics CONNECT Center Trinity College Dublin Dublin Ireland The Electronic and Electrical Engineering Department CONNECT Centre Trinity College Dublin Dublin Ireland

We investigate resource allocation for quantum entanglement distribution over an optical network. We characterize and model a network architecture that employs a single broadband quasi-deterministic time-frequency heralded Einstein-Podolsky-Rosen (EPR) pair source, and develop a routing and spectrum allocation scheme for distributing entangled photon pairs over such a network. As our setting allows separately solving the routing and spectrum allocation problems, we first find an optimal polynomial-time routing algorithm. We then employ max-min fairness criterion for spectrum allocation, which presents an NP-hard problem. Thus, we focus on approximately-optimal schemes. We compare their performance by evaluating the max-min and median number of EPR-pair rates assigned by them, and the associated Jain index. We identify two polynomial-time approximation algorithms that perform well, or better than others under these metrics. We also investigate scalability by analyzing how the network size and connectivity affect performance using Watts-Strogatz random graphs. We find that a spectrum allocation approach that achieves higher minimum EPR-pair rate can perform significantly worse when the median EPR-pair rate, Jain index, and computational resources are considered. Additionally, we evaluate the effect of the source node placement on the performance. © 2025 IEEE. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Enhanced Data Mining Algorithms for Sybil Attack Prevention in Truth Discovery 24

Enhanced Data Mining Algorithms for Sybil Attack Prevention ...

引用

3rd International Conference on Algorithms, Data Mining, and Information Technology, ADMIT 2024

作者： Shao, Yanjing Zhao, Wei Liu, Jianghua Xu, Lei Xu, Chungen School of Mathematics and Statistics Nanjing University of Science and Technology China National Key Laboratory of Security Communication China School of Computer Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)9798400718120

In crowdsourcing systems, where substantial amounts of data from various contributors are aggregated to discern reliable information, privacy concerns are often managed through differential privacy techniques. However, these systems are vulnerable to Sybil attacks, where attackers create multiple fake contributors to gain undeserved rewards. The presence of differential privacy noise complicates the detection of these fraudulent contributors, thereby reducing the accuracy of truth discovery. To address this challenge, we introduce an enhanced data mining algorithm, Truth Discovery against Sybil Attacks (TDSA). This algorithm is specifically designed to improve truth discovery by effectively mitigating Sybil attacks and reducing transmission errors in data mining contexts, utilizing machine learning clustering algorithms and lattice-based linear coding techniques. TDSA optimizes the mining process to better handle malicious data contributions and reduces errors associated with data aggregation. Experimental results on real-world datasets demonstrate that TDSA improves accuracy by approximately 20% compared to conventional methods lacking Sybil attack defenses, highlighting its efficacy in advanced data mining applications. © 2024 Copyright held by the owner/author(s).

关键词： Data aggregation

来源：评论

学校读者我要写书评

暂无评论

Revisiting LARS for Large Batch Training Generalization of Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第5期6卷 1321-1333页

作者： Do, Khoi Nguyen, Minh-Duong Hoa, Nguyen Tien Tran-Thanh, Long Tran, Nguyen H. Pham, Quoc-Viet Trinity College Dublin School of Computer Science and Statistics Dublin 2 D02PN40 Ireland Pusan National University Department of Information Convergence Engineering Busan46241 Korea Republic of Hanoi University of Science and Technology School of Electrical and Electronic Engineering Hanoi100000 Viet Nam University of Warwick School of Computer Science CoventryCV4 7AL United Kingdom The University of Sydney School of Computer Science DarlingtonNSW2006 Australia Kyung Hee University Department of Computer Science and Engineering Yongin446-701 Korea Republic of

This article investigates large batch training techniques using layer-wise adaptive scaling ratio (LARS) across diverse settings. In particular, we first show that a state-of-the-art technique, called LARS with the warm-up, tends to be trapped in sharp minimizers early on due to redundant ratio scaling. Additionally, a fixed steep decline in the latter phase restricts deep neural networks from effectively navigating early-phase sharp minimizers. To address these issues, we propose time varying LARS (TVLARS), a novel algorithm that replaces warm-up with a configurable sigmoid-like function for robust training in the initial phase. TVLARS promotes gradient exploration early on, surpassing sharp optimizers and gradually transitioning to LARS for robustness in later stages. Extensive experiments demonstrate that TVLARS consistently outperforms LARS and LAMB in most cases, with up to 2% improvement in classification scenarios. In all self-supervised learning cases, TVLARS achieves up to 10% performance improvement. © 2020 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Multi-Graph Spatio-Temporal Graph Traffic Flow Prediction in Bangkok:An Application of a Continuous Convolutional Neural Network

引用

computer Modeling in Engineering & sciences 2025年第1期142卷 579-607页

作者： Pongsakon Promsawat Weerapan Sae-dan Marisa Kaewsuwan Weerawat Sudsutad Aphirak Aphithana Department of Civil Engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand Department of Computer Engineering Faculty of EngineeringRamkhamkaeng UniversityBangkok10240Thailand Department of Statistics Faculty of ScienceRamkhamkaeng UniversityBangkok10240Thailand

The ability to accurately predict urban traffic flows is crucial for optimising city ***,various methods for forecasting urban traffic have been developed,focusing on analysing historical data to understand complex mobility *** learning techniques,such as graph neural networks(GNNs),are popular for their ability to capture spatio-temporal ***,these models often become overly complex due to the large number of hyper-parameters *** this study,we introduce Dynamic Multi-Graph Spatial-Temporal Graph Neural Ordinary Differential Equation Networks(DMST-GNODE),a framework based on ordinary differential equations(ODEs)that autonomously discovers effective spatial-temporal graph neural network(STGNN)architectures for traffic prediction *** comparative analysis of DMST-GNODE and baseline models indicates that DMST-GNODE model demonstrates superior performance across multiple datasets,consistently achieving the lowest Root Mean Square Error(RMSE)and Mean Absolute Error(MAE)values,alongside the highest *** the BKK(Bangkok)dataset,it outperformed other models with an RMSE of 3.3165 and an accuracy of 0.9367 for a 20-min interval,maintaining this trend across 40 and 60 ***,on the PeMS08 dataset,DMST-GNODE achieved the best performance with an RMSE of 19.4863 and an accuracy of 0.9377 at 20 min,demonstrating its effectiveness over longer *** Los_Loop dataset results further emphasise this model’s advantage,with an RMSE of 3.3422 and an accuracy of 0.7643 at 20 min,consistently maintaining superiority across all time *** numerical highlights indicate that DMST-GNODE not only outperforms baseline models but also achieves higher accuracy and lower errors across different time intervals and datasets.

关键词： Graph neural networks convolutional neural network deep learning dynamic multi-graph spatio-temporal

来源：评论

学校读者我要写书评

暂无评论

Improved Sparse Coded Features for Automatic Identification and Discrimination of Exudates and Drusen in Retinal Fundus Images

引用

SN computer science 2025年第1期6卷 1-12页

作者： Kumar, Mukesh Rani, Kumi Department of Mathematics and Statistics University of Houston-Downtown Houston 77002 TX United States Department of Computer Science and Engineering SRM Institute of Science and Technology Delhi-NCR Campus Ghaziabad India

Diabetic Retinopathy is a medical condition in people having diabetes in which damage occurs to the retina and can cause partial or complete vision loss. It is the most common reason for vision loss in the world. Diabetic Retinopathy is characterized by the appearance of retinal lesions such as microaneurysms, exudates, cotton wool spots, and haemorrhages. Age-Related Macular Degeneration (ARMD) is another eye disease which causes gradual loss of vision with age and is characterized by the appearance of drusen. Exudates and Drusen are known as bright lesions as they appear as yellow deposits in the retina. In this paper, we propose an automated method for the classification of bright lesions in retinal fundus images based on improved sparse coded features and Support Vector Machine (SVM). We employ Scale-Invariant Feature Transform (SIFT) to extract interesting regions in the image in the form of key points and extract local low-level features in the neighbourhoods of key-points. After that, we use the sparse coding technique to get high-level sparse coded features that are used for classification using SVM. Experimental results reveal that the proposed approach gives an accuracy, sensitivity, a specificity of 92.90%, 89.60%, 95.40% for exudate classification and 93.80%, 89.60%, 95.80% for drusen classification, with a dictionary of 300 atoms on a dataset of 1158 images. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Diabetic retinopathy Drusen Exudates Region of interest Retinal fundus images Sparse coding

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：