检索结果-内蒙古大学图书馆

8th World Conference on Smart Trends in Systems Security and Sustainability, WorldS4 2024

作者： Olaifa, Moses Malele, Vusumuzi Department of Computer Systems Engineering Faculty of ICT Tshwane University of Technology Pretoria South Africa Unit of Data Science and Computing Vaal Campus North-West University Vanderbijlpark South Africa

ISBN: (纸本)9789819786947

Over the past few decades, mortality rates associated with air quality pollution have risen in numerous countries around the globe. This pollution stems from different factors such as meteorological conditions, human activities from urban industrialization, vehicular emission, and so on. Air pollution constituents such as NO2, CO, SO, and coarse and fine particulate matter for different locations have been analyzed to learn both correlation and inter-dependency for long and short terms. However, many of these studies overlook datasets collected using low-cost tools and equipment. Most of the time, datasets of this nature are marred with inconsistencies and gaps at irregular intervals. This may render the air pollutant data unsuitable. In order to test the suitability of machine learning algorithms on such dataset, this study conducts a time-series forecast analysis using the prophet algorithm. Two additional models including linear regressor and random forest regressor are trained and tested on the same dataset and a comparative analysis of the three models is performed. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

M3-Net: A Multi-Scale Nuclei Segmentation Model for Breast Cancer Histopathology Using Contextual Patches and Attention Mechanism

M3-Net: A Multi-Scale Nuclei Segmentation Model for Breast C...

引用

IEEE International Symposium on Biomedical Imaging

作者： Arbab Sufyan Mohammad Faizal Ahmad Fauzi Wong Lai Kuan Faculty of Engineering Multimedia University Cyberjaya Malaysia Faculty of Computing & Informatics Multimedia University Cyberjaya Malaysia

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Histopathological analysis, particularly of nuclear morphology, is critical for identifying malignancies. Accurate nuclei segmentation plays a pivotal role in this process, as it enables detailed assessment of nuclear size, shape, and distribution patterns. Traditional segmentation methods, however, often fail to capture fine details, lack broader context, and struggle with overlapping nuclei of varying sizes and shapes, especially when relying on single-scale approaches. To address these challenges, we propose a multi-scale context-based encoder-decoder model named M3-Net (Multi-Scale, Multi-Level, Multi-Stream Network) that integrates both global and local tissue features. Evaluations demonstrate that M3-Net effectively segments overlapping nuclei and diverse structures, providing a robust solution for automated nuclei segmentation in breast cancer pathology.

关键词： Image segmentation Accuracy Image analysis Histopathology Shape Image color analysis Morphology Breast cancer Context modeling Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Quantum-Secured E-Commerce with Blockchain, BB84 and BLAKE3 Encryption Using GNN

Quantum-Secured E-Commerce with Blockchain, BB84 and BLAKE3 ...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Harikrishnan S Gopikrishnan R M. L. Sworna Kokila V. Bibin Christopher Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

The rapid advancements in quantum computing present significant challenges to traditional cryptographic techniques, posing risks to the security of e-commerce transactions. Existing systems are vulnerable to quantumenabled cyberattacks, especially as classical encryption methods, such as RSA and ECC, become obsolete in the face of quantum algorithms. In response, the research proposes an innovative quantum-secure e-commerce fraud detection framework that integrates Graph Neural Networks (GNNs) with Quantum Key Distribution (BB84 QKD), Quantum-Proof-of-Work (QPoW), blockchain technology, and post-quantum cryptographic techniques, including BLAKE3 encryption. The key challenge addressed in the work is ensuring transaction security and fraud detection in a quantum-enabled environment, where classical cryptographic systems are no longer sufficient. Traditional fraud detection mechanisms also struggle to detect subtle anomalies in complex, quantumsecured transaction networks. This approach overcomes these issues by leveraging deep learning-based anomaly detection through GNNs, which model blockchain transactions as graphs to capture intricate relationships between entities. The combination of BB84 QKD ensures secure key distribution, while QPoW offers a resilient consensus mechanism, and BLAKE3 encryption provides fast and secure hashing. The framework aims to offer a robust, scalable solution for ecommerce platforms, financial institutions, and digital identity systems by combining quantum-secure encryption with advanced machine learning for fraud detection. By addressing the growing threat of quantum computing, the methodology provides enhanced security for sensitive transactions, ensuring long-term protection against future quantum-enabled attacks.

关键词： Quantum computing Scalability Graph neural networks Fraud Encryption Consensus protocol Security Electronic commerce Computer crime Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Lightweight Transfer Learning-Based Pipeline for the Detection and Prediction of Citrus Plant Diseases

SSRN

引用

SSRN 2025年

作者： Aswini, E. Vijayakumaran, C. Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Tamilnadu Kattankulathur India

One of the essential nutrients Vitamin C is abundantly found among citrus fruits and holds a lot of significance in supporting public health and economic benefit to the country and the stakeholders in the Citrus industry. Citrus fruit production is greatly affected as they are susceptible to various range of diseases. Thus, protecting them from diseases has a direct impact on the growth and yield of Citrus production. Thus, providing support in the form of early disease detection and prediction can enhance productivity to a greater extent. This frames the motivation behind this work and a deep learning-based classifier is suggested to enhance the accuracy of the Citrus plant disease prediction. Though numerous deep learning-based classifier exists in literature, their significant limitation is the need for high computational resources. This makes them unsuitable to deploy on low-end devices. To address this issue, a pipeline that possesses the key processes like classification, augmentation, transfer learning, and image enhancement as a comprehensive methodology to improve the predictive performance and easy deployment features. The approach mainly focuses on solving the data imbalance issues that have detrimental effects on classifier training. To solve this, we used SCLAHE (Spatially Adaptive Histogram Equalization) for image enhancement, which improves the visibility of critical features in citrus leaf images. Additionally, we incorporate RL-GAN (Reinforcement Learning Generative Adversarial Network) for real-time data augmentation, generating synthetic images that enhance the training dataset and help to address the imbalance. The effectiveness of our method has been validated through extensive evaluation using two prominent datasets: Citrus Leaves and CCL-20. The results reveal an impressive accuracy rate of 99.42%, along with six parameter counts and ten FLOP (floating-point operations) counts. This high level of accuracy demonstrates the potential of our deep

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Drone-Based Public Surveillance Using 3D Point Clouds and Neuro-Fuzzy Classifier

引用

Computers, Materials & Continua 2025年第3期82卷 4759-4776页

作者： Yawar Abbas Aisha Ahmed Alarfaj Ebtisam Abdullah Alabdulqader Asaad Algarni Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh12372Saudi Arabia Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Saudi Arabia Department of Computer Science and Engineering College of InformaticsKorea UniversitySeoul02841Republic of Korea Cognitive Systems Lab University of BremenBremen28359Germany

Human Activity Recognition(HAR)in drone-captured videos has become popular because of the interest in various fields such as video surveillance,sports analysis,and human-robot ***,recognizing actions from such videos poses the following challenges:variations of human motion,the complexity of backdrops,motion blurs,occlusions,and restricted camera *** research presents a human activity recognition system to address these challenges by working with drones’red-green-blue(RGB)*** first step in the proposed system involves partitioning videos into frames and then using bilateral filtering to improve the quality of object foregrounds while reducing background interference before converting from RGB to grayscale *** YOLO(You Only Look Once)algorithm detects and extracts humans from each frame,obtaining their skeletons for further *** joint angles,displacement and velocity,histogram of oriented gradients(HOG),3D points,and geodesic Distance are *** features are optimized using Quadratic Discriminant Analysis(QDA)and utilized in a Neuro-Fuzzy Classifier(NFC)for activity ***-world evaluations on the Drone-Action,Unmanned Aerial Vehicle(UAV)-Gesture,and Okutama-Action datasets substantiate the proposed system’s superiority in accuracy rates over existing *** particular,the system obtains recognition rates of 93%for drone action,97%for UAV gestures,and 81%for Okutama-action,demonstrating the system’s reliability and ability to learn human activity from drone videos.

关键词： Activity recognition geodesic distance pattern recognition neuro fuzzy classifier

来源：评论

学校读者我要写书评

暂无评论

Selfish-Free Influential Nodes Detection in Mobile Social Networks 2

Selfish-Free Influential Nodes Detection in Mobile Social Ne...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Abdelmohsen, Doaa Abdelkader, Tamer Hamdy, Mohamed Elbahnasy, Khaled Ain Shams University Faculty of Computer and Information Sciences Cairo Egypt Galala Unversity Faculty of Computer Science and Engineering Suez Egypt King Abdul Aziz University Faculty of Computing and Information Technology Saudi Arabia Jeddah International College Saudi Arabia

ISBN: (纸本)9798331506995

Mobile networks where users group in communities based on their interests, and disseminate data mainly to their community using their mobile devices, are called Mobile Social Networks (MSN). However, the efficiency of data dissemination becomes a challenging problem in these networks. Using influential users can improve the efficiency of data dissemination. An influential user should have an effective activity on the network and influence other users. The participation behavior of nodes in the network dramatically affects the detection process of influential nodes. Self-sufficient nodes who selectively participate in the dissemination of data in the network may reduce the influence of the other nodes. This paper proposes detecting influential nodes that consider the negative effects of selfish behavior. The performance analysis of the proposed selfish-free influential node detection protocol is presented by comparing it to another one that does not consider the selfishness problem. This comparison shows that the proposed protocol achieves efficiency up to 30% in a environment of selfish behavior. © 2025 IEEE.

关键词： Publishing

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey on Intelligent Reflecting Surfaces and Unmanned Aerial Vehicles Integration for Enhanced Communication in Massive Networks 11

A Comprehensive Survey on Intelligent Reflecting Surfaces an...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Attar, Hani Ababneh, Jafar Hafez, Mohamed Rachini, Ali Solyman, Ahmed Bahy, Ramy M. Zarqa University Faculty of Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah21448 Saudi Arabia Zarqa University Faculty of Information Technology Cyber Security Department Zarqa Jordan INTI-IU-University Nilai Faculty of Engineering Feqs Malaysia Department of Computer Science and Information Technology Jounieh Lebanon School of Computing Engineering and Built Environment Glasgow Caledonian University Glasgow United Kingdom Technical Research Center Cairo Egypt

ISBN: (纸本)9798331509293

Intelligent Reflecting Surfaces (IRSs) offer a revolutionary approach to wireless communication by dynamically controlling the properties of electromagnetic waves. By manipulating wavefronts without requiring radio frequency links, IRSs can enhance spectrum and energy efficiency, reduce costs, and improve overall system performance. Unmanned Aerial Vehicles (UAVs) have garnered significant attention due to their mobility and adaptability. However, real-time data transmission between UAVs can be hindered by obstacles and security risks. By combining IRSs and UAVs, we can create unparalleled opportunities in demanding environments. Through coordinated movements and intelligent wave reflection, both systems can optimize wireless signal propagation. This paper provides a comprehensive review of IRS-assisted UAV communications. We explore existing research, introduce novel technologies and applications, and highlight potential research directions for developing low-cost and energy-efficient wireless systems. Additionally, we address current challenges and outline promising areas for future study. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Driven Smart Cities: Review of Key Applications and Emerging Trends

Blockchain-Driven Smart Cities: Review of Key Applications a...

引用

2nd International Conference on Advanced Innovations in Smart Cities, ICAISC 2025

作者： Wimal, Kesara Cullen, Gary Donovan, John Atlantic Technological University Letterkenny Co. Department of Computing Donegal Ireland Atlantic Technological University Sligo Co. Faculty of Engineering and Design Sligo Ireland

ISBN: (纸本)9798331506995

The future of blockchain technology holds significant promise across various sectors, driven by its inherent decentralisation, transparency, and security capabilities. As industries increasingly recognise the potential benefits, the global blockchain market is projected to grow substantially. Concurrently, the smart city concept has gained significant traction worldwide, as governments and corporations aspire to create urban environments that leverage technology to enhance efficiency and quality of life. In this regard, blockchain technology has emerged as a promising solution, offering decentralised, secure, and transparent data management which is critical for the sustainable development of smart cities. This review paper explores the integration of blockchain technology in smart city frameworks which is considered timely. It further synthesises findings from recent literature in blockchain applications across six key components of smart cities: digital infrastructure, urban mobility, public safety, public health, environmental resource management, and governance. As cities evolve to meet the demands of rapid urbanisation, the decentralised and immutable nature of blockchain offers unique advantages for building transparent, secure, and efficient urban ecosystems. This paper also examines possible future trends that point towards a future where blockchain serves as a foundational layer in smart city infrastructure. By summarising current applications and identifying future research directions, this review paper provides a comprehensive resource for future researchers and policymakers who are aiming to leverage blockchain in the development of resilient and citizen-focused urban environments. © 2025 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Machine Learning to Enhance the V2V Communication-based IoD Using Companding Dataset

Machine Learning to Enhance the V2V Communication-based IoD ...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： O. Daoud Q. Hamarsheh A. Damati S. Al Jaafrah O. Qasem M. Al-Khawaldah Electrical and Computing Engineering School of Engineering and Computing American International University Al-Jahra Kuwait Electrical Engineering Department Faculty of Engineering and Technology Philadelphia University Amman Jordan Researcher

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

This paper investigates the improvement of Vehicle-to-Vehicle (V2V) communications in the Internet of Drones (IoD) scenario for the reduction of the Peak-to-Average Power Ratio (PAPR) problem in Orthogonal Frequency Division Multiplexing (OFDM) systems. Motivated by the recent research on machine learning and deep neural network, this study will attempt to optimize Quality of Service (QoS) by means of a multiprocessing approach based on Daubechies wavelets. The proposed scheme integrates high-performance PAPR reduction schemes, such as µ-law companding, hybrid precoding-companding, and neural network-based adaptive algorithms. Deep reinforcement learning-driven approach in clipping and filtering is further proposed, which can offer real-time adaptation for the high-demanding communications. Results show a considerable gain in PAPR, over 60% PAPR reduction under high SNR conditions. These findings show that IoD can sustain stable V2V connections in urban use cases, thereby providing a scalable solution for 5G and beyond networks.

关键词： 5G mobile communication Vehicular ad hoc networks Peak to average power ratio Machine learning Quality of service Real-time systems Internet Reliability Drones Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Introduction to Special Issue on IEEE MetroSea 2023

引用

IEEE Journal of Oceanic engineering 2025年第2期50卷 507-508页

作者： Potter, John Robert Ferreira, Fausto Daponte, Pasquale Migliaccio, Maurizio Department of Electronic Systems Norway Faculty of Electrical Engineering and Computing University of Zagreb Zagreb10000 Croatia Università degli Studi del Sannio Dipartimento di Ingegneria Benevento Italy Dipartimento di Ingegneria Università degli Studi di Napoli Parthenope Napoli Italy

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：