检索结果-内蒙古大学图书馆

DeepEarthMY: A Remote Sensing Dataset for Tropical Land-Cover Segmentation

IEEE Access 2025年 13卷 69103-69115页

作者： Mohammed Najib, Shaaban Pee, Chih-Yang Ting, Choo-Yee Wong, Lai-Kuan Multimedia University Faculty of Computing and Informatics Selangor Cyberjaya63100 Malaysia

Land-cover mapping is essential for applications such as urban planning, natural resource management, and environmental monitoring. However, tropical equatorial regions pose unique challenges to land-cover classification due to dense vegetation, persistent cloud cover, and spectral similarity across land-cover types. Moreover, existing land-cover classification models often perform poorly in these regions as they are primarily trained on datasets from non-equatorial climates. To address this gap, we introduce DeepEarthMY, a high-resolution land-cover mapping dataset specifically designed for equatorial regions. The dataset contains 4,007 meticulously annotated images from 52 diverse regions across Malaysia, representing key land-cover types such as forests, buildings, roads, water bodies, agricultural lands, and barren land. We evaluated the dataset by performing land-cover segmentation on selected state-of-the-art semantic segmentation models, including DC-Swin, HRNet, and UNetFormer. The experimental results reveal that the DC-Swin model achieves the best performance, with a mIoU score of 80.23%. To further evaluate the significance of region-specific datasets for land-cover classification, we performed cross-dataset testing on two datasets: DeepEarthMY from the equatorial region and LoveDA from the temperate climate, using five-fold cross-validation. HRNet models trained on DeepEarthMY achieved a mIoU of 77.2% on DeepEarthMY but only 33.2% on the LoveDA test set. Conversely, models trained on LoveDA achieved 51.4% and 43% on the LoveDA and DeepEarthMY test sets, respectively. This significant performance gap highlights the need for region-specific datasets to advance land-cover research, particularly in equatorial climates where land-cover datasets are scarce. In conclusion, the DeepEarthMY dataset can be an invaluable resource for remote sensing in the equatorial region. The dataset is available at https://***/records/14242124. © 2013 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Cybersecurity Risk with a Phishing Simulation Website 24

Analyzing Cybersecurity Risk with a Phishing Simulation Webs...

引用

9th International Conference on Cloud computing and Internet of Things, CCIOT 2024

作者： Ali, Alya Nasuha Binti Mohamed Rahman, Siti Husna Abdul Faculty of Computing & Informatics Multimedia University Selangor Malaysia

ISBN: (纸本)9798400717161

Phishing is a cyberattack that exploits human psychology and technical vulnerabilities. Previous research has revealed inconsistency of relation between age and phishing susceptibility. Hence, this project aims to identify which age group is more susceptible to phishing. Therefore, to achieve these objectives, this project developed and deployed a phishing simulation website to analyse which age group is more vulnerable. Respondents are considered successfully phished if they submitted information to the phishing website. The project adopted previous researcher's phishing process with addition of two phases as a guideline. The phases were Planning, Preparation, Attack, Valuable Acquisition, Knowledge Transfer and Result Analysis. A blog was developed to redirect phishing victims to an e-Learning page to raise their cybersecurity awareness. Persuasion techniques used in this simulation were Reward and Urgency. The phishing website gained 146 clicks and 89 form submissions. Adults aged 18 to 59 years old (group A) has a higher phishing success rate of compared to adults aged 60 years and above (group B). These findings suggest younger adults are more susceptible to phishing. Future research should involve larger sample size and seek broader input from participants. Copyright © 2024 held by the owner/author(s). Publication rights licensed to ACM.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

An Integrated Web-Based Approach for Email Analysis Investigation Tool 24

An Integrated Web-Based Approach for Email Analysis Investig...

引用

9th International Conference on Cloud computing and Internet of Things, CCIOT 2024

作者： Bari, Fawzul Rahman, Siti Husna Abdul Faculty of Computing & Informatics Multimedia University Selangor Malaysia

ISBN: (纸本)9798400717161

Phishing websites have often been used for online and email fraud, spreading unwanted content. It has been important to find them before any user data was entered. In recent years, numerous attempts have been made to identify these phishing websites. To identify phishing web pages, most current methods trained classification models using manually constructed lexical and statistical features from the textual content of websites. The time-consuming method of extracting hand-crafted features, which required specialized domain knowledge to determine which features were useful for a given platform, was one of the limitations of these phishing detection approaches. To address these issues, this project aimed to develop a website which is an Integrated Web-based Approach for Email Analysis Investigation Tool (IWAEAIT) that used an external API like Virus total to analyses phishing websites and ip-api to get the location of the email. The project's goal was to ensure that anyone could use this website to identify if an email was phishing or not, even if they had no prior IT experience. This project also included features like file attachment analysis and a feature that let users take a screenshot of the website without really visiting it to stop users from visiting phishing websites, URL scan analysis and email artefacts extractor to get the location of the email. Copyright © 2024 held by the owner/author(s).

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

A Robust Resource-Aware Framework for YOLO-Based Object Detection in Dynamic and Multi-Platform Resource-Constrained Environments

引用

IEEE Access 2025年 13卷 79977-79995页

作者： Shiddiqi, Ary Mazharuddin Navastara, Dini Adni Studiawan, Hudan Romadhona, Yasinta Azhar, Muhammad Fath Mushaffa Rahma, Fayruz Bramantoro, Arif Alzahrani, Ahmad A. Institut Teknologi Sepuluh Nopember Faculty of Intelligent Electrical and Informatics Technology Department of Informatics Surabaya60111 Indonesia Telkom University Informatics Study Program Surabaya Campus Surabaya60231 Indonesia Universitas Islam Indonesia Department of Informatics Yogyakarta55584 Indonesia Universiti Teknologi Brunei School of Computing and Informatics Bandar Seri BegawanBE1410 Brunei King Abdulaziz University Faculty of Computing and Information Technology 21589 Saudi Arabia

Efficient management of resources such as CPU, RAM, and disk storage is a critical challenge for object detection systems that rely on multi-camera video streaming, especially for resource-constrained devices. These constraints frequently result in the risk of overheating and potential system failure during high workloads. This paper presents a novel Resource-Aware Framework (RA-Framework), designed to optimize resource allocation using dynamic adaptation mechanisms. The RA-Framework dynamically manages CPU, RAM, and disk storage resources for YOLO-based object detection, supporting multiple camera streams and scheduling mechanisms. The framework was implemented in resource-constrained environments using various YOLO models with single and dual-camera setups. Experimental results showed that the RA-Framework successfully reduced average CPU usage by up to 68.62%, decreased RAM consumption by approximately 13.47%, and extended the time for disk usage to increase by 1% by more than 500% in specific scenarios. In contrast, systems without the RA-Framework experienced higher resource utilization and greater susceptibility to resource scarcity or even overheating. © 2013 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Modified Metaheuristic Optimization Algorithm for Hyperparameter Tuning in Mental Health Applications 6

Modified Metaheuristic Optimization Algorithm for Hyperparam...

引用

6th International Conference on Mobile computing and Sustainable informatics, ICMCSI 2025

作者： Kozakijevic, Stanislava Jovanovic, Luka Tedic, Smiljana Jankovic, Ninoslava Zivkovic, Miodrag Bacanin, Nebojsa Faculty of Media and Communication Singidunum University Belgrade Serbia Faculty of Informatics and Computing Singidunum University Belgrade Serbia

ISBN: (纸本)9798331522667

The World health organization considers a mentally healthy person to be able to manage life’s stresses, work productively, and contribute to their communities. However, mental disorders, affecting 970 million people in 2019, often reduce quality of life, necessitating accurate diagnosis and therapy. Affective disorders, encompassing depressive and manic episodes, vary in severity and pattern, with conditions like bipolar disorder and recurrent mood disorders identified through ICD-10 classifications. Diagnosis, typically made by expert teams, remains challenging due to the complex and variable nature of mental disorders, leading to frequent misdiagnoses that hinder treatment progress and erode patient trust. Artificial intelligence (AI) holds promise in supporting mental health diagnosis by identifying subtle patterns in symptoms and validating expert conclusions. While AI’s specialized nature poses limitations, integrating it into clinical practice can improve diagnostic accuracy and reduce errors. High quality models can assist doctors by ruling out less likely conditions and confirming diagnoses. Optimizing AI models, however, requires effective hyperparameter selection, a complex task classified as NP-hard. Metaheuristic algorithms offer a solution, enabling efficient parameter tuning and improving AI model performance. Given the critical implications of accurate mental health diagnoses, leveraging AI and optimization techniques is essential to enhance outcomes and improve lives. This work proposed a modified metahetusirc aimed at optimizing classification accuracy. When evaluated on a genuine dataset the best performing models attain an accuracy of 0.972222 suggesting feasibility in real world situations. © 2025 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

Optimizing Machine Learning for Malicious Blockchain Node Detection Using Modified Metaheuristic 1

Optimizing Machine Learning for Malicious Blockchain Node De...

引用

1st International Conference on AIML-Applications for Engineering and Technology, ICAET 2025

作者： Bacanin, Nebojsa Vicentijevic, Marko Jovanovic, Luka Njegus, Angelina Radomirovic, Branislav Zivkovic, Miodrag Singidunum University Faculty of Informatics and Computing Belgrade Serbia Singidunum University Faculty of Technical Sciences Belgrade Serbia

ISBN: (纸本)9798350355611

The decentralized architecture of blockchain tech-nology introduces various challenges, particularly in Proof of Stake (PoS) networks, where malicious nodes can undermine the consensus process and threaten the integrity of the network. Nodes with significant stakes may disproportionately influence validation, weakening the network's decentralization. Despite ongoing advancements in blockchain security, there remains a notable gap in research on the integration of artificial intelli-gence (AI) and optimization techniques for enhancing blockchain security. This paper proposes an approach, utilizing a CatBoost classifier optimized with a modified Particle Swarm Optimization (PSO) algorithm, designed specifically for this study. A compar-ative analysis, performed on a real-world dataset, demonstrates the effectiveness of the proposed method, with the most accurate models achieving an accuracy of 87.13%. The findings highlight the potential of AI -driven optimization in improving blockchain security. Future research will focus on the application of AI and optimization techniques to further refine blockchain protocols, enhance detection and prevention of security threats, and improve overall network performance. © 2025 IEEE.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Addressing Imbalance in Health Datasets: A New Method NR-Clustering SMOTE and Distance Metric Modification

引用

Computers, Materials & Continua 2025年第2期82卷 2931-2949页

作者： Hairani Hairani Triyanna Widiyaningtyas Didik Dwi Prasetya Afrig Aminuddin Department of Electrical Engineering and Informatics Faculty of EngineeringUniversitas Negeri MalangMalang65145Indonesia Department of Computer Science Universitas BumigoraMataram83127Indonesia Department of Computer Graphic and Multimedia Faculty of ComputingCollege of Computing and Applied SciencesUniversiti Malaysia Pahang Al-Sultan AbdullahPekan26600Malaysia

An imbalanced dataset often challenges machine learning, particularly classification methods. Underrepresented minority classes can result in biased and inaccurate models. The Synthetic Minority Over-Sampling Technique (SMOTE) was developed to address the problem of imbalanced data. Over time, several weaknesses of the SMOTE method have been identified in generating synthetic minority class data, such as overlapping, noise, and small disjuncts. However, these studies generally focus on only one of SMOTE’s weaknesses: noise or overlapping. Therefore, this study addresses both issues simultaneously by tackling noise and overlapping in SMOTE-generated data. This study proposes a combined approach of filtering, clustering, and distance modification to reduce noise and overlapping produced by SMOTE. Filtering removes minority class data (noise) located in majority class regions, with the k-nn method applied for filtering. The use of Noise Reduction (NR), which removes data that is considered noise before applying SMOTE, has a positive impact in overcoming data imbalance. Clustering establishes decision boundaries by partitioning data into clusters, allowing SMOTE with modified distance metrics to generate minority class data within each cluster. This SMOTE clustering and distance modification approach aims to minimize overlap in synthetic minority data that could introduce noise. The proposed method is called “NR-Clustering SMOTE,” which has several stages in balancing data: (1) filtering by removing minority classes close to majority classes (data noise) using the k-nn method;(2) clustering data using K-means aims to establish decision boundaries by partitioning data into several clusters;(3) applying SMOTE oversampling with Manhattan distance within each cluster. Test results indicate that the proposed NR-Clustering SMOTE method achieves the best performance across all evaluation metrics for classification methods such as Random Forest, SVM, and Naїve Bayes, compared t

关键词： SMOTE modification Clustering-SMOTE manhattan distance

来源：评论

学校读者我要写书评

暂无评论

End-to-end optimized ensemble model for Alzheimer’s disease detection 19

End-to-end optimized ensemble model for Alzheimer’s disease...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Hassan, Abdelrahman Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Alzheimer's disease (AD) is a progressive neurodegenerative disorder with an increasing prevalence among the elderly, making early and accurate diagnosis critical for effective intervention and management. This paper introduces an end-to-end machine learning pipeline optimized for detecting AD using multimodal data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). The study proposes an ensemble model that integrates key modalities—demographics, cognitive scores, neuropsychological assessments, and MRI data—via early fusion to enhance AD detection. Various machine learning models, including Logistic Regression, Gradient Boosting, AdaBoost, XGBoost, Support Vector Machine, and Neural Networks, are compared, and feature selection is optimized through Recursive Feature Elimination, ANOVA F-value, and mutual information methods, with mutual information showing the most efficacy. With further hyperparameter tuning, the highest accuracy is achieved at 95.85%, with Gradient Boosting as the top-performing model. Additional experiments assess and evaluate individual modality contributions, underscoring the predictive value of cognitive scores and neuropsychological features. To enhance clinical interpretability, we incorporate model explainability using LIME and SHAP, which identify key features influencing model predictions across different AD stages. Explainable AI (XAI) is essential in healthcare for providing transparency and supporting clinician confidence by highlighting which biomarkers, such as MMSE, CDRSB, and PTAU, contribute most to diagnostic outcomes. This study demonstrates classical machine learning's potential in AD diagnostics, offering a pathway to cost-effective and clinically viable models for neurodegenerative disease management. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Large Language Models for Smart Pharmacy Systems: Enhancing Drug Safety and Operational Efficiency 19

Leveraging Large Language Models for Smart Pharmacy Systems:...

引用

19th International Conference on Ubiquitous Information Management and Communication, IMCOM 2025

作者： Osheba, Abdelrahman Abou-El-Ela, Ahmed Adel, Osama Maaod, Youssef Abuhmed, Tamer El-Sappagh, Shaker Faculty of Computer Science and Engineering Galala University Egypt College of Computing and Informatics Sungkyunkwan University Korea Republic of

ISBN: (纸本)9798331507817

Adverse drug reactions (ADRs) remain a crucial challenge in healthcare systems, highly contributing to patient mortality. We present an innovative smart pharmacy system that utilizes advanced large language models (LLMs) to enhance drug safety and pharmacy operational efficiency. Our system integrates real-time data from patient's prescriptions, medication databases, and electronic health records (EHR) to automate the detection of potential drug interactions, optimizing clinical decision-making and reducing ADR-related risks. The system's architecture is designed to easily manage prescription processing for patients, inventory management and control, and Pharmacist consultations through an intelligent chatbot interface. Key features include real-time tracking of medication expiration and inventory levels, an interaction checker API for identifying and mitigating risky drug combinations, and an LLM-powered chatbot for accurate data analysis and visualization. By combining advanced computational techniques with AI-driven insights, our smart pharmacy system not only improves medication safety but also eases pharmacy operations. This transformative approach holds the potential to significantly reduce ADR-related hospital admissions and enhance overall healthcare delivery. Our research underscores the vital role of AI and LLMs in modern pharmacy practice, offering an inclusive solution that integrates easily into existing healthcare infrastructures. The proposed smart pharmacy system can be plugged into hospital EHR systems to automatically track patient medications. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Intelligent and Secure Evolved Framework for Vaccine Supply Chain Management Using Machine Learning and Blockchain

引用

SN Computer Science 2025年第2期6卷 1-28页

作者： Abdel-salam, Mahmoud Elhoseny, Mohamed El-hasnony, Ibrahim M. Faculty of Computers and Information Science Mansoura University Mansoura Egypt College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates

Supply chain management (SCM) ensures that fragile goods are delivered from their origin to their destination without suffering any damage. The COVID-19 pandemic’s widespread has exposed systemic weaknesses in SCM across a variety of sectors, particularly healthcare. This paper aims to tackle issues related to vaccine expiration and fraudulent vaccine records by facilitating vaccine traceability and innovative contract features. The proposed model suggests utilizing an intelligent and secure framework that merges machine learning intelligent techniques with blockchain technology. The proposed model utilizes the Ethereum blockchain’s characteristics to establish novel smart contracts between diverse participants in the supply chain. In addition, the proposed model presents two modules to assist in predicting the demand for vaccines and analyzing the sentiment of vaccine reviews to improve the quality of vaccines. Therefore, an Improved Honey Badger Algorithm (IHBA) is presented to enhance the performance of the Long Short-Term Memory (LSTM) algorithm in predicting vaccine demand besides the credibility evaluation of reviews. For the vaccine demand prediction module, a real dataset obtained from the centers for Disease Control and Prevention (CDC) is collected and the proposed model is applied obtaining the minimum RMSE of 1.3828 for the prediction results compared with other approaches. For the review analysis module, a publicly available dataset from the University of California, Irvine (UCI) is used, and the proposed model achieved a high accuracy of user reviews of 90.6% compared with other related approaches. The proposed model is compared with other related metaheuristic algorithms and the standard deep learning optimizers. The proposed new algorithm outperforms other competitors for tuning the hyperparameters of deep learning models. Finally, the proposed system presents implications for sustainable supply chain management, enterprise operations, and public pol

关键词： Blockchain HBA Intelligent LSTM Intelligent machine learning Intelligent model Machine learning Supply chain management Sustainability Traceability

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：