检索结果-内蒙古大学图书馆

On the performance of hybrid TDMA–NOMA-RIS empowered indoor flying networks under dynamic blockages and imperfect SIC

引用

Physical Communication 2025年 71卷

作者： Singh, Gurinder Salameh, Haythem Bany Ayyash, Moussa al-Obiedollah, Haitham Elgala, Hany Department of Electronics and Communication The LNM Institute of Information Technology Jaipur India College of Engineering Al Ain University Al Ain United Arab Emirates Department of Computing Information Mathematical Sciences and Technology Chicago State University United States Department of Electrical Engineering Faculty of Engineering The Hashemite University Zarqa13133 Jordan Department of Electrical and Computer Engineering at the University at Albany State University of New York United States

This article investigates the outage performance of reconfigurable intelligent surfaces (RIS)-assisted hybrid time division multiple access (TDMA) and non-orthogonal multiple access (NOMA)-based indoor flying networks (IFNs), taking into account the influence of dynamic blockages and imperfect successive interference cancellation (SIC) conditions. We utilize a stochastic geometry framework to demonstrate that the RIS-assisted hybrid TDMA–NOMA-enabled IFN system improves outage performance over the traditional OMA scheme with RIS. The results reveal that achieving optimal performance with integration of hybrid TDMA–NOMA into IFNs requires precise adjustments to the range of unmanned aerial vehicle (UAV) deployment heights within a specific threshold. © 2025 Elsevier B.V.

关键词： Micro air vehicle (MAV)

来源：评论

学校读者我要写书评

暂无评论

Patch-Based and Non-Patch-Based inputs Comparison into Deep Neural Models: Application for the Segmentation of Retinal Diseases on Optical Coherence Tomography Volumes

arXiv

引用

arXiv 2025年

作者： al-Saih, Khaled al-Shargie, Fares al-Hiyali, Mohammed Isam alhejaili, Reham Laboratoire LIMOS CNRS UMR 6158 Université Clermont-Auvergne Aubiere63170 France The School of Health Professions Department of Rehabilitation and Movement Sciences Rutgers University NewarkNJ07102 United States Medical Instruments Technology Engineering Department AL Mansour University College Baghdad10068 Iraq Department of Computer Science and Artificial Intelligence College of Computer Science and Engineering University of Jeddah Jeddah23218 Saudi Arabia

Worldwide, sight loss is commonly occurred by retinal diseases, with age-related macular degeneration (AMD) being a notable facet that affects elderly patients. Approaching 170 million persons wide-ranging have been spotted with AMD, a figure anticipated to rise to 288 million by 2040. For visualizing retinal layers, optical coherence tomography (OCT) dispenses the most compelling non-invasive method. Frequent patient visits have increased the demand for automated analysis of retinal diseases, and deep learning networks have shown promising results in both image and pixel-level 2D scan classification. However, when relying solely on 2D data, accuracy may be impaired, especially when localizing fluid volume diseases. The goal of automatic techniques is to outperform humans in manually recognizing illnesses in medical data. In order to further understand the benefit of deep learning models, we studied the effects of the input size. The dice similarity coefficient (DSC) metric showed a human performance score of 0.71 for segmenting various retinal diseases. Yet, the deep models surpassed human performance to establish a new era of advancement of segmenting the diseases on medical images. However, to further improve the performance of the models, overlapping patches enhanced the performance of the deep models compared to feeding the full image. The highest score for a patch-based model in the DSC metric was 0.88 in comparison to the score of 0.71 for the same model in non-patch-based for SRF fluid segmentation. The objective of this article is to show a fair comparison between deep learning models in relation to the input (Patch-Based vs. NonPatch-Based). © 2025, CC BY-NC-ND.

关键词： Optical coherence tomography

来源：评论

学校读者我要写书评

暂无评论

IP SafeGuard - An AI-Driven Malicious IP Detection Framework

引用

IEEE Access 2025年 13卷 90249-90261页

作者： Siam, Abdullah al alazab, Moutaz Awajan, albara Hasan, Md Rakibul Obeidat, Areej Faruqui, Nuruzzaman Daffodil International University Daffodil Smart City Birulia Department of Software Engineering Dhaka 1216 Bangladesh Oryx Universal College with Liverpool John Moores University School of Computing and Data Sciences Cybersecurity Department Doha 34110 Qatar Al-Balqa Applied University Faculty of Artificial Intelligence Department of Intelligent Systems Al-Salt 19385 Jordan Bangladesh University of Professionals (BUP) Department of Computer Science and Engineering Dhaka Bangladesh Amman Jordan

The rising frequency and sophistication of cyberattacks have made real-time malicious IP detection a critical challenge for modern Security Operations Center (SOC). Traditional solutions, such as static blacklists and manual IP reputation checks, are no longer sufficient in today's dynamic threat scenario. To overcome these constraints, we present IP SafeGuard, an AI-driven platform that incorporates multi-source threat intelligence, sophisticated feature engineering, and machine learning (ML)for real-time IP categorization. The framework collects data from AbuseIPDB, VirusTotal, and other sources to compute a Dynamic Threat Score (DTS) for each IP address. It leverages an XGBoost-based classification model to achieve high accuracy and low false-positive rates, even in skewed datasets. Experimental findings indicate the improved performance of IP SafeGuard, with an accuracy of 98.2%, a precision of 97.8%, and a recall of 98.5%. The average detection duration of 45 milliseconds makes it appropriate for real-time SOC integration, enabling automated incident response through Security Information and Event Management (SIEM) alerting and firewall blocking. The framework's modular design assures scalability and adaptability, making it a vital tool for high-volume situations. By overcoming the limits of old approaches and using the power of ML, IP SafeGuard considerably boosts the efficiency and efficacy of current cybersecurity systems. Future work involves expanding the system to enable new threat intelligence sources and studying federated learning for secure and privacy-preserving threat information exchange. © 2013 IEEE.

关键词： Artificial Intelligence Cyber attack Cyber defense Cyber Security IP Address SOC Threat Intelligence

来源：评论

学校读者我要写书评

暂无评论

Integration of Consumer Electronics in Precision Agriculture Using Low-Carbon Wheat Lodging Drone Images

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Dasari, Rakeshnag alsaadi, Mahmood Nimma, Divya Ramesh, Janjhyam Venkata Naga Tiwari, Mohit Jangir, Pradeep Santhi, M.V.B.T. Turayevich, Jumaniyazov Inomjon Soni, Mukesh Department of Cse Acharya Nagarjuna university Nagarjuna Nagar Guntur522510 India University of Al Maarif College of Sciences Department of Computer Sciences Al Anbar31001 Iraq Data Analyst in Ummc University of southern Mississippi United States Graphic Era Hill University Department of Cse Dehradun248002 India Graphic Era Deemed To Be University Department of Cse Uttarakhand Dehradun248002 India Bharati Vidyapeeth's College of Engineering Department of Computer Science and Engineering Delhi110063 India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Biosciences Chennai602 105 India Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Amman19328 Jordan Koneru Lakshmaiah Education Foundation Department of Computer Science and Engineering AP Vaddeswaram India Tashkent State University of Economics Department of Finance and financial technologies Tashkent Uzbekistan Lovely Professional University Division of Research and Development Phagwara India Dr. D. Y. Patil School of Science and Technology Tathawade Pune India

Agricultural consumer electronics, such as drones, sensors, and robotics, play a pivotal role in addressing challenges like wheat lodging, which can significantly impact crop yield and quality. This study leverages consumer-grade UAVs to classify wheat lodging types-root lodging and stem lodging-using high-resolution RGB images captured at three altitudes (15, 45, and 91 meters). By employing automatic segmentation techniques, datasets were generated for each altitude, and a refined EfficientNetV2-C model was proposed for classification. The model incorporates a Coordinate Attention (CA) mechanism to enhance feature extraction and Class-Balanced Focal Loss (CB-Focal Loss) to address data imbalance, achieving an average accuracy of 93.58%. This research highlights the integration of advanced AI-based classification with low-carbon agricultural drones, underscoring their relevance to consumer electronics. Compared to four conventional machine learning and two deep learning models, EfficientNetV2-C demonstrated superior performance at all altitudes while maintaining minimal carbon emissions. The study also examines the influence of UAV flight altitude on classification efficacy, revealing that while machine learning models were unaffected, deep learning models showed reduced performance at higher altitudes due to feature loss. These findings emphasize the potential of UAVs as accessible, scalable, and sustainable tools for real-time agricultural monitoring in precision farming. © 2025 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Leveraging Deep Learning for Accurate User Journey Prediction and Revenue Enhancement on Online Platforms

Leveraging Deep Learning for Accurate User Journey Predictio...

引用

Smart Systems for applications in Electrical sciences (ICSSES), International Conference on

作者： Selvarani V. Kanpur Rani Sakar Fatah Sulaiman V. Selvi ali ali Saber Mohammed M. Karthik Ministry of Education's Innovation Cell New Delhi India Department of EEE Hindustan Institute of Technology and Science Chennai India Department of Business Administration College of Administrative and Financial Sciences Knowledge University Erbil Iraq Department of computer science Mother Teresa Women's University Kodaikanal India Department of Computer Engineering Technologies Al Kitab University Kirkuk Iraq Department of AI & DS K.Ramakrishnan College of Engineering Trichy India

ISBN: (数字)9798331507671

ISBN: (纸本)9798331507688

The rapid evolution of online platforms has transformed how businesses engage with customers, making accurate user journey prediction crucial for enhancing revenue. This study investigates the application of deep learning techniques, particularly Multi-Layer Perceptron-Gated Recurrent Unit (MLP-GRU) models, to analyze and predict user behavior effectively. By leveraging a comprehensive dataset collected from e-commerce sales, we implement a systematic approach that includes data collection, preprocessing through Min-Max normalization, feature extraction using attention mechanisms, and revenue enhancement strategies. The attention mechanism allows the model to focus on significant user interactions, dynamically weighing the importance of various features to improve predictive accuracy. Our findings demonstrate that the MLP-GRU model not only captures intricate patterns in user behavior but also enables personalized recommendations that significantly boost conversion rates. By integrating deep learning with user journey analytics, businesses can optimize their marketing strategies, tailor user experiences, and ultimately drive higher revenue. The proposed method is implemented in Python and has an accuracy of about 99.11% which is higher than other existing methods like CNN, BiLSTM and LSTM. This research contributes to the growing body of knowledge in the field of artificial intelligence in e-commerce and provides actionable insights for practitioners aiming to leverage data-driven strategies to enhance customer engagement and satisfaction.

关键词： Deep learning Accuracy Attention mechanisms Systematics Predictive models Data collection Smart systems Feature extraction Electronic commerce Business

来源：评论

学校读者我要写书评

暂无评论

Assessment of water scarcity as a risk factor for cholera outbreaks

引用

Science of the Total Environment 2025年 978卷 179412页

作者： Magers, Bailey Usmani, Moiz Brumfield, Kyle D. Huq, Anwar Colwell, Rita R. Jutla, Antarpreet S. Geohealth and Hydrology Laboratory Department of Environmental Engineering Sciences University of Florida GainesvilleFL United States Civil Construction and Environmental Engineering University of Alabama at Birmingham BirminghamAL United States Maryland Pathogen Research Institute University of Maryland College ParkMD United States University of Maryland Institute for Advanced Computer Studies University of Maryland College ParkMD United States

Introduction: Increasing aridity and incidence of droughts pose a significant threat to human health, primarily in exacerbating water scarcity, and is projected to become more frequent and severe as a result of related environmental changes in many regions globally. Concomitantly, water scarcity will force populations to utilize potentially contaminated water sources, hence increasing exposure to waterborne diseases, notably cholera. Proliferation of Vibrio cholerae, causative agent of cholera, is driven by environmental factors. Notably, temperature and precipitation have been employed in providing predictive awareness of cholera, allowing early warning and mitigation. The impact of droughts on incidence and spread of cholera is less understood. Methods: This study aimed to quantify relationships among temperature, precipitation, and droughts as a basis for establishing the connection of environmental parameters and outbreaks of cholera. Thirteen cholera outbreaks between 2003 and 2023 in four African countries (Ethiopia, Kenya, Nigeria, and Senegal) were assessed using odds ratio and k-means clustering analysis. Results: Cholera outbreaks were 3.07 (95 % CI: [0.95, 9.88]) times more likely when drought conditions (negative precipitation anomalies, positive temperature anomalies, and negative Standardized Precipitation-Evapotranspiration Index) were present, compared to their absence. When excess rainfall was also considered, the odds ratio increased to 3.50 (95 % CI: [1.03, 11.90]). Complementary evidence obtained using k-means clustering analysis supported the conclusion that outbreaks of cholera were common during drought conditions. Conclusions: Considering the last few decades with increased severity and frequency of droughts in cholera-impacted regions, climate projections indicate the threat of cholera outbreaks will continue, especially noting increasing reports of cholera globally. Hence, predictive intelligence systems for rapid risk assessment, with resp

关键词： Cholera Climate Drought Vibrio cholerae

来源：评论

学校读者我要写书评

暂无评论

Number plate recognition smart parking management system using IoT

引用

Measurement: Sensors 2025年 37卷

作者： Ditta, allah Ahmed, Muhammad Maroof Mazhar, Tehseen Shahzad, Tariq alahmed, Yazan Hamam, Habib Department of Information Sciences Division of Science and Technology University of Education Lahore54000 Pakistan School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Science and Information Technology School Education Department Government of Punjab Layyah31200 Pakistan Department of Computer Science COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan Software Engineering Al Ain University Al Ain University Abu Dhabi United Arab Emirates Faculty of Engineering University of de Moncton MonctonNBE1A3E9 Canada School of Electrical Engineering University of Johannesburg Johannesburg2006 South Africa Av. Grandes Ecoles LibrevilleBP 1989 Gabon Bridges for Academic Excellence - Spectrum Tunis Tunisia

This study aims to address the urban vehicle parking issues by proposing a solution using Automatic Number Plate Recognition (ANPR) through image processing and a sensor-based hardware system. Integrating these technologies forms a Smart Parking Management System (SPMS) to automate parking processes and enhance the parking experience. The study aims to create an efficient system that eliminates manual vehicle registration and optimizes space utilization. ANPR and IoT-based sensors help users identify the available slots and pay only for the actual parking duration, which will help to minimize the fixed billing rates. The proposed ANPR system processes vehicle number plates at entry, ensuring seamless identification and eliminating manual registration. IoT sensors monitor real-time slot occupancy, transmitting data to a web admin panel. This panel provides insights such as entry and exit times, total parking duration, and billing costs, facilitating efficient management and remote monitoring. The ANPR-based SPMS reduces reliance on manual processes, streamlining entry procedures. By dynamically assessing slot availability through IoT sensors, users can locate unoccupied spaces quickly, which enhances user convenience. The web admin panel allows administrators to monitor the system remotely, ensuring smooth operations and maintaining accurate records. This study introduces a comprehensive solution to urban parking challenges by integrating ANPR and IoT technologies. The SPMS improves efficiency, reduces human resource needs, and enhances user experience with flexible billing based on actual duration. The combination of hardware and software provides a foundation for effective urban parking management. © 2024 The Authors

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Loss Functions in Deep Learning: A Comprehensive Review

arXiv

引用

arXiv 2025年

作者： Elharrouss, Omar Mahmood, Yasir Bechqito, Yassine Serhani, Mohamed Adel Badidi, Elarbi Riffi, Jamal Tairi, Hamid Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates Department of Information Systems College of Computing and Informatics University of Sharjah Sharjah United Arab Emirates Department of Informatics Faculty of Sciences Dhar El Mahraz Sidi Mohamed Ben Abdellah University Fez Morocco

Loss functions are at the heart of deep learning, shaping how models learn and perform across diverse tasks. They are used to quantify the difference between predicted outputs and ground truth labels, guiding the optimization process to minimize errors. Selecting the right loss function is critical, as it directly impacts model convergence, generalization, and overall performance across various applications, from computer vision to time series forecasting. This paper presents a comprehensive review of loss functions, covering fundamental metrics like Mean Squared Error and Cross-Entropy to advanced functions such as Adversarial and Diffusion losses. We explore their mathematical foundations, impact on model training, and strategic selection for various applications, including computer vision (Discriminative and generative), tabular data prediction, and time series forecasting. For each of these categories, we discuss the most used loss functions in the recent advancements of deep learning techniques. also, this review explore the historical evolution, computational efficiency, and ongoing challenges in loss function design, underlining the need for more adaptive and robust solutions. Emphasis is placed on complex scenarios involving multi-modal data, class imbalances, and real-world constraints. Finally, we identify key future directions, advocating for loss functions that enhance interpretability, scalability, and generalization, leading to more effective and resilient deep learning models. © 2025, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Novel computer-Aided Diagnosis System for the Early Detection of alzheimer’s Disease

引用

computers, Materials & Continua 2023年第3期74卷 5483-5505页

作者： Meshal alharbi Shabana R.Ziyad Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAl KharjSaudi Arabia

Aging is a natural process that leads to debility,disease,and ***’s disease(AD)causes degeneration of the brain cells leading to cognitive decline and memory loss,as well as dependence on others to fulfill basic daily *** is the major cause of ***-aided diagnosis(CADx)tools aid medical practitioners in accurately identifying diseases such as AD in *** study aimed to develop a CADx tool for the early detection of AD using the Intelligent Water Drop(IWD)algorithm and the Random Forest(RF)*** IWD algorithm an efficient feature selection method,was used to identify the most deterministic features of AD in the *** is an ensemble method that leverages multiple weak learners to classify a patient’s disease as either demented(DN)or cognitively normal(CN).The proposed tool also classifies patients as mild cognitive impairment(MCI)or *** dataset on which the performance of the proposed CADx was evaluated was sourced from the alzheimer’s Disease Neuroimaging Initiative(ADNI).The RF ensemble method achieves 100%accuracy in identifying DN patients from CN *** classification accuracy for classifying patients as MCI or CN is 92%.This study emphasizes the significance of pre-processing prior to classification to improve the classification results of the proposed CADx tool.

关键词： alzheimer’s disease dementia mild cognitive impairment computer-aided diagnosis intelligent water drop algorithm random forest

来源：评论

学校读者我要写书评

暂无评论

Secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks

引用

alexandria engineering Journal 2025年 128卷 127-143页

作者： Shayla Islam S.M. Topazal Mohammad Kamrul Hasan Raenu al Kolandaisamy Huda Saleh Abbas Nguyen Vo Rahul Thakkar Muhammad Attique Khan Deepak Gupta Dina Abdulaziz alHammadi Institute of Computer Science and Digital Innovation UCSI University Kuala Lumpur 56000 Malaysia Center for Cyber Security Faculty of Information Science and Technology the National University of Malaysia 43600 Bangi Selangor Malaysia Department of computer science College of Computer Science and Engineering Taibah University Madina Saudi Arabia Victorian Institute of Technology Melbourne Australia Center of AI College of Computer Engineering and Science Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Maharaja Agrasen Institute of Technology Delhi India Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O.Box 84428 Riyadh 11671 Saudi Arabia

The emergence of 5 G and 6 G networks promises significant advancements in the Internet of Medical Things (IoMT) by enabling real-time medical data transmission and continuous connectivity for mobile healthcare devices. However, traditional Handover (HO) mechanisms face latency, security, energy consumption, and scalability challenges when supporting fast-moving and dense IoMT environments. This paper presents a secure and fast mobility handover scheme for IoMT in 5 G and future 6 G networks, incorporating a predictive algorithm, Blockchain-Based (BC-B) decentralized authentication mechanism, and AI-driven anomaly detection. The predictive algorithm anticipates device movement and pre-allocates resources at the target Base Station (BS), reducing HO latency by 20–30 % in 5 G and up to 40 % in 6 G. Meanwhile, blockchain-based authentication ensures tamper-proof and decentralized security, reducing vulnerability to cyberattacks by 90 % compared to traditional methods. Additionally, the energy consumption during HO events is reduced by 20–35 %, dropping from 15 mJ in traditional schemes to 12 mJ in 5 G and further to 10 mJ in 6 G. The scheme also incorporates AI-driven anomaly detection, achieving an accuracy of 96.7 %, ensuring proactive identification and mitigation of potential security threats. The analyzed scheme maintains consistent throughput with less than 5 % reduction and scales effectively for up to 300 devices per cell. The simulation results demonstrate significant improvements across key performance metrics, including latency, security, energy efficiency, and scalability, making this approach highly suitable for critical IoMT applications such as telesurgery, remote patient monitoring, and innovative healthcare environments. These advancements position the analyzed framework as a cornerstone for next-generation (NG) healthcare networks.

关键词： 4G Fourth-Generation 5G Fifth-Generation 6G Sixth-Generation AR Augmented Reality NG Next-Generation IoT Internet of Things IoMT Internet of Medical Things TPBs Terabit Per Second BC-B Blockchain-Based URLLC Ultra-Reliable Low Latency Communications EMBB Enhanced Mobile Broadband MMTC Massive Machine-Type Communications AI Artificial Intelligence MIoT Massive Internet of Things DoS Denial-of-Service MIMO Multiple-Input Multiple-Output HOBP Handover Blocking Probability HOSR Handover Success Rate ADA Anomaly Detection Accuracy SLA Service Level Agreement VR Virtual Reality HO Handover BC Blockchain Ms millisecond KM kilometer THz Terahertz B5G Beyond-5G ML Machine Learning DL Deep Learning EC Energy Consumption BS Base Station ECC Elliptic Curve Cryptography QS Quality of Server E2E End-to-End MJ megaJoule XR Extended Reality D2D Device to Device PLR Packet Loss Ratio Handover Internet of Medical Things (IoMT) 5G networks 6G technology Security concerns Blockchain Digital healthcare Internet of Things Cybersecurity

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：