检索结果-内蒙古大学图书馆

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Secure Multi-User ISAC systems With STAR-RIS: A Deep Reinforcement Learning Approach for 6G Networks

引用

IEEE Access 2025年 13卷 31472-31484页

作者： Kamal, Mian Muhammad Zain Ul Abideen, Syed Al-Khasawneh, M.A. Alabrah, Amerah Sohail Ahmed Larik, Raja Irfan Marwat, Muhammad Southeast University School of Electronic Science and Engineering Jiangning Jiangsu Nanjing211189 China Qingdao University College of Computer Science and Technology Qingdao266071 China Al-Ahliyya Amman University Hourani Center for Applied Scientific Research Amman19111 Jordan Skyline University College School of Computing University City Sharjah Sharjah United Arab Emirates King Saud University College of Computer and Information Science Department of Information Systems Riyadh11543 Saudi Arabia Ilma University Department of Computer Science Sindh Karachi75190 Pakistan University of Science and Technology Bannu Department of Software Engineering Bannu28100 Pakistan

The rapid evolution of wireless communication technologies and the increasing demand for multi-functional systems have led to the emergence of integrated sensing and communication (ISAC) as a key enabler for future 6G networks. Simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs) have recently garnered significant attention for their ability to enhance signal coverage and improve system efficiency. This paper investigates a STAR-RIS-assisted ISAC system designed to secure communication for multiple legitimate users (LUs) while safeguarding against multiple eavesdroppers (Eves). By jointly optimizing the base station (BS) transmit beamforming, STAR-RIS transmission and reflection coefficients, and receive filters, the proposed framework aims to maximize the long-term average secrecy rate for all LUs. Constraints are imposed to ensure minimum echo signal-to-noise ratios (SNRs) for sensing and meet the achievable rate requirements of LUs. To address the inherent complexity of this non-convex problem, two deep reinforcement learning (DRL) algorithms are proposed. Numerical results demonstrate that the proposed system achieves significant improvements in secrecy rate compared to conventional RIS setups. This work provides a scalable and efficient approach for secure multi-user ISAC systems, making it highly relevant for future 6G networks, smart cities, and IoT applications. © 2025 The Authors.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent QV2X Routing for Traffic Management in Consumer IoV Using STGNN and Reinforcement Learning

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Jamal, Syed Saqib Muhammad, Afaq Song, Wang-Cheol Jeju National University Department of Electronic Engineering Jeju Korea Republic of College of Computing and Mathematics Computer Engineering Department and Interdisciplinary Research Center for Intelligent Secure Systems Dhahran Saudi Arabia

In the Consumer Internet of Vehicles (CIoV), reliable and timely data communication is essential for enhancing driver experience and safety. This paper introduces an innovative QV2X routing strategy that uses Spatio-Temporal Graph Neural Networks (STGNN) and Q-learning to optimize packet traffic in CIoV. By predicting network conditions and adapting to real-time data flows, our approach directly addresses consumer needs for efficient data transmission, reduced communication delays, and improved infotainment access. The integration of predictive models with adaptive learning mechanisms not only optimizes packet delivery but also minimizes latency and packet loss, critical for consumer applications like real-time navigation assistance and hazard warnings. Our key contribution is a dynamic packet traffic management system designed for consumer use, enhancing network reliability and efficiency for everyday vehicle users. experimental results validate that our model surpasses existing benchmarks by improving packet delivery ratios by up to 15% and reducing end-to-end delays by up to 20% in urban traffic scenarios. This advancement demonstrates our strategy's effectiveness in enriching consumer experiences and safety in vehicular communications. © 1975-2011 IEEE.

关键词： Packet loss

来源：评论

学校读者我要写书评

暂无评论

Improved chaotic fruit fly optimization with elman neural network based data-driven approach on product reviews classification

引用

Alexandria Engineering Journal 2025年 127卷 628-641页

作者： Alghamdi, Mohammed Al-shathry, Najla I. Said, Yahia Beyari, Hasan Sorour, Shaymaa Sattar, Khalid Nazim Abdul Alallah, Fouad Shoie Alshareef, Abdulrhman Department of Information Systems College of Computer Science King Khalid University Abha Saudi Arabia Department of Language Preparation Arabic Language Teaching Institute Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar73213 Saudi Arabia Department of Administrative and Financial Sciences Applied College Umm Al-Qura University Makkah Saudi Arabia Department of Management Information Systems College of Business Administration King Faisal University Al-Ahsa31982 Saudi Arabia Department of Computer Science and Information College of Science Majmaah University Majmaah11952 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia

In the digital era, business platforms have considerably evolved towards online stores on the internet. Through the internet-based platform, customers can easily buy products through their smartphones and receive delivery at the place without going to the shopping mall. On the other hand, the disadvantage of these platforms is that customers need to learn about the product quality. Thus, these platform services frequently offer customer feedback to give feedback about the shipped items. Feedback is a valuable source for analyzing customer satisfaction. Customer satisfaction is effectively enhanced by performing a Sentiment Analysis (SA) of many customer ratings on E-commerce platforms. Yet, predicting the correct sentiment difference in customer feedback is challenging due to complicated logic, sequence length, and text pattern adjustments. This article focuses on designing and developing Enhanced NLP with Data-driven Product Reviews Classification using the improved chaotic fruit fly optimization (ENLPPR-ICFFO) method. The major goal of the ENLPPR-ICFFO method is to detect and classify the sentiments existing in product ratings. To accomplish this, the presented ENLPPR-ICFFO method employs data pre-processing to be consistent. Then, the Continuous Bag-of-Words (CBoW) method is utilized for the feature extraction. The extreme learning machine (ELM) method is used for the product review classification. The ENLPPR-ICFFO methodology includes an ICFFO-based hyperparameter selection technique for improving the overall product review classification technique. The empirical findings of the projected ENLPPR-ICFFO methodology are tested using a set of datasets. The performance validation of the ENLPPR-ICFFO technique portrayed superior accuracy values of 98.04 % and 96.57 % over existing methods under Amazon-Fine-Food-Reviews and Amazon-Products datasets. © 2025 The Authors

关键词： User experience

来源：评论

学校读者我要写书评

暂无评论

A hybrid blockchain and AI-based approach for attack protection to secure internet of medical things networks

引用

Alexandria Engineering Journal 2025年 128卷 223-230页

作者： Hadeel Alsolai Fahd N. Al-Wesabi Ali M. Al-Sharafi Asma Alshuhail Abdulbasit A. Darem Bandar M. Alghamdi Fouad Shoie Alallah Abdulrahman Alzahrani Department of Information Systems College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information Technology University of Bisha Bisha 67714 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Department of Computer Science and Engineering College of Computer Science and Engineering University of Hafr Al Batin Saudi Arabia

The Internet of Medical Things (IoMT) has revolutionized healthcare by enabling real-time monitoring, remote diagnosis, and seamless data exchange among medical devices and providers. However, the interconnected and distributed nature of IoMT systems exposes them to significant cybersecurity threats, including data breaches and unauthorized access. This study aims to develop a secure and scalable framework to safeguard IoMT environments using blockchain technology, federated learning, and dynamic consensus algorithms. The proposed approach integrates artificial intelligence to detect threats and employs federated learning to maintain patient privacy while training models collaboratively. experimental evaluation of the framework shows improved data security, reduced response times, and enhanced system trustworthiness. The results suggest that the integration of blockchain and AI-driven mechanisms offers a robust solution to IoMT cybersecurity challenges, paving the way for more reliable and efficient healthcare systems.

关键词： Internet of medical things (IoMT) Blockchain security Federated learning AI-driven anomaly detection Cyber threat mitigation

来源：评论

学校读者我要写书评

暂无评论

Feature enhancement model with up sampling based cyber threat attack detection and classification on imbalanced dataset in Industrial Internet of Things

引用

Alexandria Engineering Journal 2025年 128卷 247-258页

作者： Hayam Alamro Fahd N. Al-Wesabi Sultan Alahmari Jawhara Aljabri Shouki A. Ebad Asma Alshuhail Fouad Shoie Alallah Abdulrhman Alshareef Mahir Mohammed Sharif Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh 11671 Saudi Arabia Department of Computer Science Applied College at Mahayil King Khalid University Saudi Arabia King Abdul Aziz City for Science and Technology (KACST) Cybersecurity Institute Riyadh Saudi Arabia Department of Computer Science University College in Umluj University of Tabuk Saudi Arabia Center for Scientific Research and Entrepreneurship Northern Border University Arar 73213 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal University Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Department of Computer and Self Development Preparatory Year Deanship Prince Sattam bin Abdulaziz University AlKharj Saudi Arabia

With the fast growth and utilization of artificial intelligence (AI) models, the Industrial Internet of Things (IIoT) has remarkably progressed in locating industrial communication and enhancing industrial methods quickly. In Industry 5.0, the hyper-automation method is a technical trend that navigates manufacturing objects to intellectual devices of IIoT, smart, agile software, cloud computing, smart robotics, and embedded modules by reliability and higher intricacy. Machine learning (ML) and deep learning (DL) methods were established for identifying anomalies by understanding the usual behaviour methods of the cyber threat attack and identifying and detecting deviations. This study proposes a Feature Enhancement Model with a White Shark Optimizer-based Cyber Threat Attack Detection and Classification (FEWSO-CTADC) technique on an Imbalanced Dataset in an IIoT environment. The primary focus of the FEWSO-CTADC technique is to enhance the automatic classification and detection of cyber threats in the IIoT environment. Initially, the FEWSO-CTADC technique implements a data preprocessing model to scale the raw information into a uniform format. Next, the SMOTE technique is used to manage the imbalanced class distribution in the attack recognition database. Moreover, the WSO-based feature subset selection is accomplished to select the superior set of features. Finally, the FEWSO-CTADC method utilizes the stacked auto-encoder (SAE) method for attack classification and recognition. Extensive experiments were conducted to demonstrate the improved performance of the FEWSO-CTADC approach, and the results were compared across various methods. The performance validation of the FEWSO-CTADC approach exhibited a superior value of 99.20 % over recent techniques under diverse metrics.

关键词： Cyber threat Stacked auto-encoder White shark optimizer Feature enhancement model Industrial Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Verify All Traffic: Towards Zero-Trust In-Network Intrusion Detection against Multipath Routing

引用

IEEE Journal on Selected Areas in Communications 2025年第6期43卷 2155-2171页

作者： Zhao, Ziming Li, Zhaoxuan Xie, Xiaofei Liu, Zhipeng Li, Tingting Yu, Jiongchi Zhang, Fan Chen, Binbin School of Software Technology Zhejiang University Ningbo315100 China College of Computer Science and Technology Zhejiang University Hangzhou310027 China ZJU-Hangzhou Global Scientific and Technological Innovation Center 311200 China Key Laboratory of Blockchain and Cyberspace Governance of Zhejiang Province 310027 China Jiaxing Research Institute Zhejiang University 314000 China Zhengzhou Xinda Institute of Advanced Technology Zhengzhou450001 China Singapore State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security UCAS Beijing100049 China School of Computing and Information Systems Singapore Management University Singapore188065 Singapore Advanced Digital Sciences Center Singapore138632 Singapore Singapore University of Technology and Design SingaporeB96049 Singapore

With the popularity of encryption protocols, machine learning (ML)-based traffic analysis technologies have attracted widespread attention. To adapt to modern high-speed bandwidth, recent research is dedicated to advancing zero-trust intrusion detection by offloading feature extraction and model inference into the network dataplane. Especially, with the rise of programmable switches, achieving line-speed ML inference becomes promising. However, existing research only considers a single switch node as a relay to conduct evaluation. This is far from real-world deployments involving multiple switches (given that zero-trust security assumes that threats can originate from anywhere, including within the network), particularly the multi-path routing phenomenon that exists in practice. In this paper, we reveal practical challenges in the context of enabling line-speed model inference in the network dataplane. Furthermore, we propose FCPlane, the forwarding and computing integrated dataplane for zero-trust intrusion detection that aims to enable efficient load balancing while providing reliable traffic analysis results, even against multipath routing. The core idea is to reconcile forwarding and computation to the flowlet level, for which a tailor-made Markov chain model is designed. Based on two public traffic datasets, we evaluate seven state-of-the-art in-network traffic analysis models deployed in four types of topologies (three with multipath routing and one without) to explore performance impact and demonstrate the effectiveness of our proposal. © 1983-2012 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Comparing Large Language Model AI and Human-Generated Coaching Messages for Behavioral Weight Loss

引用

Journal of Technology in Behavioral Science 2025年 1-12页

作者： Huang, Zhuoran Berry, Michael P. Chwyl, Christina Hsieh, Gary Wei, Jing Forman, Evan M. Khoury College of Computer Sciences Northeastern University 440 Huntington Ave Boston 02115 MA United States VA Connecticut Healthcare System West Haven 06516 CT United States Portland Psychotherapy Clinic Research and Training Center 3700 N Williams Ave. Portland 97227 OR United States Department of Human Centered Design & Engineering University of Washington Seattle 98195 WA United States School of Computing and Information Systems The University of Melbourne Parkville 3052 VIC Australia Center for Weight Eating and Lifestyle Science Drexel University 3141 Chestnut Street Stratton Hall Philadelphia 19104 PA United States Department of Psychological and Brain Sciences Drexel University 3141 Chestnut Street Stratton Hall Philadelphia 19104 PA United States

Automated coaching messages for weight control can save time and costs, but their repetitive, generic nature may limit their effectiveness compared to human coaching. Large language model (LLM) based artificial intelligence (AI) chatbots, like ChatGPT, could offer more personalized and novel messages to address repetition with their data-processing abilities. While LLM AI demonstrates promise to encourage healthier lifestyles, studies have yet to examine the feasibility and acceptability of LLM-based BWL coaching. Eighty-seven adults in a weight-loss trial (BMI ≥ 27 kg/m²) rated ten coaching messages’ helpfulness (five human-written, five ChatGPT-generated) using a 5-point Likert scale, providing additional open-ended feedback to justify their ratings. Participants also identified which messages they believed were AI-generated. The evaluation occurred in two phases: messages in Phase 1 were perceived as impersonal and negative, prompting revisions for messages in Phase 2. In Phase 1, AI-generated messages were rated less helpful than human-written ones, with 66% receiving a helpfulness rating of 3 or higher. However, in Phase 2, the AI messages matched the human-written ones regarding helpfulness, with 82% scoring three or above. Additionally, 50% were misidentified as human-written, suggesting AI’s sophistication in mimicking human-generated content. A thematic analysis of open-ended feedback revealed that participants appreciated AI’s empathy and personalized suggestions but found them more formulaic, less authentic, and too data-focused. This study reveals the preliminary feasibility and perceived helpfulness of LLM AIs, like ChatGPT, in crafting potentially effective weight control coaching messages. Our findings also underscore areas for future enhancement. © The Author(s) 2025.

关键词： Artificial intelligence ChatGPT Large language model MHealth Weight loss

来源：评论

学校读者我要写书评

暂无评论

SmartEdge: Smart Healthcare End-to-End Integrated Edge and Cloud computing System for Diabetes Prediction Enabled by Ensemble Machine Learning

arXiv

引用

arXiv 2025年

作者： Hennebelle, Alain Dieng, Qifan Ismail, Leila Buyya, Rajkumar Abu Dhabi United Arab Emirates Lab School of Computing and Information Systems University of Melbourne Melbourne Australia Lab Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates Emirates Center for Mobility Research United Arab Emirates National Water and Energy Center UAE University Abu Dhabi Al-Ain United Arab Emirates

The Internet of Things (IoT) revolutionizes smart city domains such as healthcare, transportation, industry, and education. The Internet of Medical Things (IoMT) is gaining prominence, particularly in smart hospitals and Remote Patient Monitoring (RPM). The vast volume of data generated by IoMT devices should be analyzed in real-time for health surveillance, prognosis, and prediction of diseases. Current approaches relying on Cloud computing to provide the necessary computing and storage capabilities do not scale for these latency-sensitive applications. Edge computing emerges as a solution by bringing cloud services closer to IoMT devices. This paper introduces SmartEdge, an AI-powered smart healthcare end-to-end integrated edge and cloud computing system for diabetes prediction. This work addresses latency concerns and demonstrates the efficacy of edge resources in healthcare applications within an end-to-end system. The system leverages various risk factors for diabetes prediction. We propose an Edge and Cloud-enabled framework to deploy the proposed diabetes prediction models on various configurations using edge nodes and main cloud servers. Performance metrics are evaluated using, latency, accuracy, and response time. By using ensemble machine learning voting algorithms we can improve the prediction accuracy by 5% versus a single model *** Codes 68T01, 68T09, 68M14, 68W10, 68W15 © 2025, CC BY.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Information Monitoring on the Web: A Scalable Solution

引用

World Wide Web 2002年第4期5卷 263-304页

作者： Liu, Ling Tang, Wei Buttler, David Pu, Calton Center for Experimental Research of Computing Systems College of Computing Georgia Institute of Technology AtlantaGA30332-0280 United States

This paper presents WebCQ, a continual query system for large-scale Web information monitoring. WebCQ is designed to discover and detect changes to Web pages efficiently, and to notify users of interesting changes with personalized messages. Users' Web page monitoring requests are modeled as continual queries on the Web and referred to as Web page sentinels. The system consists of five main components: a change detection robot that discovers and detects changes, a proxy cache service that reduces the communication traffics to the original information provider on the remote server, a trigger evaluation tool that can filter only the changes that match certain thresholds, a personalized change presentation tool that highlights Web page changes, and a change notification service that displays and delivers interesting changes and fresh information to the right users at the right time. This paper describes the WebCQ system with an emphasis on the general issues in designing and engineering a large-scale information change monitoring system on the Web. There are two main contributions. First, we present the mechanisms that WebCQ provides to support various types of Web page sentinels for finding and displaying interesting changes to Web pages. The large collection of sentinel types allows WebCQ to efficiently locate and monitor a wide range of changes in Web pages. The second contribution is the development of sentinel grouping techniques for efficient and scalable processing of large number of concurrently running triggers and Web page sentinels. We report our initial experimental results showing the effectiveness of the proposed solutions. © 2002, Kluwer Academic Publishers.

关键词： Websites

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：