检索结果-内蒙古大学图书馆

Polyp image segmentation based on improved planet optimization algorithm using reptile search algorithm

Neural computing and Applications 2025年第8期37卷 6327-6349页

作者： Abd Elaziz, Mohamed Al-qaness, Mohammed A. A. Al-Betar, Mohammed Azmi Ewees, Ahmed A. Department of Mathematics Faculty of Science Zagazig University Zagazig Egypt College of Physics and Electronic Information Engineering Zhejiang Normal University Jinhua321004 China Zhejiang Institute of Optoelectronics Jinhua321004 China Faculty of Computer Science and Engineering Galala University Suze435611 Egypt Ajman University Ajman346 United Arab Emirates College of Computing and Information Technology University of Bisha Bisha Saudi Arabia Department of Computer Damietta University Damietta Egypt Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman Jordan

To recognize the potential for colon polyps to develop into cancer over time, early diagnosis is crucial for preventative healthcare. Timely identification significantly improves the prognosis and treatment outcomes for colorectal cancer patients. Image segmentation is crucial in medical image analysis for accurate diagnosis and treatment planning. Therefore, in this study, we present an alternative multilevel thresholding polyp segmentation method (MPOA) to enhance the segmentation of polyp images. The proposed method is based on enhancing the planet optimization algorithm (POA) by integrating operators from the reptile search algorithm (RSA). The evaluation of the developed MPOA is tested with different polyp images and compared with other image segmentation approaches. The results highlight the superior capability of MPOA, as evidenced by various performance measures in effectively segmenting polyp images. Furthermore, metrics such as peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and fitness values demonstrate that MPOA outperforms the basic version of POA and other methods. The evaluation outcomes underscore the significant impact of RSA in enhancing the performance of POA for the segmentation of polyp images. © The Author(s) 2025.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Advancing public health through Spatial Data Infrastructures: a review of global practices, governance and policy recommendations

引用

Discover public health 2025年第1期22卷 1-11页

作者： Adeleye, Victor Mayowa Ashinze, Patrick Okeoyo, Teslim El Nabbout, Veronica Phiri, Emmanuel Chileshe Gautam, Gargi Chukwunonso, Collins Adebayo, Alhazan Amir Ali, Halima Monsurat, Ekemode Oluwadamilola Department of Engineering & Computing School of Architecture Computing and Engineering University of East London London United Kingdom Ekiti State University Teaching Hospital Ekiti Nigeria Faculty of Clinical Sciences University of Ilorin Teaching Hospital Ilorin Nigeria University of Medicine and Pharmacy Iasi Romania Faculty of Medicine Copperbelt University School of Medicine Ndola Zambia Department of Medicine Georgian National University SEU Tbilisi Georgia Northern Arizona University Flagstaff United States First Technical University Ibadan Nigeria Comboni College of Science and Technology Khartoum Sudan Department of Anatomy Faculty of Basic Medical Sciences University of Ilorin Ilorin Nigeria

Background: Spatial Data Infrastructure (SDI) frameworks provide a foundation for the integration and sharing of geospatial data, essential for public health decision-making. Effective governance of SDIs plays a critical role in improving health outcomes through disease surveillance, resource allocation, and health equity. While well-established SDIs like INSPIRE (Europe), NSDI (USA), and ASDI (Australia) offer functional models, they still face challenges. In contrast, regions like Africa and Asia struggle with SDI development due to disparities in funding, regulatory compliance, and technological integration. Objectives: This study evaluates the role of government-regulated SDIs in shaping public health outcomes, focusing on gaps in governance, accessibility, interoperability and policies guiding geospatial data in public health contexts. Methods: A systematic search was conducted across Scopus, PubMed, and Google Scholar on May 30th, 2024, yielding 129 articles. After screening, 75 articles were excluded for being non-SDI specific, editorial, or abstract-only. Data extraction focused on SDI governance and public health outcomes, and thematic analysis was used to assess the impact on disease surveillance, healthcare access, and data sharing. Results: Out of 127 articles obtained, 33 addressed technological aspects of SDIs, with only two specifically focusing on public health. No studies addressed SDI policies directly within the public health framework, highlighting a significant research gap. Conclusion: The lack of SDI policy integration in designing its platform in a public health context underscores the need for targeted research. Improved governance, policy frameworks, and collaboration in regions like Africa and Asia are essential to developing SDIs that can enhance public health outcomes. © The Author(s) 2025.

关键词： Policy Public health SDI governance Spatial Data Structure (SDI)

来源：评论

学校读者我要写书评

暂无评论

An Optimal Cluster Head and Secure Route Path Selection Using Multi Objective—GWO Approach in Wireless Sensor Networks

An Optimal Cluster Head and Secure Route Path Selection Usin...

引用

International Conference on 6G Communications Networking and Signal Processing, SGCNSP 2023

作者： Muvva, Vijaya Bhaskar Reddy Almoussawi, Zainab abed Naik, Narayan Madhavan, Sowmya Praveena, Hirald Dwaraka Department of Information Technology College of Computing and Information Sciences University of Technology and Applied Sciences -Shinas Shinas Oman College of Islamic Science Ahl Al Bayt University Karbala Iraq Department of IS&E Canara Engineering College Visvesvaraya Technological University Karnataka BantwalBelagavi India Department of Electronics and Communication Engineering Nitte Meenakshi Institute of Technology Bengaluru India Andhra Pradesh Tirupati India

ISBN: (纸本)9789819778751

Wireless Sensor Networks (WSNs) play a crucial role ranging from environmental control to queue tracking. These networks are established by deploying numerous tiny sensor nodes that communicate with each other wirelessly. However, the routing paths in WSNs often suffer from delays in timely information delivery. The proposed Multi Objective Grey Wolf Optimization (MOGWO) aims to address these challenges where information transmission may converge slowly and routing paths may struggle in large-dimensional spaces. The objective of MOGWO is to efficiently send information by selecting the shortest path based on the regions. The MOGWO focuses on achieving high efficiency by choosing the shortest path to explore information. In the context of network routing MOGWO optimizes the path to the destination considering the energy levels of the sensor nodes. The proposed MOGWO method demonstrates superior performance compared to existing methods such as PSO, Black Widow Optimization (BWO) and Ant Colony Optimization (ACO). Specifically, the MOGWO method yields better results, achieving an energy consumption of 43 J, Packet Delivery Ratio (PDR) of 90%, and End-To-End Delay (ETED) of 33 s. This outperforms existing methods, highlighting the effectiveness of the MOGWO approach in enhancing network routing paths in WSN. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

AI Modeling and Water Quality Sensing Technique Proffers Water Security: An Open Review

AI Modeling and Water Quality Sensing Technique Proffers Wat...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： Wilfred Blessing N.R Suresh Palarimath Hemalatha Gunasekaran Sk Wasim Haidar Sutherlin Subitha G Sarmila J College of Computing and Information Sciences University of Technology and Applied Sciences Ibri Sultanate of Oman College of Computing and Information Sciences University of Technology and Applied Sciences Salalah Sultanate of Oman Department of Computer Science and Engineering Stella Mary’s College of Engineering Kanyakumari District India Department of Computer Science and Engineering St. Xavier’s Catholic College of Engineering Chunkankadai Tamil Nadu India

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Water Quality Sensors (WQSs) are becoming a promised tool in water quality data assessment and scientific value of aquatic structure. Such sensors are broadly used to produce live results by evaluating major water quality parameters and components. Artificial intelligence (AI) based WQSs and machine learning (ML) algorithms primarily enable long term operations for real time detention of water quality information at different time periods. Messaging services, alarms, alerts and other proper warnings are given to water quality managers or assessing communities while the quality deterioration occurs at the particular water quality checking sites. A good number of impressive challenges are identified in hosting the variety of sensors to manage, warehouse and analyze incessant water quality information that they generate periodically. This paper places interests in highlighting lack of suitable assessment standards and determine logistical deliberations for fruitful implementations together with transportation, storage services and appropriate trustworthy communication. The main objective is to identify the designs targeting water security that support to monitor, reassure and protect the water resources all the way through uninterrupted quality supervision in addition to AI features. This open review also discusses a variety of applications in water quality sensors, AI modeling, electronic tongues and indices, hence results the knowledge of improvement required for upgrading the quality in water resources through computer technologies and models.

关键词： Wireless sensor networks Reviews Computational modeling Transportation Water quality Predictive models Artificial intelligence Water resources Intelligent sensors Monitoring

来源：评论

学校读者我要写书评

暂无评论

Quantitative Cybersecurity Analysis Framework for Cyber Physical Systems: A Conceptual Approach

IEEE Open Journal of the Computer Society

引用

IEEE Open Journal of the Computer Society 2025年第01期6卷 613-626页

作者： Abdulhamid, Alhassan Kabir, Sohag Ghafir, Ibrahim Lei, Ci Hindi, Khalil El Hammoudeh, Mohammad Faculty of Engineering and Digital Technologies University of Bradford BradfordBD7 1DP United Kingdom College of Computer and Information Sciences King Saudi University P.O. Box 70474 Riyadh11543 Saudi Arabia School of Computing and Mathematics Manchester Metropolitan University ManchesterM15 6BH United Kingdom

Cyber-physical systems (CPS) are indispensable in various sectors, enabling convenient and efficient processes in today’s rapidly evolving technological landscape. However, the integration of internet-enabled components with physical processes exposes CPS to numerous security threats, rendering them susceptible to potential cyber-attacks. This paper presents a quantitative analysis framework for evaluating the security attributes of CPS conceptual design. Focusing on CPS design architecture, the framework models and quantifies security attributes by considering various dimensions. The paper demonstrates the integration of qualitative expert input into a fuzzy logic system to address the challenges and uncertainties associated with vulnerability data in CPS security quantification. Additionally, it examines the statistical dependence of basic attack steps (BASs) and their impact on the overall system security analysis, taking into account the intricate connectivity of CPS and the vulnerabilities that attackers could exploit. The novelty of the proposed framework lies in its integrated approach to modelling and quantifying security attributes in the CPS environment while considering uncertainties in vulnerability data and dependencies between security events. The computation of statistical and stochastic dependencies among BASs is achieved by mapping the attack tree (AT) to a higher statistical model of the Bayesian network (BN) model. The application of this framework was demonstrated using an intelligent glucose monitoring and insulin administration system (IGMIAS). The framework’s general nature makes it adaptable for quantifying cybersecurity behaviours in any CPS environment. ©2020 IEEE.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) Architecture for Lung Cancer Subtype Classification

Convolutional Neural Network-Long Short-Term Memory (CNN-LST...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： S. Ahamed Nishath Suresh Rasappan Francis Saviour Devaraj Information Technology Department College of Computing and Information Sciences University of Technology and Applied Sciences-Ibri Ibri Sultanate of Oman Mathematics Department University of Technology and Applied Sciences-Ibri Ibri Sultanate of Oman

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

Lung cancer is a leading cause of cancer-related deaths worldwide. Accurate classification of lung cancer subtypes is crucial for effective treatment. This study proposes a Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture for classifying lung cancer subtypes: Adenocarcinoma, Squamous Cell Carcinoma, and Lymph Node involvement. Our model achieves 95.38% on a dataset LC105K of 105,000 images, outperforming traditional methods. The CNN-LSTM architecture extracts features from images and models temporal dependencies, improving classification accuracy.

关键词： Technological innovation Accuracy Squamous cell carcinoma Memory architecture Lung cancer Feature extraction Convolutional neural networks Reliability Lymph nodes Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Learning with Prototypical Networks for Improved Memory Forensics

引用

IEEE Access 2025年 13卷 79397-79409页

作者： Malik, Muhammad Fahad Gul, Ammara Saadia, Ayesha Alserhani, Faeiz M. Air University Department of Cyber Security Islamabad Pakistan Birmingham City University Faculty of Computing Birmingham United Kingdom Air University Department of Computer Science Islamabad Pakistan Jouf University College of Computer and Information Sciences Department of Computer Engineering and Networks Al Jouf72388 Saudi Arabia

Securing computer systems requires effective methods for malware detection. Memory forensics analyzes memory dumps to identify malicious activity, but faces challenges including large and complex datasets, constantly evolving malware threats, and limited labeled data for training algorithms among others. This research introduces a novel approach for malware detection using memory forensics and prototypical networks. As the first application of prototypical networks to the Dumpware10 dataset (to the best of authors knowledge), our findings highlight the potential of few-shot learning for memory forensics-based malware detection, opening new avenues for research in this domain. Prototypical networks are a type of few-shot learning algorithm that excels at classifying new categories with minimal examples. Utilizing the publicly available Dumpware10 dataset, which includes 10 malware classes and one benign class, we preprocess memory dumps using denoising and A-Hash functions to reduce noise and redundancy. The prototypical network is trained on the first four malware classes and the benign class. It’s then tested on a dataset with one additional class (first five malware classes and the benign class). We progressively increase the number of test classes to eleven. Within each training episode, five training images are used as support samples, with all remaining images designated as query samples. Our goal isn’t to predict exact class labels, but to assess the similarity between query images and prototypes using a distance metric. If the label of a prototype matches the query image and the distance falls below a threshold, it’s considered a true positive. This approach achieves an average accuracy of 92% with eleven classes, the highest across all scenarios and comparable to previous work using machine and deep learning algorithms on this dataset. © 2013 IEEE.

关键词： Computer forensics

来源：评论

学校读者我要写书评

暂无评论

Deciphering the Geometric Bonferroni Mean Operator in Pythagorean Neutrosophic Sets Framework

引用

Neutrosophic Sets and Systems 2025年 75卷 139-161页

作者： Kamari, Mohammad Shafiq Bin Mohammad Rodzi, Zahari Bin Md. Al-Obaidi, R.H. Al-Sharqi, Faisal Al-Quran, Ashraf Shlaka, Rawan A. College of Computing Informatics and Mathematics Studies MARA University of Technology Negeri Sembilan Branch Seremban Campus Negeri Sembilan Seremban70300 Malaysia Faculty of Science and Technology National University of Malaysia Selangor Bandar Baru Bangi43600 Malaysia Fuel and Energy Techniques Engineering Department College of Engineering and Technologies AI-mustaqbal University Babylon51001 Iraq Department of Mathematics Faculty of Education for Pure Sciences University of Anbar Anbar Ramadi Iraq Department of Basic Sciences Preparatory Year King Faisal University Al-Ahsa31982 Saudi Arabia College of Pharmacy National University of Science and Technology Dhi Qar Iraq

The Geometric Bonferroni Mean (GBM), is an extension of The Bonferroni mean (BM), that combines both BM and the geometric mean, allowing for the representation of correlations among the combined factors while acknowledging the inherent uncertainty within the decision-making process. Within the framework of Pythagorean neutrosophic set (PNS) that encompasses truth, indeterminacy, and falsity-membership degrees, each criterion can be integrated into a unified PNS value, portraying the overall evaluation of that criterion by employing the Geometric Bonferroni mean. This study aims to enhance decision-making in Pythagorean neutrosophic framework by introducing an aggregation operator to PNS using the Geometric Bonferroni Mean. Additionally, it proposes a normalized approach to resolve decision-making quandaries within the realm of PNS, striving for improved solutions. The novel Pythagorean Neutrosophic Normalized Weighted Geometric Bonferroni Mean (PNNWGBM) aggregating operator has been tested in a case of multi-criteria decision-making (MCDM) problem involving the selection of Halal products suppliers with several criteria. The result shows that this aggregating operator is offering dependable and pragmatic method for intricate decision-making challenges and able to effectively tackle uncertainty and ambiguity in MCDM problem. © 2025, University of New Mexico. All rights reserved.

关键词： Mathematical operators

来源：评论

学校读者我要写书评

暂无评论

Innovative Approaches in Predictive Analysis and Personalized Online Shopping Recommendations with AI Powered-Chat

Innovative Approaches in Predictive Analysis and Personalize...

引用

Artificial Intelligence, Applications, Innovation and Ethics (AI2E), International Conference for

作者： Bazeer Ahamed Fajlul Kareem Mohamed Yasin Noor Mohamed University of Technology and Applied Sciences College of Computing and Information Sciences-Al Musannah Sultanate of Oman Information Technology Sultan Qaboos University Muscat Sultanate of Oman

ISBN: (数字)9798331513733

ISBN: (纸本)9798331513740

Customers are more exposed than ever to the necessary quantity of information about goods and services nowadays. As a result, there is a great deal of variability in consumer demand, making it difficult for retailers to provide the appropriate goods and services in accordance with client preferences. Recommender systems can use consumer evaluations, comments, and shared experiences regarding a product as an efficient way to learn about the preferences of the customer. Users' buying lists, viewer lists, and product purchase counts are regarded as the primary core attributes for doing the analysis of the items watched and purchased in order to recommend products to users. This uses a hybrid recommendation methodology that blends data analytics, collaborative filtering, and machine learning. It is possible to create a framework for forecasting consumer behavior. Users are increasingly using social media in the current situation to get prompt customer assistance; however, the majority of these complaints were unanswered or not addressed at all. A new conversational system has been created to automatically generate responses to user inquiries on social media in order to address this problem.

关键词： Technological innovation Ethics Data analysis Consumer behavior Social networking (online) Machine learning Electronic commerce Predictive analytics Forecasting Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Face image authentication scheme based on MTCNN and SLT

引用

Multimedia Tools and Applications 2025年 1-43页

作者： Thabit, Rasha Al-Askari, Mohanad A. Mohammed, Dunya Zeki Anaam, Elham Abdulwahab Mahmood, Zainab H. Jabbar, Dina Jamal Salih, Zahraa Aqeel Information System Department College of Computer Sciences and Information Technology University of Al-Anbar Al-Anbar Iraq Computer Engineering Department College of Engineering Al-Iraqia University Baghdad Iraq Electronic and Communications Engineering Department College of Engineering Gilgamesh University Baghdad Iraq Faculty of Computing and Informatics Multimedia University Selangor Cyberjaya Malaysia Department of Cybersecurity Engineering College of Information Engineering Al-Nahrain University Baghdad Iraq Electrical Engineering Technical Collage Middle Technical University Baghdad Iraq Department of Business Administration Alamaal University College Baghdad Iraq

DeepFakes and face image manipulation methods have been widely distributed in the last few years and several techniques have been presented to check the authenticity of the face image and detect manipulation if exists. Most of the available manipulation detection techniques have been successfully applied to reveal one type of manipulation under specific conditions, however, many limitations and challenges can be encountered in this field. To overcome some limitations and challenges, this paper presents a new face image authentication (FIA) scheme based on Multi-Task Cascaded Conventional Neural Networks (MTCNN) and watermarking in Slantlet transform (SLT) domain. The proposed FIA scheme has three main algorithms that are face detection and selection, embedding, and extraction algorithms. Different block sizes have been used to divide the image into non-overlapping blocks followed by classifying them into two groups that are blocks from face area (FA) and blocks from the remaining area (RA) of the image. In the embedding algorithms, the authentication information is generated from FA blocks and embedded in the RA blocks. In the extraction algorithms, the embedded information is extracted from RA blocks and compared with the calculated data from FA blocks to reveal manipulations and localize the manipulated blocks if exist. Extensive experiments have been conducted to evaluate the performance of the proposed FIA scheme for different face images. The experimental work included tests for payload, capacity, visual quality, time complexity, and localization of manipulations. The results proved the efficiency of the proposed scheme in detecting and localizing different face image manipulations such as attributes attacks, retouching attacks, expression swap, face swap, and morphing attacks. The proposed scheme overcomes many limitations and it is 100% accurate in localizing the tampered blocks which makes it a better candidate for practical applications. © The Author(s), un

关键词： Authentication

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：