检索结果-内蒙古大学图书馆

Automatic melanoma and non-melanoma skin cancer diagnosis using advanced adaptive fine-tuned convolution neural networks

引用

Discover Oncology 2025年第1期16卷 1-27页

作者： Khan, Muhammad Amir Mazhar, Tehseen Ali, Muhammad Danish Khattak, Umar Farooq Shahzad, Tariq Saeed, Mamoon M. Hamam, Habib School of Computing Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam 40450 Malaysia School of Computer Science National College of Business Administration and Economics Lahore 54000 Pakistan Department of Computer Science COMSATS University Islamabad Abbottabad Campus Abbottabad 22060 Pakistan School of Information Technology UNITAR International University Kelana Jaya Petaling Jaya 47301 Malaysia Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal 57000 Pakistan Department of Communications and Electronics Engineering Faculty of Engineering University of Modern Sciences (UMS) Yemen Sana’a 00967 Yemen Faculty of Engineering University de Moncton Moncton E1A3E9 NB Canada School of Electrical Engineering Department of Electrical and Electronic Engineering Science University of Johannesburg Johannesburg South Africa Hodmas University College Taleh Area Mogadishu Banadir 521376 Somalia Bridges for Academic Excellence—Spectrum Tunis Centre-Ville 1002 Tunisia Department of Computer Science School Education Department Government of Punjab Layyah 31200 Pakistan

Skin Cancer is an extensive and possibly dangerous disorder that requires early detection for effective treatment. Add specific global statistics on skin cancer prevalence and mortality to emphasize the importance of early detection. Example: “Skin cancer accounts for 1 in 5 diagnosed cancers globally, with melanoma causing over 60,000 deaths annually. Manual skin cancer screening is both time-intensive and expensive. Deep learning (DL) techniques have shown exceptional performance in various applications and have been applied to systematize skin cancer diagnosis. However, training DL models for skin cancer diagnosis is challenging due to limited available data and the risk of overfitting. Traditionally approaches have High computational costs, a lack of interpretability, deal with numerous hyperparameters and spatial variation have always been problems with machine learning (ML) and DL. An innovative method called adaptive learning has been developed to overcome these problems. In this research, we advise an intelligent computer-aided system for automatic skin cancer diagnosis using a two-stage transfer learning approach and Pre-trained Convolutional Neural Networks (CNNs). CNNs are well-suited for learning hierarchical features from images. Annotated skin cancer photographs are utilized to detect ROIs and reset the initial layer of the pre-trained CNN. The lower-level layers learn about the characteristics and patterns of lesions and unaffected areas by fine-tuning the model. To capture high-level, global features specific to skin cancer, we replace the fully connected (FC) layers, responsible for encoding such features, with a new FC layer based on principal component analysis (PCA). This unsupervised technique enables the mining of discriminative features from the skin cancer images, effectively mitigating overfitting concerns and letting the model adjust structural features of skin cancer images, facilitating effective detection of skin cancer features. The sys

关键词： Advanced adaptive fine-tuned Convolution neural networks Melanoma and non-melanoma skin cancer

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Enhanced Energy-Efficient Architectures for Sustainable Internet of Things Ecosystems 1st

Blockchain-Enhanced Energy-Efficient Architectures for Susta...

引用

1st International Conference on Advanced Network Technologies and Computational Intelligence, ICANTCI 2024

作者： Goyal, S.B. Rajawat, Anand Singh Verma, Chaman Illés, Zoltán Singh, Jaiteg Faculty of Information Technology City University Petaling Jaya46100 Malaysia School of Computer Sciences and Engineering Sandeep University Nashik India Department of Media and Educational Informatics Faculty of Informatics Eötvös Loránd University Budapest Hungary Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura India

ISBN: (纸本)9783031860683

Novel technique are required to ensure the long-term viability and maximize the efficiency of energy consumption in the constantly changing Internet of Things (IoT) landscape. In order to accomplish these objectives, this study examines the potential use of blockchain technology into IoT architectural concepts. Our approach utilizes blockchain technology to effectively manage and enhance energy consumption in IoT devices and networks. This is achieved by capitalizing on the decentralized, secure, and transparent characteristics of blockchain. Our objective is to do this by developing a decentralized ledger system that documents all energy transactions and interactions inside an Internet of Things (IoT) environment. This strategy utilizes blockchain technology to provide accountability and real-time monitoring of energy consumption, hence facilitating improved energy allocation and consumption. We delve into the concept and execution of smart contracts that ensure transactions and automate energy-conservation procedures, thereby diminishing the necessity for centralized authority and alleviating energy wastage. In addition, we examine the possibility of blockchain technology to enable direct energy transfer between Internet of Things (IoT) devices. This feature facilitates the development of a self-sustaining Internet of Things ecosystem by enabling devices with surplus energy to vend it to those requiring it. We also tackle the difficulties associated with the integration of blockchain with IoT, such as the energy consumption resulting from blockchain activities and the ability to effectively handle large volumes of data. Furthermore, we offer resolutions to these problems. The proposed framework improves the energy efficiency of IoT ecosystems and promotes their sustainability by advocating for the use of renewable energy sources and decreasing carbon footprints. Through the utilization of simulations and real-world illustrations, we showcase the efficacy of our bl

关键词： Clean energy

来源：评论

学校读者我要写书评

暂无评论

Menstrual cycle inspired latent diffusion model for image augmentation in energy production

引用

Scientific Reports 2025年第1期15卷 1-19页

作者： Mahmoud, Gamal M. Elbaz, Mostafa Said, Wael Elsonbaty, Amira A. Department of Electrical Engineering Pharos University in Alexandria Alexandria Egypt Department of Computer Science Faculty of Computers and Informatics Kafrelsheikh University Kafrelsheikh Egypt Computer Science Department Faculty of Computers and Informatics Zagazig University Zagazig 44511 Egypt Communication and Electronics Department High Institute of Engineering and Technology New Damietta 34517 Egypt

In the energy production domain, image classification is critical for monitoring, diagnostics, and operational optimization tasks. Latent diffusion models (LDMs) have shown potential in generating diverse images during the augmentation process based on text input. However, they are hindered by pixel integrity, texture consistency, and mode collapse. This paper introduces menstrual cycle-inspired latent diffusion model (MCI-LDM), a novel framework that addresses these challenges with three key modifications. First, a menstrual cycle-inspired metaheuristic algorithm is integrated to improve generated images’ pixel integrity and structural coherence. Second, an adaptive attention mechanism is employed to dynamically focus on critical regions during image generation, ensuring that fine details are preserved. Third, a multi-scale feature enhancement module is incorporated to capture global structures and local textures, mitigating mode collapse and enhancing overall image quality. Extensive experiments were conducted on five energy-related datasets, demonstrating the superior performance of MCI-LDM in terms of image augmentation, diversity, and generation accuracy. The results highlight the efficiency of the proposed model, making it a valuable tool for improving image classification and data augmentation in energy sector applications. MCI-LDM outperforms LDM by generating more diverse images, with a higher Inception Score (7.1 vs. 5.4) and a lower Fréchet Inception Distance (22.5 vs. 35.2), indicating better quality and variation. Additionally, MCI-LDM preserves image integrity more effectively, achieving superior PSNR (32.7 dB vs. 28.5 dB) and SSIM (0.92 vs. 0.78). © The Author(s) 2025.

关键词： Energy production Image augmentation Latent diffusion model MCI-LDM Menstrual cycle-inspired metaheuristic

来源：评论

学校读者我要写书评

暂无评论

A Bibliometric and Social Media Analysis of the Nexus Between Blockchain Technology and Finance 2nd

A Bibliometric and Social Media Analysis of the Nexus Betwee...

引用

2nd International Conference on Intelligent Manufacturing and Robotics, ICIMR 2024

作者： Ayodele, Olamide Emmanuel Ajibade, Temiloluwa Iyanuoluwa Oyebode, Oluwadare Joshua Akintoye, Kayode Akinlekan Ajayi, Babatunde Adedotun Adediran, Anthonia Oluwatosin Ajibade, Samuel-Soma M. Majeed, Anwar P. P. Abdul Luo, Yang Department of Banking and Finance Ekiti State University Ekiti State Ado Ekiti Nigeria Department of Business Management Scholar School System Birmingham United Kingdom Civil and Environmental Engineering Afe Babalola University Ekiti State Ado Ekiti Nigeria Department of Computer Science The Federal Polytechnic Ekiti State Ado Ekiti Nigeria Department of Cyber Security Faculty of Computing and Informatics Ladoke Akintola University of Technology Ogbomoso Nigeria Department of Real Estate Faculty of Built Environment Universiti Malaya KL Kuala Lumpur Malaysia Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Malaysia Department of Computer Engineering Istanbul Ticaret University Istanbul Turkey Suzhou Taicang215400 China

ISBN: (纸本)9789819639489

This study explores Blockchain technology in the global financial industry using trends analysis, bibliometric analysis, and a literature appraisal using Elsevier Scopus data from 2016 to 2023. The Blockchain in Finance (BCF) study produced 185 publications: 53.5% papers, 45.4% conference proceedings, and 1.1% reviews. Analysis of the subject area revealed three important computer Science, engineering, and Decision Sciences articles. However, source title analysis showed that ACM International Conference Proceeding Series, Sustainability Switzerland, and E3S Web of Conferences publish BCF research most often. According to the stakeholders study, Jon M. Truby and Qatar University (Qatar) are the top BCFin researchers and affiliations with 4% and % publications, respectively. China produces the most research on the topic. Due to active support from funding sources like the Chinese National Natural Science Foundation (NNSF), 18 publications have been funded. Co-occurrence of keywords The investigation indicated that BCFin’s top keywords include Blockchain, Finance, and Supply Chain Finance. Three clusters with 4–8 keywords, 132 linkages, and 866 TLS were found via cluster analysis. Keywords classify the clusters as Integrated Business Solutions (Cluster 1), Digital Commerce Infrastructure (Cluster 2), and Decentralized Financial Network (Cluster 3). The findings indicate that BCFin is a dynamic and influential multidisciplinary study field. BCFin has transformed the global financial sector by improving trust, transaction security, and communication. It still struggles with interoperability, system integration, and sustainability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

ACHealthChain blockchain framework for access control and privacy preservation in healthcare

引用

Scientific Reports 2025年第1期15卷 1-25页

作者： Tawfik, Ahmed M. Al-Ahwal, Ayman Eldien, Adly S. Tag Zayed, Hala H. Computer Science Department Faculty of Computers and Artificial Intelligence Benha Egypt Communication and Electronics Department Pyramids-Institute for Engineering and Technology Giza Egypt Electrical Engineering Department Faculty of Engineering at Shoubra Benha Egypt Faculty of Engineering Egypt University of Informatics (EUI) Cairo Egypt

Ensuring privacy and confidentiality in healthcare data management remains a critical challenge. Traditional centralized access control mechanisms are susceptible to security breaches, including unauthorized access, data leakage, and single points of failure, as well as privacy violations such as patient record exposure and improper data sharing. To address these issues, this paper proposes ACHealthChain, a blockchain-based framework leveraging Hyperledger Fabric for decentralized and transparent access control. The framework integrates the InterPlanetary File System (IPFS) for decentralized storage and ensures privacy through Hyperledger Fabric channels. ACHealthChain features PolicyChain for fine-grained access control and revocation, structuring patient health data into separate subchains for EHRs and diagnoses with permissioned access. Additionally, LogChain enhances auditing and accountability. A series of experiments evaluate ACHealthChain’s performance and scalability, considering metrics such as throughput, latency, and resource utilization. Results demonstrate that ACHealthChain improves throughput by 19.7% and reduces latency by 87%, outperforming existing frameworks built on the same platform. The scalability analysis further confirms the framework’s capability to handle increasing workloads within an expanding blockchain network. ACHealthChain presents a promising solution for secure and efficient healthcare data sharing with potential real-world applications. © The Author(s) 2025.

关键词： Access control Blockchain Electronic health records Privacy Security

来源：评论

学校读者我要写书评

暂无评论

Structural Properties of Non-Linear Cellular Automata: Permutivity, Surjectivity and Reversibility

arXiv

引用

arXiv 2025年

作者： Ramdhane, Firas Ben Dennunzio, Alberto Margara, Luciano Menara, Giuliamaria Department of Informatics Systems and Communications University of Milano-Bicocca Italy Department of Computer Science and Engineering University of Bologna Cesena Italy University of Sfax Faculty of Sciences of Sfax Tunisia

This paper explores the algebraic conditions under which a cellular automaton with a non-linear local rule exhibits surjectivity and reversibility. We also analyze the role of permutivity as a key factor influencing these properties and provide conditions that determine whether a non-linear CA is (bi)permutive. Through theoretical results and illustrative examples, we characterize the relationships between these fundamental properties, offering new insights into the dynamical behavior of non-linear CA. Copyright © 2025, The Authors. All rights reserved.

关键词： Linear algebra

来源：评论

学校读者我要写书评

暂无评论

Flicker Visibility With Different Spectra of White Light

引用

IEEE Transactions on Industry Applications 2025年

作者： Kukacka, Leos Hergesel, Jan Necasek, Jakub Bilek, Petr Vik, Michal Stiegler, Robert Pourarab, Morteza Meyer, Jan Drapela, Jiri Technical University of Liberec Faculty of Mechatronics Informatics and Interdisciplinary Studies Institute-of Mechatronics and Computer Engineering Liberec Czech Republic Technical University of Liberec Faculty of Textile Engineering Department of Material Engineering Czech Republic Technische Universität Dresden Institute of Electrical Power Systems and High Voltage Engineering Chair of Electrical Power Supply Dresden01069 Germany Brno University of Technology Faculty of Electrical Engineering and Communications Brno61600 Czech Republic

The standard flickermeter (voltage flickermeter) algorithm commonly used for the evaluation of flicker severity in current electromagnetic compatibility standards originates from the 1980 s. It was developed to mimic irritation of an average human observer by flickering incandescent lamp as a reference light source and optimized to voltage fluctuations caused by arc furnaces. However, the algorithm is questionable as the situation in the grid changed since the 1980 s;many modern devices are being connected to the grid, creating voltage distortion patterns which are not properly recognized by the voltage flickermeter. In addition, incandescent lamps have been largely replaced by discharge lamps and later by LEDs. Transitioning the algorithm from incandescent lamp light to LED light requires detailed revision of every part of the algorithm. This paper is concerned with verifying the frequency weighting function of the average human observer which is one of the bases of the voltage flickermeter, as well as of the derived light flickermeter. Flicker sensitivity of 34 human observers is measured with two different light sources (LED warm and neutral white, incandescent lamp) and compared with the frequency weighting function used in the current specification of the flickermeters in standards. Finally, an optimization of the weighting function is proposed based on the findings. © 1972-2012 IEEE.

关键词： Flickering

来源：评论

学校读者我要写书评

暂无评论

Supervised methods of machine learning for email classification: a literature survey

引用

Systems Science and Control engineering 2025年第1期13卷

作者： AlShaikh, Muath Alrajeh, Yasser Alamri, Sultan Melhem, Suhib Abu-Khadrah, Ahmed Cybersecurity Department College of Engineering Al Ain University Abu Dhabi United Arab Emirates Department of Computer Science College of Computing and Informatics Saudi Electronic University Riyadh Saudi Arabia Department of Electrical Engineering Al-Balqa Applied University Faculty of Engineering As-Salt Jordan

In today’s digital landscape, email is acknowledged as a critical conduit for global data exchanges. With a surge in data volume, malefactors exploit user identities, leading to data misuse. Cybercriminals employ electronic transgressions such as phishing and spam to orchestrate security infractions. Machine learning counters these breaches using myriad techniques, demonstrating significant efficiency in identifying phishing emails. We can divide machine learning into two types: supervised and unsupervised. Supervised learning requires pre-training the model on labelled datasets, amalgamating classification, and regression learning. Notably, supervised methodologies such as support vector machines (SVMs), naive Bayes, decision trees, neural networks, random forests, and deep learning have been exploited for spam filtering. This review delves into issues concerning spam filtering and email classification through supervised machine learning techniques, offering a comprehensive evaluation of strategies, methods, performance indicators, and the benefits and drawbacks of different research. This information allows researchers to assess the efficiency and effectiveness of supervised learning algorithms, laying the foundation for advanced email categorization techniques. © 2025 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： Support vector regression

来源：评论

学校读者我要写书评

暂无评论

Organising unstructured data using Double Net Self-Organising Map (DNSOM) model

引用

Soft Computing 2025年 1-22页

作者： You, Cheng Chun Lim, Seng Poh Lee, Chen Kang Tan, Joi San Lim, Seng Chee Department of Computer Science Faculty of Information and Communication Technology Universiti Tunku Abdul Rahman Jalan University Bandar Barat Perak Kampar 31900 Malaysia Department of Computing Lee Kong Chian Faculty of Engineering and Science Universiti Tunku Abdul Rahman Jalan Sungai Long Bandar Sungai Long Cheras Selangor Kajang 43000 Malaysia School of Computing and Informatics ViTrox College 746 Persiaran Cassia Selatan 3 Batu Kawan Industrial Park Penang Bandar Cassia 14110 Malaysia

Surface reconstruction is the process of representing surfaces using the data obtained from scanning devices. When the data obtained is unstructured during data collection, it can cause problems in presenting the surface due to the lack of connectivity information for the data. It shows that data collection is a crucial task in surface reconstruction. Previous works have proved that Self-Organising Map (SOM) models can be used to organise unstructured data. However, the 2-D SOM model will generate a surface with holes for the closed surfaces. Besides, the 3-D SOM model will generate an incorrect surface due to the connectivity of the internal neurons. In addition, the Cube Kohonen SOM (CKSOM) model is limited to the same grid size. Hence, a SOM model known as Double Net SOM (DNSOM) is proposed via the merging of two 2-D SOMs to overcome the issues. Three data sets (cube, sphere, and talus bone) with different grid sizes are applied to test the models. When the grid size of all the models increases, the surface becomes smoother. The DNSOM contains a lower quantisation error than the 2-D SOM and the lowest topographic error among the other SOM models. It performs faster than the 3-D SOM and CKSOM. It presents the correct closed surface with a smaller number of neurons and different grid sizes. Microsoft Visual Studio 2022 with the C++ programming language is used to develop the models, while GNUPlot is used to visualise the results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Self-organising map Surface reconstruction Unstructured data Visualisation

来源：评论

学校读者我要写书评

暂无评论

The role of moral intention and moral obligation in predicting attitudes toward avoiding AIgiarism: A protection motivation theory perspective

引用

computers in Human Behavior Reports 2025年 18卷

作者： Ali, Ismail Mohamed Arpaci, Ibrahim Faculty of Computing SIMAD University Somalia Department of Software Engineering Faculty of Engineering and Natural Sciences Bandirma Onyedi Eylul University Balikesir Turkey Department of Computer Science and Engineering College of Informatics Korea University Seoul 02841 South Korea

Traditional methods of combating plagiarism have proven ineffective due to the dual use of AI chatbots to plagiarize and avoid detection. Therefore, there is a growing rationale to focus on moral responsibility towards protecting academic integrity. This study investigated the impact of students' moral intentions and moral obligations on their attitudes toward avoiding AI-assisted plagiarism (AIgiarism). Data was collected from a representative group of 263 students and analyzed using “partial least squares structural equation modeling” (PLS-SEM) and “artificial neural network” (ANN). The results revealed that students' moral intentions and obligations positively influenced their attitudes towards avoiding AIgarism. “Protection motivation theory” (PMT) constructs positively predicted students' moral intentions. Moreover, the results of the ANN analysis showed that moral obligation and intention were the most critical factors influencing students’ attitudes toward avoiding plagiarism. This study will help educational institutions develop AI-supported anti-plagiarism solutions in areas such as identification, instilling moral responsibility, and creating an environment of trust and support. © 2025 The Authors

关键词： AIgiarism Moral intention Moral obligation Plagiarism Protection motivation theory

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：