检索结果-内蒙古大学图书馆

23rd International Conference on Machine Learning and Cybernetics, ICMLC 2024

作者： Pichit, Sitthikun Chen, Shyi-Ming National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Asia University Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798331528041

This paper proposes a new score function (SF) of interval-valued intuitionistic fuzzy values (IVIFVs) in order to overcome the shortcomings of the existing SFs of IVIFVs, which are not be able to distinguish the ranking orders (ROs) of alternatives in some situations. We design the proposed SF of IVIFVs based on the properties that the larger the membership degrees of IVIFVs results in the larger the score values (SCVs) of IVIFVs;the smaller the non-membership degrees of IVIFVs results in the larger the SCVs of IVIFVs. The experimental result shows that the proposed SF of IVIFVs outperforms the existing SFs of IVIFVs. © 2024 IEEE.

关键词： Fuzzy models

来源：评论

学校读者我要写书评

暂无评论

Feature Selection in Socio-Economic Analysis: A Multi-Method Approach for Accurate Predictive Outcomes

引用

International Journal of Crowd science 2025年第1期9卷 64-78页

作者： Al-Qerem, Ahmad Ali, Ali Mohd Jebreen, Issam Nabot, Ahmad Rajab, Mohammed Alauthman, Mohammad Aldweesh, Amjad Aburub, Faisal Alangari, Someah Alzgol, Musab Computer Science Department Faculty of Information Technology Zarqa University Zarqa13110 Jordan Communications and Computer Engineering Department Faculty of Engineering Al-Ahliyya Amman University Amman19328 Jordan University Headquarter University of Anbar Ramadi31001 Iraq Department of Information Security University of Petra Amman11196 Jordan College of Computing and Information Technology Shaqra University Shaqra11911 Saudi Arabia Department of Business Intelligence and Data Analytics University of Petra Amman11196 Jordan Computer Information Systems Department Faculty of Information Technology Isra University Amman11622 Jordan

Feature selection is a cornerstone in advancing the accuracy and efficiency of predictive models, particularly in nuanced domains like socio-economic analysis. This study explores nine distinct feature selection methods, utilizing a heart disease dataset as a representative model for complex socio-economic systems. Our findings identified four universally recognized features as critical across all selection methods. However, the divergence in significance attributed to other features by different methods underscores the inherent variability in selection techniques. When the top four features were incorporated into twelve classification models, a noticeable surge in predictive accuracy was observed, emphasizing their foundational role in enhancing model outcomes. The variations among methods stress the need for a methodical and discerning approach to feature selection, especially in data-rich socio-economic landscapes. As we venture further into an era defined by data-driven decision-making, rigour and precision in feature selection become indispensable. Future research should extend this approach to broader datasets, ensuring the robustness and adaptability of our findings. © The author(s) 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A privacy-preserving deep learning framework for highly authenticated blockchain secure storage system

引用

Multimedia Tools and Applications 2024年第36期83卷 84299-84329页

作者： Haque, Sheikh Moeen Ul Sofi, Shabir Ahamd Sholla, Sahil Department of Information Technology NIT Srinagar Jammu and Kashmir Hazratbal190006 India Department of Computer Science and Engineering Islamic University of Science and Technology Jammu and Kashmir Awantipora192122 India

To ensure the privacy, integrity, and security of the user data and to prevent the unauthorized access of data by illegal users in the blockchain storage system is significant. Blockchain networks are widely used for the authentication of data between the data user and the data owner. However, blockchain networks are vulnerable to potential privacy risks and security issues concerned with the data transfer and the logging of data transactions. To overcome these challenges and enhance the security associated with blockchain storage systems, this research develops a highly authenticated secure blockchain storage system utilizing a rider search optimized deep Convolution Neural Network(CNN) model. The architecture integrates the Ethereum blockchain, Interplanetary File System (IPFS), data users, and owners, in which the Smart contracts eliminate intermediaries, bolstering user-owner interactions. In tandem, blockchain ensures immutable transaction records, and merging IPFS with blockchain enables off-chain, distributed storage of data, with hash records on the blockchain. The research accomplishes privacy preservation through six-phase network development: system establishment, registration, encryption, token generation, testing, and decryption. Parameters for secure transactions are initialized, user registration provides genuine user transaction credentials, and encryption guarantees data security, employing optimized Elliptic Curve Cryptography (ECC). Further, the optimized ECC algorithm is developed utilizing a novel rider search optimization that utilizes search and rescue characteristics of human, and rider characteristics for determining the shorter key lengths. Token generation involves issuing digital tokens on a blockchain platform, followed by testing using a deep CNN classifier to detect anomalies and prevent unauthorized data access during the test phase. The decryption of data is conducted for registered users. The developed rider search optimized deep CN

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

DFU_XAI: A Deep Learning-Based Approach to Diabetic Foot Ulcer Detection Using Feature Explainability

引用

Biomedical Materials and Devices 2024年第2期2卷 1225-1245页

作者： Biswas, Shuvo Mostafiz, Rafid Paul, Bikash Kumar Uddin, Khandaker Mohammad Mohi Hadi, Md. Abdul Khanom, Fahmida Department of Information and Communication Technology Mawlana Bhashani Science and Technology University Institute of Information Technology Noakhali Science and Technology University Department of Software Engineering Daffodil International University Department of Computer Science and Engineering Dhaka International University Department of Computer Science: Information Technology University of Nebraska Omaha Department of Mathematics American International University – Bangladesh

Diabetic foot ulcer (DFU) is a potentially fatal complication of diabetes. Traditional techniques of DFU analysis and therapy are more time-consuming and costly. Artificial intelligence (AI), particularly deep neural networks, has demonstrated remarkable effectiveness in medical applications. Despite this, the lack of explainability of deep learning models is currently viewed as a key hurdle to using these approaches in actual clinical settings. In this research, we present the DFU_XAI framework for assessing the interpretability of explainable-driven deep learning (DL) models. DFU_XAI evaluates five DL models (Xception, DenseNet121, ResNet50, InceptionV3, and MobileNetV2) to establish a transparent DL framework using three state-of-the-art explanation methods: Shapley additive explanation (SHAP), local interpretable model-agnostic explanations (LIME), and gradient-weighted class activation mapping (Grad-CAM). ResNet50 outperformed the other four models with remarkable results: 98.75% accuracy, 99.2% precision, 97.6% recall, 98.4% F1-score, and 98.5% AUC. For the most part, it can locate diabetic foot ulcers precisely on a diabetic foot and discriminate between diabetic foot ulcers and healthy feet in the DFU dataset. A heat map will indicate the precise location of the ulcer that needs care. © The Author(s), under exclusive licence to Springer science+Business Media, LLC 2024.

关键词： Convolutional neural networks Deep learning Diabetic foot ulcers Explainable AI

来源：评论

学校读者我要写书评

暂无评论

Enhancing Anomaly Detection in Agriculture by Considering the Impact of Concept Drift: An Exploratory Study Using Digital Replica 23

Enhancing Anomaly Detection in Agriculture by Considering th...

引用

5th World Symposium on Software Engineering, WSSE 2023

作者： Huo, Dongyang Malik, Asad Waqar Ravana, Sri Devi Ur Rahman, Anis Ahmedy, Ismail Department of Information Systems Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia Islamabad Pakistan Department of Computer Systems and Technology Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798400708053

The advent of precision agriculture is disrupting traditional farming practices, leading to a significant increase in the data flow. However, current anomaly detection methods overlook the impact of concept drift. The phenomenon of concept drift refers to the changes in the underlying distribution of the data over time, which can result in unexpected and misleading results. As such, it is essential to consider the impact of theconcept drift in the context of anomaly detection in precision agriculture. This study uses a digital replica of an agricultural system equipped with intelligent agents to examine the system dynamics and the temporal variability of end-to-end data flow in precision agriculture. It highlights the need for robust methods that can effectively address the challenges posed by concept drift and systems’ dynamism enabling accurate and reliable anomaly detection in the IoT farming system. © 2023 Copyright held by the owner/author(s).

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

Explainable ensemble deep learning-based model for brain tumor detection and classification

引用

Neural Computing and Applications 2025年第3期37卷 1289-1306页

作者： Hosny, Khalid M. Mohammed, Mahmoud A. Salama, Rania A. Elshewey, Ahmed M. Department of Information Technology Faculty of Computers and Information Zagazig University P.O.BOX 44519 Zagazig Egypt Department of Computer Science Faculty of Computers and Information Suez University P.O.BOX 43221 Suez Egypt Department of Information Technology Faculty of Computers and Information Suez University P.O.BOX 43221 Suez Egypt

Brain tumors are very dangerous as they cause death. A lot of people die every year because of brain tumors. Therefore, accurate classification and detection in the early stages can help in recovery. Various deep learning techniques have achieved good results in brain tumor classification. The traditional deep learning methods and training the neural network from scratch are time-consuming and can last for weeks of training. Therefore, in this work, we proposed an ensemble approach depending on transfer learning that utilizes pre-trained models of DenseNet121 and InceptionV3 to detect three forms of brain tumors: meningioma, glioma, and pituitary. While developing the ensemble model, some changes were made to the architecture of pre-trained models by replacing their classifiers (fully connected and SoftMax layers) with a new classifier to adopt the recent task. In addition, gradient-weighted class activation maps (Grad-CAM) are an explainable model to verify results and achieve high confidence. The suggested model was validated using a publicly available dataset and achieved 99.02% accuracy, 98.75% precision, 98.98% recall, and a 98.86% F1 score. The suggested approach outperformed others in detecting and classifying brain tumor MRI data, and verifying results using the explainable model achieved a high degree of trust. © The Author(s) 2024.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Improved Dynamic Johnson Sequencing Algorithm(DJS)in Cloud Computing Environment for Efficient Resource Scheduling for Distributed Overloading

引用

Journal of Systems science and Systems Engineering 2024年第4期33卷 391-424页

作者： Anurag Sinha Pallab Banerjee Sharmistha Roy Nitasha Rathore Narendra Pratap Singh Mueen Uddin Maha Abdelhaq Raed Alsaqour Department of Computer Science Engineering ICFAI Tech SchoolICFAI UniversityJharkhandRanchi834004India Department of Computer Science Engineering Amity UniversityJharkhandRanchi835303India Department of Computing and Information Technology Usha Martin UniversityRanchi835103India Department of Information Technology Bharti Vidyapeeth’s College of EngineeringPaschim ViharNew DelhiIndia Department of CSE Delhi UniversityNew DelhiIndia College of Computing and Information Technology University of Doha for Science and TechnologyDoha24449Qatar Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdurrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Information Technology College of Computing and InformaticsSaudi Electronic University93499RiyadhSaudi Arabia

This study introduces an innovative approach to optimize cloud computing job distribution using the Improved Dynamic Johnson Sequencing Algorithm(DJS).Emphasizing on-demand resource sharing,typical to Cloud Service Providers(CSPs),the research focuses on minimizing job completion delays through efficient task *** Johnson’s rule from operations research,the study addresses the challenge of resource availability post-task *** advocates for queuing models with multiple servers and finite capacity to improve job scheduling models,subsequently reducing wait times and queue *** Dynamic Johnson Sequencing Algorithm and the M/M/c/K queuing model are applied to optimize task sequences,showcasing their efficacy through comparative *** research evaluates the impact of makespan calculation on data file transfer times and assesses vital performance indicators,ultimately positioning the proposed technique as superior to existing approaches,offering a robust framework for enhanced task scheduling and resource allocation in cloud computing.

关键词： First come first served(FCFS)scheduling round robin task scheduling queuing model Johnson scheduling algorithm

来源：评论

学校读者我要写书评

暂无评论

Advances in Machine Learning-driven Quality Control within ERP Systems: A Comprehensive Survey 11

Advances in Machine Learning-driven Quality Control within E...

引用

11th IEEE International Conference on Intelligent Computing and information Systems, ICICIS 2023

作者： Qaddoori Aldoori, Shaymaa Ahmed Mabrouk, Mohamed Mahmoud, Abeer M. Cairo Egypt Faculty of Computer and Information Science Computer Science Department Cairo Egypt

ISBN: (纸本)9798350322101

Enterprise Resource Planning (ERP) systems have become essential instruments in contemporary corporate operations, offering significant benefits in process optimization and efficient data management. The assurance of quality and dependability in these intricate systems is of utmost significance given that errors or inconsistencies might yield extensive ramifications. This study highlights the importance of quality control within ERP systems, emphasizing the crucial role of accuracy and integrity in facilitating efficient decision-making processes and optimizing operational efficiency. This analysis explores the increasing importance of upholding ERP quality as firms become increasingly dependent on these systems to traverse intricate business environments. In addition, this study explores the capacity of machine learning to enhance quality control procedures. Machine learning techniques, owing to their ability to examine large datasets and identify subtle patterns, provide a transformative shift away from the traditional rule-based approaches. Machine learning enhances the capacity to anticipate problems, reduce interruptions, and maintain consistent operational performance by employing real-time anomaly detection, predictive modeling, and adaptation to shifting ERP settings. This study explores the complex confluence of technology and business imperatives, highlighting the transformative impact of the collaboration between machine learning and quality control on the evolution of ERP systems. © 2023 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Appearance and motion-based unusual crowd events detection using multiple moving objects

引用

Multimedia Tools and Applications 2024年第42期83卷 90177-90189页

作者： Babu, K. Atlas, L. Godlin Sreeji, S. Arjun, K.P. Rasmi, A. Senthilvel, P. Gururama Computational Intelligence SRM Institute of Science & Technology Chengalpet Kattankulathur603203 India Department of Computer Science and Engineering Bharath Institute of Higher Education and Research Chennai India Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Department of Computer Science and Engineering Gitam University Karnataka Bengaluru India Information Science and Engineering RRIT Bangalore India Saveetha University Chennai602 105 India

Unusual crowd analysis is an important problem in surveillance video due to their features cannot be extracted efficiently on the crowd scenes. To overcome this challenge, this paper introduced the appearance and motion based unusual events detection method by using multiple moving objects. This method includes appearance and motion based computation, and moving objects trajectory analysis. By using these all techniques, the unusual crowds and their activities can be obtained by analyzing moving objects size and the distance among multiple moving objects. Two benchmark datasets such as PETS 2009 and UMN are used for the experimental results. Also, several existing algorithms are compared with the proposed method to evaluate the effectiveness of the proposed work. The comparative analysis results proved that the proposed method achieved best accuracy for unusual crowd events. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： And trajectory analysis Appearance based analysis Distance based analysis Unusual crowd events detection

来源：评论

学校读者我要写书评

暂无评论

Decentralizing Social Data: A Blockchain-Based Approach to Transparent and Trustworthy Social Networks 5

Decentralizing Social Data: A Blockchain-Based Approach to T...

引用

5th IEEE Middle East and North Africa COMMunications Conference, MENACOMM 2025

作者： El Ghor, Hussein Nakhal, Bilal Nasr, Sara Daher, Mohamad MUBS University ARCAS Research Center Faculty of Arts and Sciences Beirut Lebanon Beirut Arab University Mathematics and Computer Science Department Beirut Lebanon Lebanese University Faculty of Science Department of Computer Science Beirut Lebanon AUT University Department of Computer Science and Information Technology Beirut Lebanon

ISBN: (纸本)9798331519957

The rise of online social network (OSN) platforms has revealed pivotal issues with regards to data transparency and the concerns on the user's consent. Users are barely aware of how their data is used. To this end, this paper investigates the notion of applying blockchain technology for decentralizing social data, thus bringing more privacy and trust to the abstract concept of OSN platforms. We propose a Blockchain-Based Distributed Social Network System (B2DSN) that uses Hyperledger Fabric and InterPlanetary File System (IPFS) to secure sovereignty rights of data and offer greater control to users' data subjects. Hyperledger fabric is used to collect friends and data that are analyzed from social networks. We integrate consensus and verification methods directly within topic-based communities to provide trustworthiness of OSN platforms and eliminate the dissemination of rumors, and fake news. The feasibility of B2DSN is proved based on the integration of decentralized overlay network data flow, data sovereignty and verification and topic-based communities. The experimental simulation for data integrity demonstrates that the B2DSN model based on blockchain is feasible in securing and verifying the authenticity of social data even for large-scale OSNs. © 2025 IEEE.

关键词： Blockchain hyperledger fabric IPFS privacy Social network transparency

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：