检索结果-内蒙古大学图书馆

3rd International Conference on Creative Communication and Innovative technology, ICCIT 2024

作者： Ismail, Amelia Ritahani Zulhazmi Rafiqi Azhary, Muhammad Zaharin Noor Azwan, Nor Aiman Ismail, Ahsiah Alsaiari, Nisrin Amer International Islamic University Malaysia Kulliyyah of Information Communication Technology Department of Computer Science Kuala Lumpur Malaysia International Islamic University Malaysia Kulliyyah of Information and Communication Technology Department of Computer Science Kuala Lumpur Malaysia Arab Open University Faculty of Computer Studies Saudi Arabia

ISBN: (纸本)9798350367492

Convolutional Autoencoders (CAEs) are neural network architectures specifically designed for image-processing tasks. CAEs also show a great performance in image denoising as it has the capability to efficiently eliminate noise from images while retaining crucial features and structural integrity. However, the effectiveness of CAEs in denoising tasks can be limited by the specific characteristics and complexities present in the images;for example, different intensities and distribution of noise will lead to challenges in achieving consistent and highquality denoising results across diverse datasets like medical images. This paper, therefore, explores the capabilities of CAEs in effectively denoising images corrupted by varying levels of Gaussian noise. The CAE's performance is evaluated under different levels of noise severity using two datasets: PathMNIST and Brain MRI Scan images. Findings indicate that at a low noise level, CAEs achieve impressive results with PathMNIST images, demonstrating high image fidelity. However, Brain MRI Scan images show moderate denoising suggesting opportunities for improvement. As noise severity increases, both datasets experience reduced denoising performance, highlighting the need for enhanced CAE configurations to maintain image quality in critical applications like medical diagnosis. © 2024 IEEE.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

An Efficient Approach Based on Remora Optimization Algorithm and Levy Flight for Intrusion Detection

引用

Intelligent Automation & Soft Computing 2023年第7期37卷 235-254页

作者： Abdullah Mujawib Alashjaee Department of Computer Sciences Faculty of Computing and Information TechnologyNorthern Border UniversityRafha91911Kingdom of Saudi Arabia

With the recent increase in network attacks by threats,malware,and other sources,machine learning techniques have gained special attention for intrusion detection due to their ability to classify hundreds of features into normal system behavior or an attack ***,feature selection is a vital preprocessing stage in machine learning *** paper presents a novel feature selection-based approach,Remora Optimization Algorithm-Levy Flight(ROA-LF),to improve intrusion detection by boosting the ROA performance with *** developed ROA-LF is assessed using several evaluation measures on five publicly available datasets for intrusion detection:Knowledge discovery and data mining tools competition,network security laboratory knowledge discovery and data mining,intrusion detection evaluation dataset,block out traffic network,Canadian institute of cybersecu-rity and three engineering problems:Cantilever beam design,three-bar truss design,and pressure vessel design.A comparative analysis between developed ROA-LF,particle swarm optimization,salp swarm algorithm,snake opti-mizer,and the original ROA methods is also *** results show that the developed ROA-LF is more efficient and superior to other feature selection methods and the three tested engineering problems for intrusion detection.

关键词： Feature selection metaheuristic algorithms intrusion detection Remora optimization algorithm Levy flight

来源：评论

学校读者我要写书评

暂无评论

Contextual use of a Smart Farm Irrigation system using the Internet of Things (IoT)

Contextual use of a Smart Farm Irrigation System using the I...

引用

2024 International Conference on science, Engineering and Business for Driving Sustainable Development Goals, SEB4SDG 2024

作者： Adegoke, Michael Abejide Abogunrin, Abidemi Ogunbiyi, Temitope Elizabeth Ashade, Bidemi Tosin Ogunsola, Kayode Arogundade, Oluwasefunmi LTale Bells University of Technology Department of Computer Science and Information Technology Ota Nigeria Bells University of Technology Department of Biological Sciences Ota Nigeria Federal University of Agriculture Department of Computer Science Abeokuta Nigeria

ISBN: (纸本)9798350358155

A crucial component of agricultural output is water, and its production can be reduced by a shortage, which negatively affects food security. To address this developing issue, irrigation was employed as a form of water management. Various irrigation methods were employed, but there were various limitations to those methods, such as soil and water erosion due to the inability of soil moisture determination. This work focuses on the creation of an irrigation system based on the Internet of Things for sustainable agriculture. The implementation was done using an Arduino microcontroller programmed in the C programming language. The application's data on soil moisture level, valve condition, and remote management of the smart irrigation system were all displayed using an Arduino microcontroller. In Nigeria, the smart irrigation system was tested on three different soil types: clay, loam, and sandy. Data, including the moisture reading and irrigation time, were acquired after inserting the moisture sensor probe into the soil sample. The average time taken to irrigate clay, loamy, and sandy soil at 2kg, 5kg, 8 kg, and 10kg was 10.93s, 15s, 19.75s, 23.25s;9.5s, 12.4s, 17s, 21.5s;8.25s, 11.3s, 14.7s, and 20.2s, respectively. This system helps reduce soil erosion as it monitors and reads soil moisture in real time. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

A Novel Metadata Based Multi-Label Document Classification Technique

引用

computer systems science & Engineering 2023年第8期46卷 2195-2214页

作者： Naseer Ahmed Sajid Munir Ahmad Atta-ur Rahman Gohar Zaman Mohammed Salih Ahmed Nehad Ibrahim Mohammed Imran BAhmed Gomathi Krishnasamy Reem Alzaher Mariam Alkharraa Dania AlKhulaifi Maryam AlQahtani Asiya A.Salam Linah Saraireh Mohammed Gollapalli Rashad Ahmed Barani Institute of Information Technology(BIIT) PMAS Arid Agriculture UniversityRawalpindi46000PunjabPakistan Department of Computer Science(CS) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman Bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Faculty Computer Science and Information Technology Universiti Tun Hussein Onn MalaysiaBatu PahatMalaysia Department of Computer Engineering(CE) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia College of Business Administration Imam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia Department of Computer Information System(CIS) College of Computer Science and Information Technology(CCSIT)Imam Abdulrahman bin Faisal UniversityP.O.Box 1982Dammam31441Saudi Arabia ICS Department King Fahd University of Petroleum and MineralsDhahran31261Saudi Arabia

From the beginning,the process of research and its publication is an ever-growing phenomenon and with the emergence of web technologies,its growth rate is *** a rough estimate,more than thirty thousand research journals have been issuing around four million papers annually on *** engines,indexing services,and digital libraries have been searching for such publications over the ***,getting the most relevant articles against the user requests is yet a *** is mainly because the articles are not appropriately indexed based on the hierarchies of granular subject *** overcome this issue,researchers are striving to investigate new techniques for the classification of the research articles especially,when the complete article text is not available(a case of nonopen access articles).The proposed study aims to investigate the multilabel classification over the available metadata in the best possible way and to assess,“to what extent metadata-based features can perform in contrast to content-based approaches.”In this regard,novel techniques for investigating multilabel classification have been proposed,developed,and evaluated on metadata such as the Title and Keywords of the *** proposed technique has been assessed for two diverse datasets,namely,from the Journal of universal computer science(***)and the benchmark dataset comprises of the articles published by the Association for computing machinery(ACM).The proposed technique yields encouraging results in contrast to the state-ofthe-art techniques in the literature.

关键词： Multilabel classification indexing metadata content/data mining

来源：评论

学校读者我要写书评

暂无评论

Electricity Consumption Classification using Various Machine Learning Models

EAI Endorsed Transactions on Energy Web

引用

EAI Endorsed Transactions on Energy Web 2024年 11卷 1-6页

作者： Paikaray, Bijay Kumar Jena, Swarna Prabha Mondal, Jayanta Van Thuan, Nguyen Tung, Nguyen Trong Mallick, Chandrakant Bhubaneswar India Department of Electronics and Communication Engineering Centurion of University of Technology and Management Odisha India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Faculty of Engineering Technology Hung Vuong University Viet Nam Quality Assurance Dong A University Viet Nam Department of Computer Science & Information Technology GITA Autonomous College Odisha Bhubaneswar India

INTRODUCTION: As population has increased over successive generations, human dependency on electricity has increased to the point where it has become a norm and indispensable, and the idea of living without it has become unthinkable. OBJECTIVES: Machine learning is emerging as a fundamental method for performing tasks autonomously without human intervention. Forecasting electricity consumption is challenging due to the many factors that influence it;embracing modern technology with its heavy focus on machine learning and artificial intelligence is a potential solution. METHODS: This study employs various machine learning algorithms to forecast power usage and determine which method performs best in predicting the dataset based on different variables. RESULTS: Eight models were tested, including Linear Regression, DT Classifier, RF Classifier, KNN, DT Regression, SVM, Logistic Regression, and GNB Classifier. The Decision Tree model had the greatest accuracy of 98.3%. CONCLUSION: The Decision Tree model’s accuracy can facilitate efficient use of electricity, leading to both conservation of electricity and cost savings, and be a guiding light in future planning. Copyright © 2024 Paikaray, B.K. et al., licensed to EAI. This open-access article is distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transforming, and building upon the material in any medium so long as the original work is properly cited.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network

引用

Multimedia Tools and Applications 2024年 1-22页

作者： Alrowais, Fadwa Jamjoom, Arwa A. Karamti, Hanen Umer, Muhammad Alsubai, Shtwai Abate, Andrea F. Ashraf, Imran Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Computer Science The Islamia University of Bahawalpur Bahawalpur Pakistan Department of Computer Science College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University P.O. Box 151 Al-Kharj11942 Saudi Arabia Department of Computer Science University of Salerno Fisciano84084 Italy Department of Information and Communication Engineering Yeungnam University Gyeongsan38541 Korea Republic of

Cerebral stroke indicates a neurological impairment caused by a localized injury to the central nervous system resulting from a diminished blood supply to the brain. Today, stroke stands as a global menace linked to the premature mortality of millions of people globally. Consequently, it is crucial to simulate how different risk factors impact the incidence of strokes and artificial intelligence is emerging as a suitable tool for achieving this goal. This study aims to construct dependable learning prediction models for stroke illness. The proposed approach can handle the inherent difficulty posed by a significant imbalance in classes, where the number of stroke patients is notably smaller compared to the healthy class. The study also provides a model based on an adaptive neuro-fuzzy inference system logic and convolutional neural networks (CNN) for accurate stroke prediction. An adaptive neuro-fuzzy inference system logic approach is adopted as it incorporates the capabilities of artificial intelligence and fuzzy inference, thereby having the potential to yield superior outcomes. The efficacy of the suggested method is extensively analyzed involving machine and deep learning classifiers and considering metrics relevant to encompass both the capacity for generalization and the accuracy in predicting. The proposed fuzzy-CNN model outperforms with the most considerable accuracy of 98.97% when using the original dataset, resampled dataset, and data imputation. K-fold cross-validation also shows superior results with an average accuracy of 99.6% for five folds. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Clustering Approaches in Cloud Environments

International Journal of Interactive Mobile Technologies

引用

International Journal of Interactive Mobile Technologies 2023年第19期17卷 70-94页

作者： Al-Ghuwairi, Abdel-Rahman Al-Fraihat, Dimah Sharrab, Yousef Kreishan, Yazeed Alsarhan, Ayoub Idhaim, Hasan Qahmash, Ayman Department of Software Engineering Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Software Engineering Faculty of Information Technology Isra University Amman Jordan Department of Data Science and Artificial Intelligence Faculty of Information Technology Isra University Amman Jordan Department of Information Technology Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Information Systems Faculty of Prince Al-Hussein Bin Abdallah II for Information Technology The Hashemite University Zarqa Jordan Department of Information Systems Computer Science College King Khalid University Abha Saudi Arabia

This study focuses on the challenge of developing abstract models to differentiate various cloud resources. It explores the advancements in cloud products that offer specialized services to meet specific external needs. The study proposes a new approach to request processing in clusters, improving downtime, load distribution, and overall performance. A comparison of three clustering approaches is conducted: local single cluster, local multiple clusters, and multiple cloud clusters. Performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness are evaluated through experiments with 50 requests. All three approaches achieve a 100% success rate, but processing times vary. The local single cluster has the longest duration, while the local multiple clusters and multiple cloud clusters perform better and offer faster processing, scalability, fault tolerance, and availability. From a cost perspective, the local single cluster and local multiple clusters incur capital and operational expenses, while the multiple cloud clusters follow a pay-as-you-go model. Overall, the local multiple clusters and multiple cloud clusters outperform the local single cluster in terms of performance, scalability, fault tolerance, resource allocation, availability, and cost-effectiveness. These findings provide valuable insights for selecting appropriate clustering strategies in cloud environments. © 2023 by the authors of this article. Published under CC-BY.

关键词： Fault tolerance

来源：评论

学校读者我要写书评

暂无评论

A Comparative Analysis on Three Duplication Elements in Copy-Move Forgery using PatchMatch-Based Detection Method 8

A Comparative Analysis on Three Duplication Elements in Copy...

引用

8th IEEE International Conference on Software Engineering and computer systems, ICSECS 2023

作者： Nor Azaimi, Nur Izzati Abd Warif, Nor Bakiah Ismail, Nor-Syahidatul N Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia Centre for Information Security Research Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia Universiti Malaysia Pahang Al-Sultan Abdullah Faculty of Computing Department of Computer System and Networking Pekan Pahang Malaysia

ISBN: (纸本)9798350310931

Image forgery is the alteration of a digital image to hide some of the important and useful information. Copy-move forgery (CMF) is one of the most difficult to detect because the copied part of the image has the same characteristics as the original image. Most of the existing datasets only highlight additional attacks in the copied part. Since there are no categories of duplication elements in the datasets, this research analyzed three categories of duplication elements in CMF which are animals, food and non-living things using DEFACTO and CoMo3Dataset. The analysis is performed on PatchMatch-based detection method and the results show that the method able to maintain at least 83% for all duplication elements in both DEFACTO and CoMo3Dataset. Furthermore, the method is able to detect a minimum 92% score for the food category in both datasets. © 2023 IEEE.

关键词： Copy-Move forgery DEFACTO duplication regions PatchMatch

来源：评论

学校读者我要写书评

暂无评论

CancerBot: A Retrieval-Augmented Generation based Cancer Chatbot Using Large Language Models 18

CancerBot: A Retrieval-Augmented Generation based Cancer Cha...

引用

18th International Conference on Open Source systems and Technologies, ICOSST 2024

作者： Azam, Ayesha Naz, Zubaira Khan, Muhammad Usman Ghani Al-Khwarizmi Institute of Computer Science University of Engineering and Technology Lahore Pakistan Information Technology University Lahore Pakistan University of Engineering and Technology Department of Computer Science Lahore Pakistan

ISBN: (纸本)9798331508692

Cancer is the second leading cause of death globally, highlighting the urgent need for innovative solutions to support patients and healthcare providers. Remote and digital cancer care interventions, such as chatbots, are more relevant than ever, offering timely information and personalized assistance. With the rise of conversational AI, chatbots have emerged as a potential solution to bridge this gap, offering 24/7 assistance and personalized responses. This paper introduces CancerBot, a Retrieval-Augmented Generation (RAG) system designed to address the need for reliable, contextually relevant cancer-related information. Built on top of a large language model LLaMA-2, and integrated with a vector database, CancerBot retrieves relevant medical literature to generate accurate responses, minimizing the risk of hallucinations. Through synthetic testing and evaluation using metrics such as faithfulness, context relevancy, and response relevancy, our results demonstrate that the RAG-based CancerBot significantly outperforms the standard LLaMA-2 model in addressing cancer-specific queries. This advancement showcases the potential of RAG systems to improve patient care by providing reliable, context-driven information that enhances patient engagement and healthcare decision-making. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Bitcoin Price Prediction Using Deep Learning Models 4

Bitcoin Price Prediction Using Deep Learning Models

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Hajare, Rasika Puri, Chetan Gote, Pradnyawant M. Faculty of Engineering and Technology Department of Computer Science and Design Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

Forecasting the price of bitcoins is significant in contemporary research, given the fact that the digital currency is relatively unpredictable and highly integrated in global securities markets. This paper compares the use of three deep learning models, namely recurrent neural networks (RNN), gated recurrent unit (GRU), and a convolutional neural network-long short-term memory (CNN-LSTM) for Bitcoin price prediction. Historical Bitcoin price data is used in the dataset, and every one of the models is trained and tested based on its performance to predict future prices based on past data. The proposed models include the RNN and GRU, which incorporate sequential dependency mappings to learn complex sequences, and the CNN-LSTM structures combine convolution layers for feature extraction and LSTM layers for sequencing. Different models' competency is discussed using the averaged Mean Squared Error (MSE) and graphs of the model's prediction against actual prices. The experimental results reveal that the proposed CNN-LSTM model has better prediction accuracy than RNN and GRU in time-series forecasting tasks, indicating that more complex architecture hybrid models might provide better forecasting performance. In analyzing and analyzing cryptocurrency price dynamics, this investigation gives information about the opportunities and challenges of these models to enhance future research. © 2025 IEEE.

关键词： Prediction models

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：