检索结果-内蒙古大学图书馆

Iraqi Journal for Computer Science and Mathematics 2025年第2期6卷 72-81页

作者： AlRababah, Ahmad AbdulQadir Aljahdali, Mohammed Khalid Al jahdali, Abdulrahim Abdulhamid AlGhanmi, Mohammed Saleh Al Barazanchi, Israa Ibraheem Department of Computer Science Faculty of Computing and Information Technology in Rabigh King Abdulaziz University Saudi Arabia College of Engineering University of Warith Al-Anbiyaa Karbala Iraq

Arabic script is exhibited in a cursive style, which is a departure from the norm in many common languages, and the shapes of letters are contingent on their positions within words. The form of the first letter is influenced by the subsequent letter, middle letters are shaped by both preceding and succeeding letters, and the shape of the final letter is determined by the preceding letter. Additionally, certain letters are found to have strikingly similar shapes, making Arabic text recognition a formidable challenge in computer vision. The challenge of detecting and recognizing Arabic handwritten text is addressed in this paper by proposing a novel system that integrates two Deep Learning models without the constraints of a predefined dictionary or language model. Object Detection techniques are employed in the first model to accurately identify lines, words, and punctuation marks, providing a robust foundation for text recognition. In the second model, a powerful recognition system is developed, trained on the IFN/ENIT dataset to predict character sequences from handwritten text images. The architecture is comprised of a convolutional neural network (CNN) with residual connections, followed by a Bi-directional Long Short-Term Memory (BLSTM) layer, and culminates in a fully connected layer. State-of-the-art results in unconstrained Arabic text recognition tasks are achieved by this approach. © 2025 The Author(s).

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

PneuX-Net: An Enhanced Feature Extraction and Transformation Approach for Pneumonia Detection in X-Ray Images

引用

IEEE Access 2025年 13卷 84024-84037页

作者： Munir, Kashif Usama Tanveer, Muhammad Alyamani, Hasan J. Bermak, Amine Ur Rehman, Atiq Khwaja Fareed University of Engineering and Information Technology Institute of Information Technology Rahim Yar Khan 64200 Pakistan King Abdulaziz University Faculty of Computing and Information Technology in Rabigh Department of Information Systems Jeddah 21589 Saudi Arabia Hamad Bin Khalifa University Division of Information and Computing Technology College of Science and Engineering Doha Qatar

Pneumonia is a critical respiratory condition characterized by inflammation in the alveoli, leading to impaired gas exchange and severe respiratory distress. It poses a significant threat to high-risk populations, including neonates, geriatric patients, and immunocompromised individuals. Early and precise detection is crucial to optimizing treatment strategies and reducing morbidity and mortality rates. To address this problem, we propose PneuX-Net, an ensemble-based feature extraction framework that integrates multiple machine learning (ML) models Random Forest (RF), Gaussian Naïve Bayes (GNB) and K-Nearest Centroid (KNC). Random Forest (RF) builds multiple decision trees to identify complex, non-linear patterns within the feature space. Gaussian Naïve Bayes (GNB) utilizes a probabilistic framework based on Bayes’ theorem to manage uncertainty in feature distributions. K-Nearest Centroid (KNC) improves class distinction by clustering feature vectors according to their proximity to centroids. The ensemble methodology harnesses the complementary strengths of these models, improving feature representation and mitigating overfitting, a prevalent issue in white-box models. To validate the effectiveness of PneuX-Net, we conduct extensive experimentation using a 10-fold cross-validation approach. Our results demonstrate that the PneuX-Net+KNC model achieves a remarkable 99.91% accuracy, highlighting its robustness and reliability in pneumonia classification tasks. This ensemble-driven methodology underscores the potential of machine learning in augmenting clinical decision-making by providing an accurate and automated pneumonia detection framework. © 2013 IEEE.

关键词： healthcare AI machine learning medical diagnosis pneumonia detection PneuX-Net

来源：评论

学校读者我要写书评

暂无评论

Federated learning with Blockchain on Denial-of-Service attacks detection and classification of edge IIoT networks using Deep Transfer Learning model

引用

Computers and Electrical Engineering 2025年 124卷

作者： Abdullah, Monir Mengash, Hanan Abdullah Maray, Mohammed Alrslani, Faheed A.F. Alkhudhayr, Hanadi Alghanmi, Nouf Atiahallah Subahi, Alanoud Majdoubi, Jihen Department of Computer Science and Artificial Intelligence College of Computing and Information Technology University of Bisha Bisha67714 Saudi Arabia 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 College of Computer Science King Khalid University Abha Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology Northern Border University Rafha Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Rabigh25732 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Rabigh25732 Saudi Arabia Engineering and Technical Programs Unit Applied College Majmaah University Al-Majmaah11952 Saudi Arabia

With the rapid evolution of Internet of Things (IoT) and artificial intelligence (AI), the industry 4.0 era has arisen. As per the IBM prediction, by the constant spread of 5G technology, the IoT intend to be more extensively utilized in industries. Recently, federated learning (FL) turned out to be significant focus among Industrial IoT (IIoT) scholars. Conversely, numerous devices in IIoT presently hold an issue of low computational power, so these devices can't able to function well while challenging the updating and training method tasks in FL. The latest development of machine learning (ML) and deep learning (DL) approaches will help to reinforce these IDSs. The secrecy behaviour of these databases and extensive advent of combative outbreaks makes it challenging for main institutions to transmit their fragile data. Therefore, the current study designs a Federated Learning on Denial-of-Service Attacks Detection and Classification using Deep Transfer Learning (FLDoSADC-DTL) model for BC-supported IIoT environment. The aim of the presented FLDoSADC-DTL approach is to recognize the presence of DoS attacks in the BC-based IIoT environment. To enable secure communication in the IIoT networks, BC technology is used. To accomplish this, the FLDoSADC-DTL technique performs sand cat swarm algorithm (SCSA) based feature subset selection. For the DoS attack detection process, a stacked auto-encoder (SAE) model is utilized in this study. Finally, the black widow optimization algorithm (BWOA) can be implemented for hyperparameter tuning of the SAE technique. A widespread of experiments were performed to emphasize the higher performance of FLDoSADC-DTL method. The complete experimentation outcomes indicated the enhanced performance of FLDoSADC-DTL approach over other recent methods. © 2025 Elsevier Ltd

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Biomedical Antenna Design Optimization Using Multi-Objective Inverse Neural Networks

引用

Progress in Electromagnetics Research C 2025年 154卷 47-59页

作者： Ben Melouka, Rania Ibtissam Tighilt, Yamina Zebiri, Chemseddine Karaçuha, Kamil Ferhat Hamida, Abdelhak Mashat, Arwa Alaoui, Nail Department of Electronics University of Ferhat Abbas Setif-1 Setif19000 Algeria Department of Electronics Faculty of Engineering University of Ferhat Abbas Setif-1 Setif19000 Algeria Electrical Engineering Department Istanbul Technical University Istanbul Turkey Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University P. O. Box 344 Rabigh21911 Saudi Arabia Laboratoire de Modélisation Simulation et Optimisation des Systèmes Complexes Réels University of Djelfa Djelfa17000 Algeria

A new approach based on an Inverse Artificial Neural Network (IANN) for Multi-Objective Antenna design is presented in this paper. The network sets geometrical variables as the output and uses three antenna performances as inputs. The proposed ANN model is structured into two distinct parts: In the first part, three autonomous branches establish the correlation among the S parameters, gain, specific absorption rate (SAR), and geometric variables of the antenna. The outputs of these branches are used as input in the second part to derive a distinctive solution for these geometric variables. The proposed antenna dimensions are 20 × 24 × 1.58 mm3, and an ultra-wideband of 4.1 GHz to 8.7 GHz is achieved in free space and on human tissue, which coincides with the 5.8 GHz ISM band. Body temperature and specific absorption rate are simulated using the suggested rectangular patch antenna. The resulting optimized antenna holds promising potential for biomedical applications. © 2025, Electromagnetics Academy. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Blockchain based solid waste classification with AI powered tracking and IoT integration

引用

Scientific Reports 2025年第1期15卷 1-15页

作者： Alabdali, Aliaa M. Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University P. O. Box 344 Rabigh 21911 Saudi Arabia

Smart waste management is vital for reducing environmental impact and improving quality of life in smart cities. This study presents an AI-driven waste classification model that integrates IoT and Blockchain technologies. IoT-connected bins transmit data to a central server, which uses blockchain to ensure secure, transparent data storage. AI algorithms, including machine learning (ML) and deep learning (DL), classify waste in real-time, optimizing waste collection and recycling. Blockchain ensures data integrity, while ML and DL models enhance sorting efficiency. The system aims to improve waste management and sustainability through intelligent decision-making and secure data handling. Performance will be assessed using retrieval metrics and visualization tools to evaluate the impact of hybrid ML and DL models on waste detection and classification. © The Author(s) 2025.

关键词： Artificial intelligent Internet of things Smart applications Smart waste management

来源：评论

学校读者我要写书评

暂无评论

An exploratory analysis of longitudinal artificial intelligence for cognitive fatigue detection using neurophysiological based biosignal data

引用

Scientific Reports 2025年第1期15卷 1-17页

作者： Nooh, Sameer Ragab, Mahmoud Aboalela, Rania AL-Ghamdi, Abdullah AL-Malaise Abdulkader, Omar A. Alghamdi, Ghadah Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah 21589 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Rabigh Saudi Arabia Information Systems Department School of Engineering Computing and Design Dar Al-Hekma University 22246 Jeddah Saudi Arabia Faculty of Computer Studies Arab Open University Riyadh Saudi Arabia Department of Computer Science School of Engineering Computing and Design Dar Al-Hekma University Jeddah 22246 Saudi Arabia

Cognitive fatigue is a psychological condition characterized by opinions of fatigue and weakened cognitive functioning owing to constant stress. Cognitive fatigue is a critical condition that can significantly impair attention and performance, among other cognitive abilities. Monitoring this condition in real-world settings is crucial for detecting and managing adequate break periods. Bridging this research gap is significant, as it has substantial implications for developing more effectual and less intrusive wearable devices to track cognitive fatigue. Many models consider intricate biosignals, like electrooculogram (EOG), electroencephalogram (EEG), or detection of basic heart rate inconstancy parameters. Artificial Intelligence (AI)-driven methods aid in handling and categorizing these biosignals, recognizing fatigue-related patterns with higher accuracy. This technique is essential in high-demand surroundings such as education, healthcare, and workplaces or where cognitive fatigue may affect decision-making and performance. Therefore, the study presents an Exploratory Analysis of Longitudinal Artificial Intelligence for Cognitive Fatigue Detection Using Neurophysiological Based Biosignal Data (EALAI-CFDNBD) approach. The main aim of the EALAI-CFDNBD model is to detect cognitive fatigue using neurophysiological-based biosignal data. Primarily, the EALAI-CFDNBD model utilized the linear scaling normalization (LSN) model to ensure that the input features were appropriately scaled for subsequent analysis. Furthermore, the binary olympiad optimization algorithm (BOOA)-based feature selection is utilized to extract the most informative features, reducing the data dimensionality. The graph convolutional autoencoder (GCA) classifier is employed to classify cognitive fatigue detection. Finally, the multi-objective hippopotamus optimization (MOHO) method is utilized for parameter tuning, optimizing the model’s hyperparameters to enhance overall detection accuracy. An exte

关键词： Artificial intelligence Biosignal data Cognitive fatigue detection Electroencephalogram Feature selection Neurophysiological

来源：评论

学校读者我要写书评

暂无评论

A Content-Based Medical Image Retrieval Method Using Relative Difference-Based Similarity Measure

引用

Intelligent Automation & Soft computing 2023年第8期37卷 2355-2370页

作者： Ali Ahmed Alaa Omran Almagrabi Omar MBarukab Department of Computer Science Faculty of Computing and Information TechnologyKing Abdulaziz University–RabighRabigh21589Saudi Arabia Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityJeddah21589Saudi Arabia Department of Information Technology Faculty of Computing and Information TechnologyKing Abdulaziz University-RabighRabigh21589Saudi Arabia

Content-based medical image retrieval(CBMIR)is a technique for retrieving medical images based on automatically derived image *** are many applications of CBMIR,such as teaching,research,diagnosis and electronic patient *** methods are applied to enhance the retrieval performance of CBMIR *** new and effective similarity measure and features fusion methods are two of the most powerful and effective strategies for improving these *** study proposes the relative difference-based similarity measure(RDBSM)for *** new measure was first used in the similarity calculation stage for the CBMIR using an unweighted fusion method of traditional color and texture ***,the study also proposes a weighted fusion method for medical image features extracted using pre-trained convolutional neural networks(CNNs)*** proposed RDBSM has outperformed the standard well-known similarity and distance measures using two popular medical image datasets,Kvasir and PH2,in terms of recall and precision retrieval *** effectiveness and quality of our proposed similarity measure are also proved using a significant test and statistical confidence bound.

关键词： Medical image retrieval feature extraction similarity measure fusion method

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Meta-Classifier of Fuzzy Clustering and Logistic Regression for Diabetes Prediction

引用

Computers, Materials & Continua 2022年第6期71卷 6089-6105页

作者： Altyeb Altaher Taha Sharaf Jameel Malebary Department of Information Technology Faculty of Computing and Information Technology in RabighKing Abdulaziz UniversityJeddahSaudi Arabia

Diabetes is a chronic health condition that impairs the body’s ability to convert food to energy,recognized by persistently high levels of blood *** diabetes can cause many complications,including retinopathy,nephropathy,neuropathy,and other vascular *** learning methods can be very useful for disease identification,prediction,and *** paper proposes a new ensemble learning approach for type 2 diabetes prediction based on a hybrid meta-classifier of fuzzy clustering and logistic *** proposed approach consists of two ***,a baselearner comprising six machine learning algorithms is utilized for predicting ***,a hybrid meta-learner that combines fuzzy clustering and logistic regression is employed to appropriately integrate predictions from the base-learners and provide an accurate prediction of *** hybrid metalearner employs the Fuzzy C-means Clustering(FCM)algorithm to generate highly significant clusters of predictions from *** predictions of base-learners and their fuzzy clusters are then employed as inputs to the Logistic Regression(LR)algorithm,which generates the final diabetes prediction *** were conducted using two publicly available datasets,the Pima Indians Diabetes Database(PIDD)and the Schorling Diabetes Dataset(SDD)to demonstrate the efficacy of the proposed method for predicting *** compared with other models,the proposed approach outperformed them and obtained the highest prediction accuracies of 99.00%and 95.20%using the PIDD and SDD datasets,respectively.

关键词： Ensemble learning fuzzy clustering diabetes prediction machine learning

来源：评论

学校读者我要写书评

暂无评论

Coronavirus Detection Using Two Step-AS Clustering and Ensemble Neural Network Model

引用

Computers, Materials & Continua 2022年第6期71卷 6307-6331页

作者： Ahmed Hamza Osman Department of Information System Faculty of Computing and Information Technology King Abdulaziz University RabighSaudi Arabia

This study presents a model of computer-aided intelligence capable of automatically detecting positive COVID-19 instances for use in regular medical *** proposed model is based on an Ensemble boosting Neural Network architecture and can automatically detect discriminatory features on chestX-ray images through Two Step-As clustering algorithm with rich filter families,abstraction and weight-sharing *** contrast to the generally used transformational learning approach,the proposed model was trained before and after *** compilation procedure divides the datasets samples and categories into numerous sub-samples and subcategories and then assigns new group labels to each new group,with each subject group displayed as a distinct *** retrieved characteristics discriminant cases were used to feed the Multiple Neural Network method,which was then utilised to classify the *** Two Step-AS clustering method has been modified by pre-aggregating the dataset before applying Multiple Neural Network algorithm to detect COVID-19 cases from chest X-ray *** forMultiple Neural Network and Two Step-As clustering algorithms were optimised by utilising Ensemble Bootstrap Aggregating algorithm to reduce the number of hyper parameters they *** testswere carried out using theCOVID-19 public radiology database,and a cross-validationmethod ensured *** proposed classifier with an accuracy of 98.02%percent was found to provide the most efficient outcomes *** result is a lowcost,quick and reliable intelligence tool for detecting COVID-19 infection.

关键词： Two step-AS clustering ensemble learning bootstrap aggregating multiple neural network covid-19 X-ray images

来源：评论

学校读者我要写书评

暂无评论

Pervasive Attentive Neural Network for Intelligent Image Classification Based on N-CDE’s

引用

Computers, Materials & Continua 2024年第4期79卷 1137-1156页

作者： Anas W.Abulfaraj Department of Information Systems Faculty of Computing and Information TechnologyKing Abdulaziz UniversityRabigh21911Saudi Arabia

The utilization of visual attention enhances the performance of image classification *** attentionbased models have demonstrated notable performance,but many of these models exhibit reduced accuracy when confronted with inter-class and intra-class similarities and ***-Controlled Differential Equations(N-CDE’s)and Neural Ordinary Differential Equations(NODE’s)are extensively utilized within this ***’s possesses the capacity to effectively illustrate both inter-class and intra-class similarities and differences with enhanced *** this end,an attentive neural network has been proposed to generate attention maps,which uses two different types of N-CDE’s,one for adopting hidden layers and the other to generate attention *** distinct attention techniques are implemented including time-wise attention,also referred to as bottom N-CDE’s;and element-wise attention,called topN-CDE’***,a trainingmethodology is proposed to guarantee that the training problem is sufficiently *** classification tasks including fine-grained visual classification andmulti-label classification,are utilized to evaluate the *** proposedmethodology is employed on five publicly available datasets,including CUB-200-2011,ImageNet-1K,PASCAL VOC 2007,PASCAL VOC 2012,and MS *** obtained visualizations have demonstrated that N-CDE’s are better appropriate for attention-based activities in comparison to conventional NODE’s.

关键词： Differential equations neural-controlled DE image classification attention maps N-CDE’s

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：