检索结果-内蒙古大学图书馆

Proposed Framework for Detection of Breast Tumors

computers, Materials & Continua 2023年第2期74卷 2927-2944页

作者： Mostafa Elbaz Haitham Elwahsh Ibrahim Mahmoud El-Henawy Department of Computer Science Faculty of Computers and InformaticsKafrelsheikh UniversityKafrelsheikhEgypt Department of Computer Science Faculty of Computers and InformaticsZagazig UniversityZagazigEgypt

computer vision is one of the significant trends in computer *** plays as a vital role in many applications,especially in the medical *** detection and segmentation of different tumors is a big challenge in the medical *** proposed framework uses ultrasound images from Kaggle,applying five diverse models to denoise the images,using the best possible noise-free image as input to the U-Net model for segmentation of the tumor,and then using the Convolution Neural Network(CNN)model to classify whether the tumor is benign,malignant,or *** main challenge faced by the framework in the segmentation is the speckle ***’s is a multiplicative and negative issue in breast ultrasound imaging,because of this noise,the image resolution and contrast become reduced,which affects the diagnostic value of this imaging *** result,speckle noise reduction is very vital for the segmentation *** framework uses five models such as Generative Adversarial Denoising Network(DGAN-Net),Denoising U-Shaped Net(D-U-NET),Batch Renormalization U-Net(Br-UNET),Generative Adversarial Network(GAN),and Nonlocal Neutrosophic ofWiener Filtering(NLNWF)for reducing the speckle noise from the breast ultrasound images then choose the best image according to peak signal to noise ratio(PSNR)for each level of *** five used methods have been compared with classical filters such as Bilateral,Frost,Kuan,and Lee and they proved their efficiency according to PSNR in different levels of *** five diverse models are achieved PSNR results for speckle noise at level(0.1,0.25,0.5,0.75),(33.354,29.415,27.218,24.115),(31.424,28.353,27.246,24.244),(32.243,28.42,27.744,24.893),(31.234,28.212,26.983,23.234)and(33.013,29.491,28.556,25.011)forDGAN,Br-U-NET,D-U-NET,GANand NLNWF *** to the value of PSNR and level of speckle noise,the best image passed for segmentation using U-Net and classification usingCNNto detect tumor *** experiments proved

关键词： Breast tumor speckle noise GAN model U-Net model neutrosophic

来源：评论

学校读者我要写书评

暂无评论

Neutrosophic-Supported Machine Learning Models for Oral Disease Classification

引用

Neutrosophic Sets and Systems 2025年 79卷 657-668页

作者： Elezmazy, Ibrahim M. El-Shahat, Doaa Zagazig University Faculty of Computers and Informatics Computer Science Egypt

This study is presented to investigate the influence of the neutrosophic (NS) domain on the performance of the most common machine learning (ML) models. Specifically, it evaluates the effectiveness of Random Forest (RF), Extra Trees (ET), K-Neighbors (KNN), Gaussian Naive Bayes (GaussianNB), and Decision Tree (DT) classifiers in detecting oral diseases. The NS domain divides any image into three membership components: falsity (F), indeterminacy (I) and truth (T), where T denotes the degree to which each pixel in an image is a member of a particular class or category, F denotes the degree to which the pixel is not a member of that class or category and I denotes the degree of uncertainty or indeterminacy. This domain is herein employed to divide the images into three datasets (T, I, and F). Those three datasets, in addition to the original dataset, one by one, are divided into training and testing datasets with a splitting ratio of 80% and 20%, respectively. Afterwards, the five studied ML models are trained on the training dataset before being assessed on the testing dataset to show their ability to generalize using four performance indicators, such as precision, accuracy, F1-score and recall. According to the experimental results, the I-domain, when compared to the other domains, could considerably increase the performance of four of the five studied ML models, meaning that the NS domain might improve the ML models' performance in categorizing oral diseases more correctly. Among all studied models, the RF classifier with the I-domain has the highest classification accuracy, indicating that it is a strong alternative for oral disease classification. © 2025, University of New Mexico. All rights reserved.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advanced deep learning models based on neutrosophic logic for the analysis of brain tumor medical images

引用

Neutrosophic Sets and Systems 2025年 82卷 924-939页

作者： Atef, Dina El Shahat, Doaa Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt

The categorization of medical photographs poses considerable difficulties owing to noise, uncertainty, and ambiguous information. Conventional deep learning models frequently encounter difficulties in addressing this issue, resulting in diminished diagnostic precision, particularly in the context of low-quality or ambiguous situations. This work presents a hybrid methodology that combines Neutrosophic Set (NS) theory with deep learning models to improve magnetic resonance imaging (MRI) picture classification in uncertain settings. NS theory delineates three domains: True (T), Indeterminate (I) and False (F) to address picture uncertainty and noise, hence enhancing deep learning models' capacity to analyze complex, ambiguous visual data. To assess the methodology, four advanced deep learning models MobileNet, VGG16, DenseNet121 and InceptionV3 were employed, and their efficacy was analyzed on brain tumor medical image datasets. The findings demonstrate that models trained on NS-transformed data, especially DenseNet and inception, produce enhanced results relative to those trained on the original data, attaining notably higher accuracy, precision, and recall. This illustrates that integrating NS theory into deep learning models markedly improves their capacity to categorize uncertain and noisy MRI pictures, offering a reliable method for enhancing diagnostic accuracy in medical imaging. © 2025, University of New Mexico. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

MCI-GAN: a novel GAN with identity blocks inspired by menstrual cycle behavior for missing pixel imputation

引用

Neural Computing and Applications 2025年第16期37卷 9669-9703页

作者： Marie, Hanaa Salem Elbaz, Mostafa Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa35712 Egypt Department of Computer Science Faculty of Computers and Informatics Kafrelsheikh University Kafrelsheikh Egypt

This paper presents MCI-GAN, a novel menstrual cycle imputation (MCI) and generative adversarial network (GAN) framework designed to address the challenge of missing pixel imputation in medical images. Inspired by the intelligent behavior of the endometrial lining during the menstrual cycle, our method introduces four key innovations. First, we propose a novel metaheuristic algorithm that assigns weights to surround pixels based on menstrual cycle behavior, ensuring that the imputed pixels maintain structural integrity and coherence with their neighbors, thus preserving overall image quality. Second, to enhance the learning capability of the GAN, identity blocks are integrated into the network architecture, improving the network’s ability to capture complex spatial relationships and leading to more accurate and consistent imputation of missing pixels. Third, we introduce an adaptive loss function that dynamically adjusts the penalty for pixel discrepancies based on local image context, allowing the model to focus on areas where accurate imputation is most critical and thereby enhancing overall image fidelity. Fourth, the framework incorporates a multi-scale feature extraction mechanism, enabling the GAN to process and combine information at various levels of detail, ensuring that both fine-grained textures and larger structural patterns are accurately captured during the imputation process. The efficacy of MCI-GAN is demonstrated across three diverse medical imaging datasets: mammograms, magnetic resonance imaging (MRI) scans, and skin lesion images. Our results show that the proposed method significantly outperforms existing approaches in terms of accuracy and structural coherence, offering a robust solution for missing pixel imputation in medical imaging. © The Author(s) 2025.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Intelligent Elderly Care: Practicing Ambiguity Neutrosophic Theory for Optimization Contemporary Machine Learning Techniques in Elderly Care

引用

Neutrosophic Sets and Systems 2025年 79卷 436-453页

作者： Ismail, Mahmoud M. Metwaly, Ahmed A. ElKomy, Osama Al-Ghamry, Alaa Mohamed, Mona Decision Support Department Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Department of Information Technology Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Higher Technological Institute 10th of Ramadan City44629 Egypt

One of the biggest challenges facing healthcare systems throughout the world is the aging population. The growing number of elderly citizens in need of specialized care is severely straining the available resources and care methods. It is sometimes difficult for traditional care techniques to address the complex and varied requirements of this expanding population. To fix these challenges, inclusion of contemporary technology is imperative and pragmatic solutions such as Internet of Thing (IoT), cloud computing (CC), and artificial intelligence (AI) techniques such as machine learning (ML), deep learning (DL). Such AI has potential role to make elderly care services (ECSs) to be intelligent ECSs (IECSs) through providing proactivity and earlier detection based on smart IoT sensors. Therefore, this study seeks to achieve two objectives. Firstly, leveraging the capabilities of ML techniques to revolutionize care delivery to be intelligent, optimize resource allocation, and proactive. Secondly, evaluating the robustness of utilized ML techniques in serving study's objectives. Accordingly, utilized ML Techniques consider alternatives (MLTs) that evaluate based on CRiteria Importance Through Inter-criteria Correlation (CRITIC) to obtain weights for criteria which alternatives evaluated based on. These weights are leveraging in Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) to rank MLTs alternatives. For bolstering the evaluation process, we are integrating uncertainty theory of Probabilistic Simplified Neutrosophic Set (PSNS) which effectively captures the inherent uncertainty and imprecision. © 2025, University of New Mexico. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Novel Framework of Segmentation 3D MRI of Brain Tumors

引用

computers, Materials & Continua 2023年第2期74卷 3489-3502页

作者： Ibrahim Mahmoud El-Henawy Mostafa Elbaz Zainab H.Ali Noha Sakr Department of Computer Science Faculty of Computers and InformaticsZagazig UniversityZagazigEgypt Department of Computer Science Faculty of Computers and InformaticsKafrelsheikh UniversityKafrelsheikhEgypt Department of Embedded Network Sys.and Tec. Faculty of Artificial IntelligenceKafrelsheikh UniversityKafrelsheikhEgypt Computers Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansouraEgypt

Medical image segmentation is a crucial process for computer-aided diagnosis and *** image segmentation refers to portioning the images into small,disjointed parts for simplifying the processes of analysis and *** and speckle noise are different types of noise in magnetic resonance imaging(MRI)that affect the accuracy of the segmentation process ***,image enhancement has a significant role in MRI *** paper proposes a novel framework that uses 3D MRI images from Kaggle and applies different diverse models to remove Rician and speckle noise using the best possible noise-free *** proposed techniques consider the values of Peak Signal to Noise Ratio(PSNR)and the level of noise as inputs to the attention-U-Net model for segmentation of the *** framework has been divided into three stages:removing speckle and Rician noise,the segmentation stage,and the feature extraction *** framework presents solutions for each problem at a different stage of the *** the first stage,the framework uses Vibrational Mode Decomposition(VMD)along with Block-matching and 3D filtering(Bm3D)algorithms to remove the ***,the most significant Rician noise-free images are passed to the three different methods:Deep Residual Network(DeRNet),Dilated Convolution Auto-encoder Denoising Network(Di-Conv-AE-Net),andDenoising Generative Adversarial Network(DGAN-Net)for removing the speckle *** Bm3D have achieved PSNR values for levels of noise(0,0.25,0.5,0.75)for reducing the Rician noise by(35.243,32.135,28.214,24.124)and(36.11,31.212,26.215,24.123)*** framework also achieved PSNR values for removing the speckle noise process for each level as follows:(34.146,30.313,28.125,24.001),(33.112,29.103,27.110,24.194),and(32.113,28.017,26.193,23.121)forDeRNet,Di-Conv-AE-Net,and DGAN-Net,*** experiments that have been conducted have proved the efficiency of the proposed framework a

关键词： MRI Rician noise speckle noise segmentation deep learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

Mendel

引用

Mendel 2023年第2期29卷 307-322页

作者： Amin, Reham El-Taweel, Ghada Ali, Ahmed Fouad Tahoun, Mohamed Department of Computer Science Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt

The vast amounts of data, lack of scalability, and low detection rates of traditional intrusion detection technologies make it impossible to keep up with evolving and increasingly sophisticated cyber threats. Therefore, there is an urgent need to detect and stop cyber threats early. Deep Learning has greatly improved intrusion detection due to its ability to self-learn and extract highly accurate features. In this paper, a Hybrid XG Boosted and Long Short-Term Memory algorithm (HXG-BLSTM) is proposed. A comparative analysis is conducted between the computational performance of six established evolutionary computation algorithms and the recently developed bio-inspired metaheuristic algorithm called Zebra Optimisation Algorithm. These algorithms include the Particle Swarm Optimisation Algorithm, the Bio-inspired Algorithms, Bat Optimisation Algorithm, Firefly Optimisation Al-gorithm, and Monarch Butterfly Optimisation Algorithm, as well as the Genetic Algorithm as an Evolutionary Algorithm. The dimensionality curse has been miti-gated by using these metaheuristic methods for feature selection, and the results are compared with the wrapper-based feature selection XGBoost algorithm. The proposed algorithm uses the CSE-CIC-IDS2018 dataset, which contains the lat-est network attacks. XGBoost outperformed the other FS algorithms and was used as the feature selection algorithm. In evaluating the effectiveness of the newly proposed HXGBLSTM, binary and multi-class classifications are considered. When comparing the performance of the proposed HXGBLSTM for cyber threat detection, it outperforms seven innovative deep learning algorithms for binary classification and four of them for multi-class classification. Other evaluation criteria such as recall, F1 score, and precision have been also used for comparison. The results showed that the best accuracy for binary classification is 99.8%, with F1-score of 99.83%, precision of 99.85%, and recall of 99.82%, in extensive and detaile

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Novel Framework for Generating Criminals Images Based on Textual Data Using Identity GANs

引用

computers, Materials & Continua 2023年第7期76卷 383-396页

作者： Mohamed Fathallah Mohamed Sakr Sherif Eletriby Department of Computer Science Faculty of Computers and InformationKafrelsheikh UniversityKafrelsheikhEgypt Department of Computer Science Faculty of Computers and InformationMenoufia UniversityMenoufiaEgypt

Text-to-image generation is a vital task in different fields,such as combating crime and terrorism and quickly arresting *** several years,due to a lack of deep learning and machine learning resources,police officials required artists to draw the face of a *** methods of identifying criminals are inefficient and *** paper presented a new proposed hybrid model for converting the text into the nearest images,then ranking the produced images according to the available *** framework contains two main steps:generation of the image using an Identity Generative Adversarial Network(IGAN)and ranking of the images according to the available data using multi-criteria decision-making based on neutrosophic *** IGAN has the same architecture as the classical Generative Adversarial Networks(GANs),but with different modifications,such as adding a non-linear identity block,smoothing the standard GAN loss function by using a modified loss function and label smoothing,and using mini-batch *** model achieves efficient results in Inception Distance(FID)and inception score(IS)when compared with other architectures of GANs for generating images from *** IGAN achieves 42.16 as FID and 14.96 as *** it comes to ranking the generated images using Neutrosophic,the framework also performs well in the case of missing information and missing data.

关键词： GAN deep learning text-to-image identity GAN

来源：评论

学校读者我要写书评

暂无评论

Deep learning based anomaly detection in real-time video

引用

Multimedia Tools and Applications 2025年第11期84卷 9555-9571页

作者： Elmetwally, Ahmed Eldeeb, Reem Elmougy, Samir Department of Computer Science Faculty of Computers and Information Mansoura University Mansoura35516 Egypt Department of Computer Science Misr Higher Institute for Commerce and Computers Mansoura35511 Egypt

Many security cameras have been put up in places like airports, roads, and banks for the safety of these public places. These cameras make a lot of video data, and most security camera recordings are only ever seen when something strange happens. This means that monitoring has to be done by people, which is time-consuming and often wrong, so automatic ways of monitoring have to be used. In this paper, we propose a system that automatically detects irregular events in videos based on the integration of Inflated 3D Convolution Network (I3D-ResNet50) and deep Multiple Instance Learning (MIL). This system considers both regular and unusual videos as negative and positive packets, respectively. Each video snippet is a case of that packet. An anomaly score is generated for each video snippet using a fully connected Neural Network (NN). After processing videos, we used an I3D-ResNet50 to extract features after applying 10-crop augmentations to the UCF-101 dataset that contains 130 GB of videos with 13 abnormal events such as fighting, stealing, abuse, etc., as well as normal events. Our experimental results show that the AUC is 82.85% with only 10,000 iterations compared with other approaches. This means that our model is better at spotting anomalies in real-time videos. © The Author(s) 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Utilization Prediction Model for Cloud Datacenter

引用

IAENG International Journal of Applied Mathematics 2025年第2期55卷 307-331页

作者： Bliedy, Doaa Khafagy, Mohamed H. Badry, Rasha M. Department of Information Systems Faculty of Computers and Artificial Intelligence Fayoum University Egypt Department of Computer Science Faculty of Computers and Artificial Intelligence Fayoum University Egypt

Much research has been done on predicting resource utilization in the cloud to avoid over- and under-provisioning resources. Most existing systems focus on estimating the utilization of one or two resources at most, including memory, CPU, storage, network, or servers dedicated to cloud applications;they do not consider the correlation between resources. A maximum of one or two machine learning algorithms is employed for prediction purposes. Additionally, traditional prediction methods in the cloud provide a one-dimensional output. Most current solutions predict resources, such as memory and CPU utilization, as a single output. Unfortunately, a one-dimensional output in resource provision and usage cannot capture the relationship between the application requirements of different resources, such as CPU, memory, CPU cores, disk, and network;this results in incomplete and inaccurate information and prediction results. Efficient resource allocation and management require predicting several parameters using multivariate state variables. This study presents a multi-resource utilization prediction model that uses several machine learning approaches, such as support vector regression, random forests, MLP regression, neural networks (NN) using Adam and SGD optimizers, and decision tree regression. The prediction model is based on univariate and multivariate time series. Google cluster trace data is used to evaluate the work. Four experiments are executed on the dataset, seeking to predict the resources for different time series interval periods. The various algorithms’ mean absolute errors (MAE), root mean square error, mean absolute percentage error and R-squared are compared to determine which technique achieves the lowest error rate. The experimental results have shown that the prediction model yields better accuracy than previous research. © (2024), (International Association of Engineers). All rights reserved.

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：