检索结果-内蒙古大学图书馆

Neutrosophic-Supported Machine Learning Models for Oral Disease Classification

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

Synthesis of batik motifs using a diffusion - generative adversarial network

引用

Multimedia Tools and Applications 2025年第7期84卷 3407-3438页

作者： Octadion, One Yudistira, Novanto Kurnianingtyas, Diva Informatics Engineering Faculty of Computer Science Universitas Brawijaya Malang Indonesia

This paper presents a novel approach for generating intricate Batik motifs using a modified Diffusion-Generative Adversarial Network (Diffusion-GAN) augmented with StyleGAN2-Ada. Motivated by the rich cultural heritage of Indonesian Batik, our research addresses the challenge of synthesizing high-quality, diverse patterns that capture the artistry and complexity of traditional designs. Traditional generative models often struggle with stability and fidelity in artistic synthesis. We integrate StyleGAN2-Ada and Diffusion techniques to overcome these limitations, optimizing model architecture and employing a curated Batik dataset. Evaluation metrics including Frechet Inception Distance (FID), Kernel Inception Distance (KID), precision, recall, and non-redundancy assess the quality and diversity of generated motifs. Our results demonstrate significant advancements in the realism and authenticity of synthesized Batik patterns, leveraging Diffusion-GAN to enhance detail and artistic fidelity. By exploring the intersection of deep learning and cultural art, this research contributes to the preservation and evolution of Batik as a cultural artifact. References to prior works underscore the evolution of Artificial Intelligence (AI) in cultural heritage preservation, highlighting the potential of modern AI techniques to innovate within traditional art forms like Batik. In summary, this study showcases the efficacy of the proposed Diffusion-GAN methodology in synthesizing original and convincing Batik motifs, while identifying opportunities for further refinement and complexity in motif synthesis. The dataset and code can be accessed here: https://***/octadion/diffusion-stylegan2-ada-pytorch © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Proposed Framework for Detection of Breast Tumors

引用

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

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

Enhancing demand forecasting through combination of anomaly detection and continuous improvement

引用

Soft Computing 2025年第2期29卷 1243-1258页

作者： Jahani, Meysam Zojaji, Zahra Raji, Fatemeh Faculty of Computer Engineering University of Isfahan Isfahan Iran School of Computer Science and Informatics De Montfort University Leicester United Kingdom

Demand forecasting has emerged as a crucial element in supply chain management. It is essential to identify anomalous data and continuously improve the forecasting model with new data. However, existing literature fails to comprehensively cover both aspects of anomaly detection and continuous improvement in demand forecasting. This study proposes an enhanced model to improve accuracy in the demand forecasting. The proposed model introduces a novel data handling method that incorporates an anomaly detection autoencoder, improved with anomaly correction mechanisms. The data handling approach simultaneously detects data anomalies, distinguishes between expected and unexpected anomalies, and corrects anomalous data, ensuring cleaner input for demand forecasting. Then, the proposed model employs a long short-term memory architecture for demand forecasting, enhanced with a continuous improvement method. Thus, the model not only forecasts demand but also retrains the model when the anomaly data surpasses the predetermined threshold, thereby improving the accuracy of forecasting. The results show that the proposed model outperforms other models in detecting data anomalies, achieving an average precision-recall of 0.922, a receiver operating characteristic value of 0.739, and a significance level of less than 0.05. Finally, the model exhibits superior performance in demand forecasting, with average mean squared error, root mean squared error, and mean absolute error values of 33.167, 4.347, and 1.509, respectively, all with a significance level of less than 0.05. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Demand response

来源：评论

学校读者我要写书评

暂无评论

Advanced Cross-Language Clone Detection Using Modified AST and Graph Neural Network

Advanced Cross-Language Clone Detection Using Modified AST a...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Swilam, Zeina Hamdy, Abeer Pester, Andreas Faculty of Informatics & Computer Science Cairo Egypt

ISBN: (纸本)9798350367560

Cross-language code clone detection is a critical issue in software engineering, driven by the increasing use of multi-language systems within large-scale projects. Code clones-fragments of code with similar functionality but varied implementations-complicate software maintenance, elevating the risk of defects and increasing the cost of debugging and refactoring. Traditional Abstract Syntax Trees (ASTs) are widely used for clone detection but are often insufficient for cross-language scenarios due to their limitations in capturing comprehensive structural and semantic information. To overcome these limitations, this research introduces a modified AST, enhanced by the inclusion of Condition-Type Edges, which effectively model logical dependencies within control structures. This novel extension offers a deeper semantic understanding of the code's decision-making processes, addressing the shortcomings of conventional ASTs that focus solely on syntactic relationships. By integrating this modified AST with Graph Neural Networks (GNNs), our approach learns robust feature representations that capture semantic and structural variations across programming languages. Experimental evaluations on Java-Python code pairs show a notable improvement in detection accuracy, achieving a recall of 0.96, precision of 0.88, and an F1 score of 0.92, outperforming state-of-the-art techniques. These findings underscore the value of Condition-Type Edges in enhancing AST representations, providing a more reliable framework for cross-language code clone detection, and ultimately improving software quality and maintenance in multi-language environments. © 2024 IEEE.

关键词： Program debugging

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 1-35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

UNRAVELING THE EFFECTIVENESS OF THE K-NN ALGORITHM FOR IMBALANCED DATA IN RESEARCH TOPIC RECOMMENDATIONS

引用

Xinan Jiaotong Daxue Xuebao/Journal of Southwest Jiaotong University 2024年第1期59卷 271-282页

作者： Muludi, Kurnia Aisyah, Nonik Nama, Gigih Forda Lumbanraja, Favorisen R. Informatics & Business Institute Darmajaya Bandar Lampung35142 Indonesia Computer Science Department Faculty of Science The University of Lampung Bandar Lampung Indonesia Informatics Engineering Department Faculty of Science The University of Lampung Bandar Lampung Indonesia

This study addresses the challenge of selecting research topics for undergraduate students, focusing on computer science, by evaluating a recommendation model based on the k-Nearest Neighbor algorithm (kNN). The objective is to enhance the accuracy of research topic recommendations in the presence of imbalanced data. The methodology involves data cleaning, transformation, and correlation-based feature selection, with a particular focus on addressing missing values and optimizing the feature set. The Synthetic Minority Over-Sampling Technique (SMOTE) is employed to balance the dataset. The model development includes a comprehensive analysis of various k values, leading to the identification of k=3 with Manhattan distance as the optimal configuration, achieving an accuracy of 82%. The experiment explores different training data proportions, revealing that a 90:10 ratio yields the highest accuracy. This study incorporates a Grid Search technique for hyperparameter tuning, highlighting the importance of selecting appropriate distance metrics and nearest neighbor values. The system implementation is presented with user and administrator interfaces. Findings indicate varying model performance across research categories, emphasizing the need for category-specific evaluation metrics. The study concludes with a discussion on the significance of the results, which contribute to the improvement of research topic recommendation systems for students through the integration of advanced machine learning techniques. © 2024 by the authors.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Maximizing complex features to minimize the detectability of content-adaptive steganography

引用

Multimedia Tools and Applications 2024年 1-19页

作者： Setiadi, De Rosal Ignatius Moses Rustad, Supriadi Andono, Pulung Nurtantio Shidik, Guruh Fajar Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Quantum Computing and Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia

Content-adaptive steganography has three rules that need to be fulfilled to maximize the performance of the cost function, thereby increasing resistance to steganalysis attacks. This study proposes a combination method of image sharpening, Fuzzy edge detection, and residual weighting to maximize the performance of the three rules. Image sharpening is found to be useful for detailing complex features as required by the complexity first rule, while fuzzy edge detection is found to be effective in maximizing the spreading second rule. The clustering third rule is also implemented by customizing the cost of the pixels outside the embedding areas. Embedding simulation is applied to a modified MiPOD method, which we named MaxMiPOD, where SRM and maxSRMd2 steganalysis trials are carried out at payloads of 0.05, 0.1, 0.2, 0.3, 0.4, and 0.5 bpp. The proposed method produces a very significant performance increase of undetectability compared to the MiPOD standard and state-of-the-art methods, especially at a payload of 0.05 bpp. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

Navigating Autism: The Role of Collaborative Virtual Reality in Social Skills Development 17

Navigating Autism: The Role of Collaborative Virtual Reality...

引用

17th International Conference on computer Supported Education, CSEDU 2025

作者： Sharaf, Nada Faculty of Informatics and Computer Science The German International University Egypt

ISBN: (纸本)9789897587467

Autism Spectrum Disorders (ASD) require new interventions because social communication can be specially challenging. Such interventions could help social skills grow. Collaborative virtual reality (VR) technology enables having different interactive and engaging environments. It offers a promising ways for improving many skills since people can safely engage with others as well as learn with others. This paper reviews the application of collaborative VR in improving social skills among children with ASD. The reviews shows the potential of collaborative VR to simulate deeply dynamic social interactions in a carefully controlled setting as well. Different studies show that collaborative VR use can help children with ASD improve empathy, social understanding, and teamwork. However, there are still some difficulties including accessibility as well as the possible need for individualized interventions and potential sensory overload. This review points out the opportunities that collaborative VR provides for meaningful learning improvements and for the large practice of social interactions in an engaging way. It also discusses the actual obstacles,that need to be addressed, to completely maximize the advantages of VR technologies regarding social skills development in ASD. The provided analysis could help support innovation and research in the field. Copyright © 2025 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Engineering education

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：