检索结果-内蒙古大学图书馆

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

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

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

A Framework for Food Availability Forecasting Using Temporal Knowledge Graph

A Framework for Food Availability Forecasting Using Temporal...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Eltaki, Nada Nagaty, Khaled Elzanfaly, Doaa Maghawry, Noura The British University in Egypt Faculty of Informatics and Computer Science Department of Information System Cairo Egypt The British University in Egypt Faculty of Informatics and Computer Science Department of Computer Science Cairo Egypt Helwan University Faculty of Informatics and Computer Science Department of Information System Cairo Egypt

ISBN: (纸本)9798350367560

The entire world encounters a significant problem which is food availability. 'Zero-hunger' is the second Sustainable Development Goal (SDG) of the goals established by the United Nations in 2015. With the increasing number of people and various factors affecting food availability such as climate and country-based food production rate, food forecasting models have become increasingly essential. However, traditional forecasting techniques are limited in dealing with the data and identifying the relationships between them within a specific timestamp. This paper proposes a framework for an intelligent food availability forecasting model built using deep learning techniques and based on a temporal knowledge graph where different timestamps are taken into consideration. The proposed framework helps in enhancing and overcoming the challenges and limitations of the recent forecasting techniques leading to a dynamic, scalable, intelligent forecasting model. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on weed and crop classification using machine learning and deep learning

引用

Artificial Intelligence in Agriculture 2024年第3期13卷 45-63页

作者： Faisal Dharma Adhinata Wahyono Raden Sumiharto Department of Computer Science and Electronics Faculty of Mathematic and Natural SciencesUniversitas Gadjah MadaYogyakartaIndonesia Faculty of Informatics Institut Teknologi Telkom PurwokertoCentral JavaIndonesia

Machine learning and deep learning are subsets of Artificial Intelligence that have revolutionized object detection and classification in images or *** technology plays a crucial role in facilitating the transition from conventional to precision agriculture,particularly in the context of weed *** agriculture,which previously relied on manual efforts,has now embraced the use of smart devices for more efficient weed ***,several challenges are associated with weed detection,including the visual similarity between weed and crop,occlusion and lighting effects,as well as the need for early-stage weed ***,this study aimed to provide a comprehensive review of the application of both traditional machine learning and deep learning,as well as the combination of the two methods,for weed detection across different crop *** results of this review show the advantages and disadvantages of using machine learning and deep ***,deep learning produced superior accuracy compared to machine learning under various *** learning required the selection of the right combination of features to achieve high accuracy in classifyingweed and crop,particularly under conditions consisting of lighting and early growth ***,a precise segmentation stage would be required in cases of *** learning had the advantage of achieving real-time processing by producing smaller models than deep learning,thereby eliminating the need for additional ***,the development of GPU technology is currently rapid,so researchers are more often using deep learning for more accurate weed identification.

关键词： Deep learning Machine learning Precision agriculture Weed control Weed detection

来源：评论

学校读者我要写书评

暂无评论

High performance of Dengue shock syndrome detection using extreme gradient boosting with ANOVA feature selection

Journal of Biotech Research

引用

Journal of Biotech Research 2024年 16卷 22-31页

作者： Muflikhah, Lailil Iskandar, Agustin Yudistira, Novanto Nadlori, Isbat Uzzin Dewanto, Bambang Nur Faculty of Computer Science Brawijaya University Malang India Faculty of Medicine Brawijaya University Malang India Department of Informatics Engineering and Computer Politeknik Elektronika Negeri Surabaya India Faculty of Technology Information Merdeka University Malang India

Dengue shock syndrome (DSS) is an infectious disease that affects millions of people every year all over the world. Early detection of DSS is essential for providing effective therapy and promoting patient recovery. In this work, we proposed a method to enhance DSS detection by combining the Extreme Gradient Boosting (XGBoost) algorithm with variance (ANOVA) feature selection analysis. We used a clinical dataset that contained important information gleaned from people with dengue virus infection. The dataset used for the research was collected from patients at Syaiful Anwar Hospital and consisted of 501 instances. Of these, 401 cases were related to DSS, while the other instances were unrelated to this specific medical condition. An analysis of variance (ANOVA) evaluated the most significant factors that distinguished persons with DSS from those with other dengue diseases. After that, the XGBoost model gave the characteristics of the selected features. For evaluation, we split the data into 80% and 20% for training and testing, respectively. The experimental result showed that the created model had a high degree of performance evaluation in detecting DSS. The highest performance achieved an accuracy of 0.839, precision of 0.875, recall of 0.92, and f1-score of 0.897. Most importantly, the model could detect DSS early on, enabling more proactive therapy and faster responses for individuals at risk of developing the condition. © (2024), (Bio Tech System). All Rights Reserved.

关键词： Patient treatment

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

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

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

SEDARU-net: a squeeze-excitation dilated based residual U-Net with attention mechanism for automatic melanoma lesion segmentation

引用

Multimedia Tools and Applications 2024年 1-28页

作者： Lafraxo, Samira El Ansari, Mohamed Koutti, Lahcen Kerkaou, Zakaria Souaidi, Meryem LabSIV Department of Computer Science Faculty of Sciences Ibnou Zohr University Agadir80000 Morocco Department of Computer Sciences Faculty of Sciences Informatics and Applications Laboratory Moulay Ismail University Meknès Morocco

One of the most dangerous types of skin cancer, malignant melanoma, must be detected early on in order to receive successful therapy. If melanoma is not diagnosed in a timely manner, it might possibly result in death. According to clinical research, because of their varied hue, texture, and imperceptible borders, these early melanoma indications are very challenging for dermatologists to recognize. Therefore, it’s crucial to suggest an automated method that can accurately identify and distinguish between benign and malignant melanoma. Numerous automated methods have been developed by scientists to segment abnormalities from dermoscopic images. On the other hand, conventional models could find it difficult to reliably capture the multi-scale properties, which could result in inconsistent segmentation performance for a variety of object shapes and sizes. Furthermore, models with complicated forms and bounds, such as U-Net and DeepLabV3+, have difficulty properly segmenting tiny, thin, or complex lesions. Thus, we introduce A Squeeze-Excitation Dilated Residual U-Net with Attention Mechanism (SEDARU-Net) in this paper, a novel and automated semantic segmentation network for efficient skin lesion segmentation. To keep spatial information across layers and capture both local and global context, the model is built on U-net combined with dilated convolution. To solve optimization problems, residual blocks are used instead of the basic U-net units. This enhances feature learning, encourages better feature reuse, and allows for the creation of deeper and more robust networks. In order to encourage feature recalibration, global context awareness, and spatial adaptation, each residual block is supplemented with squeeze and excitation units. In addition, The attention gate is also included in the skip connection part of the network to enhance the beneficial channel dimension characteristics and suppress the unreliable background features. According to the results of the experim

关键词： Dermatology

来源：评论

学校读者我要写书评

暂无评论

Combined deep convolutional neural networks for abnormality classification in wireless capsule endoscopy images

引用

Multimedia Tools and Applications 2025年 1-29页

作者： Garbaz, Anass Lafraxo, Samira Charfi, Said El Ansari, Mohamed Koutti, Lahcen Salihoun, Mouna LabSIV Department of Computer Science Faculty of Sciences Ibn Zohr University Agadir Morocco Informatics and Applications Laboratory Department of Computer Science Faculty of Sciences My Ismail University Meknes Morocco Faculty of Medicine and Pharmacy of Rabat Mohammed V University Rabat Morocco

A digestive disease is a condition that affects the gastrointestinal (GI) tract, ranging from mild to severe. Common issues include heartburn, cancer, irritable bowel syndrome, and lactose intolerance. Additionally, other intestinal concerns such as bleeding, polyps, celiac disease, Crohn’s disease, ulcers, diverticulitis, small bowel syndrome, and intestinal ischemia represent further digestive illnesses. Wireless capsule endoscopy (WCE) is a device designed for endoscopic exploration that employs a compact camera to capture images of the GI tract as it passes through. WCE significantly aids in the identification of GI tract disorders. However, due to the capsule’s rapid transit and the potential for blurry, ambiguous images, abnormalities in certain regions of the intestine may be overlooked. Moreover, frames can become hazy if obstructed by food or stool waste. In this research, we propose a method for detecting abnormalities in WCE images to address these limitations. To achieve high classification performance through the extraction of both high-level and low-level features, we employ a deep CNN that integrates the DenseNet121 model with a residual block. Experimental studies demonstrate that our proposed method outperforms state-of-the-art techniques on two publicly available WCE datasets, one focused on bleeding and the other on various abnormalities. The accuracy of the proposed architecture is 96.96% for the Kvasir-Capsule Dataset and 99.50% for the MICCAI 2017 dataset. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Endoscopy

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：