检索结果-内蒙古大学图书馆

Unsupervised multiplex graph diffusion networks with multi-level canonical correlation analysis for multiplex graph representation learning

引用

science China(information sciences) 2025年第3期68卷 66-79页

作者： Sichao FU Qinmu PENG Yange HE Baokun DU Bin ZOU Xiao-Yuan JING Xinge YOU School of Electronic Information and Communications Huazhong University of Science and Technology Platform Operation and Marketing Center JD Retail Faculty of Mathematics and Statistics Hubei Key Laboratory of Applied Mathematics Hubei University School of Computer Science Wuhan University

In recent years, unsupervised multiplex graph representation learning(UMGRL) has received increasing research interest, which aims to learn discriminative node features from the multiplex graphs supervised by data without the guidance of labels. Although these designed UMGRL methods have obtained great success in various graph-related tasks, most existing UMGRL models still have the following issues: highly depending on complex self-supervised strategies(i.e., data augmentation,pretext tasks, and negative pairs sampling), restricted receptive fields, and only aggregating low-frequency information between nodes. In this paper, we propose a simple unsupervised multiplex graph diffusion network(UMGDN) with the aid of multi-level canonical correlation analysis to solve the above issues. Specifically, we first decouple the feature transform and propagation processes of the graph convolution layer to further improve the generalization of the learnable parameters. And then, we propose adaptive diffusion propagation to capture long-range dependency relationships between nodes, not the local neighborhood interactions. Finally, a multi-level canonical correlation analysis loss on both the feature transform and propagation processes is proposed to maximize the correlation of the same node features from multiple graphs for guiding model optimization. Compared to the existing UMGRL models, our proposed UMGDN does not need to introduce any data augmentation, negative pairs sampling techniques, complex pretext tasks, and also adaptively aggregates the optimal frequency information between nodes to generate more robust node embeddings. Extensive experiments on four popular datasets and two graph-related tasks demonstrate the effectiveness of the proposed method.

关键词： unsupervised multiplex graph representation learning graph neural networks node classification node clustering

来源：评论

学校读者我要写书评

暂无评论

A novel U-net model for brain tumor segmentation from MRI images

引用

Alexandria Engineering Journal 2025年 126卷 220-230页

作者： Obayya, Marwa Alshuhail, Asma Mahmood, Khalid Alanazi, Meshari H. Alqahtani, Mohammed Aljehane, Nojood O. Almansour, Hamad Al-Hagery, Mohammed Abdullah Department of Biomedical Engineering College of Engineering Princess Nourah bint Abdulrahman University PO Box 84428 Riyadh11671 Saudi Arabia Department of Information Systems College of Computer Sciences & Information Technology King Faisal university Saudi Arabia Department of Information Systems Applied College at Mahayil King Khalid University Saudi Arabia Department of Computer Science College of Sciences Northern Border University Arar Saudi Arabia Department of Information System and Cyber Security College of Computing and Information Technology University of Bisha Bisha61922 Saudi Arabia Department of Computer Science Faculty of Computers and Information Technology University of Tabuk Tabuk Saudi Arabia Applied Collage Najran University Najran Saudi Arabia Department of Computer Science College of Computer Qassim University Saudi Arabia

Segmentation of brain tumors aids in diagnosing the disease early, planning treatment, and monitoring its progression in medical image analysis. Automation is necessary to eliminate the time and variability associated with traditional segmentation methods. Convolutional neural networks (CNNs) and U-Net architectures have demonstrated their efficiency and effectiveness in segmenting brain tumors from MRI images using deep learning techniques. The paper presents an improved U-Net-based segmentation algorithm that integrates nested skip paths to improve encoder-decoder feature fusion. The performance of segmentation was optimized by utilizing a variety of activation functions and loss functions, including Dice Loss and Intersection over Union (IoU). A high level of accuracy was demonstrated in the proposed model when it was evaluated using the LGG Segmentation Dataset. The proposed approach for segmenting medical images has been shown to be both robust and efficient in a comparative analysis. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Neutrosophic Approach to Robust Web Security: Mitigating XSS Attacks

引用

Neutrosophic Sets and systems 2025年 79卷 1-22页

作者： Salama, A.A. Aboelfotoh, El-Said F. El-Bakry, Hazem M. Khalid, Huda E. Essa, Ahmed K. Sabbagh, Ramiz El-Morshedy, Doaa S. Department of Mathematics and Computer Science Faculty of Science Port Said University Egypt Department of Information Systems Faculty of Computers and Information Mansoura University Mansoura Egypt Telafer University Telafer Iraq Department of the Scientific Affairs Telafer University Mosul Iraq

Cross-Site Scripting (XSS) is one of the most grievous vulnerabilities-a pitfall through which web applications are affected. These types of attacks are complex, and the available threat landscape is always changing, making it hard for conventional security tools to effectively detect or prevent these types of attacks. We present here an approach that detects and prevents XSS attacks on Web pages. Since Neutrosophism works with different kinds of data, it aims at the validity degree of the attack. This way the system understands the different types of attacks and allows the system to act more effectively. Our system combines (1) static analysis-to look into the code behind the website-with (2) dynamic analysis-to watch the website in action. Moreover, a proactive defense watches your user behavior and scrubs every input/output. © 2025, University of New Mexico. All rights reserved.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Enhancing Performance of Machine Learning Models in Healthcare: An Analytical Framework for Assessing and Improving Data Quality 5th

Enhancing Performance of Machine Learning Models in Healthca...

引用

5th International Conference on Advances in information Communication Technology and Computing, AICTC 2024

作者： Al-Hgaish, Areen Atan, Rodziah Yaakob, Razali Osman, Mohd Hafeez Department of Software Engineering and Information Systems Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang44330 Malaysia Department of Computer Science Faculty of Computer Science and Information Technology Universiti Putra Malaysia Serdang44330 Malaysia

ISBN: (纸本)9789819761050

The utilization of Data-Driven Machine Learning (DDML) models in the healthcare sector poses unique challenges due to the crucial nature of clinical decision-making and its impact on patient outcomes. A primary concern in this domain is the data quality that forms the basis for these models, which is essential for their effectiveness. While numerous studies are dedicated to leveraging Machine Learning (ML) to enhance patient care, a substantial gap exists in understanding and evaluating the quality of training data before training ML models. This issue is exacerbated by the lack of well-defined standards to ensure that data characteristics align with the specific goals of ML in healthcare. To address this, our study introduces a conceptual three-dimensional framework focusing on data accuracy, completeness, and consistency aimed at assessing and improving the quality of training data. This framework is designed to enhance the performance, predictability, and interpretability of healthcare-specific ML models and reduce biases, thus bridging current research gaps and laying the groundwork for future developments in ML-driven healthcare systems. This paper presents the initial step for our proposed Data Quality Framework (DQF), which addresses the three dimensions mentioned above. It discusses its potential implications and applications in healthcare data, and its main goal is to provide a comprehensive overview of the proposed DQF, illustrating its significance in advancing healthcare data quality and ultimately improving patient outcomes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

An efficient feature selection and classification system for microarray cancer data using genetic algorithm and deep belief networks

引用

Multimedia Tools and Applications 2025年第8期84卷 4393-4434页

作者： Lawrence, Morolake Oladayo Jimoh, Rasheed Gbenga Yahya, Waheed Babatunde Department of Computer Science Faculty of Computing & Applied Sciences Baze University Abuja Nigeria Department of Computer Science Faculty of Communication & Information Sciences University of Ilorin Kwara State Ilorin Nigeria Department of Statistics Faculty of Physical Sciences University of Ilorin Kwara State Ilorin Nigeria

Cancer is one of the most devastating health conditions in the world. In the diagnosis and treatment of the various forms of cancer illness, studies have shown that early detection of the cancer by clinical methods usually takes a considerable lengthy time. This informs searching for an alternative non-clinical diagnosis of cancer cases using microarray technology. Therefore, this study develops an efficient feature selection and classification method for high-dimensional microarray cancer data by combining Genetic Algorithms (GA) and Deep Belief Networks (DBN). The study employed a GA for selecting the most informative gene biomarker and DBN for the classification of biological samples. In a Monte Carlo experiment, the simulated and real-life microarray datasets were partitioned into 95% training and 5% test samples at 100 to 1000 epochs. The classifier was constructed using the training datasets while its efficiency was assessed on the test sample using the Misclassification Error Rate, Sensitivity, Specificity, and Receiver Operating Characteristic Analysis. The GA and DBN were implemented using Caret and Deepnet (R statistical packages). The proposed GADBN method was implemented using simulated and real-life datasets, which yielded out-of-bag average classification accuracy of 98.8% and 93.1% respectively. The proposed GADBN outperformed the other existing classifiers;and the GADBN method was more efficient with a smaller Misclassification Error Rate (MER) for Leukaemia 1 (0.18), Prostate 1 (0.35) and Prostate 3 (0.09) datasets than some of the existing methods under various performance indices considered. The proposed model is a powerful and effective instrument for identifying useful features in microarray cancer data and classifying the cancer types accordingly. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Water potability classification based on hybrid stacked model and feature selection

引用

Environmental science and Pollution Research 2025年第13期32卷 7933-7949页

作者： Elshewey, Ahmed M. Youssef, Rasha Y. El-Bakry, Hazem M. Osman, Ahmed M. Department of Computer Science Faculty of Computers and Information Suez University P.O. Box: 43221 Suez Egypt Department of Information Systems Faculty of Computers and Information Suez University P.O. Box: 43221 Suez Egypt Department of Information Systems Faculty of Computers and Information Mansoura University P.O. Box: 35516 Mansoura35516 Egypt

Clean water requires accurate water quality categorization. A water potability (WP) dataset with pH, hardness, solids, chloramines, sulfate, conductivity, and other metrics for 3276 water bodies was used in this paper. After median imputation for missing values, normalization for feature scaling, and class imbalance correction using SMOTE, the Kaggle public dataset was prepared. With binary particle swarm optimization (BPSO) and binary whale optimization algorithm (BWAO), feature selection (FS) was used to determine the most important features for classification. A subset of seven essential characteristics is selected with the lowest average error of 0.3745 by the BPSO. Random forest (RF), gradient boosting (GB), support vector machine (SVM), Extra Tree (ET), decision tree (DT), and XGBoost are tested for WP prediction. The ET classifier ranked first, with 70.63% accuracy and 71.17% F1-score. Predictive performance was improved by stacking random forest, extra trees, and XGBoost base learners with Logistic Regression meta-learner. The stacking model improved with 69.53% accuracy, 70.23% F1-score, and 77.62% AUC. We found that stacking uses high-performing models to create a strong and balanced categorization framework. This paper shows that ensemble learning can improve WP categorization and that stacking may be a feasible way for measuring and managing water quality. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Multi-Output and Multi-Task Regression for Supershape Reconstruction from 3D Point Clouds

Informatica (Slovenia)

引用

Informatica (Slovenia) 2025年第5期49卷 37-48页

作者： Remmach, Hassnae Razak, Siti Fatimah Abdul Ullah, Arif Yogarayan, Sumendra Sayeed, Md Shohel Mrhari, Amine Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh40000 Morocco Faculty of Information Science and Technology Multimedia University Ayer Keroh75450 Malaysia Research in Computer Science Laboratory Faculty of Sciences Ibn Tofail University Kenitra Morocco

In a number of industries, including computer graphics, robotics, and medical imaging, three-dimensional reconstruction is essential. In this research, a CNN-based Multi-output and Multi-Task Regressor with deep learning capabilities is proposed for three-dimensional object reconstruction from 3D point cloud. Our approach is grounded in the original Point Net architecture, which addresses the difficulties associated with convolution when applied to point clouds. Firstly, this paper is modified using a Multi-Output Regressor to accurately recreate Super forms from 3D point clouds. Using this method, we first extract features from the 3D point cloud using Point Net. After that, a Multi-Output Regressor receives these data and uses them to anticipate the Super shape parameters needed to reconstruct the shape. Taking in the data, the Multi-Output Regressor retrieved characteristics from Point Net and simultaneously predicts several outcomes. Second, a Multi-Task Regressor is used to modify the Point Net. The network gains from the capacity to transfer knowledge from one task to another, improving the model's overall performance. The model would forecast the ten parameters needed to create the shape in the case of rebuilding Super shapes. The test findings were better than expected;they are intriguing in terms of prediction accuracy and cost, and they update the result by 80%, which is a good accomplishment for the study. © 2025 Slovene Society Informatika. All rights reserved.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Responding to platform owner moves: A 14-year qualitative study of four enterprise software complementors

Responding to platform owner moves: A 14-year qualitative st...

引用

作者： Kude, Thomas Huber, Thomas L. Faculty of Information Systems and Applied Computer Sciences University of Bamberg Germany Department of Information Systems Decision Sciences and Statistics ESSEC Business School Cergy France

Integrating the competition and the cooperation perspectives on value co-creation in platform ecosystems, this study explores complementor responses to platform owner moves that adversely affect the complementor's positioning. Our primary focus is to discern dynamic patterns of complementor responses and to understand their role in the process of re-stabilising the complementor's positioning. To this end, we conducted a 14-year longitudinal study, analysing 21 move-response instances across four platform partnerships. Our findings reveal three distinct complementor response archetypes: insist, pivot, and detach. Over time, complementors combine these archetypes into three unique response patterns. Through progressive diverging, complementors sidestep platform owner moves by diversifying their offer beyond the focal ecosystem. Although this can entail substantial multi-homing costs, it reduces dependence on the platform owner and bolsters resilience against future moves. Through adaptive oscillating, complementors use platform owner moves as opportunities to gradually diversify their offer within the focal ecosystem. This stepwise market expansion makes them resilient against future moves, while mitigating costs and efforts related to multi-homing. Through persistent insisting, complementors can re-establish their previous positioning, but at the cost of increased dependence on the platform owner, leaving the complementor vulnerable to future moves. We synthesise these findings in our process model of complementor positioning. Emphasising the importance of complementor responses in fostering resilient software ecosystems, this model bears important implications for research on platform governance and platform-dependent entrepreneurship. © 2024 The Authors. information systems Journal published by John Wiley & Sons Ltd.

关键词： Ecosystems

来源：评论

学校读者我要写书评

暂无评论

Energy and QoS-aware virtual machine placement approach for IaaS cloud datacenter

引用

Neural Computing and Applications 2025年第4期37卷 2211-2237页

作者： Elsedimy, E.I. Herajy, Mostafa Abohashish, Sara M. M. Department of Information Technology Management Faculty of Management Technology and Information Systems Port Said University Port Said Egypt Department of Mathematics and Computer Science Faculty of Science Port Said University Port Said Egypt Cyber Secuirty Department Faculty of Science Al-Esraa University College Baghdad Iraq

Virtualization technology enables cloud providers to abstract, hide, and manage the underlying physical resources of cloud data centers in a flexible and scalable manner. It allows placing multiple independent virtual machines (VMs) on a single server in order to improve resource utilization and energy efficiency. However, determining the optimal VM placement is crucial as it directly impacts load balancing, energy consumption, and performance degradation within the data center. Furthermore, deciding on VM placement based on a single factor is usually insufficient to improve data center performance because many factors must be considered, and ignoring them may be too expensive. This paper improves a new multi-objective VM placement (MVMP) algorithm using a quantum particle swarm optimization (QPSO) technique. We call it QPSO-MOVMP, and its objective is to find the Pareto optimal solution for the VM placement problem by balancing different goals. This algorithm generates Pareto optimal solutions that save power by minimizing the number of running physical machines, avoid performance degradation by maintaining service level agreement (SLA), and improve load balancing by keeping server loads at optimal utilization. The experimental results show that QPSO-MOVMP had superior performance in terms of power consumption and performance degradation compared to three other multi-objective algorithms and three conventional single-objective algorithms. Simulation results show that the proposed QPSO-MOVMP achieves a consumption of 2.4 × 104 watts in power. Furthermore, it outperformed the others, achieving a minimum of 12% SLA breaches while experiencing a significant surge in requests from VMs. Moreover, the proposed model generated Pareto solutions that had a better distribution than those derived from a comparative method. © The Author(s) 2025.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Work in Progress: Supporting Distributed Practice with a Gamified E-Learning Course 27th

Work in Progress: Supporting Distributed Practice with a ...

引用

27th International Conference on Interactive Collaborative Learning, ICL 2024

作者： John, Isabel Hess, Anne Fertig, Tobias Faculty of Computer Science and Business Information Systems Technical University of Applied Sciences Würzburg-Schweinfurt Sanderheinrichsleitenweg 20 Würzburg97074 Germany

ISBN: (纸本)9783031835193

For the teaching of agile methods in an IT undergraduate course we developed a gamified blended learning course. We created the course with gamification elements such as videos, quizzes, badges, and points in the learning management system Moodle. In this paper, we first share our experiences with distributed practice in this course and how gamification supported our flipped classroom approach. We also briefly present results of a survey study that investigated intrinsic motivation with an earlier version of the course and that revealed mixed results, i.e., an increase of intrinsic motivation for some factors, but not for all factors. The evaluation results and observations motivated a future research agenda aimed at further improving and continuously evaluating the impact of gamification on intrinsic motivation to ultimately promote distributed practice as well as sustained learning combined with fun for the students. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

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：