检索结果-内蒙古大学图书馆

Adaptive isomap feature extractive gradient deep belief network classifier for diabetic retinopathy identification

Multimedia Tools and Applications 2025年第9期84卷 6349-6370页

作者： Singh, Alka Kumar, Rakesh Gandomi, Amir H. Department of Computer Science and Engineering Madan Mohan Malaviya University of Technology Gorakhpur India Faculty of Engineering & Information Technology University of Technology Sydney SydneyNSW Australia Óbuda University Budapest1034 Hungary

Diabetic retinopathy (DR) is an infection that bases eternal visualization loss in patients with diabetes mellitus. With DR, the glucose level in the blood increases, as well as its viscosity, this results in fluid leakage into surrounding tissues in the retina. In other words, DR represents the pathology of capillaries and venules in the retina with leakage effects, being the main acute retinal disorder caused by diabetes. Many DR detection methods have been previously discussed by different researchers;however, accurate DR detection with a reduced execution time has not been achieved by existing methods. The proposed method, the Shape Adaptive box linear filtering-based Gradient Deep Belief network classifier (SAGDEB) Model, is performed to enhance the accuracy of DR detection. The objective of the SAGDEB Model is to perform an efficient DR identification with a higher accuracy and lower execution time. This model comprises three phases: pre-processing, feature extraction, and classification. The shape adaptive box linear filtering image pre-processing is carried out to reduce the image noise without removing significant parts of image content. Then, an isomap geometric feature extraction is performed to compute features of different natures, like shape, texture, and color, from the pre-processed images. After that, the Adaptive gradient Tversky Deep belief network classifier is to perform classification. The deep belief network is probabilistic and generative graphical model that consists of multiple layers such as one input unit, three hidden units, and one output unit. The extracted image featuresare considered in the input layer and these images are sent to hidden layers. Tversky similarity index is applied in hidden layer 1 to analyze the extracted features with testing features. Regarding the similarity value, the sigmoid activation function is determined in hidden layer 2 so different levels of DR can be identified. Finally, the adaptive gradient method is

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Decentralized MIMO systems With Imperfect CSI Using LMMSE Receivers

引用

IEEE Journal on Selected Topics in Signal Processing 2025年第2期19卷 331-348页

作者： Zhuang, Zeyan Zhang, Xin Xu, Dongfang Song, Shenghui Eldar, Yonina C. The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Hong Kong The Hong Kong University of Science and Technology Division of Integrative Systems and Design Hong Kong Hong Kong The Weizmann Institute of Science Department of Mathematics and Computer Science Rehovot7610001 Israel

Centralized baseband processing (CBP) is required to achieve the full potential of massive multiple-input multiple-output (MIMO) systems. However, due to the large number of antennas, CBP suffers from two major issues: 1) Extensive data interconnection between radio frequency (RF) circuitry and the central processing unit;and 2) high-dimensional computation. To this end, decentralized baseband processing (DBP) has been proposed, where the antennas at the base station are partitioned into clusters connected to separate RF circuits and equipped with separate computing units. However, the optimal fusion scheme that maximizes signal-to-interference-and-noise ratio (SINR) and the related performance analysis for DBP with general spatial correlation and imperfect channel state information (CSI) have not been studied. In this paper, we consider a decentralized MIMO system where all clusters adopt linear minimum mean-square error (LMMSE) receivers. We first establish an optimal linear fusion scheme that has high computational and data input/output costs. To reduce the cost, we then propose two suboptimal fusion schemes with reduced complexity. For all three schemes, we study the SINR performance by leveraging random matrix theory and demonstrate conditions under which the suboptimal schemes are optimal. Furthermore, we determine the optimal regularization parameter for the LMMSE receiver, identify the best antenna partitioning strategy, and prove that the SINR will decrease as the number of clusters increases. Numerical simulations validate the accuracy of the theoretical results. © 2025 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Slant Polarized Wideband Vivaldi Antenna Array Feed for Monopulse Radar Reflectors

Design and Implementation of a Slant Polarized Wideband Viva...

引用

2025 IEEE Radio and Wireless Symposium, RWS 2025

作者： Masoumi, Reza Kazemi, Robab Fathy, Aly E. University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran University of Tennessee Department of Electrical Engineering and Computer Science KnoxvilleTN United States

ISBN: (纸本)9798350377743

Traditionally, conical ridge horn antennas are used for feeding large reflectors, but they can cause grating lobes in arrays. This paper introduces a compact Vivaldi antenna for monopulse radar, featuring a planar feed structure that offers a wider bandwidth and simplifies manufacturing. The innovative design of the Vivaldi antenna incorporates strategically placed grooves and a circular dielectric lens to enhance gain and reduce sidelobe levels. Operating from 6 GHz to 18 GHz with proper impedance matching, the antenna is 23 mm wide (0.9λ at 12 GHz), making it over 66% smaller than traditional designs. The antennas are angled in 2 × 2 array configuration to overlap, with a center-to-center spacing of 11.3 mm (0.68λ at 18 GHz), ensuring that no grating lobes are present across the entire bandwidth. This innovative antenna effectively feeds an elliptical reflector, providing high gain, broadband capabilities, and significant null depth, ensuring accurate and efficient performance in monopulse radar applications. © 2025 IEEE.

关键词： Monopulse radar

来源：评论

学校读者我要写书评

暂无评论

Enhancing Elderly Care with Socially Assistive Robots: A Holistic Framework for Mobility, Interaction, and Well-Being

引用

IEEE Access 2025年 13卷 82698-82717页

作者： Naseer, Fawad Nasir Khan, Muhammad Tahir, Muhammad Addas, Abdullah Kashif, Hasnain Beaconhouse International College Computer Science and Software Engineering Department Faisalabad38000 Pakistan Government College University Lahore Electrical Engineering Department Lahore54000 Pakistan Sir Syed University of Engineering and Technology Department of Software Engineering Karachi75300 Pakistan Prince Sattam Bin Abdulaziz University College of Engineering Department of Civil Engineering Al-Kharj11942 Saudi Arabia King Abdulaziz University Faculty of Architecture and Planning Landscape Architecture Department Jeddah21589 Saudi Arabia University of South Asia Department of Computer Science Lahore54000 Pakistan

The global elderly population is projected to double by 2050, creating challenges in mobility, social isolation, and cognitive decline. Socially Assistive Robots (SARs) offer a promising solution, yet gaps remain in integrating mobility assistance with cognitive and emotional support. The research developed a comprehensive framework for SARs, emphasizing user-centered design, technological innovation, and cultural adaptability. A mixed-methods approach was employed with 200 participants aged 60+, from diverse settings, including rehab centers, retired groups, old age communities and nursing homes. Results demonstrated a 33.3% improvement in mobility scores and a 40% increase in social engagement. Health metrics revealed a 22% reduction in falls, a 15% rise in physical activity, and a 90% user satisfaction rate. Gender and age differences were evident, with males aged 71+ showing higher mobility improvements (35.6%) and females aged 71+ reporting the highest satisfaction (93%). Long-term data indicated sustained benefits, with participants retaining 80% of mobility gains and social engagement levels 38% above baseline after six months. These findings highlight the importance of culturally sensitive and user-centered SAR designs in promoting elderly well-being. The research offers a robust foundation for integrating SARs into elderly care systems, emphasizing adaptability, sustainability, and ethical considerations for future implementation. © 2013 IEEE.

关键词： Nursing

来源：评论

学校读者我要写书评

暂无评论

EAFL: Edge-Assisted Federated Learning for real-time disease prediction using privacy-preserving AI

引用

Iran Journal of computer science 2025年 1-11页

作者： Rawas, Soha Samala, Agariadne Dwinggo Faculty of Science Department of Mathematics and Computer Science Beirut Arab University Beirut Lebanon Faculty of Engineering Universitas Negeri Padang West Sumatra Padang Indonesia

The growing demand for real-time disease prediction in healthcare necessitates advanced AI frameworks capable of ensuring both computational efficiency and patient privacy. This study introduces an Edge-Assisted Federated Learning (EAFL) system designed for real-time disease prediction while preserving sensitive data using privacy-preserving AI techniques. Leveraging lightweight convolutional neural networks and federated learning, the framework decentralizes model training across simulated edge nodes, reducing reliance on centralized data storage. Differential privacy mechanisms are integrated to secure inter-node communications, enhancing data protection. The proposed framework was evaluated on publicly available datasets, including CheXpert and COVID-19 radiography, achieving an accuracy of 94.2% and 97.5%, respectively, with minimal latency (0.85 s per prediction). Comparative analysis reveals that the EAFL system matches the performance of centralized AI models while significantly reducing privacy risks. To demonstrate scalability, additional evaluation was conducted across different dataset distributions, revealing consistent performance across varying data characteristics and medical scenarios. This research offers a scalable, privacy-focused solution that bridges the gap between real-time disease prediction and secure data handling, paving the way for its adoption in modern healthcare applications. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Disease prediction Edge AI Federated learning GDPR compliance in AI Healthcare data security

来源：评论

学校读者我要写书评

暂无评论

L2H-NeRF: low- to high-frequency-guided NeRF for 3D reconstruction with a few input scenes

引用

Visual computer 2025年 1-12页

作者： Bao, Taoqi Ye, Jiangnan Bao, Zhankong Leow, Chee Siang Hu, Haoji Lu, Jianfeng Fujishiro, Issei Xu, Jiayi School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China College of Information Science & Electronic Engineering Zhejiang University Hangzhou China Department of Mechatronics University of Yamanashi Kofu Japan Department of Information and Computer Science Faculty of Science and Technology Keio University Yokohama Japan

Nowadays, three-dimensional (3D) reconstruction techniques are becoming increasingly important in the fields of architecture, game development, movie production, and more. Due to common issues in the reconstruction process, such as perspective distortion and occlusion, traditional 3D reconstruction methods face significant challenges in achieving high-precision results, even when dense data are used as inputs. With the advent of neural radiance field (NeRF) technology, high-fidelity 3D reconstruction results are now possible. However, high computational resources are usually required for NeRF computations. Recently, a few data inputs are used to ensure the highest quality. In this paper, we propose an innovative low- to high-frequency-guided NeRF (L2H-NeRF) framework that decomposes scene reconstruction into coarse and fine stages. For the first stage, a low-frequency enhancement network based on a vision transformer is proposed, where the low-frequency-based globally coherent geometric structure is recovered, with the dense depth restored in a depth completion way. In the second stage, a high-frequency enhancement network is incorporated, where the high-frequency-related detail is compensated by robust feature alignment across adjacent views using a plug-and-play feature extraction and matching module. Experiments demonstrate that both the accuracy of the geometric structure and the feature detail of the proposed L2H-NeRF outperforms state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

Detecting Advanced Persistent Threat Exfiltration with Ensemble Deep Learning Tree Models and Novel Detection Metrics

引用

IEEE Access 2025年 13卷 81803-81822页

作者： Cai, Xiaojuan Zhang, Haibo Ahmed, Chuadhry Mujeeb Koide, Hiroshi Kyushu University Faculty of Information Science and Electrical Engineering Department of Information Science and Technology Fukuoka819-0395 Japan Kyushu Institute of Technology Faculty of Computer Science and Systems Engineering Department of Artificial Intelligence Fukuoka Iizuka820-8502 Japan Newcastle University School of Computing Secure and Resilient Systems Group Newcastle upon TyneNE1 7RU United Kingdom Kyushu University Section of Cyber Security for Information Systems Research Institute for Information Technology Fukuoka819-0395 Japan

Advanced Persistent Threats (APTs) involve attackers maintaining a long-term presence on victim systems, leading to the stealthy exfiltration of sensitive data during network transfers. Despite existing methods to detect and halt APT data exfiltration, these attacks continue to pose significant threats to sensitive information and result in substantial commercial losses. Current approaches primarily focus on preemptive measures, which are insufficient once early-stage detection fails due to a lack of continuous monitoring. We propose an effective and efficient network monitoring method to address this gap and detect APT exfiltration during data transfer. Our approach assumes the presence of an undetected APT attacker within the victim system. We examine data exfiltration across three exfiltration traffic environments: exfiltration over command control channels, exfiltration over transfer size limitations, and their combinations. We introduce two detection metrics: Package Transfer Rate and Byte Transfer Rate. Utilizing these metrics, we measure network traffic, categorize APT attack environments, and train deep neural network models, named EDXGB, using ensembled decision trees to predict APT exfiltration. Our method is validated on two public datasets and compared against six baseline methods. Additionally, we simulate real-world exfiltration scenarios by creating three exfiltration traffic environments for each dataset. The results demonstrate that our method effectively detects APT exfiltration across various network environments, enhancing data protection and secure transfer. The code is open source and available at https://***/cxjuan/EDXGB-for-APT. © 2013 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

ResNet50-Based Deep Learning Model for Lung Disease Detection

ResNet50-Based Deep Learning Model for Lung Disease Detectio...

引用

2025 International Conference on Multi-Agent systems for Collaborative Intelligence, ICMSCI 2025

作者： Hajbe, Janhavi R. Patle, Sneha K. Talvekar, Shreya V. Khonde, Tanvi W. Yesankar, Prajyot R. Faculty of Engineering and Technology Department of Computer Science & Design Sawangi Maharashtra Wardha442001 India

ISBN: (纸本)9798331509828

By enabling a highly accurate examination of the chest x-ray, deep learning, for example, is changing the methods of recognizing lung disorders. In order to classify lung diseases, such as bacterial pneumonia, viral pneumonia, TB, and COVID-19, this work describes the use of ResNet50, a kind of CNN and a deep learning technique. We prove the potential of deep learning to discern these diseases from the two conventional approaches and most importantly, the patterns one could implicitly observe. The article also discusses the challenges that deep learning may pose on to the healthcare industry including data privacy, availability of data and the issue of overfitting. The paper links with this part by looking at the future of this area of specialization, which includes;multimodal fusion, operational AI, real-time identification, personalized care, data issues, and concerns, and ethics. But if deep learning is successful in addressing all the above-discussed challenges then it can bring the situation to the real world where the identification of lung diseases happens in a previous phase which in turn results in better treatment procedures and higher patient outcomes. © 2025 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Software design and FPGA implementation of optimized medical image fusion techniques

引用

Multimedia Tools and Applications 2025年 1-31页

作者： Elshazly, E.A. El-Shafai, Walid El-Hoseny, Heba El-Rabaie, El-Sayed M Zahran, O. Abdelwahab, Safey A. S. El-Halawany, M.M. Fikry, R.M. Elaraby, S.M. Faragallah, Osama S. Mohamed, Wael A. Mahmoud, Korany R. Abd El-Samie, Fathi E. Cairo Egypt Computer Science Department Prince Sultan University Riyadh11586 Saudi Arabia Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Faculty of Computer Studies Arab Open University 11681 Riyadh Saudi Arabia Department of Information Technology College of Computers and Information Technology Taif University 11099 Taif21944 Saudi Arabia Department of Electrical Engineering Faculty of Engineering Benha University Benha Egypt Electronics and Communications Engineering Department Faculty of Engineering Helwan University Helwan Egypt Giza Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University P.O. Box 84428 Riyadh11671 Saudi Arabia

Nowadays, medical image fusion plays a crucial role in enhancing the diagnosis accuracy and the clinical decision-making process in various healthcare applications. This research work presents a comprehensive study of the design and implementation of optimized medical image fusion techniques using a combination of software and Field-Programmable Gate Array (FPGA) technologies. The proposed medical image fusion strategy is based on the utilization of Discrete Wavelet Transform (DWT) and Modified Central Force Optimization (MCFO). The implementation of the proposed technique as well as the traditional medical image fusion techniques is considered using an appropriate software design and FPGA. The presented techniques aim to overcome the limitations of traditional fusion techniques by integrating advanced image processing algorithms, optimization algorithms, and parallel computing capabilities offered by FPGA platforms. The first step in the proposed framework is to match the histogram of one of the images with that of the other, so that both images will have the same dynamic range. After that, the DWT is used to decompose the images that should be fused together. Based on some constraints, the MCFO optimization algorithm is used to evaluate the optimum level of decomposition and the optimum parameters for the best fusion quality. Finally, to improve the obtained visual quality and reinforce the information in the fusion result, an additional contrast enhancement step using adaptive histogram equalization is applied to the fusion result. Comparative study between the proposed optimized DWT-based fusion framework, the traditional Principal Component Analysis (PCA), Additive Wavelet Transform (AWT), and DWT-based fusion techniques is presented. Various metrics of fusion quality are considered, including average gradient, standard deviation, local contrast, entropy, edge strength, Peak Signal-to-Noise Ratio (PSNR), Qab/f, and processing time. The proposed optimized DWT-ba

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

Cloud Computing and Neutrosophic Logic: Navigating Uncertainty in Educational Administration

引用

Neutrosophic Sets and systems 2025年 78卷 102-449页

作者： Yasser, Ibrahim Abd El-Khalek, Aya A. Khalid, Huda E. Salama, A.A. Essa, Ahmed K. Engineering Faculty University of Mansoura Mansoura35516 Egypt Communications and Electronics Engineering Department Nile Higher Institute for Engineering and Technology Mansoura35524 Egypt Telafer University The Administration Assistant for the President of the Telafer University Telafer Iraq Department of Mathematics and Computer Science Faculty of Sciences Port Said University Port Said42526 Egypt

Educational institutions face inherent uncertainties in student performance, stakeholder priorities, and data analysis. This paper explores how cloud computing, with its data storage, analytics, and collaboration tools, can address these uncertainties in educational administration. We propose a neutrosophic framework utilizing "truth," "falsity," and "indeterminacy" values to represent these complexities within educational data. Real-world case studies analyze how cloud computing can reduce uncertainties and improve decision-making. Our findings reveal that cloud computing offers significant potential for navigating the "fog" of educational administration, but its effectiveness is enhanced by considering the "indeterminacy" inherent in educational data through the neutrosophic framework. This research contributes a unique neutrosophic perspective to the use of cloud computing for improved and more informed decision-making in educational administration. © 2025, University of New Mexico. All rights reserved.

关键词： Case Studies Cloud Computing Decision-Making Educational Administration Educational Data Neutrosophic Logic Uncertainty

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：