检索结果-内蒙古大学图书馆

MLPFormer: MLP-integrated transformer for colorectal histopathology whole slide image segmentation

Neural Computing and Applications 2025年第6期37卷 4651-4661页

作者： Wang, Yuxuan Li, Dan Li, Xuechen Guo, Yan Zuo, Yanfei Shen, Linlin Department of Computer Science Wenzhou-Kean University Wenzhou China School of Electronics and Information Engineering Wuyi University Jiangmen China Department of Histo Pathology Shanghai Histo Pathology Diagnostic Center Shanghai China College of Computer Sicence and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

Colorectal intraepithelial neoplasia is a precancerous lesion of colorectal cancer, which is mainly diagnosed using pathological images. According to the characteristics of lesions, precancerous lesions can be classified into four different grades, i.e., background, normal, low and high level. However, due to the continuity of lesion development, tissue in different stages has high similarity. Recently, visual transformers have achieved impressive results in different visual tasks, due to their capacity of capturing long-range dependencies. However, due to computational cost, transformer cannot well extract detailed feature, which is important for lesion grading. To accurately segment pathological tissues with high similarity, in this work, we embed the multi-head MLP mixer module in the transformer network to extract cell and edge information. Furthermore, we propose a hierarchical MLP decoder to facilitate multi-scale feature fusion. The proposed transformer, namely MLPFormer, achieves remarkable results against competitive baselines on the Histo-CRC Biopsy dataset. The experimental results demonstrate that MLPFormer significantly outperforms the competitive baselines, i.e., a 3% dice improvement is achieved over the SegFormer series. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

SABiT-MNet: Scale-Adaptive Autoencoder with BiT-M Model for Identifying AMD Grades

SABiT-MNet: Scale-Adaptive Autoencoder with BiT-M Model for ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： El-Den, Niveen Nasr Elsharkawy, Mohamed Ghazal, Mohammed Mahmoud, Ali Sandhu, Harpal Mahdi, Hani El-Baz, Ayman Department of Computer and System Engineering Ain Shams University Egypt Department of Bioengineering University of Louisville LouisvilleKY United States Electrical Computer and Biomedical Engineering Department Abu Dhabi University Abu Dhabi United Arab Emirates

ISBN: (纸本)9798350368741

Accurate early diagnosis is crucial in addressing Age-related Macular Degeneration (AMD), a chronic retinal disease that is a leading cause of blindness among the elderly. Medical imaging, particularly fundus imaging, is essential in facilitating timely detection and intervention. Due to the variability in image sizes within our dataset, this paper introduces the SABiT-MNet model, which effectively discriminates between healthy retinas, dry AMD, and wet AMD. The model integrates a novel scale-adaptive (SA) approach by combining an autoencoder with Big Transfer (BiT) as its backbone. Unlike traditional resizing methods, which often result in the loss of critical diagnostic information, the SA model dynamically adjusts to varying image sizes, preserving key retinal features essential for accurate diagnosis. The primary aim of this architecture is to retain crucial details in fundus images to ensure precise classification. In this study, 648 subjects were recruited through the Comparisons of AMD Treatments Trials study group, sponsored by the University of Pennsylvania. Experimental results demonstrate that the proposed SABiT-MNet model outperforms state-of-the-art approaches, including transformer-based models, achieving superior diagnostic accuracy. The model recorded performance metrics of 94% accuracy, 97% sensitivity, and 93.94% specificity. To further validate the robustness of the system, we tested it on the public ODiR dataset, where it achieved similarly promising results, confirming the effectiveness of our approach. © 2025 IEEE.

关键词： AMD Deep Learning fundus photography

来源：评论

学校读者我要写书评

暂无评论

Enhanced Neutrosophic Set and Machine Learning Approach for Kidney Disease Prediction

引用

Neutrosophic Sets and systems 2025年 80卷 465-477页

作者： Al-Doori, Humam M. Alkellezli, Tareef S. Abdelhafeez, Ahmed Eassaa, Mohamed Sawah, Mohamed S. El-Douh, Ahmed A. Cybersecurity Sciences Department College of Science Ashur University Baghdad Iraq Cybersecurity Engineering Department College of Engineering Ashur University Baghdad Iraq Computer Science Department Faculty of Information System and Computer Science October 6 University Giza12585 Egypt Applied Science Research Center Applied Science Private University Amman Jordan Department of Computer Science Faculty of Information Technology Ajloun National University P.O.43 Ajloun26810 Jordan Cybersecurity Technology Engineering Department College of Engineering Technology Ashur University Baghdad Iraq

Kidney disease (KD) is a gradually increasing global health concern. It is a chronic illness linked to higher rates of morbidity and mortality, a higher risk of cardiovascular disease and numerous other illnesses, and expensive medical expenses. The machine learning (ML) models are applied for KD prediction with higher accuracy and precision. The KD dataset has uncertainty and vague information, so, we used the neutrosophic set (NS) to deal with vague and uncertainty information in the KD dataset. The KD dataset is converted into the N-KD dataset with three membership functions: truth, indeterminacy, and falsity. Three ML models are used in this study such as logistic regression (LR), support vector machine (SVM), and k-nearest neighbor (KNN). These ML models are applied to the N-KD dataset. The results show the LR has higher accuracy and precision on the N-KD dataset than the original KD dataset. © 2025, University of New Mexico. All rights reserved.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Evaluating the Privacy and Security Implications of Mobile Apps 8

Evaluating the Privacy and Security Implications of Mobile A...

引用

8th International Conference on Electronics, Materials engineering and Nano-Technology, IEMENTech 2025

作者： Mazumder, Shafiul Islam Shovon, Sazzadul Islam Chowdhury, Md Tanvir Islam, Minhajul Raisa, Habiba Azad Rahman, Habibur Sumon, Monjurul Islam Khan, Md. Khalid Mahbub American International University Department of Computer Science and Engineering Dhaka Bangladesh Central Michigan University Department of Information System Michigan United States East West University Department of Computer Science and Engineering Dhaka Bangladesh Department of Computer Science and Engineering Dhaka Bangladesh

ISBN: (纸本)9798331520762

The rapid growth of mobile applications, combined with an increasing reliance on these apps for a variety of purposes, has prompted serious concerns about user privacy and data security. This study aims to assess the privacy practices, data handling methods, and security vulnerabilities of mobile apps in a variety of categories, including social media, e-commerce, health and fitness, and financial management. This study identifies major privacy and security issues by examining privacy policies and terms of service, as well as how these apps handle sensitive data. The study also examines free and premium apps' privacy procedures, taking into account the implications for user data protection. The findings illustrate differences in data handling and security standards across different app categories, highlighting the importance of transparent privacy policies, strong security mechanisms, and limited data sharing to protect user information. The research helps to define standards and best practices for promoting secure app activity, increasing user confidence, and guaranteeing a safer digital environment. © 2025 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Machine learning for Internet of Things (IoT) device identification: a comparative study

引用

PeerJ computer Science 2025年 11卷 1-34页

作者： Tahaei, Hamid Liu, Anqi Forooghikian, Hamid Gheisari, Mehdi Zaki, Faiz Anuar, Nor Badrul Fang, Zhaoxi Huang, Longjun Institute of Artificial Intelligence Shaoxing University Shaoxing China School of Computing and Data Science Xiamen University Malaysia Selangor Malaysia Department of Management Islamic Azad University of Kish Kish Iran Department of Computer System and Technology Faculty of Computer Science and Information Technology Universiti Malaya Selangor Kuala Lumpur Malaysia Department of Computer Science and Engineering Shaoxing University Shaoxing China

The rapid deployment of millions of connected devices brings significant security challenges to the Internet of Things (IoT). IoT devices are typically resource-constrained and designed for specific tasks, from which new security challenges are introduced. As such, IoT device identification has garnered substantial attention and is regarded as an initial layer of cybersecurity. One of the major steps in distinguishing IoT devices involves leveraging machine learning (ML) techniques on device network flows known as device fingerprinting. Numerous studies have proposed various solutions that incorporate ML and feature selection (FS) algorithms with different degrees of accuracy. Yet, the domain needs a comparative analysis of the accuracy of different classifiers and FS algorithms to comprehend their true capabilities in various datasets. This article provides a comprehensive performance evaluation of several reputable classifiers being used in the literature. The study evaluates the efficacy of filter-and wrapper-based FS methods across various ML classifiers. Additionally, we implemented a Binary Green Wolf Optimizer (BGWO) and compared its performance with that of traditional ML classifiers to assess the potential of this binary meta-heuristic algorithm. To ensure the robustness of our findings, we evaluated the effectiveness of each classifier and FS method using two widely utilized datasets. Our experiments demonstrated that BGWO effectively reduced the feature set by 85.11% and 73.33% for datasets 1 and 2, respectively, while achieving classification accuracies of 98.51% and 99.8%, respectively. The findings of this study highlight the strong capabilities of BGWO in reducing both the feature dimensionality and accuracy gained through classification. Furthermore, it demonstrates the effectiveness of wrapper methods in the reduction of feature sets. 2025 Tahaei et al.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

FDDSGCN: Fractional Decoupling Dynamic Spatiotemporal Graph Convolutional Network for Traffic Forecasting

FDDSGCN: Fractional Decoupling Dynamic Spatiotemporal Graph ...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Xu, Jinpeng Zhao, Chunna Yang, Jing Huang, Yaqun Yang, Yaoyuan Yee, Por Lip School of Information Science & Engineering Yunnan University Kunming China Department of Computer System and Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798350368741

Urban traffic flow management faces increasing challenges due to accelerating urbanization. Traffic data collected from roadside sensors contain complex temporal and spatial dependencies that interact simultaneously. Although Graph Neural Networks and Recurrent Neural Networks have been successful in capturing these dependencies, two critical issues remain: 1) Treating all traffic signals equally fails to capture the nuanced spatiotemporal dependencies hidden in time series data;2) Dynamic traffic conditions hinder the accurate capture of local spatial dependencies, thereby limiting prediction accuracy and reliability. To address these challenges, we propose an innovative model, FDDSGCN. To resolve the first issue, we introduce Fractional Residual Decomposition, which effectively separates traffic data into spatial and temporal signals. For the second issue, we employ Dynamic Spatial-Temporal Graph Convolution with fractional-order weight adjustments to dynamically capture local dependencies. Additionally, the Long Short-Term Dependency module analyzes both long-term and short-term dependencies. Extensive experiments on three public datasets demonstrate the superior performance and practical value of our model. © 2025 IEEE.

关键词： dynamic graph learning Fractional Residual decomposition spatial-temporal graph Traffic prediction

来源：评论

学校读者我要写书评

暂无评论

Fast alternating minimization algorithm for coded aperture snapshot spectral imaging based on sparsity and deep image priors

引用

Applied Optics 2025年第14期64卷 4121-4131页

作者： Zhao, Qile Zhao, Xianhong Ma, Xu Chen, Xudong Arce, Gonzalo R. Key Laboratory of Photoelectronic Imaging Technology System of Ministry of Education of China School of Optics and Photonics Beijing Institute of Technology Beijing100081 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore Department of Electrical and Computer Engineering University of Delaware NewarkDE19716 United States

Coded aperture snapshot spectral imaging is a computational imaging technique used to reconstruct three-dimensional hyperspectral images from one or several two-dimensional projection measurements. However, fewer projection measurements or more spectral channels lead to a severely ill-posed problem, in which case regularization methods have to be applied. In order to significantly improve the accuracy of reconstruction, this paper proposes a fast alternating minimization algorithm based on the sparsity and deep image priors of natural images. By integrating deep image prior into the principle of compressive sensing reconstruction, the proposed algorithm can achieve state-of-the-art results without any training dataset. Extensive experiments show that the Fama-SDIP method significantly outperforms prevailing methods on simulation and real HSI datasets. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved. © 2025 Optica Publishing Group (formerly OSA). All rights reserved.

关键词： Computational Imaging

来源：评论

学校读者我要写书评

暂无评论

Soft-GNN:towards robust graph neural networks via self-adaptive data utilization

引用

Frontiers of computer Science 2025年第4期19卷 1-12页

作者： Yao WU Hong HUANG Yu SONG Hai JIN National Engineering Research Center for Big Data Technology and System Service Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China College of Information and Communication National University of Defense TechnologyWuhan 430019China Department of Computer Science and Operations Research Universitéde MontréalMontreal H3C 3J7Canada

Graph neural networks(GNNs)have gained traction and have been applied to various graph-based data analysis tasks due to their high ***,a major concern is their robustness,particularly when faced with graph data that has been deliberately or accidentally polluted with *** presents a challenge in learning robust GNNs under noisy *** address this issue,we propose a novel framework called Soft-GNN,which mitigates the influence of label noise by adapting the data utilized in *** approach employs a dynamic data utilization strategy that estimates adaptive weights based on prediction deviation,local deviation,and global *** better utilizing significant training samples and reducing the impact of label noise through dynamic data selection,GNNs are trained to be more *** evaluate the performance,robustness,generality,and complexity of our model on five real-world datasets,and our experimental results demonstrate the superiority of our approach over existing methods.

关键词： graph neural networks node classification label noise robustness

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-based smart galliformes farm management system

引用

Journal of Umm Al-Qura University for engineering and Architecture 2025年第1期16卷 64-77页

作者： Himel, Galib Muhammad Shahriar Islam, Md. Masudul Kader, Md. Nasimul Rahman, Mustafizur School of Computing and Mathematical Sciences University of Greenwich London United Kingdom Department of Computing and Information System Daffodil International Academy Dhaka Bangladesh Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Department of Computing and Information System Daffodil International University Dhaka Bangladesh

This article introduces an Artificial Intelligent-driven system for Galliformes Farm Management, consulting, and disease control. Comprising both a web-based mobile app and a website, the system integrates physical electronic devices to regulate intelligent automation. The application employs Artificial Neural Network and computer vision for the identification of breeds and the recognition of diseases in galliform birds, utilizing TensorFlow for real-time detection. It notifies local farmers about bird flu infections with an integrated infection map using Google's map Application Programming Interface. The system also controls farm temperature and humidity through microcontrollers and sensors, offering consulting features such as cost calculation, food chart generation, and drug suggestions. © The Author(s) 2025.

关键词： Artificial intelligence Breed identification Disease classification Image classification Poultry farm automation Smart farm management

来源：评论

学校读者我要写书评

暂无评论

Collaborative Deadline-sensitive Multi-task Offloading in Vehicular-Cloud Networks 17

Collaborative Deadline-sensitive Multi-task Offloading in Ve...

引用

17th International Conference on COMmunication systems and NETworkS, COMSNETS 2025

作者： Kumar, Prasanna Sushma, S.A. Chandrasekaran, K. Addya, Sourav Kanti National Institute of Technology Karnataka Cloud and Smart System Services Lab Department of Computer Science and Engineering Surathkal India Siddaganga Institute of Technology Cloud and Smart System Services Lab Tumakuru India

ISBN: (纸本)9798331531195

With the growing technological advancements in the Internet and advanced functionalities in vehicular networks, it becomes crucial to execute tasks quickly and efficiently. However, the limited onboard computational capacity and vehicle mobility make it challenging to accomplish latency-sensitive tasks efficiently. Task offloading provides a promising solution to overcome these challenges. Cloud data centers provide efficient solutions, but returning the results to the vehicles takes longer due to the large physical distance. Leveraging edge servers to execute latency-sensitive tasks provides a fast, interactive response and less transmission cost. However, in a dynamic network, vehicles will be in constant motion with varying speeds, resulting in frequent handoffs from one base station to another. Our proposed work aims to select the optimal nodes to perform binary offloading with minimum cost using the collaborative vehicular network. We use a greedy-based offloading approach to address these challenges and achieve better quality-of-service and quality-of-experience in a dynamic environment to minimize costs, delay reduction ratio, and satisfaction ratio. The proposed work outperforms the baseline by 60.44%, 53.43% in reducing total system cost, delay reduction ratio, and 36% improvement in the satisfaction ratio compared to baseline algorithms. © 2025 IEEE.

关键词： Quality of service

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：