检索结果-内蒙古大学图书馆

COVID19 detection in chest x-ray using vision-transformer with different patch dimensions

Procedia computer science 2024年 235卷 3438-3446页

作者： Seifedine Kadry Laith Abualigah Rubén González Crespo Elena Verdú Robertas Damasevicius Vijendra Singh Venkatesan Rajinikanth Department of Applied Data Science Noroff University College Kristiansand Norway Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Computer Science Department Al al-Bayt University Mafraq 25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan MEU Research Unit Middle East University Amman 11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang 11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya 27500 Malaysia Higher School of Engineering and Technology Universidad Internacional de La Rioja Logroño 26006 Spain Department of Applied Informatics Vytautas Magnus University 53361 Kaunas Lithuania School of Computer Science University of Petroleum and Energy Studies Dehradun 248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India

computerized disease detection systems (CDDs) have proven effective for automatic screening in recent years. Among the standard procedures in hospitals for faster and more accurate diagnosis is medical imaging-based disease screening. We aim to develop a CDD that detects COVID-19 using chest X-rays pre-trained vision transformers (PVTs). This scheme includes the following steps: (1) collecting images and resizing them, (2) implementing PVT for feature extraction, and (3) binary classifying the results and validating the proposed schemes. To prove the merit of the developed scheme, 4800 images (2400 normal and 2400 COVID-19) are analyzed. MLP classifiers verify the PVT performance using patch sizes of 6, 12, and 24. A patch size 24 results in 97.5% accuracy for the proposed CDD system. When patch sizes are increased to 12, accuracy increases to over 98%. For this specific task, smaller patch sizes are more effective. These high-accuracy results demonstrate the effectiveness of the developed scheme for detecting COVID-19 in chest X-rays.

关键词： Covid19 X-ray Vision-transformer Patch-size Classification

来源：评论

学校读者我要写书评

暂无评论

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

arXiv

引用

arXiv 2024年

作者： Ye, Maoyuan Zhang, Jing Liu, Juhua Liu, Chenyu Yin, Baocai Liu, Cong Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China IFLYTEK Research IFLYTEK CO. LTD. China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue 639798 Singapore

The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset. Subsequently, with these complete labels, we launch the end-to-end trainable Hi-SAM based on the TS architecture with a customized hierarchical mask decoder. During inference, Hi-SAM offers both automatic mask generation (AMG) mode and promptable segmentation (PS) mode. In the AMG mode, Hi-SAM segments pixel-level text foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing. As for the PS mode, Hi-SAM provides word, text-line, and paragraph masks with a single point click. Experimental results show the state-of-the-art performance of our TS model: 84.86% fgIOU on Total-Text and 88.96% fgIOU on TextSeg for pixel-level text segmentation. Moreover, compared to the previous specialist for joint hierarchical detection and layout analysis on HierText, Hi-SAM achieves significant improvements: 4.73% PQ and 5.39% F1 on the text-line level, 5.49% PQ and 7.39% F1 on the paragraph level layout analysis, requiring 20× fewer training epochs. The code is available at Hi-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Masks

来源：评论

学校读者我要写书评

暂无评论

Automatic liver-vessel examination from CT slice using Kapur’s thresholding and watershed algorithm

引用

Procedia computer science 2024年 235卷 1824-1831页

computerized medical image examination (CMIE) plays a significant role in modern hospitals to achieve the necessary tasks, like segmentation and classification. By segmenting an image, we can extract a particular section for examination. A two-dimensional computed tomography (CT) slice was used for liver-vessel examination (LiVE). A simple automatic technique for supporting LiVE is being developed in this research. A CT slice is collected, a 3D to 2D conversion is done, (ii) Kapur’s tri-level thresholding and Hummingbird-Optimizer is used to enhance the CT slice, (iii) the watershed algorithm (WA) is used to extract the vessel, and (iv) the WA is compared and verified against the segmentation methods chosen. WA provides better segmentation results than other methods because it is an automatic approach. Using the chosen image database, the proposed technique achieves an overall segmentation accuracy of >97%. Other segmentation problems can be used in the future to verify the merit of this scheme.

关键词： liver CT liver-vessel Kapur’s thresholding hummingbird-optimizer watershed-algorithm

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Deep Learning Framework for Gastrointestinal Tract Classification Based on Endoscopic Images

A Hybrid Deep Learning Framework for Gastrointestinal Tract ...

引用

Communication & Computing (WCONF), World Conference on

作者： Shridhar Kulkarni Gopal Kumar Thakur Kumbham Bhargavi Ch Ramesh Babu G Bindu Madhavi Pundru Chandra Shaker Reddy Department of Data Sciences Harrisburg University of Science & Technology Pennsylvania United States of America Department of CSE (AI & ML) Keshav Memorial Institute of Technology Hyderabad Telangana India Department of Information Technology Matrusri Engineering College Hyderabad Telangana India Department of CSE (AIML) Geethanjali College of Engineering and Technology Hyderabad India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798350395327

ISBN: (纸本)9798350395334

This work introduces a set of pre-trained models that can accurately identify GI (gastrointestinal) diseases and disorders using endoscopic pictures. For the purpose of disease classification in the gastrointestinal system, we provide GIT- NET, a weighted average ensemble model. We used an eight- class KVASIR v2 dataset to test the model. Using individual models for categorization increases the likelihood of misclassification because they might not learn all the classes' traits sufficiently. One possible explanation is that different models may excel at learning the traits of certain classes relative to others. We provide an ensemble-model that uses the anticipations of three pre-trained models, namely DenseNet201 (94.54% accuracy), InceptionV3 (88.38% accuracy), &ResNet50 (90.58% accuracy). The two approaches used to aggregate the anticipations of the base learners are model averaging. Based on the results of the model evaluations, the weighted average ensemble achieved a 95.00% success rate, while the model averaging ensemble achieved a 92.96% success rate. Both the model average ensemble and each distinct model are surpassed in performance by the weighted average ensemble. When using an ensemble of base learners, features that were mislearned by discrete base learners can be accurately classified, according to the evaluation results.

关键词： Deep learning Accuracy Computational modeling Aggregates Manuals Gastrointestinal tract Diseases Tumors Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

An Empirical Approach of Developing Domain Based Ontology in the Field of Bioinformatics

An Empirical Approach of Developing Domain Based Ontology in...

引用

Advance Computing and Innovative Technologies in engineering (ICACITE), International Conference on

作者： Devanolla Suresh E.Afreen Banu R. Karthikeyan Pramod Kumar Naik Safaa Hallol Mohammed Tareq Hafdhi Abdtawfeeq Department of Computer Science & Technology Madanapalle Institute of Technology & Science Madanapalle CSE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of CSE Artificial Intelligence and Data Analytics Sri Ramachandra Institute of Higher Education and Research Department of CSE Dayananda Sagar University Bengaluru Collage of Pharmacy National University of Science and Technology Dhi Qar Iraq Al-Farahidi university Baghdad Iraq

ISBN: (数字)9798350360165

ISBN: (纸本)9798350360172

From a macro viewpoint, it is essential to comprehend the similarities across human illnesses in order to identify underlying mechanisms at the microscopic level. Previous studies have shown that employing machine learning methods or merging many data sources can improve performance in sickness similarity measurement. However, there is currently a gap in the development of a useful framework for information extraction and integration from a range of biological data using deep learning models. We introduce CoGO, a Contrastive learning system that predicts commonalities in illnesses based on gene networks and ontology structure. Gene ontology (GO) and gene interaction network domain information is integrated into CoGO using graph deep learning models. Graph deep learning models are first used to encode gene and GO word features from independent graph structure data. Gene and GO characteristics are then mapped via a nonlinear projection to a shared embedding space. Next, by using cross-view contrastive loss to increase the agreement of related gene-GO links, meaningful gene representations are generated. Finally, to calculate disease similarity, CoGO computes the cosine similarity of sickness representation vectors derived from related gene embeddings.

关键词： Deep learning Biological system modeling Soft sensors Microscopy Merging Ontologies Information retrieval

来源：评论

学校读者我要写书评

暂无评论

CNN segmentation of skin melanoma in pre-processed dermoscopy images

引用

Procedia computer science 2024年 235卷 2775-2782页

作者： Seifedine Kadry Elena Verdú Robertas Damasevicius Laith Abualigah Vijendra Singh Venkatesan Rajinikanth Department of Applied Data Science Noroff University College Kristiansand Norway Artificial Intelligence Research Center (AIRC) Ajman University Ajman 346 United Arab Emirates Department of Electrical and Computer Engineering Lebanese American University Byblos Lebanon Higher School of Engineering and Technology Universidad Internacional de La Rioja Logroño 26006 Spain Department of Applied Informatics Vytautas Magnus University 53361 Kaunas Lithuania Computer Science Department Al al-Bayt University Mafraq 25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman 19328 Jordan MEU Research Unit Middle East University Amman 11831 Jordan School of Computer Sciences Universiti Sains Malaysia Pulau Pinang 11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya 27500 Malaysia School of Computer Science University of Petroleum and Energy Studies Dehradun 248007 India Department of Computer Science and Engineering Division of Research and Innovation Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai 602105 India

Using medical data to improve diagnosis accuracy has recently become common practice in hospitals. A modern computing environment has enabled real-time diagnosis of medical data using Convolutional Neural Networks (CNNs). To extract and evaluate skin melanoma recorded with digital dermatoscopy images (DDI), we developed a CNN segmentation framework. In this proposal, four phases are proposed: (i) DDI collection and resizing, (ii) DDI enhancement using pre-processing techniques, (iii) CNN segmentation for lesion extraction, (v) Comparing the extracted sections to the ground truth images, and (v) Verifying whether the framework is valid. Using DDI pre-processed with (i) Traditional procedures, (ii) Otsu’s thresholding, (iii) Kapur’s thresholding, and (iv) Fuzzy-Tsallis thresholding, this proposal examines the different CNN segmentation schemes presented in the literature. For mining skin lesions, the Moth-Flame Algorithm (MFA) combined with tri-level thresholding achieves an optimal threshold for the DDI. With Fuzzy-Tsallis thresholding images, the VGG-UNet performs better than the alternatives. This framework helps to achieve better values of Jaccard (88.47±2.13%), Dice (93.08±1.17%), and Accuracy (98.64±0.71%) on the chosen DDI database.

关键词： Watershed-algorithm skin melanoma segmentation Fuzzy-Tsallis entropy Moth-Flame algorithm evaluation

来源：评论

学校读者我要写书评

暂无评论

$k$k-TEVS: A $ k$k-Times E-Voting Scheme on Blockchain With Supervision

引用

IEEE Transactions on Dependable and Secure Computing 2024年第3期22卷 2326-2337页

作者： Yang Liu Debiao He Min Luo Lianhai Wang Cong Peng School of Cyber Science and Engineering Wuhan University Wuhan China Institute of Information Technology Shenzhen Institute of Information Technology Shenzhen China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shanghai Technology Innovation Centre of Distributed Privacy-Preserving Artificial Intelligence Matrix Elements Technologies Shanghai China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

The e-vote is regarded as a way to express the opinion that the voters ask for. Actually, the e-vote could be applied wildly like questionnaire, survey and feedback. Moreover, the coexistences of efficiency and security as well as transparency and privacy could be considered as building blocks in the e-vote system. The blockchain could provide a public access board to reduce the storage costs for the field consisted of the vote group manager (GM) with its vote assistants (VA). Particularly the $k$ -times anonymous authentication ( $k$ -TAA) could also be a practical approach to preserve voters’ privacy and reduce the computation costs during the vote process. However, the e-vote scheme with pure $k$ -TAA strategy could damage either the supervision of voting or the efficiency and consistency of authentication process. What’s more, the impacts of dishonest voters couldn’t be stopped until the vote end. To tackle these problems, we apply the accumulator technology to add or revoke the voters at any time and extend the framework of $k$ -TAA with the update process for the e-vote on blockchain for supervision ( $ k$ -TEVS). In our scheme, the voter updates his membership witness and proves the fact that he is still a valid member with respective VA under the latest accumulator value. What’s more, this witness update operation is not contained in the authentication process, which means that the authentication process is still constant and efficient. Moreover, our add or delete update process with signature of knowledge needs only one pairing operation. For the security, we prove that the relaxed anonymity still holds in the $ k$ -TEVS framework. Finally, We implement $ k$ -TEVS scheme, the Emura’s work [1] and the Huang’s work [2] for comparison. Then we make time cost and communication cost experiments, which present the feasibility and practicality of this scheme.

关键词： Blockchains Authentication Costs Protocols Security Privacy Surveys Electronic voting computer science Information security

来源：评论

学校读者我要写书评

暂无评论

Efficient Last-iterate Convergence Algorithms in Solving Games

arXiv

引用

arXiv 2023年

作者： Meng, Linjian Zhang, Youzhi Ge, Zhenxing Yang, Shangdong Ding, Tianyu Li, Wenbin Yang, Tianpei An, Bo Gao, Yang National Key Laboratory for Novel Software Technology Nanjing University China Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation CAS Hong Kong Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications China Microsoft Corporation United States School of Computer Science and Engineering Nanyang Technological University Singapore

To establish last-iterate convergence for Counterfactual Regret Minimization (CFR) algorithms in learning a Nash equilibrium (NE) of extensive-form games (EFGs), recent studies reformulate learning an NE of the original EFG as learning the NEs of a sequence of (perturbed) regularized EFGs. Consequently, proving last-iterate convergence in solving the original EFG reduces to proving last-iterate convergence in solving (perturbed) regularized EFGs. However, the empirical convergence rates of the algorithms in these studies are suboptimal, since they do not utilize Regret Matching (RM)-based CFR algorithms to solve perturbed EFGs, which are known the exceptionally fast empirical convergence rates. Additionally, since solving multiple perturbed regularized EFGs is required, fine-tuning across all such games is infeasible, making parameter-free algorithms highly desirable. In this paper, we prove that CFR+, a classical parameter-free RM-based CFR algorithm, achieves last-iterate convergence in learning an NE of perturbed regularized EFGs. Leveraging CFR+ to solve perturbed regularized EFGs, we get Reward Transformation CFR+ (RTCFR+). Importantly, we extend prior work on the parameter-free property of CFR+, enhancing its stability, which is crucial for the empirical convergence of RTCFR+. Experiments show that RTCFR+ significantly outperforms existing algorithms with theoretical last-iterate convergence guarantees. Copyright © 2023, The Authors. All rights reserved.

关键词： Nash equilibrium

来源：评论

学校读者我要写书评

暂无评论

Incomplete multi-view clustering via efficient anchor tensor recovery framework

引用

Neural Networks 2025年 190卷 107652页

作者： Ji, Jintian Feng, Songhe Huang, Jie Wei, Taotao Feng, Xiang Lv, Peiwu Li, Bing School of Computer Science and Technology Beijing Jiaotong University Beijing100044 China Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China Jiangsu Railway Group Co. Ltd. Nanjing210012 China Jiangsu Province Engineering Research Center of Intelligent and Green Railway Nanjing210012 China Beijing100190 China

Tensor-based Incomplete Multi-view Clustering (TIMC) methods have received widespread attention due to the powerful data recovery capability of capturing cross-view high-order correlation. Although such methods have achieved remarkable progress, they still suffer from the following problems: (1) The extremely high computational complexity makes it hard for tensor-based methods to handle large-scale multi-view data. (2) Geometric structure constraints in the sample space often lead to high computational complexity and redundancy of structural information. (3) The commonly used Tensor Nuclear Norm (TNN) over-penalizes the primary rank components, leading to a sub-optimal representation tensor. Being aware of these, we propose Incomplete Multi-View Clustering with Efficient Anchor Tensor Recovery Framework (EATER). Specifically, it learns a group of anchors to construct a low-rank anchor tensor to recover the missing data with the high-order correlation among views and the geometric structure in the learned representation tensor is enhanced by an Anchor Laplacian Regularization (ALR). Moreover, instead of employing TNN, we adopt a tighter Non-convex Tensor Rank (NTR) to capture the multi-view high-order correlation effectively. An efficient iterative optimization algorithm is designed to solve the EATER, which is time-economical and enjoys favorable convergence. Extensive experimental results on various datasets demonstrate the superiority of the proposed algorithm as compared to state-of-the-art methods. © 2025

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Intelligent Personalized Nutrition Guidance System Using IoT and Machine Learning Algorithm

Intelligent Personalized Nutrition Guidance System Using IoT...

引用

International Conference on Smart Technologies For Smart Nation (SmartTechCon)

作者： P. Santhuja Elangovan Guruva Reddy Subramani Roy Choudri M. Muthulekshmi S. Balaji Department of Computer Science Engineering CMR Technical Campus Hyderabad Telangana India Department of Artificial Intelligence and Data Science Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh India Department of Computer Science and Engineering Vardhaman College of Engineering Hyderabad Telangana India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India Department of Information Technology Sri Shanmugha College of Engineering and Technology Salem Tamil Nadu India

Nowadays, dietary issues are increasing around the world. Numerous problems, such as weight gain, obesity, diabetes, etc., can arise from an unbalanced diet. By integrating image processing, the system can assess food images in new ways to provide personalized solutions for better eating habits. The system uses machine learning, IoT, and image processing techniques to evaluate food image data and extract useful information. IoT devices like smartphones or specialized cameras take images of food and send to the cloud for analysis. The Support Vector Machine (SVM) is a machine learning technique that is integrated with Internet of Things (IoT) technology in this study to propose a novel method for creating a system that uses personalized nutritional suggestions. The SVM algorithm is then used to analyze and analyze this data to find patterns, correlations, and individual dietary requirements. A cloud database is used to process and store all the data related to food consumption. The system analyzes food images and determines the nutrition and caloric content of the food using image processing and segmentation. The system takes up new abilities using an extensive collection of dietary records that have been labeled and include details about the sorts of foods, portion sizes, and nutritional value. The system can predict and identify users' nutritional needs, deficits, and personalized dietary objectives by using this trained SVM model to their nutritional data.

关键词：

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：