检索结果-内蒙古大学图书馆

10th International Conference on Frontier Computing, FC 2020

作者： Li, Pengzhi Li, Jianqiang Xie, Haihua Pei, Yan Feng, Hui School of Software Engineering Beijing University of Technology Beijing100124 China Computer Science Division University of Aizu Aizuwakamatsu965-8580 Japan

ISBN: (纸本)9789811601149

In this paper, we propose a diagnosis and classification method of colonography CT Images based on deep learning and image reconstruction, which is processed to increase the difference between pathological features and other healthy tissues and improve the accuracy of pathological images classification. It is difficult to accurately distinguish polyps features owing to the variability of appearances, fuzzy boundaries, heterogeneous densities, shapes and sizes of lesions. Some study results show that the ResNet network has a better performance than other methods and has broad application prospects in the identification of CT images. We used the improved ResNet network as the classification model. We completed the classification experiment on the colonography datasets. Through comparative experiments, we found gradient features play an important role in the classification of colonography CT images. More unexpectedly, for CT images of colonography, the classification effect of CT images with small information entropy is excellent. A new "RGB" image containing two channels of gradient features and one channel of LBP features is very effective for classification, which may be a new attempt. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need

arXiv

引用

arXiv 2024年

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MURDOC: Transforming Pixels into Perception for Camouflage Detection

MURDOC: Transforming Pixels into Perception for Camouflage D...

引用

Conference on Digital Avionics Systems (DASC)

作者： Debra Hogue Zak Kastl Joseph Karch Don Nguyen Lacey Schley Justin Lewis Shane Connelly Chris Weaver School of Computer Science at the University of Oklahoma. US Air Force's 76th Software Engineering Group. Oklahoma Aerospace and Defense Innovation Institute at the University of Oklahoma. Department of Psychology and Center for Applied Social Research the University of Oklahoma School of Computer Science at the University of Oklahoma

ISBN: (数字)9798350349610

ISBN: (纸本)9798350349627

The MURDOC project introduces an application to enhance trustworthiness and explainability in computer vision models, focusing on camouflage detection. It aims to address the need for transparent and interpretable AI systems in sensitive domains such as security and defense. MURDOC integrates advanced eXplainable AI techniques including off-ramps for collecting interpretable insights, attention mechanisms for high-lighting relevant features, and a user-centric image pre-processing tool within the visualization interface. This paper offers an assessment of MURDOC's potential impact on trustworthiness and explainability in camouflaged object detection tasks. It discusses and assesses the potential effectiveness of off-ramps in gathering XAI output at various model stages, such as feature maps, attention mechanisms, and activation maps. Additionally, the paper investigates how user-driven image pre-processing mechanisms may enhance the trustworthiness of the model's predictions and decisions, allowing users to modify the input and observe prediction changes. As a work in progress, the development of MURDOC shows promise in bridging the gap for transparency and interpretability in camouflage detection. The paper also discusses the challenges, future directions, and potential applications of MURDOC's capabilities in diverse domains requiring transparent and trustworthy AI systems. The source code for the version of MURDOC in this paper is available on GitHub at: https://***/Department-70/DASC_2024.

关键词： Visualization Attention mechanisms Uncertainty Source coding Buildings Security Artificial intelligence Graphical user interfaces Testing software development management

来源：评论

学校读者我要写书评

暂无评论

Beyond Accuracy: Evaluating certainty of AI models for brain tumour detection

引用

computers in Biology and Medicine 2025年 193卷 110375-110375页

作者： Nisa, Zaib Un Bhatti, Sohail Masood Jaffar, Arfan Mazhar, Tehseen Shahzad, Tariq Ghadi, Yazeed Yasin Almogren, Ahmad Hamam, Habib Department of Computer Science and Information Technology The Superior University Lahore54600 Pakistan Lahore54600 Pakistan School of Computer Science National College of Business Administration and Economics Lahore54000 Pakistan Department of Computer Engineering COMSATS University Islamabad Sahiwal Campus Sahiwal57000 Pakistan Department of Computer Science and Software Engineering Al Ain University Abu Dhabi12555 United Arab Emirates Department of Computer Science College of Computer and Information Sciences King Saud University Riyadh11633 Saudi Arabia School of Electrical Engineering University of Johannesburg Johannesburg2006 South Africa Av. Grandes Ecoles LibrevilleBP 1989 Gabon University of Ha'il Ha'il55476 Saudi Arabia Department of Computer Science School Education Department Government of Punjab Layyah31200 Pakistan Faculty of Engineering Uni de Moncton MonctonNBE1A3E9 Canada

Brain tumors pose a severe health risk, often leading to fatal outcomes if not detected early. While most studies focus on improving classification accuracy, this research emphasizes prediction certainty, quantified through loss values. Traditional metrics like accuracy and precision do not capture confidence in predictions, which is critical for medical applications. This study establishes a correlation between lower loss values and higher prediction certainty, ensuring more reliable tumor classification. We evaluate CNN, ResNet50, XceptionNet, and a Proposed Model (VGG19 with customized classification layers) using accuracy, precision, recall, and loss. Results show that while accuracy remains comparable across models, the Proposed Model achieves the best performance (96.95 % accuracy, 0.087 loss), outperforming others in both precision and recall. These findings demonstrate that certainty-aware AI models are essential for reliable clinical decision-making. This study highlights the potential of AI to bridge the shortage of medical professionals by integrating reliable diagnostic tools in healthcare. AI-powered systems can enhance early detection and improve patient outcomes, reinforcing the need for certainty-driven AI adoption in medical imaging. © 2025

关键词： Electrotherapeutics

来源：评论

学校读者我要写书评

暂无评论

Convolution-Enhanced Transformer with Frequency Domain Contrastive Learning for Image Deraining

Convolution-Enhanced Transformer with Frequency Domain Contr...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Cheng Wang Wei Li School of Artificial Intelligence and Computer Science & Jiangsu Key Laboratory of Media Design and Software Technology & Engineering Research Center of Itelligent Technology for Healthcare Ministry of Education Jiangnan University Wuxi China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Rainfall, as a ubiquitous atmospheric phenomenon, causes visual image degradation through rain streaks, which in turn hinders human vision and degrades the performance of subsequent computer vision algorithms. In order to further improve the performance of visual algorithms in harsh rain environments, image rain removal technology has become a hot topic in this field. In computer vision, the integration of the Vision Transformer (ViT) marks an important progress, and its transfer application to the image rain removal task has achieved remarkable success. However, the application of transformers in this task still faces challenges. While they excel at modelling long-range dependencies, transformers are less adept at modelling local contexts for image restoration tasks. Moreover, the internal transmission of features within dense transformer layers often needs more finesse. In this paper, we tackle these shortcomings by incorporating convolutional mechanisms within both the self-attention components of the transformer blocks and the subsequent feed-forward networks. We refine the feature flows amalgamated between recursive transformer blocks by utilizing feature fusion strategies. To further refine the high-frequency textural details of images, we employ frequency domain contrastive learning techniques to augment the delineation of contrastive sample information, ensuring that the restored image closely resembles the clear image in terms of texture structure while maintaining a distinction from the rain image. Extensive quantitative and qualitative experimental results show that the proposed deraining network surpasses mainstream methods on public datasets.

关键词： computer vision Visualization Rain Frequency-domain analysis Computational modeling Contrastive learning Transformers

来源：评论

学校读者我要写书评

暂无评论

Learning Generalizable Models via Disentangling Spurious and Enhancing Potential Correlations

arXiv

引用

arXiv 2024年

作者： Wang, Na Qi, Lei Guo, Jintao Shi, Yinghuan Gao, Yang The National Key Laboratory for Novel Software Technology The National Institute of Healthcare Data Science Nanjing University Nanjing210023 China The School of Computer Science and Engineering Southeast United States Ministry of Education Nanjing211189 China

Domain generalization (DG) intends to train a model on multiple source domains to ensure that it can generalize well to an arbitrary unseen target domain. The acquisition of domain-invariant representations is pivotal for DG as they possess the ability to capture the inherent semantic information of the data, mitigate the influence of domain shift, and enhance the generalization capability of the model. Adopting multiple perspectives, such as the sample and the feature, proves to be effective. The sample perspective facilitates data augmentation through data manipulation techniques, whereas the feature perspective enables the extraction of meaningful generalization features. In this paper, we focus on improving the generalization ability of the model by compelling it to acquire domain-invariant representations from both the sample and feature perspectives by disentangling spurious correlations and enhancing potential correlations. 1) From the sample perspective, we develop a frequency restriction module, guiding the model to focus on the relevant correlations between object features and labels, thereby disentangling spurious correlations. 2) From the feature perspective, the simple Tail Interaction module implicitly enhances potential correlations among all samples from all source domains, facilitating the acquisition of domain-invariant representations across multiple domains for the model. The experimental results show that Convolutional Neural Networks (CNNs) or MultiLayer Perceptrons (MLPs) with a strong baseline embedded with these two modules can achieve superior results, e.g., an average accuracy of 92.30% on Digits-DG. Source code is available at https://***/RubyHoho/DGeneralization. Copyright © 2024, The Authors. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Research on the structure of a cloud field distribution measurement system in a high-speed icing wind tunnel

Research on the structure of a cloud field distribution meas...

引用

2024 International Conference on Optoelectronic Materials and Devices, ICOMD 2024

作者： Zhang, Quan Qing, Chao Zuo, Chenglin Hu, Jiahui Li, Yan School of Computer Science and Software Engineering Southwest Petroleum University Chengdu610500 China Low Speed Aerodynamics Institute China Aerodynamics Research and Development Center Sichuan Mianyang621000 China Key Laboratory of Icing and Anti/De-Icing China Aerodynamics Research and Development Center Mianyang621000 China Intelligent Oil and Gas Laboratory Southwest Petroleum University Chengdu610500 China

ISBN: (数字)9781510689046

ISBN: (纸本)9781510689039

This study addresses the need for cloud uniformity measurement in icing wind tunnel experiments by designing and developing a laser extinction tomography system for circular icing wind tunnels. The system is aimed at enhancing the accuracy of wind tunnel experiments simulating aircraft icing behavior, providing precise data for research on aircraft icing and anti-icing technologies. The system consists of 24 radiation sources and 24 detectors, uniformly distributed around a circular ring with a diameter of 800 mm, enabling real-time monitoring and analysis of cloud field uniformity. Using COMSOL multiphysics simulation software, the propagation paths of the laser through the cloud field were simulated, optimizing the arrangement of radiation sources and detectors to improve measurement accuracy. By integrating the Algebraic Reconstruction Technique (ART) with regularization methods, the image reconstruction algorithm enhances both precision and stability, effectively capturing the spatial distribution of the cloud field. Experimental results demonstrate that the system accurately reflects the cloud field distribution, with the error ratio controlled within acceptable limits, validating the system’s accuracy and reliability. This system provides a high-precision measurement platform for aircraft icing research and anti-icing technology experiments. © 2025 SPIE.

关键词： Tomography

来源：评论

学校读者我要写书评

暂无评论

CARE-EMRs: Efficient and Privacy-Preserving Data Sharing Framework for Electronic Medical Records

CARE-EMRs: Efficient and Privacy-Preserving Data Sharing Fra...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yu Tao Lu Zhou Yi Zhu Yuhang Li Chunpeng Ge College of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Nanjing China College of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Collaborative Innovation Center of Novel Software Technology and Industrialization Nanjing China Joint SDU-NTU Centre for Artificial Intelligence Research (C-FAIR) & Software School Shandong University Jinan China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Cross-institutional Electronic Medical Records (EMRs) sharing significantly improves healthcare quality and reduces costs. Current EMRs are often stored on cloud servers and protected by Attribute-based Encryption (ABE) for access control. Cross-institutional sharing allows doctors to request EMRs access from target Healthcare Institutions (HIs) through attribute-based collaboration, enabling flexible and secure access. However, existing collaboration in practical EMRs sharing scenarios suffers from inefficiency, hindering timely access and treatment. This paper proposes an efficient and privacy-preserving data sharing framework for EMRs, called CARE-EMRs. CARE-EMRs enables efficient EMRs data access for doctors across different HIs through an outsourcing mechanism. Furthermore, we designed an improved cryptographic primitive PPD-CP-ABE to serve as the security foundation for CARE-EMRs framework, ensuring privacy of the outsourced process. We prove the security of CARE-EMRs. Performance analysis indicates that it significantly reduces the computation and communication overhead.

关键词： Performance evaluation Privacy Data privacy Collaboration Medical services Outsourcing Performance analysis Encryption Servers Electronic medical records

来源：评论

学校读者我要写书评

暂无评论

Classical approaches and new deep learning trends to assist in accurately and efficiently diagnosing ear disease from otoscopic images

Classical approaches and new deep learning trends to assist ...

引用

European Workshop on Visual Information Processing (EUVIP)

作者： Dhruv Chetan Jobanputra Mohammed Bennamoun Farid Boussaid Lian Xu Jafri Kuthubutheen Computer Science and Software Engineering The University of Western Australia Perth Australia Electrical Electronic and Computer Engineering The University of Western Australia Perth Australia Division of Surgery Medical School The University of Western Australia Perth Australia

Rural communities in Australia have limited access to Ear, Nose and Throat (ENT) specialists, resulting in a lack of expertise to provide a diagnosis of complex and chronic ear diseases. This literature review examines previous attempts at creating a computer-aided tool to accurately diagnose ear disease and gaps in the literature. A systematic search was conducted to identify relevant papers and the latest best trends in technology. Four papers showed significant results in ear disease detection with deep learning models providing the best performance. Some studies using larger datasets consisting of endoscopic images obtained accuracies of over 90%. No adequate model was found that used otoscopic images with a sensitivity of over 90%. Endoscopic images provide better quality images, making it unclear how the models would perform on otoscopic images. Advanced techniques such as Transformers have not yet been tested in ear disease detection and could help improve model accuracy.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepRicci: Self-supervised Graph Structure-Feature Co-Refinement for Alleviating Over-squashing

arXiv

引用

arXiv 2024年

作者： Sun, Li Huang, Zhenhao Wu, Hua Ye, Junda Peng, Hao Yu, Zhengtao Yu, Philip S. School of Control and Computer Engineering North China Electric Power University Beijing102206 China School of Computer Science Beijing University of Posts and Telecommunications Beijing100876 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Department of Computer Science University of Illinois ChicagoIL United States

Graph Neural Networks (GNNs) have shown great power for learning and mining on graphs, and Graph Structure Learning (GSL) plays an important role in boosting GNNs with a refined graph. In the literature, most GSL solutions either primarily focus on structure refinement with task-specific supervision (i.e., node classification), or overlook the inherent weakness of GNNs themselves (e.g., over-squashing), resulting in suboptimal performance despite sophisticated designs. In light of these limitations, we propose to study self-supervised graph structure-feature co-refinement for effectively alleviating the issue of over-squashing in typical GNNs. In this paper, we take a fundamentally different perspective of the Ricci curvature in Riemannian geometry, in which we encounter the challenges of modeling, utilizing and computing Ricci curvature. To tackle these challenges, we present a self-supervised Riemannian model, DeepRicci. Specifically, we introduce a latent Riemannian space of heterogeneous curvatures to model various Ricci curvatures, and propose a gyrovector feature mapping to utilize Ricci curvature for typical GNNs. Thereafter, we refine node features by geometric contrastive learning among different geometric views, and simultaneously refine graph structure by backward Ricci flow based on a novel formulation of differentiable Ricci curvature. Finally, extensive experiments on public datasets show the superiority of DeepRicci, and the connection between backward Ricci flow and over-squashing. Codes of our work are given in https://***/RiemanGraph/. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

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：