检索结果-内蒙古大学图书馆

An innovative approach to classify meniscus tears by reducing vision transformers features with elasticnet approach

Journal of Supercomputing 2025年第4期81卷 1-29页

作者： Genç, Hasan Koç, Canan Yüzgeç Özdemir, Esra Özyurt, Fatih Elazig Fethi Sekin City Hospital Elazig Turkey Faculty of Engineer Software Engineering Firat University Elazig Turkey Faculty of Engineering and Architecture Computer Engineering Bingöl University Elazig Turkey

Meniscal tears, a prevalent orthopedic condition caused by abrupt knee movements, excessive load, or injury, require an accurate diagnosis for effective treatment. This study investigates the vision transformer (ViT) models' efficacy in automated classification of meniscus pathologies. It also explores how feature reduction using the ElasticNet method can improve classification accuracy and computational efficiency. The study utilized MRI scans from a dataset comprising 5000 images collected from clinical cases. Initially, classification was performed using EfficientNet and SqueezeNet architectures. Subsequently, feature extraction was conducted using ViT models, generating a feature set of 1000 dimensions. ElasticNet was employed to reduce features before reclassification using support vector machines (SVM). Model performance was evaluated based on accuracy, precision, sensitivity, and specificity. The ViT_base_32 model achieved a classification accuracy of 99.9% with a processing time of 1.2 s. Feature reduction via ElasticNet significantly enhanced classification performance while maintaining high precision, sensitivity, and specificity. These improvements demonstrate the effectiveness of combining ViT models with ElasticNet to diagnose meniscal tears. The findings highlight the potential of vision transformer models, in conjunction with ElasticNet, to provide rapid and highly accurate diagnostic assistance for meniscal injuries. This methodology shows promise for application to other medical diagnostic domains, offering valuable advancements in healthcare technology. © The Author(s) 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

DocTTT: Test-Time Training for Handwritten Document Recognition Using Meta-Auxiliary Learning

DocTTT: Test-Time Training for Handwritten Document Recognit...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

作者： Gu, Wenhao Gu, Li Wang, Ziqiang Suen, Ching Yee Wang, Yang Concordia University Department of Computer Science and Software Engineering Canada

ISBN: (纸本)9798331510831

Despite recent significant advancements in Handwritten Document Recognition (HDR), the efficient and accurate recognition of text against complex backgrounds, diverse handwriting styles, and varying document layouts remains a practical challenge. Moreover, this issue is seldom addressed in academic research, particularly in scenarios with minimal annotated data available. In this paper, we introduce the DocTTT framework to address these challenges. The key innovation of our approach is that it uses test-time training to adapt the model to each specific input during testing. We propose a novel Meta-Auxiliary learning approach that combines Meta-learning and self-supervised Masked Autoencoder (MAE). During testing, we adapt the visual representation parameters using a self-supervised MAE loss. During training, we learn the model parameters using a meta-learning framework, so that the model parameters are learned to adapt to a new input effectively. Experimental results show that our proposed method significantly outperforms existing state-of-the-art approaches on benchmark datasets. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Residual diverse ensemble for long-tailed multi-label text classification

引用

Science China(Information Sciences) 2024年第11期67卷 92-105页

作者： Jiangxin SHI Tong WEI Yufeng LI National Key Laboratory for Novel Software Technology Nanjing University School of Artificial Intelligence Nanjing University School of Computer Science and Engineering Southeast University Key Laboratory of Computer Network and Information Integration Southeast UniversityMinistry of Education

Long-tailed multi-label text classification aims to identify a subset of relevant labels from a large candidate label set, where the training datasets usually follow long-tailed label distributions. Many of the previous studies have treated head and tail labels equally, resulting in unsatisfactory performance for identifying tail labels. To address this issue, this paper proposes a novel learning method that combines arbitrary models with two steps. The first step is the “diverse ensemble” that encourages diverse predictions among multiple shallow classifiers, particularly on tail labels, and can improve the generalization of tail *** second is the “error correction” that takes advantage of accurate predictions on head labels by the base model and approximates its residual errors for tail labels. Thus, it enables the “diverse ensemble” to focus on optimizing the tail label performance. This overall procedure is called residual diverse ensemble(RDE). RDE is implemented via a single-hidden-layer perceptron and can be used for scaling up to hundreds of thousands of labels. We empirically show that RDE consistently improves many existing models with considerable performance gains on benchmark datasets, especially with respect to the propensity-scored evaluation ***, RDE converges in less than 30 training epochs without increasing the computational overhead.

关键词： multi-label learning extreme multi-label learning long-tailed distribution multi-label text classification ensemble learning

来源：评论

学校读者我要写书评

暂无评论

GOAL: Generalized Jointly Sparse Linear Discriminant Regression for Feature Extraction

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第10期5卷 4959-4971页

作者： Lu, Haoquan Lai, Zhihui Zhang, Junhong Yu, Zhuozhen Wen, Jiajun Shenzhen University Computer Vision Institute College of Computer Science and Software Engineering Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen518060 China Peking University Shenzhen Graduate School School of Electronic and Computer Engineering Shenzhen518055 China

Ridge regression (RR)-based methods aim to obtain a low-dimensional subspace for feature extraction. However, the subspace's dimensionality does not exceed the number of data categories, hence compromising its capability of feature representation. Moreover, these methods with L2-norm metric and regularization cannot extract highly robust features from data with corruption. To address these problems, in this article, we propose generalized jointly sparse linear discriminant regression (GOAL), a novel regression method based on joint L2,1-norm and capped-L2-norm, which can integrate sparsity, locality, and discriminability into one model to learn a full-rank robust feature extractor. The sparsely selected discriminative features are robust enough to characterize the decision boundary between classes. Locality is related to manifold structure and Laplacian smoothing, which can enhance the robustness of the model. By using the multinorm metric and regularization regression framework, the proposed method obtains the projection with joint sparsity and guarantees that the rank of the projection matrix will not be limited by the number of classes. An iterative algorithm is proposed to compute the optimal solution. Complexity analysis and proofs of convergence are also given in the article. Experiments on well-known datasets demonstrate our model's superiority and generalization ability. © 2020 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Priority-Aware Resource Allocation for VNF Deployment in Service Function Chains Based on Graph Reinforcement Learning

引用

computers, Materials & Continua 2025年第5期83卷 1649-1665页

作者： Seyha Ros Seungwoo Kang Taikuong Iv Inseok Song Prohim Tam Seokhoon Kim Department of Software Convergence Soonchunhyang UniversityAsan31538Republic of Korea School of Digital Technologies American University of Phnom PenhPhnom Penh12106Cambodia Department of Computer Software Engineering Soonchunhyang UniversityAsan31538Republic of Korea

Recently,Network Functions Virtualization(NFV)has become a critical resource for optimizing capability utilization in the 5G/B5G *** decomposes the network resource paradigm,demonstrating the efficient utilization of Network Functions(NFs)to enable configurable service priorities and resource *** Service Providers(TSPs)face challenges in network utilization,as the vast amounts of data generated by the Internet of Things(IoT)overwhelm existing *** applications,which generate massive volumes of diverse data and require real-time communication,contribute to bottlenecks and *** this context,Multiaccess Edge Computing(MEC)is employed to support resource and priority-aware IoT applications by implementing Virtual Network Function(VNF)sequences within Service Function Chaining(SFC).This paper proposes the use of Deep Reinforcement Learning(DRL)combined with Graph Neural Networks(GNN)to enhance network processing,performance,and resource pooling *** facilitates feature extraction through Message-Passing Neural Network(MPNN)*** with DRL,Deep Q-Networks(DQN)are utilized to dynamically allocate resources based on IoT network priorities and *** focus is on minimizing delay times for VNF instance execution,ensuring effective resource placement,and allocation in SFC deployments,offering flexibility to adapt to real-time changes in priority and *** results demonstrate that our proposed scheme outperforms reference models in terms of reward,delay,delivery,service drop ratios,and average completion ratios,proving its potential for IoT applications.

关键词： Deep reinforcement learning graph neural network multi-access edge computing network functions virtualization software-defined networking

来源：评论

学校读者我要写书评

暂无评论

Certrust:An SDN-Based Framework for the Trust of Certificates against Crossfire Attacks in IoT Scenarios

引用

computer Modeling in engineering & Sciences 2023年第3期134卷 2137-2162页

作者： Lei Yan Maode Ma Dandan Li Xiaohong Huang Yan Ma Kun Xie School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijingChina College of Engineering QatarUniversityDohaQatar

The low-intensity attack flows used by Crossfire attacks are hard to distinguish from legitimate *** methods to identify the malicious flows in Crossfire attacks are rerouting,which is based on *** these existing mechanisms,the identification of malicious flows depends on the IP ***,the IP address is easy to be changed by *** the IP address,the certificate ismore challenging to be tampered with or ***,the traffic trend in the network is towards *** certificates are popularly utilized by IoT devices for authentication in encryption *** proposed a new way to verify certificates for resource-constrained IoT devices by using the SDN *** on DTLShps,the SDN controller can collect statistics on *** this paper,we proposeCertrust,a framework based on the trust of certificates,tomitigate the Crossfire attack by using SDN for *** goal is ***,the trust model is built based on the Bayesian trust system with the statistics on the participation of certificates in each Crossfire ***,the forgetting curve is utilized instead of the traditional decay method in the Bayesian trust system for achieving a moderate decay ***,for detecting the Crossfire attack accurately,a method based on graph connectivity is ***,several trust-based routing principles are proposed tomitigate the Crossfire *** principles can also encourage users to use certificates in *** performance evaluation shows that Certrust is more effective in mitigating the Crossfire attack than the traditional rerouting ***,our trust model has a more appropriate decay rate than the traditional methods.

关键词： Trust model certificate SDN Crossfire attack bayesian trust system forgetting curve IoT

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection Model of Time Segment Power Usage Behavior Using Unsupervised Learning

引用

Journal of Internet Technology 2024年第3期25卷 455-463页

作者： Ho, Wen-Jen Hsieh, Hsin-Yuan Tsai, Chia-Wei Software Technology Institute Institute for Information Industry Taiwan Department of Computer Science and Information Engineering National Taitung University Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taiwan

In Taiwan, the current electricity prices for residential users remain relatively low. This results in a diminished incentive for these users to invest in energy-saving improvements. Consequently, devising strategies to encourage residential users to adopt energy-saving measures becomes a vital research area. Grounded in behavioral science, this study introduces a feasible approach where an energy management system provides alerts and corresponding energy-saving recommendations to residential users upon detecting abnormal electricity consumption behavior. To pinpoint anomalous electricity usage within specific time segments, this research employs an unsupervised machine learning method, developing an anomaly detection model for the overall electricity consumption behavior of residential users. The model focuses on analyzing 2-hour intervals of electricity consumption, enabling more effective detection of abnormal usage patterns. It is trained using power consumption data collected from five actual residential users as part of an experimental study. The results indicate that the proposed anomaly detection model achieves performance metrics such as Precision, Recall, and F1-score of 0.90 or above, showcasing its potential for practical implementation. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

A Proposal of NFA Model for Anomaly Detection of Potable Water Management Process

A Proposal of NFA Model for Anomaly Detection of Potable Wat...

引用

2024 International Conference on Artificial Intelligence, Metaverse and Cybersecurity, ICAMAC 2024

作者： Balta, Deniz Balta, Musa Taştan, Deniz Berfin İskefiyeli, Murat Software Engineering Sakarya University Sakarya Turkey Computer Engineering Sakarya University Sakarya Turkey

ISBN: (纸本)9798350353488

It is very important to protect water management systems, which are one of the critical infrastructures, from intentional or accidental pollution events. Detecting possible anomalies in water processes in a short time and with high accuracy increases the emergency response capacity. For this purpose, NFAs, which are known to provide very successful results especially in network security, data processing and pattern matching, play an important role in detecting anomalies in the operation of critical infrastructure systems. In this context, the NFA-based model designed for the early detection of possible anomalies in water management processes in this study defined different states regarding the normal operations of the system and determined the transitions between these states. It was observed that this model, which was tested on real-time data collected from the water process in the Center Water infrastructure, detected anomalies with high accuracy. © 2024 IEEE.

关键词： anomaly detection Critical infrastructure Nondeterministic finite automata water management systems

来源：评论

学校读者我要写书评

暂无评论

Masked Face Detection and Recognition Using a Unified Feature Extractor 5

Masked Face Detection and Recognition Using a Unified Featur...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Iftikhar, Aroobah Shaukat, Arslan Tariq, Rimsha College of Eme Dept of Computer and Software Engineering Islamabad Pakistan Information Technology University Dept of Computer Engineering Lahore Pakistan

ISBN: (纸本)9798350394764

The research field of computer vision has recently taken an interest in the active computer vision problem of masked face recognition due to the COVID-19 pandemic. The use of face masks as a preventative measure against the spread of COVID-19 has presented a new challenge for the technology of face recognition. Masked Face Recognition (MFR) is a specific type of facial occlusion issues that obstruct vital facial features such as the mouth, nose, or chin. The purpose of research on Masked Face Detection and Recognition is to fine-tune a pre-trained model that can more accurately recognize masked faces and detect whether the person is wearing a mask or not, which can be advantageous in various applications, like security and surveillance, healthcare, retail, law enforcement, the workplace, and social media. This paper proposes an approach to enhance the performance of the single neural network architecture as a unified model capable of both detection and recognition of masked face images by achieving 99% and 98% respectively, on the MFR2 dataset. Also, a detection model is proposed that is evaluated on publicly available datasets for the detection of masked faces, which are the MDMFR dataset, the Kaggle face mask detection dataset, and the Facedatahybrid dataset. The findings of this research offer valuable insights into the potential of a pre-trained network with transfer learning to make an efficient masked face detection and recognition system and pave the way for future research in this area. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

MixSSC: Forward-Backward Mixture for Vision-based 3D Semantic Scene Completion

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5684-5696页

作者： Wang, Meng Ding, Yan Liu, Yumeng Qin, Yunchuan Li, Ruihui Tang, Zhuo The College of Computer Science and Electronic Engineering Hunan University Changsha410082 China Beijing Key Laboratory of Human-Computer Interaction Institute of Software Chinese Academy of Sciences Beijing100190 China

Vision-based semantic scene completion task aims to predict dense geometric and semantic 3D scene representations from 2D images. However, 3D modeling from a single view is an ill-posed problem, limited by the field of view and occlusion problems caused by image input. Moreover, existing methods tend to produce erroneous scene hallucinations and overly smooth boundary segmentation due to a lack of information. To address this problem, we propose MixSSC, which mixes the sparsity of forward projection with the denseness of depth-prior backward projection. The aim is to use sparse features to fill information-poor regions and dense features to enhance visible regions. Specifically, we develop the forward-backward mixture module, which enables the generation of scene mixture voxel representation by leveraging the benefits of both forward and backward projection. Subsequently, we design the semantic-spatial fusion module, which utilizes a coarse-to-fine approach to process mixture voxel features at the semantic-spatial level. Extensive experimental results on the SemanticKITTI, SSCBench-KITTI-360 and nuScenes datasets demonstrate the superiority of MixSSC. © 1991-2012 IEEE.

关键词： Semantic Segmentation

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：