检索结果-内蒙古大学图书馆

GRA: Graph Representation Alignment for Semi-Supervised Action Recognition

IEEE Transactions on Neural Networks and Learning systems 2024年第9期35卷 11896-11905页

作者： Huang, Kuan-Hung Huang, Yao-Bang Lin, Yong-Xiang Hua, Kai-Lung Tanveer, M. Lu, Xuequan Razzak, Imran National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei10607 Taiwan Indian Institute of Technology Indore Department of Mathematics Indore Simrol453552 India La Trobe University Department of Computer Science and IT MelbourneVIC3086 Australia University of New South Wales School of Computer Science and Engineering SydneyNSW2052 Australia

Graph convolutional networks (GCNs) have emerged as a powerful tool for action recognition, leveraging skeletal graphs to encapsulate human motion. Despite their efficacy, a significant challenge remains the dependency on huge labeled datasets. Acquiring such datasets is often prohibitive, and the frequent occurrence of incomplete skeleton data, typified by absent joints and frames, complicates the testing phase. To tackle these issues, we present graph representation alignment (GRA), a novel approach with two main contributions: 1) a self-training (ST) paradigm that substantially reduces the need for labeled data by generating high-quality pseudo-labels, ensuring model stability even with minimal labeled inputs and 2) a representation alignment (RA) technique that utilizes consistency regularization to effectively reduce the impact of missing data components. Our extensive evaluations on the NTU RGB+D and Northwestern-UCLA (N-UCLA) benchmarks demonstrate that GRA not only improves GCN performance in data-constrained environments but also retains impressive performance in the face of data incompleteness. © 2012 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Personalized Collaborative Search Engine for Decision Making

Personalized Collaborative Search Engine for Decision Making

引用

2024 International Conference on Communication, computer sciences and engineering, IC3SE 2024

作者： Murshleen, Mohd. Prabhu, A. Jain, Garima Tula's Institute Department Of Computer Science And Engineering Dehradun India Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of Computer Science & Business System Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350366846

Web search engines are used for retrieving information but still there exists ambiguity in their retrieval process. It is so because traditional search engines laid emphasis on matching of keywords rather than maintaining semantic relations among terms lack of ability to produce precise results, presence of ambiguous keywords and verifying needs of users are few hindrances that are acting as scenario for web search engines. The paper focuses on improving search quality of users by collecting user experiences through creating hierarchical user profile it leads to collaborative search engine that helps in reaching at particular decision then the collected user's data are uploaded to recommendation server which are than displayed a search engines like Google/Yahoo. © 2024 IEEE.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Smart contract token-based privacy-preserving access control system for industrial Internet of Things

引用

Digital Communications and Networks 2023年第2期9卷 337-346页

作者： Weizheng Wang Huakun Huang Zhimeng Yin Thippa Reddy Gadekallu Mamoun Alazab Chunhua Su Department of Computer Science City University of Hong KongHong Kong SAR999077China Division of Computer Science University of AizuFukushima965-8580Japan School of Information Technology and Engineering Vellore Institute of TechnologyTamil NaduIndia College of Engineering IT and EnvironmentCharles Darwin UniversityAustralia School of Computer Science and Cyber Engineering Guangzhou UniversityChina

Due to mobile Internet technology's rapid popularization,the Industrial Internet of Things(IIoT)can be seen everywhere in our daily *** IIoT brings us much convenience,a series of security and scalability issues related to permission operations rise to the surface during device ***,at present,a reliable and dynamic access control management system for IIoT is in urgent *** till now,numerous access control architectures have been proposed for ***,owing to centralized models and heterogeneous devices,security and scalability requirements still cannot be *** this paper,we offer a smart contract token-based solution for decentralized access control in IIoT ***,there are three smart contracts in our system,including the Token Issue Contract(TIC),User Register Contract(URC),and Manage Contract(MC).These three contracts collaboratively supervise and manage various events in IIoT *** also utilize the lightweight and post-quantum encryption algorithm-Nth-degree Truncated Polynomial Ring Units(NTRU)to preserve user privacy during the registration ***,to evaluate our proposed architecture's performance,we build a prototype platform that connects to the local ***,experiment results show that our scheme has achieved secure and dynamic access control for the IIoT system compared with related research.

关键词： Blockchain Privacy preservation Smart contract Industrial IoT

来源：评论

学校读者我要写书评

暂无评论

Measuring the Discrepancy between 3D Geometric Models using Directional Distance Fields

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年 PP卷 1-16页

作者： Ren, Siyu Hou, Junhui Chen, Xiaodong Xiong, Hongkai Wang, Wenping City University of Hong Kong Department of Computer Science Hong Kong Tianjin University School of Precision Instruments and OptoElectronic Engineering Tianjin300072 China Shanghai Jiao Tong University Department of Electronic Engineering Shanghai200240 China Texas A& M University Department of Computer Science & Engineering United States

Qualifying the discrepancy between 3D geometric models, which could be represented with either point clouds or triangle meshes, is a pivotal issue with board applications. Existing methods mainly focus on directly establishing the correspondence between two models and then aggregating point-wise distance between corresponding points, resulting in them being either inefficient or ineffective. In this paper, we propose DirDist, an efficient, effective, robust, and differentiable distance metric for 3D geometry data. Specifically, we construct DirDist based on the proposed implicit representation of 3D models, namely directional distance field (DDF), which defines the directional distances of 3D points to a model to capture its local surface geometry. We then transfer the discrepancy between two 3D geometric models as the discrepancy between their DDFs defined on an identical domain, naturally establishing model correspondence. To demonstrate the advantage of our DirDist, we explore various distance metric-driven 3D geometric modeling tasks, including template surface fitting, rigid registration, non-rigid registration, scene flow estimation and human pose optimization. Extensive experiments show that our DirDist achieves significantly higher accuracy under all tasks. As a generic distance metric, DirDist has the potential to advance the field of 3D geometric modeling. © 1979-2012 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

Weighted Average Ensembled Probability Pipeline of Pre-trained CNN Models for Hand Gesture Classification 15

Weighted Average Ensembled Probability Pipeline of Pre-train...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Gunti, Rahul Rohan Reddy, B. Swathi, Gunti Sharath Kumar Reddy, G. Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science and Engineering Chennai601103 India Vellore Institute of Technology School of Computer Science and Engineering Vellore India

ISBN: (纸本)9798350370249

The automatic detection of sign language from hand gesture images is fundamental for effective human-computer interaction, especially for individuals with hearing and speech disorders. Achieving accurate detection and classification of sign language gestures is paramount. However, accurately recognizing these gestures frequently presents challenges due to dull backgrounds, variations in gesture orientation, and fluctuations in lighting conditions. Previous approaches tried to overcome these challenges but still the model performance lacks recognition accuracy and visual quality. To address this need for accuracy, we proposed a Weighted Average Ensembled Probability Pipeline composed of EfficientNetB7, ResNet-50, and Xception models. Leveraging the Extensive Hand Gesture Recognition Database (HGRD), comprising 20,000 images, our individual models achieved notable accuracies: 96.498 % for EfficientNetB7, 93.2 % for ResNet-50, and 90.175 % for Xception. Through ensemble learning, we integrate these models to attain an impressive overall accuracy of 98.95 %. This research contributes to robust gesture recognition system and underscores the significance of ensemble techniques in enhancing performance for Gesture recognition systems. © 2024 IEEE.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Medical Plant Detection using Transfer learning Coupled with K-Nearest Neighbour Algorithm 3

Medical Plant Detection using Transfer learning Coupled with...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Srambickal, Sai Subramanian Srivastava, Aman Somasundaram, S.K. School of Computer Science and Engineering Vellore Institute of Technology Department of Computer Science and Engineering Tamil Nadu Vellore India Vellore Institute of Technology School of Computer Science and Engineering Department of Information Security Tamil Nadu Vellore India

ISBN: (纸本)9798350372120

Medical Plants are being used for more than a thousand year, with evidences dating before the Mauryain Era (around 322 BCE), they are widely used in the Ayurvedic school of medicine for therapeutic as well as medicinal purposes, it requires an expert to identify the species as well as the medical property associated with a given plant. This paper aims to use deep learning in order to identify a given plant using the leaves of the plant by using a pretrained Convolutional Neural Network (CNN) model namely ResNet50 and MobileNet to extract the latent vector which will then be passed to K-Nearest Neighbour (KNN) algorithm in order to identify the plant class, the best accuracy of the proposed models comes out to be 97.65%. © 2024 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

QCVNET - Leveraging Quantum Technology in Convolutional Neural Networks for Improved Cardiovascular Disease Prediction 5

QCVNET - Leveraging Quantum Technology in Convolutional Neur...

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Karthigeyan, S. Diviya, M. Bhuvaneswari, R. Sabhanayagam, T. Amrita School of Computing Department of Computer Science and Engineering Amrita Vishwa Vidyapeetham Chennai India Rajalakshmi Engineering College Department of Computer Science and Engineering Chennai India School of Computer Science and Engineering Galgotias University UP Greater Noida India

ISBN: (纸本)9798331528539

The primary issue of global health today is Cardio-vascular diseases (CVDs) and thus requires accurate predictive models for detecting it early. Quantum technology combined with regular deep learning techniques are used by researchers here to improve the accuracy of forecast on heart diseases. While using an expanded dataset with clinical and demographic records, an innovative approach was found to use Quantum Convolutional Neural Network (QCVNET) structure that merged quantum layers into classical CNN framework with Principal Component Analysis (PCA) that allowed for consistency of features with respect to the quantum bits' number. The performance of the QCVNET was evaluated by comparing it to Quantum LSTM, Quantum DNN, Quantum GRU, and Quantum RNN, which are other quantum models enhanced with conventional neural networks, and other traditional non-quantum models like SVM, RF, RNN and DNN, using different indicators of quality like f1-score or recall. In early CVD prediction, the QCVNET model produced an impressive accuracy of 91.73%, beating all other models, showcasing the potential impact of quantum-enhanced deep learning for timely diagnosis and personalized treatment strategies while providing means to reduce the global burden of cardiovascular diseases. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Reinforcing Artificial Neural Networks through Traditional Machine Learning Algorithms for Robust Classification of Cancer

引用

computers, Materials & Continua 2023年第5期75卷 4293-4315页

作者： Muhammad Hammad Waseem Malik Sajjad Ahmed Nadeem Ishtiaq Rasool Khan Seong-O-Shim Wajid Aziz Usman Habib Department of Computer Sciences and Information Technology University of Azad Jammu and KashmirMuzaffarabad13100Pakistan Department of Computer Science and AI College of Computer Science and EngineeringUniversity of JeddahJeddah23890Saudi Arabia Department of Computer and Network Engineering College of Computer Science and EngineeringUniversity of JeddahJeddah23890Saudi Arabia Department of AI&DS School of ComputingNational University of Computer and Emerging SciencesIslamabad44000Pakistan

Machine Learning(ML)-based prediction and classification systems employ data and learning algorithms to forecast target ***,improving predictive accuracy is a crucial step for informed *** the healthcare domain,data are available in the form of genetic profiles and clinical characteristics to build prediction models for complex tasks like cancer detection or *** ML algorithms,Artificial Neural Networks(ANNs)are considered the most suitable framework for many classification *** network weights and the activation functions are the two crucial elements in the learning process of an *** weights affect the prediction ability and the convergence efficiency of the *** traditional settings,ANNs assign random weights to the *** research aims to develop a learning system for reliable cancer prediction by initializing more realistic weights computed using a supervised setting instead of random *** proposed learning system uses hybrid and traditional machine learning techniques such as Support Vector Machine(SVM),Linear Discriminant Analysis(LDA),Random Forest(RF),k-Nearest Neighbour(kNN),and ANN to achieve better accuracy in colon and breast cancer *** system computes the confusion matrix-based metrics for traditional and proposed *** proposed framework attains the highest accuracy of 89.24 percent using the colon cancer dataset and 72.20 percent using the breast cancer dataset,which outperforms the other *** results show that the proposed learning system has higher predictive accuracies than conventional classifiers for each dataset,overcoming previous research ***,the proposed framework is of use to predict and classify cancer patients ***,this will facilitate the effective management of cancer patients.

关键词： ANN decision support systems gene-expression data hybrid classification machine learning predictive analytics

来源：评论

学校读者我要写书评

暂无评论

CbcErDL: Classification of breast cancer from mammograms using enhance image reduction and deep learning framework

引用

Multimedia Tools and Applications 2025年第15期84卷 15501-15526页

作者： Agrawal, Rohit Singh, Navneet Pratap Shelke, Nitin Arvind Tripathi, Kuldeep Narayan Singh, Ranjeet Kumar Department of Computer Science and Engineering Madhav Institute of Technology & Science Race Course Road MP Gwalior474005 India School of AI Bennett University Uttar Pradesh Greater Noida201310 India School of Computer Science and Engineering Bennett University TechZone 2 UP Greater Noida201310 India

Breast cancer is a major health concern for women worldwide, and early detection is vital to improve treatment outcomes. While existing techniques in mammogram classification have demonstrated promising results, their limitations become apparent when applied to larger datasets. The decline in performance with increased dataset size highlights the need for further research and advancements in the field to enhance the scalability and generalizability of these techniques. In this study, we propose a framework to classify breast cancer from mammograms using techniques such as mammogram enhancement, discrete cosine transform (DCT) dimensionality reduction, and deep convolutional neural network (DCNN). The first step is to improve the mammogram display to improve the visibility of key features and reduce noise. For this, we use 2-stage Contrast Limited Adaptive Histogram Equalization (CLAHE). DCT is then used to enhance mammograms to reduce residual data. It can provide effective reduction while preserving important diagnostic information. In this way, we reduce the computational complexity and increase the results of subsequent classification algorithms. Finally, DCNN is used on size-reduced DCT coefficients to learn feature discrimination and classification of mammograms. DCNN architectures have been optimized with various techniques to improve their performance, including regularization and hyperparameter tuning. We perform experiments on the DDSM dataset, a large dataset containing approximately 55,000 mammogram images, and demonstrate the effectiveness of the proposed method. We assess the proposed model’s performance by computing the precision, recall, accuracy, F1-Score, and area under the receiver operating characteristic curve (AUC). We achieve Precision and Recall values of 0.929 and 0.963, respectively. The classification accuracy of the proposed models is 0.963. Moreover, the F1-Score and AUC values are 0.962 and 0.987, respectively. These results are better a

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Hybrid Recommendation system for Safe Approach to Curated Cosmetics 3

Deep Learning-based Hybrid Recommendation System for Safe Ap...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Rohitha Chowdary, G. Tharun, J. Sivaiah, G. Raveena, S. Surendran, R. Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Insititute of Medical and Technical Science Chennai India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527549

In the rapidly evolving cosmetics market, it is imperative to prioritize customer safety while offering personalized recommendations. This study introduces a hybrid recommendation system for cosmetics, using deep learning to combine the advantages of collaborative filtering with content-based filtering. The system assesses user preferences, skin types, and ingredient sensitivities, recommending solutions that are both effective and safe. The system proposes an integration of user-based and item-based collaborative filtering methodologies with deep neural networks to effectively elucidate intricate links among individuals, items, and their characteristics. This hybrid technique facilitates the system's ability to propose goods that provide both aesthetic appeal and skin safety, therefore fostering a healthier and more confident lifestyle. The system has an impressive accuracy of 92.5% in recommending suitable cosmetic products for individual clients. This enhanced accuracy reduces the likelihood of negative reactions and elevates customer satisfaction via personalized suggestions. © 2025 IEEE.

关键词： Contrastive Learning

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：