检索结果-内蒙古大学图书馆

On Two Classes of Extended 3-Lie Algebras

Journal of Applied Mathematics and Physics 2021年第4期9卷 834-845页

作者： Yu Cheng Yansha Gao School of Data Science and Software Engineering Baoding University Baoding China College of Mathematics and Information Science Hebei University Baoding China

In this paper, based on the existing research results, we obtain the unary extension 3-Lie algebras by one-dimensional extension of the known Lie algebra L. For two known 3-Lie algebras H, M, the (μ, ρ, β)-extension of H through M is given, and the necessary and sufficient conditions for the (μ, ρ, β)-extension algebra of H through M being 3-Lie algebra are obtained, and the structural characteristics and properties of these two kinds of extended 3-Lie algebras are given.

关键词： The Unary Extension 3-Lie Algebras Lie Algebra (μ ρ β)-Extension

来源：评论

学校读者我要写书评

暂无评论

A Novel Framework for Learning and Classifying the Imbalanced Multi-Label data

引用

Computer Systems science & engineering 2024年第5期48卷 1367-1385页

作者： P.K.A.Chitra S.Appavu alias Balamurugan S.Geetha Seifedine Kadry Jungeun Kim Keejun Han Department of Computer Science and Engineering SRM Institute of Science and TechnologyTiruchirappalliTamil Nadu603203India Department of Computer Science and Engineering Periyar Maniammai Institute of Science&Technology(Deemed to be University)ThanjavurTamil Nadu613403India School of Computer Science and Engineering ChennaiTamil Nadu600048India Department of Applied Data Science Noroff University CollegeKristiansand4612Norway Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman UniversityP.O.Box 346AjmanUnited Arab Emirates Department of Electrical and Computer Engineering Lebanese American UniversityByblos10150Lebanon Department of Software Kongju National UniversityCheonan31080Republic of Korea Division of Computer Engineering Hansung UniversitySeoul02876Republic of Korea

A generalization of supervised single-label learning based on the assumption that each sample in a dataset may belong to more than one class simultaneously is called multi-label *** main objective of this work is to create a novel framework for learning and classifying imbalancedmulti-label *** work proposes a framework of two *** imbalanced distribution of themulti-label dataset is addressed through the proposed Borderline MLSMOTE resampling method in phase ***,an adaptive weighted l21 norm regularized(Elastic-net)multilabel logistic regression is used to predict unseen samples in phase *** proposed Borderline MLSMOTE resampling method focuses on samples with concurrent high labels in contrast to conventional *** minority labels in these samples are called difficult minority labels and are more prone to penalize classification *** concurrentmeasure is considered borderline,and labels associated with samples are regarded as borderline labels in the decision *** phase II,a novel adaptive l21 norm regularized weighted multi-label logistic regression is used to handle balanced data with different weighted synthetic *** on various benchmark datasets shows the outperformance of the proposed method and its powerful predictive performances over existing conventional state-of-the-art multi-label methods.

关键词： Multi-label imbalanced data multi-label learning Borderline MLSMOTE concurrent multi-label adaptive weighted multi-label elastic net difficult minority label

来源：评论

学校读者我要写书评

暂无评论

A two-stage learning approach for wind power prediction using dynamic graph convolution network hybrid model

A two-stage learning approach for wind power prediction usin...

引用

IEEE Conference on Energy Internet and Energy System Integration (EI2)

作者： Hailong Li Yongsheng Wang Shijie Guan Xuehui Wang Daorina Bao Xiaojun Liu Haotian Chen College of Data Science and Application Inner Mongolia University of Technology Huhhot China College of Information and Electrical Engineering China Agricultural University Beijing China College of Energy and Power Engineering Inner Mongolia University of Technology Hohhot China Inner Mongolia Wuchuan County Water Affairs Bureau Hohhot China School of International Information and Software Dalian University of Technology Dalian China

ISBN: (数字)9798331523527

ISBN: (纸本)9798331523534

This paper proposes an effective two-stage learning method to improve the accuracy of wind power prediction. The complex time dependency relationship between meteorological data variables is modelled using a dynamic graph convolutional network, and the wind power prediction is completed using the XGBoost model. Experimental results show that the two-stage learning method can effectively extract key time series features and has good prediction accuracy.

关键词： Learning systems Accuracy Graph convolutional networks Predictive models Wind power generation Feature extraction data models Hybrid power systems Numerical models Wind forecasting

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cloud IoT Applications with Machine Learning Driven Hybrid Key Management Protocols for WSN Performance

Optimizing Cloud IoT Applications with Machine Learning Driv...

引用

International Conference on Signal Processing, Communication, Power and Embedded System (SCOPES)

作者： Simhadri Mallikarjuna Rao B. Adinarayana Kasani Vaddikasulu Satya Prasad Dontamsetti Peesapati Surya Venkata Ranganadh Research Scholar Department of Computer Science and Engineering Aacharya Nagarjuna University Guntur Andhra Pradesh India R &D Department of EEE & CSE Ravi Technology Vishakhapatnam Andhra Pradesh India Department of Computer Science and Engineering Eluru college of engineering and technology Eluru Andhra Pradesh India Department of Artificial Intelligence and Data Science Vishnu Institute of Technology Bhimavaram Andhra Pradesh India Software Engineer USA

ISBN: (数字)9798331506452

ISBN: (纸本)9798331506469

AI-IoT integration is significant, changing the future of networking, particularly in terms of performance and security enhancements. The collection and transmission of sensitive data across secure networks is crucial for the IoT, which combines embedded systems and Networks of Wireless Sensors (WSNs). Ensuring the efficacy and security of these networks is crucial. In this research, a novel hybrid key Hybrid management protocol for Internet of Things applications using WSNs is proposed. The maximizes network performance of efficiency and security by utilizing cloud services and machine learning, specifically XGBoost. The suggested protocol creates a secure communication framework for WSNs by combining symmetric and asymmetric key management strategies. Furthermore, the centralized functions and scalability of cloud-based services enable network-wide updates and effective key distribution. The protocol offers anomaly detection, intelligent network load balancing, dynamic key management, predictive key distribution, and intelligent network load balancing by employing XGBoost-based machine learning algorithms. By using network behavior modelling and historical data analysis, the system forecasts the optimal times and locations for important updates, reducing overhead and enhancing security. Additionally, anomaly detection based on XGBoost improves the protocol's ability to recognize anomalies and potential security risks. This hybrid architecture creates a highly flexible and effective protocol for IoT-enabled WSNs by combining cloud integration, centralized key management, and AI-driven intelligence. The proposed approach performs better on the network due to proven methods and algorithms.

关键词： Support vector machines Wireless sensor networks Cloud computing Protocols Accuracy Machine learning algorithms Scalability Internet of Things Security Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Automating the Diagnosis of Cucumber Plant Diseases Using Machine Learning

Automating the Diagnosis of Cucumber Plant Diseases Using Ma...

引用

Information Technology (ACIT)

作者： Ahmed BaniMustafa Hazem Qattouz Sattam Almatarneh Khalid Mansour Raed Alazaidah Olla Bulkrock Computer Information Science Dept Higher Colleges of Technology Abu Dhabi UAE Software Engineering Dept Princess Sumaya University for Technology Amman Jordan Data Science & Artificial Intelligence Dept Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah KSA Faculty of Computer Studies Arab-Open University Bahrain Bahrain

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Farmers all over the world struggle to fight plant diseases. However, the incorrect use of pesticides can waste time, effort, and money and can also be very harmful to the environment and human health. In this work, we present an empirical study that involves identifying two pathogens related to Cucumbers plant diseases: Powdery Mildew and Alternaria Cucumerina. The study aims to develop a computer-based solution based on deep learning and machine learning algorithms to detect these diseases. To achieve this, a dataset of hundreds of samples was collected from ordinary farms in Beqaa, an agricultural region 15 KM north of Amman, Jordan. Three machine learning models were created in this study using Support Vector Machines (SVM), Logistic Regression (LR), and Multi-layer perceptron algorithms. The constructed models were applied to the dataset after embedding the dataset images using the Convolutional Neural Networks (CNN) InceptionV3 pre-trained model. The model was tested and evaluated using cross-evaluation and F1-Score, CA, AUC, Precision, Recall, and Specificity, which all showed excellent results, particularly using the SVM algorithm. The constructed methods are intended to be deployed to farms in their field condition environments using a CCTV system that can capture images of plants during growth, which can help identify plant diseases at that right stage, which would save time, effort, and money and reduce the impact of wrong and overuse of pesticides on consumers and the environment.

关键词： Support vector machines Plant diseases Pathogens Machine learning algorithms Pesticides Soil Cameras Real-time systems Mobile applications Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

DAMPER: A Dual-Stage Medical Report Generation Framework with Coarse-Grained MeSH Alignment and Fine-Grained Hypergraph Matching

arXiv

引用

arXiv 2024年

作者： Huang, Xiaofei Chen, Wenting Liu, Jie Lu, Qisheng Luo, Xiaoling Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Kowloon Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Medical report generation is crucial for clinical diagnosis and patient management, summarizing diagnoses and recommendations based on medical imaging. However, existing work often overlook the clinical pipeline involved in report writing, where physicians typically conduct an initial quick review followed by a detailed examination. Moreover, current alignment methods may lead to misaligned relationships. To address these issues, we propose DAMPER, a dual-stage framework for medical report generation that mimics the clinical pipeline of report writing in two stages. In the first stage, a MeSH-Guided Coarse-Grained Alignment (MCG) stage that aligns chest X-ray (CXR) image features with medical subject headings (MeSH) features to generate a rough keyphrase representation of the overall impression. In the second stage, a Hypergraph-Enhanced Fine-Grained Alignment (HFG) stage that constructs hypergraphs for image patches and report annotations, modeling high-order relationships within each modality and performing hypergraph matching to capture semantic correlations between image regions and textual phrases. Finally,the coarse-grained visual features, generated MeSH representations, and visual hypergraph features are fed into a report decoder to produce the final medical report. Extensive experiments on public datasets demonstrate the effectiveness of DAMPER in generating comprehensive and accurate medical reports, outperforming state-of-the-art methods across various evaluation metrics. Copyright © 2024, The Authors. All rights reserved.

关键词： Coarse-grained modeling

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Visual Background Extraction with Ghost Regions Elimination 6

Self-Adaptive Visual Background Extraction with Ghost Region...

引用

6th International Conference on Signal and Image Processing, ICSIP 2021

作者： Liu, Ling Liu, Shuai Qu, Zhong Zhou, Dongyang University of Posts and Telecommunications School of Big Data and Software Engineering College of Mobile Telecommunications of Chongqing Chongqing China Chongqing University of Posts and Telecommunications College of Computer Science and Technology Chongqing China University of Posts and Telecommunications College of Mobile Telecommunications of Chongqing Department of Management Engineering Chongqing China

ISBN: (纸本)9780738133737

The ViBe (Visual Background Extraction) algorithm uses the first frame to initialize the pixel background model for each pixel, which may introduce the ghost regions in the following video frames. Although ViBe can use its background model update mechanism to eliminate the ghost regions, it is time-consuming. Firstly, a ghost elimination algorithm is proposed in this paper in order to reduce the elimination time for the ghost regions based on its properties. Secondly, a fixed global segmentation decision threshold is used to segment pixels in ViBe algorithm. However, because it cannot adapt to the dynamic background, a self-adaptive segmentation decision threshold based on single pixel is used to adjust to the different backgrounds. Finally, a self-adaptive update factor is presented, which makes the background model more reliable and adjusts to the background changes through the self-adaptive processing. The experimental result shows that this improved method can quickly eliminate the ghost regions, and adapt to the different kinds of backgrounds, ensuring more accurate results. © 2021 IEEE.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

StyleAU: StyleGAN based Facial Action Unit Manipulation for Expression Editing

StyleAU: StyleGAN based Facial Action Unit Manipulation for ...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yanliang Guo Xianxu Hou Feng Liu Linlin Shen Lei Wang Zhen Wang Peng Liu Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Qualcomm Technologies Inc

Facial expression editing has a wide range of applications, such as emotion detection, human-computer interaction, and social entertainment. However, existing expression editing methods either fail to allow for fine-grained editing, resulting in unnatural and unrealistic facial expressions, or generate artifacts and blurs, leading to poor image quality. In this paper, we propose a novel framework called StyleAU, which is based on StyleGAN and facial action units, to address these problems. Our framework leverages the pre-trained StyleGAN prior knowledge to enable action unit editing of the face in the StyleGAN latent space, allowing precise expression editing. In addition, we use an encoder to extract multi-scale content features to achieve high-fidelity image reconstruction. Our approach qualitatively and quantitatively outperforms competing methods for action unit manipulation and expression editing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigating Principle Component Analysis Impact on the Performance of Machine Learning Classifiers: A Health Informatics Application

Investigating Principle Component Analysis Impact on the Per...

引用

Information Technology (ACIT)

作者： Ahmed BaniMustafa Sattam Almatarneh Olla Bulkrock Raed Alazaidah Hossam Almahasneh Ghassan Samara Computer Information Science Dept. Higher Colleges of Technology Abu Dhabi UAE Data Science & Artificial Intelligence Dept. Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah KSA Software Engineering Dept. Princess Sumaya University for Technology Amman Jordan Computer Science Dept. Zarqa University Zarqa Jordan

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Principal Components Analysis (PCA) is a popular dimensionality reduction and feature selection technique. It works by swiping non-informative features while retaining those that are still potentially useful. However, regardless of its wide applications in statistical analysis, the influence of PCA on the performance of classification algorithms has been rarely studied, particularly in the domain of medical image classification. In this paper, we present a thorough analysis of the influence of applying PCA on the classification of medical images. The dataset used in this study consists of thousands of images that represent four types of blood cells. These images are used to train three machine-learning classifier models after transforming images into numerical vectors using a CNN pre-trained embedding algorithm, where each image is encoded using one thousand numerical vectors. The study involves building three classification models using (1) K-nearest Neighbor (KNN), (2) Logistic Regression (LR), and (3) Random Forests (RF). Each model was built twice, once after the application of PCA to reduce the dimensionality of the embedded features and once with the original embedded features. The performance of each model is evaluated using Classification accuracy, F1, AUC, Recall, precision, and specificity metrics. The recorded performance is then compared to drawing a decisive conclusion.

关键词： Training Logistic regression Cells (biology) Nearest neighbor methods Vectors Numerical models Classification algorithms Random forests Principal component analysis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Efficient Batch Verification and Privacy-Preserving data Aggregation Scheme in V2G Networks

引用

IEEE Transactions on Vehicular Technology 2025年

作者： Wang, Congcong Wang, Chen Shen, Jian Vasilakos, Athanasios V. Wang, Bin Wang, Weizheng Department of Software Engineering Nanjing University of Information Science and Technology Nanjing210044 China the Zhejiang Key Laboratory of Digital Fashion and Data Governance the Zhejiang Provincial International Cooperation Base for Science and Technology on Cloud Computing Security and Data Aggregation Zhejiang Sci-Tech University Hangzhou310018 China Zhejiang Provincial Innovation Center of Advanced Textile Technology Shaoxing312000 China College of Computer Science and Information Technology IAU Saudi Arabia Grimstad4879 Norway Network and Data Security Hangzhou310053 China Computer Science Department City University of Hong Kong Hong Kong the Division of Computer Science University of Aizu Fukushima965–8580 Japan

In recent years, against the backdrop of smart grids, vehicle-to-grid (V2G) interaction has become a hot topic. With the increasing number of new energy vehicles, handling massive amounts of electricity transaction data has become an urgent problem in need of resolution. Ensuring the security of the vast quantities of electricity transaction data has emerged as a significant challenge. Therefore, two data aggregation schemes are proposed in this paper, both supporting batch verification and privacy protection in centralized and distributed scenarios, respectively. Firstly, an improved Paillier cryptosystem is utilized to achieve lightweight encryption in the proposed schemes. In addition, a novel distributed data aggregation structure that combines a large number of geographically distributed fog nodes with centralized cloud servers is introduced. This structure not only meets the requirements of lightweight encryption and resistance against single point failures but also reduces the communication complexity of distributed data aggregation to O(n). According to the security proofs and experimental analysis, it can be demonstrated that both proposed schemes are effective and secure, meeting the lightweight requirements of modern smart grid systems. © 2025 IEEE. All rights reserved,

关键词： data aggregation

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：