检索结果-内蒙古大学图书馆

A MLP-Mixer.a.d mixture of expert model for remaining useful life prediction of lithium-ion batteries

Frontiers of computer Science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the remaining Useful Life(rUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting rUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer.a.d Mixture of Expert(MMMe)model,for rUL *** MMMe model leverages the Gated recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable rUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise rUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

来源：评论

学校读者我要写书评

暂无评论

Enabling Lora energy awareness: A Multihop One-Hop routing Protocol for Prolonging Network Lifetime 19

Enabling LoRa energy awareness: A Multihop One-Hop Routing P...

引用

19th Annual Inter.a.ional Conference on Distributed Computing in Smart Systems and the Internet of Things, DCOSS-IoT 2023

作者： Katsidimas, Ioannis Manolopoulos, Alexandros-Ioannis Nikoletseas, Sotiris University of Patras Department of Computer Engineering and Informatics Patras Greece University of Athens Department of Physics National and Kapodistrian Athens Greece University of Patras and Computer Technology Institute and Press Diophantus Department of Computer Engineering and Informatics Patras Greece

ISBN: (纸本)9798350346497

IoT applications often rely on battery-powered nodes that may be challenging to recharge, making energy efficiency a crucial concern. In this context, routing protocols play a vital role as they dictate the paths data packets take between nodes, directly influencing the energy consumption of IoT networks. Energy-aware routing protocols have been proposed to address this issue, with the aim of optimizing energy consumption by selecting paths that minimize the energy required for data transmission and reception. These protocols employ various strategies, such as distance-based, traffic-based, and hybrid schemes, to achieve energy efficiency in IoT networks. LoraWAnprotocol has been adopted for various IoT applications with requirements in low-power.a.d extended coverage. Over the recent years attempts have been made to replace the typical star topology employed by Lora with multihop solutions, in an effort to further incr.a.e its capabilities. In this paper, we present a multihop algorithm that is based on an energy-balanced routing scheme adopted by Lora nodes to incr.a.e energy efficiency and network lifetime. Multiple one-hop routes are configured for critical nodes and a different route is selected in each transmission. Additionally, critical nodes adjust their Spr.a.ing Factor.a.d Transmission Power.a.cording to the distance of intermediate nodes. Simulation testing results verify the improved perfor.a.ce of our.a.gorithm over the direct link appr.a.h. © 2023 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Malicious Activities Prediction Over Online Social Networking Using Ensemble Model

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 461-479页

作者： S.Sadhasivam P.Valar.a.hie K.Dinakaran Department of Computer Science and Engineering K.S.R College of EngineeringThiruchengodeIndia Centre for Artificial Intelligence Chennai Institute of TechnologyChennaiIndia Department of Computer Science and Engineering S.A.Engineering CollegeChennaiIndia

With the vast advancements in Infor.a.ion technology,the emergence of Online Social Networking(OSN)has also hit its peak and captured the atten-tion of the young generation *** clone intends to replicate the users and inject massive malicious activities that pose a crucial security thr.a. to the original ***,the attackers also target this height of OSN utilization,explicitly cr.a.ing the clones of the user’s *** clone detection mechanisms are designed based on social-network *** instance,monitoring the occur-rence of clone edges is done to restrict the generation of clone ***,this assumption is unsuitable for.a.r.a.-time environment and works optimally during the simulation *** research concentrates on modeling and efﬁ-cient clone prediction and avoidance methods to help the social network activists and the victims enhance the clone prediction *** model does not rely on ***,an ensemble Adaptive random Subspace is used for clas-sifying the clone victims with k-Nearest Neighbour(k-NN)as a base classiﬁ*** weighted clone nodes are analysed using the weighted graph theory concept based on the classiﬁed *** the weighted node’s threshold value is high-er,the trust establishment is terminated,and the clones are ranked and sorted in the higher place for ***,the victims are alert to the clone propaga-tion over the online social networking end,and the validation is done using the MATLAB 2020a simulation *** model shows a better trade-off than existing appr.a.hes like random Forest(rF),Naïve Bayes(NB),and the standard graph *** perfor.a.ce metrics like True Positive rate(TPr),False Alarm rate(FAr),recall,Precision,F-measure,and rOC and run time analysis are evaluated to show the signiﬁcance of the model.

关键词： Online social network decision tree weighted measure clone attack predictive measures

来源：评论

学校读者我要写书评

暂无评论

EfficientNetB0-based Automated Diabetic retinopathy Classification in Fundus Images 3

EfficientNetB0-based Automated Diabetic Retinopathy Classifi...

引用

3rd Inter.a.ional Conference on Automation, Computing and renewable Systems, ICACrS 2024

作者： Majaw, Ezekiel Alaric Sundar, G. Naveen Nar.a.ha, D. Thangavel, Senthil Kumar Venkatesan Ajibesin, Adeyemi Abel Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore India Department of Information Technology Faculty of Informatics and Design Cape Peninsula University of Technology South Africa

ISBN: (纸本)9798331532420

The most common cause of blindness among diabetics is diabetic retinopathy. This disease must be detected in its early stages as delaying tr.a.ment can result in per.a.ent blindness. In today’s modern world with the development of technologies, automated techniques have improved the accuracy and efficiency of detecting and classifying this disease. This study suggests a deep learning model utilizing EfficientNetB0 that focuses on designing a neural network structure that requires fewer parameters and computations compared to traditional architectures. Further to help in incr.a.ing the accuracy, the image is being processed with methods like CLAHE which is an image processing algorithm that helps in enhancing the contrast while keeping the noise of the images as low as possible. Also, augmentation is being done on the images and SMOTE is applied to handle class imbalance. We collected the APTOS Blindness Detection dataset consisting of retinal fundus images. The accuracy that is being obtained from the proposed methodology is 98.78% indicating the model's effectiveness in detection and classifying between the various stages of diabetic retinopathy. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing NOMA Transmissions to Advance Federated Learning in Vehicular Networks

Optimizing NOMA Transmissions to Advance Federated Learning ...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Chen, Ziru Ni, Zhou Guan, Peiyuan Wang, Lu Cai, Lin X. Hashemi, Morteza Li, Zongzhi Illinois Institute of Technology Department of Electrical and Computer Engineering Chicago United States University of Kansas Department of Electrical Engineering and Computer Science Lawrence United States University of Oslo Department of Informatics Oslo Norway Illinois Institute of Technology Department of Civil Engineering Chicago United States

ISBN: (纸本)9798350351255

Diverse critical data, such as location infor.a.ion and driving patterns, can be collected by IoT devices in vehicular networks to improve driving experiences and r.a. safety. However, drivers are often reluctant to share their data due to privacy concerns. The Federated Vehicular Network (FVN) is a promising technology that tackles these concerns by transmitting model parameters instead of raw data, thereby protecting the privacy of drivers. Nevertheless, the perfor.a.ce of Federated Learning (FL) in a vehicular network depends on the joining ratio, which is restricted by the limited available wireless resources. To address these challenges, this paper proposes to apply Non-Orthogonal Multiple Access (NOMA) to improve the joining ratio in a FVN. Specifically, a vehicle selection and transmission power control algorithm is developed to exploit the power domain differences in the received signal to ensure the maximum number of vehicles capable of joining the FVN. Our simulation results demonstrate that the proposed NOMA-based strategy incr.a.es the joining ratio and significantly enhances the perfor.a.ce of the FVN. Index Terms - Federated Vehicular Network, NOMA © 2024 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

AFSTGCN:Prediction for multivar.a.e time series using an adaptive fused spatial-temporal graph convolutional network

引用

Digital Communications and Networks 2024年第2期10卷 292-303页

作者： Yuteng Xiao Kaijian Xia Hongsheng Yin Yu-Dong Zhang Zhenjiang Qian Zhaoyang Liu Yuehan Liang Xiaodan Li School of Information and Control Engineering China University of Mining and TechnologyXuzhou221116China Department of Informatics University of LeicesterLeicesterLE17RHUK The Affiliated Changshu Hospital of Soochow University Changshu215500China School of Computer Science and Engineering Changshu Institute of TechnologySuzhou215500China

The prediction for Multivar.a.e Time Series(MTS)explores the interrelationships among var.a.les at historical moments,extracts their relevant characteristics,and is widely used in finance,weather,complex industries and other ***,it is impor.a.t to construct a digital twin ***,existing methods do not take full advantage of the potential properties of var.a.les,which results in poor predicted *** this paper,we propose the Adaptive Fused Spatial-Temporal Graph Convolutional Network(AFSTGCN).First,to address the problem of the unknown spatial-temporal structure,we construct the Adaptive Fused Spatial-Temporal Graph(AFSTG)***,we fuse the spatial-temporal graph based on the interrelationship of spatial ***,we construct the adaptive adjacency matrix of the spatial-temporal graph using node embedding ***,to overcome the insufficient extraction of disordered correlation features,we construct the Adaptive Fused Spatial-Temporal Graph Convolutional(AFSTGC)*** module forces the reordering of disordered temporal,spatial and spatial-temporal dependencies into rule-like *** dynamically and synchronously acquires potential temporal,spatial and spatial-temporal correlations,thereby fully extracting rich hierarchical feature infor.a.ion to enhance the predicted *** on different types of MTS datasets demonstrate that the model achieves state-of-the-art single-step and multi-step perfor.a.ce compared with eight other deep learning models.

关键词： Adaptive adjacency matrix Digital twin Graph convolutional network Multivar.a.e time series prediction Spatial-temporal graph

来源：评论

学校读者我要写书评

暂无评论

Suggestion Mining for Mobile APP Quality Improvement

Suggestion Mining for Mobile APP Quality Improvement

引用

2024 Inter.a.ional Conference on Advancements in Power, Communication and Intelligent Systems, APCI 2024

作者： Mali, Makarand Lotan Patil, Nitin N. R. C. Patel Institute of Technology Department of Computer Engineering Shirpur India

ISBN: (纸本)9798350363289

User feedback is essential for mobile apps to continuously improve. However, obtaining insightful suggestions from user reviews still poses a major challenge. In order to address this issue, this study suggests a brand-new rule-based method for suggestion mining that focuses on the action verbs' capacity to provide infor.a.ion. To detect user evaluations with suggestions, our.a.pr.a.h makes use of verb semantics and pre-established criter.a.based on action verbs. We under.a.e a comprehensive perfor.a.ce evaluation on an actual dataset of mobile app evaluations to determine its efficacy. The outcomes demonstrate the substantial potential of our rule-based methodology, attaining superior memory and precision in identifying suggestions in reviews. Through the utilization of action verbs' rich infor.a.ion, our.a.pr.a.h provides a useful and effective way to automatically derive actionable suggestions from user reviews. We obtained above 89% accuracy for enhanced proposed method. In the end, this helps to improve the quality of mobile apps by enabling data-driven adjustments based on user reviews. © 2024 IEEE.

关键词： action verbs mobile app reviews quality improvement rule-based appr.a.h Suggestion mining

来源：评论

学校读者我要写书评

暂无评论

Selected Combinator.a. Problems Through the Prism of random Intersection Graphs Models 1

引用

13th Inter.a.ional Symposium on Algorithms and Complexity, CIAC 2023

作者： Spirakis, Paul G. Nikoletseas, Sotiris raptopoulos, Christoforos Department of Computer Science University of Liverpool Liverpool United Kingdom Computer Technology Institute Patras Greece Computer Engineering and Informatics Department University of Patras Patras Greece

ISBN: (数字)9783031304484

ISBN: (纸本)9783031304477

We discuss a simple, yet general family of models, namely random Intersection Graphs (rIGs), initially introduced by Karoński et al. [4] and Singer-Cohen [10]. In such models there is a universe of labels and each one of n vertices selects a random subset of. Two vertices are connected if and only if their corresponding subsets of labels intersect. A for.a. definition is given below: © 2023, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzer.a.d AG.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Software Fault Prediction in Service-Oriented Based Systems 5

Software Fault Prediction in Service-Oriented Based Systems

引用

5th IEEE Inter.a.ional Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Singh, raghuraj Kumar, Kuldeep Dr. B. R. Ambedkar National Institute of Technology Department of Computer Science & Engineering Punjab Jalandhar India National Institute of Technology Department of Computer Engineering Haryana Kurukshetra India

ISBN: (纸本)9798350383522

Software fault prediction plays a crucial role in enhancing software quality and minimizing maintenance cost. Primary goal of software fault prediction is to identify flaws before testing stage, that will save the expense and duration of software development while improving the software product's quality. In recent years, deep learning techniques have gained significant attention in the field of software fault prediction due to their.a.ility to extract complex patterns and features from large-scale software datasets. This paper.a.ms to provide a comprehensive overview of the existing research on software fault prediction using deep learning techniques. It covers a wide range of studies, including various deep learning models, feature engineering appr.a.hes, evaluation metrics, and datasets used in this domain. We examine strategies for predicting software faults in Service-Oriented Architecture based systems using deep learning and hybrid optimization-enabled deep learning methods. The findings reveal that hybrid deep learning and nature-inspired enabled deep learning techniques are more effective than just using machine learning and deep learning appr.a.hes. © 2024 IEEE.

关键词： Deep Learning Machine Learning Service Oriented Architecture (SOA) Software Fault Prediction (SFP)

来源：评论

学校读者我要写书评

暂无评论

Using Machine Learning to Identify and Categorize Personally Identifiable Infor.a.ion and Payment Card Industry Data in Textual Content 4

Using Machine Learning to Identify and Categorize Personally...

引用

4th Inter.a.ional Conference on Advanced research in Computing, ICArC 2024

作者： Arambawela, Milinda Aponso, Achala University of Westminster Computer Science and Engineering London United Kingdom Informatics Institute of Technology Department of Computing Colombo Sri Lanka

ISBN: (纸本)9798350384864

The advent of the Internet has significantly str.a.-lined daily tasks through the rapid incr.a.e of online services. Everyday activities, such as purchasing goods and scheduling appointments with healthcare professionals, have become more speedy, efficient and user-friendly with the integration of the Internet. The continuous improvement of online services has led to many people moving towards digital activities. As a result, it has heightened the recording of personal and payment transaction data across various storage mediums, including databases and log files. The protection and regulation of this sensitive data are imperative, aligning with the guidelines outlined in GDPr.a.d PCI-DSS compliances. recognizing exposed personal data poses a considerable challenge. This research introduces a novel appr.a.h to identifying payment card industry data (PCI) and personally identifiable infor.a.ion (PII). The research project proposes a machine learning-based text classification model utilizing the Convolutional Neural Network (CNN) model to discern PII and PCI data within a given text. The CNN model has been constructed and compared against Naive Bayes, Gradient Boost, random Forest, and Support Vector Machine (SVM) models. The CNN model achieved the highest accuracy at 0.96 (96%). Additionally, the F1 scores for each class were significant, with PII scoring 0.94, PCI scoring 0.95, and Nor.a. scoring 0.99. Following the model's construction and training, it was employed with the saved tokenizer's word indexes and label encoders in the developed classification tool. This tool successfully delivered the promised results, identifying exposed PII and PCI data. © 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

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：