检索结果-内蒙古大学图书馆

Federated Feature Concatenate Method for Heterogeneous Computing in Federated Learning

computers, Materials & Continua 2023年第4期75卷 351-371页

作者： Wu-Chun Chung Yung-Chin Chang Ching-Hsien Hsu Chih-Hung Chang Che-Lun Hung Department of Information and Computer Engineering Chung Yuan Christian UniversityTaoyuanTaiwan Department of Computer Science and Information Engineering Asia UniversityTaichungTaiwan Department of Medical Research China Medical University HospitalChina Medical UniversityTaichungTaiwan Department of Computer Science&Communication Engineering Providence UniversityTaichungTaiwan Institute of Biomedical Informatics National Yang Ming Chiao Tung UniversityTaipeiTaiwan

Federated learning is an emerging machine learning techniquethat enables clients to collaboratively train a deep learning model withoutuploading raw data to the aggregation server. Each client may be equippedwith different computing resources for model training. The client equippedwith a lower computing capability requires more time for model training,resulting in a prolonged training time in federated learning. Moreover, it mayfail to train the entire model because of the out-of-memory issue. This studyaims to tackle these problems and propose the federated feature concatenate(FedFC) method for federated learning considering heterogeneous *** leverages the model splitting and feature concatenate for offloadinga portion of the training loads from clients to the aggregation server. Eachclient in FedFC can collaboratively train a model with different cutting ***, the specific features learned in the deeper layer of the serversidemodel are more identical for the data class classification. Accordingly,FedFC can reduce the computation loading for the resource-constrainedclient and accelerate the convergence time. The performance effectiveness isverified by considering different dataset scenarios, such as data and classimbalance for the participant clients in the experiments. The performanceimpacts of different cutting layers are evaluated during the model *** experimental results show that the co-adapted features have a criticalimpact on the adequate classification of the deep learning model. Overall,FedFC not only shortens the convergence time, but also improves the bestaccuracy by up to 5.9% and 14.5% when compared to conventional federatedlearning and splitfed, respectively. In conclusion, the proposed approach isfeasible and effective for heterogeneous clients in federated learning.

关键词： Federated learning deep learning artificial intelligence heterogeneous computing

来源：评论

学校读者我要写书评

暂无评论

Indoors Traversability Estimation with RGB-Laser Fusion 19

Indoors Traversability Estimation with RGB-Laser Fusion

引用

19th IEEE International Conference on Automation Science and engineering, CASE 2023

作者： Sevastopoulos, Christos Theofanidis, Michail Hebri, Aref Konstantopoulos, Stasinos Karkaletsis, Vangelis Makedon, Fillia University of Texas at Arlington Department of Computer Science & Computer Engineering ArlingtonTX United States University of Texas Arlington Research Institute Fort WorthTX United States Institute of Informatics and Telecommunications Ncsr 'Demokritos' Agia Paraskevi Attica Greece

ISBN: (纸本)9798350320695

We propose a dual-stream, semi-supervised, attention-based approach that employs feature fusion of RGB and Laser Range Finder (LRF) modalities. Our method lever-ages the strength of two powerful transformer-based networks, i.e. Vision Transformer (ViT) and SegFormer, along with LRF information, to adequately predict whether the scene encountered in the image is safe for a robot to traverse. Towards this effort, we introduce an automated labelling system profiting from the combination of raw velocity readings and laser scanning information. Moreover, we show that overall GOINO-GO detection is enhanced by fusing RGB and laser modalities. Feature fusion is achieved through the employment of a Multi-Head Self-Attention (MHSA) module. Through cross-domain validation, we show that the proposed traversability estimation method can achieve decent amounts of transferability even with limited amount of training data. © 2023 IEEE.

关键词： Range finders

来源：评论

学校读者我要写书评

暂无评论

eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale, High-quality Instruction Data 41

eCeLLM: Generalizing Large Language Models for E-commerce fr...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Peng, Bo Ling, Xinyi Chen, Ziru Sun, Huan Ning, Xia Department of Computer Science and Engineering The Ohio State University United States Translational Data Analytics Institute The Ohio State University United States Department of Biomedical Informatics The Ohio State University United States

With tremendous efforts in developing effective e-commerce models, conventional e-commerce models show limited success in generalist e-commerce modeling, and suffer from unsatisfactory performance on new users and new products - a typical out-of-domain generalization challenge. Meanwhile, large language models (LLMs) demonstrate outstanding performance in generalist modeling and out-of-domain generalizability in many fields. Toward fully unleashing their power for e-commerce, in this paper, we construct ECInstruct, the first open-sourced, large-scale, and high-quality benchmark instruction dataset for e-commerce. Leveraging ECInstruct, we develop eCeLLM, a series of e-commerce LLMs, by instruction-tuning general-purpose LLMs. Our comprehensive experiments and evaluation demonstrate that eCeLLM models substantially outperform baseline models, including the most advanced GPT-4, and the state-of-the-art task-specific models in in-domain evaluation. Moreover, eCeLLM exhibits excellent generalizability to out-of-domain settings, including unseen products and unseen instructions, highlighting its superiority as a generalist e-commerce model. Both the ECInstruct dataset and the eCeLLM models show great potential in empowering versatile and effective LLMs for e-commerce. ECInstruct and eCeLLM models are publicly accessible through https://***/eCeLLM/. Copyright 2024 by the author(s)

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

Bidirectional LSTM-Based Energy Consumption Forecasting:Advancing AI-Driven Cloud Integration for Cognitive City Energy Management

引用

computers, Materials & Continua 2025年第5期83卷 2907-2926页

作者： Sheik Mohideen Shah Meganathan Selvamani Mahesh Thyluru Ramakrishna Surbhi Bhatia Khan Shakila Basheer Wajdan Al Malwi Mohammad Tabrez Quasim Department of Computer Science and Engineering Srinivasa Ramanujan CentreSASTRA Deemed UniversityKumbakonam612001India Department of Computer Science and Engineering Faculty of Engineering and TechnologyJAIN(Deemed-to-be University)Bangalore562112India School of Science Engineering and EnvironmentUniversity of SalfordManchesterM54WTUK University Centre for Research and Development Chandigarh UniversityMohali140413PunjabIndia Centre for Research Impact and Outcome Chitkara University Institute of Engineering and TechnologyChitkara UniversityRajpura140401PunjabIndia Department of Information Systems College ofComputer and Information SciencePrincessNourah bintAbdulrahmanUniversityP.O.Box 84428Riyadh11671Saudi Arabia College of Computer Science Informatics and Computer Systems Department King Khalid UniversityAbha61421Saudi Arabia Department of Computer Science and Artificial Intelligence College of Computing and Information TechnologyUniversity of BishaBisha61922Saudi Arabia

Efficient energy management is a cornerstone of advancing cognitive cities,where AI,IoT,and cloud computing seamlessly integrate to meet escalating global energy *** this context,the ability to forecast electricity consumption with precision is vital,particularly in residential settings where usage patterns are highly variable and *** study presents an innovative approach to energy consumption forecasting using a bidirectional Long Short-Term Memory(LSTM)*** a dataset containing over twomillionmultivariate,time-series observations collected froma single household over nearly four years,ourmodel addresses the limitations of traditional time-series forecasting methods,which often struggle with temporal dependencies and non-linear *** bidirectional LSTM architecture processes data in both forward and backward directions,capturing past and future contexts at each time step,whereas existing unidirectional LSTMs consider only a single temporal *** design,combined with dropout regularization,leads to a 20.6%reduction in RMSE and an 18.8%improvement in MAE over conventional unidirectional LSTMs,demonstrating a substantial enhancement in prediction accuracy and *** to existing models—including SVM,Random Forest,MLP,ANN,and CNN—the proposed model achieves the lowest MAE of 0.0831 and RMSE of 0.2213 during testing,significantly outperforming these *** results highlight the model’s superior ability to navigate the complexities of energy usage patterns,reinforcing its potential application in AI-driven IoT and cloud-enabled energy management systems for cognitive *** integrating advanced machine learning techniqueswith IoT and cloud infrastructure,this research contributes to the development of intelligent,sustainable urban environments.

关键词： Deep learning bidirectional LSTM energy consumption forecasting time-series analysis predictive modeling machine learning in energy management

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Deep Convolutional Neural Network-Based Tattoo Detection

Evaluation of Deep Convolutional Neural Network-Based Tattoo...

引用

Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC), V Congreso Internacional en

作者： E. Jiménez-Delgado C. Quesada-López A Méndez-Porras A Lara-Petitdemange J Alfaro-Velasco Graduate Program in Computer Science and Informatics University of Costa Rica Computer Engineering Department Technological Institute of Costa Rica School of Computer Science and Informatics University of Costa Rica

ISBN: (数字)9798350364538

ISBN: (纸本)9798350364545

In this study, two deep learning models for automatic tattoo detection were analyzed; a modified Convolutional Neural Network (CNN) and pre-trained ResNet-50 model. In order to achieve this, ResNet-50 uses transfer learning with fine-tuning. The purpose of this study was to evaluate the accuracy, precision, recall, F1-score, and computational efficiency of the system being considered. To augment the dataset included 1000 photos that were equally divided between those showing tattoos and those that did not show tattoos. A k-fold cross-validation approach was employed in training and testing the models. Although custom CNNs are effective, utilizing pre-trained ones like ResNet-50 can offer even better outcomes. Specifically, ResNet-50 attained a higher accuracy (0.86 compared to 0.79), precision (0.85 versus 0.78), recall (0.91 against 0.86), and F1-score (0.91 vis-a-vis 0.86) as compared to custom CNNs. In selecting these models for examination, two main motivations were considered. The first motivation is to see whether transfer learning with a pre-trained ResNet-50 model does well when compared with a customized CNN designed specifically for tattoo detection. Secondly,the intent of this study is to know what advantages can be derived from each approach and their demerits too. Furthermore, it seeks to determine if transfer learning can provide an alternative in contrast to the common CNN techniques with regards to precision and computational efficiency. In this research, two models will be evaluated in order to answer the question of what is better for tattoo detection: transfer learning or designing custom architectures.

关键词： Training Analytical models Accuracy Computational modeling Transfer learning computer architecture Real-time systems Computational efficiency Convolutional neural networks Tuning

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection With Quantified Explanations for Multivariate Time Series Networking Data

Anomaly Detection With Quantified Explanations for Multivari...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Marantis, Panagiotis Ramantas, Kostas Verikoukis, Christos Iquadrat Informatica S.L Barcelona Spain University of Patras Dept. of Computer Engineering and Informatics Patras Greece Athena Research Center Athens Greece Industrial Systems Institute Patras Greece

ISBN: (纸本)9798350351255

Next-generation telecommunication networks provide vast amounts of Multivariate Time Series monitoring data during their operation. Using these data to automatically detect anomalous system behavior is of critical importance to operators and Internet Service Providers, in order to analyze the network state and take mitigating actions to resolve possible faults. For the output of this Anomaly Detection process to be trusted, comprehensive and accurate explanations must be provided. These explanations are essential to make critical decisions that affect the network state. In this paper, we present a framework that utilizes reconstruction-based Deep Neural Network models to perform the anomaly detection task, while also using an explainability module that provides explanations of the results. The quality of the explanations is quantified through the use of interpretation labels. In addition, we provide a comparative analysis, performing Anomaly Detection on three different open-source datasets from the mobile networking domain, while testing multiple Deep Learning models and comparing their performance. The presented results show that our framework accurately detects various types of anomalies that can be present in mobile networks, while offering the flexibility to identify and select the model that offers the best performance for each dataset, in both the Anomaly Detection and explainability tasks. © 2024 IEEE.

关键词： DNNs Explainable Anomaly Detection Machine Learning Multivariate Time Series Next-Generation Networks Reconstruction-based Models

来源：评论

学校读者我要写书评

暂无评论

Towards A Knowledge Graph-based Exploratory Search for Privacy engineering 8

Towards A Knowledge Graph-based Exploratory Search for Priva...

引用

8th International Workshop on the Visualization and Interaction for Ontologies, Linked Data and Knowledge Graphs, VOILA! 2023

作者： Herwanto, Guntur Budi Ekaputra, Fajar J. Piroi, Florina Sabou, Marta Faculty of Computer Science University of Vienna Austria Department of Computer Science and Electronics Universitas Gadjah Mada Indonesia Institute of Information Systems Engineering Faculty of Informatics TU Wien Austria Institute of Data Process and Knowledge Management WU Wien Austria

The concept of privacy-by-design has gained considerable attention in the wake of legal requirements that software systems should fulfill. The interconnected knowledge on privacy concepts, legal requirements, and software development artifacts required to implement this concept can be a major burden for organizations. To address this challenge, we propose a knowledge graph-based Exploratory Search system to help organizations complete privacy engineering tasks. We identify major requirements of such systems and develop an Exploratory Search prototype built on privacy engineering knowledge that integrates different information sources. While still preliminary, this work serves as a foundation for future research on integrating privacy knowledge into software development and demonstrates the potential of Exploratory Search Systems to support the cognitive process in privacy tasks such as privacy threat identification. © 2023 Copyright for this paper by its authors.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Online Resource Allocation for User Experience Improvement in Heterogeneous MEC Systems

Online Resource Allocation for User Experience Improvement i...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ni, Weiya Tong, Jingwen Fu, Liqun Hong Kong University of Science and Technology Department of Electronic and Computer Engineering Hong Kong Xiamen University Institute of Artificial Intelligence Xiamen361005 China Xiamen University School of Informatics Xiamen361005 China

ISBN: (纸本)9798350351255

Mobile edge cloud (MEC) has emerged as a critical technology for enabling low-latency and real-time mobile device applications. However, an efficient resource allocation framework for improving the user experience in MEC with heterogeneous users is still missing, especially considering the recent sparks of AI-generated content applications. This paper proposes a double-closed-loop online resource allocation (DORA) framework for user experience improvement. This framework employs inner and outer loops to construct the optimal online allocation strategy and recommend a suitable strategy for different types of users, respectively. Based on the DORA framework, we put forth OR2A-HetU, an Online Resource Recommendation and Allocation algorithm for Heterogeneous Users, to solve this resource allocation problem. The OR2A-HetU algorithm proceeds sequentially and can converge to the optimal solution when the time horizon is sufficiently large. The numerical results show that the proposed algorithm outperforms the baseline algorithms, and the user complaint rate decreases from 48.8% to 27.5% when the available resources increase. © 2024 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

PLS-SEM Approach and Sentiment Analysis for Identifying Significant Factors of Customer Satisfaction

PLS-SEM Approach and Sentiment Analysis for Identifying Sign...

引用

2023 International Conference on Data Science and Its Applications, ICoDSA 2023

作者： Bawono, Marastika Wicaksono Aji Purwitasari, Diana Purnomo, Mauridhi Hery Sepuluh Nopember Institute of Technology Departement of Technology Management Surabaya East Java Indonesia Sepuluh Nopember Institute of Technology Departement of Informatics Engineering Surabaya East Java Indonesia Sepuluh Nopember Institute of Technology Departement of Electrical Engineering Departement of Computer Engineering Surabaya East Java Indonesia

ISBN: (纸本)9798350305197

Reviews have a direct impact on customer satisfaction. The aim of this study is to dissect and analyze a collection of 775 negative and 557 positive comment reviews, drawn from four distinct e-commerce platforms. By classifying these remarks into positive and negative sentiments, this research endeavors to illuminate underlying trends permeating these marketplaces. The research methodology employed involves field observations of online shopping experiences, utilizing data derived from 254 e-commerce customers. These data were collected via validated questionnaires and subsequently analyzed using the partial least squares structural equation modeling approach, employing the lavaan r library within the R programming environment. The questionnaire results produced a rating scale from 1 to 5, categorizing responses from 'very satisfied' to 'less satisfied', effectively illustrating both positive and negative commentary. The field comment data collected was coordinated with comment data extracted from four marketplace trading accounts. This data comment customer was analyzed using a range of comparative models such as k-nearest neighbors, multinomial naive bayes, stochastic gradient descent, and decision trees to conduct sentiment analysis. The findings reveal that the naive bayes method generates the greatest accuracy in sentiment analysis, registering an accuracy value of 0.886. Moreover, the analysis executed through r programming indicates that the e-service quality model yields the most robust results, reflected by an adjusted r-square value of 0.885. This study exerts a notable impact on service quality, as evidenced by a coefficient value of 0.865 and a perceived reputation score of 0.162. © 2023 IEEE.

关键词： Customer satisfaction

来源：评论

学校读者我要写书评

暂无评论

Hybrid-RIS Empowered UAV-Aided ISAC Systems 100

Hybrid-RIS Empowered UAV-Aided ISAC Systems

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Saikia, Prajwalita Jee, Anand Singh, Keshav Tsiftsis, Theodoros A. Boulogeorgos, Alexandros-Apostolos A. National Sun Yat-sen University Institute of Communications Engineering Kaohsiung804 Taiwan Indian Institute of Technology Delhi Department of Electrical Engineering New Delhi110016 India University of Thessaly Department of Informatics & Telecommunications Lamia35100 Greece University of Western Macedonia Department of Electrical and Computer Engineering Kozani50131 Greece

ISBN: (纸本)9798331517786

In this paper, we consider a novel hybrid reconfigurable intelligent surface (HRIS) consisting of active as well as passive reflecting elements mounted on unmanned aerial vehicle (UAV). The aim is to improve air-to-ground communication by assisting multiple users, while detecting several moving targets. We formulate an optimization model that account for statistical channel estimation errors (SCEEs) to concurrently fine-tune both active and passive phase-shift matrices, UAV trajectory and transmit beamformer for integrated sensing and communication (ISAC), while aiming to maximize the overall achievable sum-rate. Subsequently, we introduce an alternating optimization algorithm that employs a repetitive method to address the combinatorial nonconvex optimization problem and ultimately yielding a solution that is nearly optimal. Using Monte Carlo simulations, we showcase the superiority of the suggested approach in comparison to baseline schemes. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

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：