检索结果-内蒙古大学图书馆

30th International Conference on Mobile Computing and Networking, ACM MobiCom 2024

作者： Liao, Yunming Xu, Yang Xu, Hongli Yao, Zhiwei Huang, Liusheng Qiao, Chunming School of Computer Science and Technology University of Science and Technology of China China Suzhou Institute for Advanced Research University of Science and Technology of China China Department of Computer Science and Engineering University at Buffalo State University of New York United States

ISBN: (纸本)9798400704895

Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and accelerate the training of large-scale models on resource-constraint workers in edge computing (EC) system, we propose a novel split federated learning (SFL) framework, termed ParallelSFL. Concretely, we split an entire model into a bottom submodel and a top submodel, and divide participating workers into multiple clusters, each of which collaboratively performs the SFL training procedure and exchanges entire models with the PS. However, considering the statistical and system heterogeneity in edge systems, it is challenging to arrange suitable workers to specific clusters for efficient model training. To address these challenges, we carefully develop an effective clustering strategy by optimizing a utility function related to training efficiency and model accuracy. Specifically, ParallelSFL partitions workers into different clusters under the heterogeneity restrictions, thereby promoting model accuracy as well as training efficiency. Meanwhile, ParallelSFL assigns diverse and appropriate local updating frequencies for each cluster to further address system heterogeneity. Extensive experiments are conducted on a physical platform with 80 NVIDIA Jetson devices, and the experimental results show that ParallelSFL can reduce the traffic consumption by at least 21%, speed up the model training by at least 1.36X, and improve model accuracy by at least 5% in heterogeneous scenarios, compared to the baselines. © 2024 Copyright is held by the owner/author(s). Publication rights licensed to ACM.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

5G technology and Impact on Modern engineering 4

5G Technology and Impact on Modern Engineering

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Kate, Priya Pacharney, Utkarsha Datta Meghe Institute of Higher Education and Research Department of Computer Science and Engineering Faculty of Engineering and Technology Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Department of Computer Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

5G technology represents a progressive leap in Wi-Fi conversation, providing unheard-of pace, connectivity, and capacity. Its deployment has profound implications for modern engineering, impacting industries such as telecommunications, healthcare, transportation, and clever towns. With speeds up to one hundred instances quicker than 4G and latency as little as 1 millisecond, 5G permits real-time facts trade, fostering improvements like independent vehicles, far-flung surgeries, and the Internet of Things (IoT). Currently, Engineers are challenged to design infrastructure that will assist the dense community of gadgets related to 5G, necessitating advancements in antenna design, power performance, and statistics security. The era also quickens the adoption of part computing, reducing reliance on centralised facts centres and ensuring quicker processing near the date supply. The transformative impact of 5G extends beyond connectivity. It reshapes the layout and capability of present-day engineering structures, emphasising adaptability, resilience, and scalability. As 5G continues to conform, its function in driving innovation and redefining engineering paradigms becomes increasingly glaring. © 2025 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Evolution-guided Bayesian optimization for constrained multi-objective optimization in self-driving labs

引用

npj Computational Materials 2024年第1期10卷 2171-2181页

作者： Andre K.Y.Low Flore Mekki-Berrada Abhishek Gupta Aleksandr Ostudin Jiaxun Xie Eleonore Vissol-Gaudin Yee-Fun Lim Qianxiao Li Yew Soon Ong Saif A.Khan Kedar Hippalgaonkar School of Materials Science and Engineering Nanyang Technological UniversitySingapore 639798Singapore Institute of Materials Research and Engineering(IMRE) Agency for ScienceTechnology and Research(A*STAR)2 Fusionopolis WayInnovis#08-03Singapore 138634Republic of Singapore Department of Chemical and Biomolecular Engineering National University of SingaporeSingapore 117585Singapore School of Mechanical Sciences Indian Institute of Technology GoaGoa 403401India Institute of Sustainability for Chemicals Energy and Environment(ISCE2)Agency for ScienceTechnology and Research(A*STAR)1 Pesek RoadSingapore 627833Republic of Singapore Department of Mathematics National University of SingaporeSingapore 119077Singapore Institute for Functional Intelligent Materials National University of SingaporeSingapore 117544Singapore School of Computer Science and Engineering Nanyang Technological UniversitySingapore 639798Singapore

The development of automated high-throughput experimental platforms has enabled fast sampling of high-dimensional decision *** reach target properties efficiently,these platforms are increasingly paired with intelligent experimental ***,current optimizers show limitations in maintaining sufficient exploration/exploitation balance for problems dealing with multiple conflicting objectives and complex ***,we devise an Evolution-Guided Bayesian Optimization(EGBO)algorithm that integrates selection pressure in parallel with a q-Noisy Expected Hypervolume Improvement(qNEHVI)optimizer;this not only solves for the Pareto Front(PF)efficiently but also achieves better coverage of the PF while limiting sampling in the infeasible space.

关键词： optimization driving constrained

来源：评论

学校读者我要写书评

暂无评论

RAG-Enhanced Large Language Model for Intelligent Assistance from Web-Scraped Data 9

RAG-Enhanced Large Language Model for Intelligent Assistance...

引用

9th International Conference on Communication and Electronics Systems, ICCES 2024

作者： Kanataria, Nikunj Patel, Kunj Pareshbhai Patel, Hetul Niteshbhai Goel, Parth Patel, Krishna Garg, Dweepna Devang Patel Institute of Advance Technology and Research Computer Science & Engineering Department Changa Anand India Computer Science & Design Department Vallabh vidyanagar Anand India

ISBN: (纸本)9798350377972

The explosion of online information necessitates efficient and accurate methods for retrieving and analyzing relevant data. This research proposes a novel framework that leverages Retrieval-Augmented Generation (RAG) techniques to address this challenge. The framework utilizes web scraping to extract information from various sources and employs advanced language models like Llama 3, Mistral, and Gemini to generate concise and informative summaries. Furthermore, the framework incorporates embedding models such as nomic-embed-text and Gemini embedding model text embedding 001 to create semantic representations of the retrieved data and utilize FAISS for efficient indexing and retrieval. The RAGAS framework was used to evaluate the performance of different LLMs, with Llama 3.1 demonstrating the highest accuracy at 86.67%. This framework has significant implications for various applications, including personalized education, where it can be used to provide students with tailored learning materials and personalized tutoring experiences. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Prediction of Corrosion Inhibition Efficiency of Expired Pharmaceuticals: Model Development and Application

引用

Journal of Bio- and Tribo-Corrosion 2025年第1期11卷 1-12页

作者： Putra, Dzaki Asari Surya Ardyansyah, Nibras Bahy Putranto, Nicholaus Verdhy Trisnapradika, Gustina Alfa Akrom, Muhamad Rustad, Supriadi Dipojono, Hermawan Kresno Maezono, Ryo Faculty of Computer Science Study Program in Informatics Engineering Universitas Dian Nuswantoro Semarang50131 Indonesia Research Center for Materials Informatics Faculty of Computer Science Universitas Dian Nuswantoro Semarang50131 Indonesia Quantum and Nano Technologies Research Group Faculty of Industrial Technology Institut Teknologi Bandung Bandung40132 Indonesia School of Information Science Japan Advanced Institute of Science and Technology Ishikawa923-1292 Japan

Corrosion poses a significant challenge in industries due to material degradation and high maintenance costs, making effective inhibitors essential. Recent studies suggest expired pharmaceuticals as alternative corrosion inhibitors, but identifying the most efficient compounds can be time-consuming. This study applies machine learning models, particularly Gradient Boosting Regressor (GBR), to predict corrosion inhibition efficiency (CIE). The developed model is integrated into a web-based application, enabling real-time, accurate CIE predictions. Results show GBR as the more precise model for predicting CIE, with low error rates. The streamlit-based web application offers a user-friendly platform, facilitating quick identification of suitable inhibitors. It is flexible, supporting analysis beyond corrosion inhibitors, and significantly enhances the efficiency of the evaluation process. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Elite-guided equilibrium optimiser based on information enhancement:Algorithm and mobile edge computing applications

引用

CAAI Transactions on Intelligence technology 2024年第5期9卷 1126-1171页

作者： Zong-Shan Wang Shi-Jin Li Hong-Wei Ding Gaurav Dhiman Peng Hou Ai-Shan Li Peng Hu Zhi-Jun Yang Jie Wang School of Information Science and Engineering Yunnan UniversityKunmingChina Shenzhen Institute for Advanced Study University of Electronic Science and Technology of ChinaShenzhenChina Academic Affairs Office Yunnan University of Finance and EconomicsKunmingChina Faculty of Management and Economics Kunming University of TechnologyKunmingChina Department of Electrical and Computer Engineering Lebanese American UniversityBeirutLebanon Department of Computer Science and Engineering University Centre for Research and DevelopmentChandigarh UniversityChennaiIndia Department of Computer Science and Engineering Graphic Era Deemed to Be UniversityDehradunIndia School of Computer Science Fudan UniversityShanghaiChina Rackham Graduate School University of MichiganAnn ArborMIUSA Research and Development Department Youbei Technology Co.LTDKunmingChina School of Mechanical and Power Engineering Zhengzhou UniversityZhengzhouChina

The Equilibrium Optimiser(EO)has been demonstrated to be one of the metaheuristic algorithms that can effectively solve global optimisation *** the paradox between exploration and exploitation operations while enhancing the ability to jump out of the local optimum are two key points to be addressed in EO *** alleviate these limitations,an EO variant named adaptive elite-guided Equilibrium Optimiser(AEEO)is ***,the adaptive elite-guided search mechanism enhances the balance between exploration and *** modified mutualism phase reinforces the information interaction among particles and local optima *** cooperation of these two mechanisms boosts the overall performance of the basic *** AEEO is subjected to competitive experiments with state-of-the-art algorithms and modified algorithms on 23 classical benchmark functions and IEE CEC 2017 function test *** results demonstrate that AEEO outperforms several well-performing EO variants,DE variants,PSO variants,SSA variants,and GWO variants in terms of convergence speed and *** addition,the AEEO algorithm is used for the edge server(ES)placement problem in mobile edge computing(MEC)*** experimental results show that the author’s approach outperforms the representative approaches compared in terms of access latency and deployment cost.

关键词： ANT COLONY optimization CLOUD COMPUTING GENETIC ALGORITHMS SWARM intelligence

来源：评论

学校读者我要写书评

暂无评论

Analysis of Sentimental on Twitter using Content Aware Support Vector Machines

Analysis of Sentimental on Twitter using Content Aware Suppo...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2023

作者： Manikandan, B. Krishna Kumar, T. Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai India MNR Engineering and Technology Sangareddy Department of Computer Science and Engineering Hyderabad India Bharath Institute of Higher Education and Research Department of Computer Science and Engineering Chennai 73 India

ISBN: (纸本)9798350319200

In the era of the Internet's rapid expansion, social networking platforms have emerged as a crucial medium for individuals to convey their emotions and opinions to a global audience. Text, images, audio, and video are all ways for people to express themselves. Twitter, a popular social network, allows users to tweet about their daily feelings and opinions. These platforms generate vast amounts of unstructured data continuously, necessitating prompt processing to gain insights into human psychology. This processing is accomplished through sentiment analysis, a technique that assesses the emotional polarity within texts, determining whether the author holds a -Ve, +Ve, or neutral stance toward a subject, service, individual, or place. This article investigates the use of four well-known data mining classifiers, specifically the decision tree, K-nearest neighbor, naive Bayes, and support vector machine, to analyze tweet sentiments. Our findings reveal that the support vector machine consistently yields superior results compared to other algorithms, demonstrating an improvement of 4.01% in accuracy for two-class datasets and 8.05% for three-class datasets. © 2023 IEEE.

关键词： Decision Tree Sentimental Support Vector Machine Twitter Data Analysis

来源：评论

学校读者我要写书评

暂无评论

MASSFormer: Mobility-Aware Spectrum Sensing using Transformer-Driven Tiered Structure

引用

IEEE Communications Letters 2025年第6期29卷 1220-1224页

作者： Janu, Dimpal Mushtaq, Faisel Mandia, Sandeep Singh, Kuldeep Kumar, Sandeep Malaviya National Institute of Technology Electronics and Communication Engineering department Jaipur302017 India SRM University AP Electronics and Communication Engineering department Amaravati522502 India Malaviya National Institute of Technology Department of Computer Science and Engineering Jaipur302017 India Thapar Institute of Engineering and Technology Patiala147004 India Bharat Electronics Ltd Central Research Lab Ghaziabad201010 India

In this paper, we develop a novel mobility-aware transformer-driven tiered structure (MASSFormer) based co-operative spectrum sensing method that effectively models the spatio-temporal dynamics of user movements. Unlike existing methods, our method considers a dynamic scenario involving mobile primary users (PUs) and secondary users (SUs) and addresses the complexities introduced by user mobility. The transformer architecture utilizes an attention mechanism, allowing the proposed method to model the temporal dynamics of user mobility by effectively capturing long-range dependencies. The proposed method first computes tokens from the sequence of covariance matrices (CMs) for each SU. It processes them in parallel using the SU-transformer to learn the spatio-temporal features at SU-level. Subsequently, the collaborative transformer learns the group-level PU state from all SU-level feature representations. The main goal of predicting the PU states at each SU-level and group-level is to improve detection performance even more. The proposed method is tested under imperfect reporting channel scenarios to show robustness. The efficacy of our method is validated with simulation results that demonstrate its higher performance compared to existing methods in terms of detection probability Pd, sensing error, and classification accuracy (CA). © 1997-2012 IEEE.

关键词： Fading channels

来源：评论

学校读者我要写书评

暂无评论

IoT Based Monitoring System for Health During Menstruation 4

IoT Based Monitoring System for Health During Menstruation

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Khadse, Chinmaya Hajare, Shital Sheikh, Nishad Dahule, Roshni Kate, Priya Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Artificial Intelligence and Machine Learning Sawangi Maharashtra Wardha442001 India Datta Meghe Institute of Higher Education and Research Faculty of Engineering and Technology Department of Computer Science and Engineering Sawani Maharashtra Wardha442001 India

ISBN: (纸本)9798331523923

The integration of IoT and ML brought forth new prospective solutions in menstrual health management, pertaining to continuous monitoring of physiological signals and personalization of insights for women. This article discusses the usage of IoT, smartphones, and cloud-based systems for tracking vital signs, temperature, pulse rate, and flow of menstruation that will enable pro-active management of the cycle. The use of ML algorithms, including supervised models-like Random Forest and Logistic Regression-and complex techniques like RNNs and LSTM networks-offers added advantages for predicting menstrual cycles and ovulation. These technologies offer personalized health recommendations, early diagnosis of menstrual disorders, and help in communicating with healthcare providers in a very short span of time. While offering huge potential to improve women's health, concerns around data privacy, ethical considerations, and equitable access to these digital health solutions are highlighted. The existing systems showed improvements yet they encountered problems because of insufficient data diversity and health system integration as well as insufficient personalization and imprecise cycle predictions. Data privacy issues and security threats that stem from ML models along with constant bias concerns prevent broad acceptance of ML systems in general use. This research study analyzes IoT and ML applications in menstrual health today and introduces their advantages as well as the barriers that require resolution before mass acceptance can occur. The proposal introduces an approach to create menstrual tracking software through a combination of rule-based systems with ML algorithms that generates precise forecasts alongside tailored information for women who have PCOS or PCOD. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Unpaired remote sensing image super-resolution with content-preserving weak supervision neural network

引用

science China(Information sciences) 2023年第1期66卷 324-325页

作者： Jie WU Runmin CONG Leyuan FANG Chunle GUO Bob ZHANG Pedram GHAMISI College of Electrical and Information Engineering Hunan University Institute of Information Science Beijing Jiaotong University College of Computer Science Nankai University Department of Computer and Information Science University of Macau Helmholtz-Zentrum Dresden-Rossendorf Helmholtz Institute Freiberg for Resource Technology Institute of Advanced Research in Artificial Intelligence (IARAI)

Dear editor,Image super-resolution(SR) uses image processing methods to increase the resolution of the image without increasing any hardware cost. Remote sensing images with high spatial resolution contain rich imagery information, which can be utilized for object detection, building segmentation, building extraction, change detection, and so on.

关键词：

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：