检索结果-内蒙古大学图书馆

Age-of-Information-Aware Federated Learning

Journal of computer Science & technology 2024年第3期39卷 637-653页

作者：徐殷肖明军吴晨吴杰周津锐孙贺 Student Member CCF 1.School of Computer Science and TechnologyUniversity of Science and Technology of ChinaHefei 230026China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhou 215123China School of Data Science University of Science and Technology of ChinaHefei 230026China Department of Computer and Information Sciences Temple UniversityPhiladelphiaPA 19122U.S.A. CCF IEEE

Federated learning(FL)is an emerging privacy-preserving distributed computing paradigm,enabling numerous clients to collaboratively train machine learning models without the necessity of transmitting clients’private datasets to the central *** most existing research where the local datasets of clients are assumed to be unchanged over time throughout the whole FL process,our study addresses such scenarios in this paper where clients’datasets need to be updated periodically,and the server can incentivize clients to employ as fresh as possible datasets for local model *** primary objective is to design a client selection strategy to minimize the loss of the global model for FL loss within a constrained *** this end,we introduce the concept of“Age of Information”(AoI)to quantitatively assess the freshness of local datasets and conduct a theoretical analysis of the convergence bound in our AoI-aware FL *** on the convergence bound,we further formulate our problem as a restless multi-armed bandit(RMAB)***,we relax the RMAB problem and apply the Lagrangian Dual approach to decouple it into multiple ***,we propose a Whittle’s Index Based Client Selection(WICS)algorithm to determine the set of selected *** addition,comprehensive simulations substantiate that the proposed algorithm can effectively reduce training loss and enhance the learning accuracy compared with some state-of-the-art methods.

关键词： federated learning Age of Information restless multi-armed bandit Whittle’s index

来源：评论

学校读者我要写书评

暂无评论

Combining Remote Sensing Dataset, Machine Learning, and Explainable AI for Detailed Human Development Index Monitoring in East Java, Indonesia

Combining Remote Sensing Dataset, Machine Learning, and Expl...

引用

2024 International Conference on Information technology Research and Innovation, ICITRI 2024

作者： Aprianto, Kasiful Saputra, Irwansyah Riana, Dwiza Universitas Nusa Mandiri Master of Computer Science Student Faculty of Information Technology Jakarta Indonesia Universitas Nusa Mandiri Faculty of Information Technology Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350376210

This study integrates satellite imagery, machine learning, and explainable AI to enhance the predictive accuracy and interpretability of the Human Development Index (HDI) in East Java, Indonesia. Using advanced models, particularly Random Forest Regression, the research achieved an R-squared value of 0.8709, explaining approximately 87% of the variance in HDI. Feature importance analysis identified Night Time Light (NTL) as the most influential predictor with an importance score of 0.4910, indicating a strong correlation with urban development and economic activity. Other significant predictors included the Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI), reflecting the importance of environmental conditions in development metrics. SHAP (SHapley Additive exPlanations) analysis provided insights into individual feature contributions, enhancing model transparency and supporting targeted policy interventions. For instance, higher NTL was associated with increased HDI, highlighting urbanization's role in development, while pollutants like NO2 and SO2 negatively impacted HDI. This study underscores the effectiveness of integrating satellite data and machine learning in socioeconomic analyses and offers a robust framework for future HDI monitoring. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Drowsiness Detection System using Facial Landmarks and Eye Blink Analysis 5

Real-Time Drowsiness Detection System using Facial Landmarks...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Manhas, Vishal Singh Sahani, Prince Upase, Shankar Venkatrao Ashtagi, Rashmi Under Graduate Student Department Of Computer Engineering Vishwakarma Institute Of Technology Pune India Department Of Computer Engineering Vishwakarma Institute Of Technology Pune India

ISBN: (纸本)9798400709418

This paper explores the critical issue of driver drowsiness and its significant contribution to road accidents. A real-time drowsiness detection system that harnesses the power of computer vision and facial landmark recognition to enhance safety and prevent accidents in situations where drowsiness poses a significant risk, such as drowsy driving. This system combines various libraries and techniques, including Dlib for face detection and facial landmark identification and OpenCV for image processing. Its core functionality involves capturing video frames from a camera feed, locating faces within each frame, and then focusing on the eyes and eyebrows to assess the individual's level of alertness. This assessment is primarily based on the analysis of eye blinking patterns, with specific attention to the blink ratio, which serves as a key indicator. Depending on the calculated blink ratio, the system classifies the person's state into three distinct categories: "SLEEPING,""Drowsy,"or "Active."These categories are conveyed to the user through real-time text overlays on the video feed, each represented by a specific color. The value of this project lies in its potential to prevent accidents caused by drowsiness, a major factor contributing to road accidents worldwide. By continuously monitoring and evaluating the individual's state of alertness, this system provides immediate feedback and intervention when drowsiness is detected, thus contributing to safer driving and potentially extending its applicability to other domains where alertness is critical, such as operating heavy machinery or monitoring individuals in critical work environments. Furthermore, this project offers a foundation for further development and integration with advanced technologies, potentially evolving into a comprehensive safety system with broader applications in areas where real-time alertness assessment is essential for reducing risks and enhancing overall safety. © 2023 ACM.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Algorithmic Loan Risk Prediction Method Based on PSO-GWO-Catboost 4

Algorithmic Loan Risk Prediction Method Based on PSO-GWO-Cat...

引用

4th International Conference on Machine Learning and computer Application, ICMLCA 2023

作者： Chen, Suihai How, Bong Chih Chiu, Po Chan Faculty of Computer Science and Information Technology's Student Unimas Borneo Sarawak94300 Malaysia

ISBN: (纸本)9798400709449

Loan risk analysis is a common challenge faced by global financial institutions. Under the background of big data, it is of practical significance to prevent loan risk by the machine learning algorithm. Aiming at the characteristics of unbalanced loan data and high noise, this paper proposes an improved Gray Wolf optimization strategy (PSO-GWO). PSO-GWO is used to optimize the parameters of the CatBoost model. In this method, the Gray Wolf algorithm (GWO) is further optimized by particle swarm optimization (PSO), and when combined with it, the convergence performance of the model is improved, the parameters of the model are reduced, and the model is simplified. To a certain extent, it avoids the inefficiency of the Gray Wolf algorithm, balances the ability of local search and global development, and improves the accuracy of the model. Compared with the traditional credit evaluation model, PSO-GWO-CatBoost has better accuracy and practical application value. © 2023 ACM.

关键词： Risk analysis

来源：评论

学校读者我要写书评

暂无评论

Marine Robot for Underwater Surveillance

Marine Robot for Underwater Surveillance

引用

2025 IEEE International students' Conference on Electrical, Electronics and computer Science, SCEECS 2025

作者： Vishnu Gowda, H.P. Reddy, Deepa N Gowda, Tejas B Shrikala, R. Yogitha, H.N. Bms Institute of Technology and Management Student of Department of Electronics and Communication Engineering Bengaluru560064 India Bms Institute of Technology and Management Department of Electronics and Communication Engineering Bengaluru560064 India Bms Institute of Technology and Management Student of Department of Computer Science Engineering Bengaluru560064 India

ISBN: (纸本)9798331529833

Underwater surveillance has become a crucial area of research, particularly for marine exploration and environmental monitoring, with marine robots playing a vital role. These robots, equipped with sensors and cameras, capture real-time data and images from underwater environments, reducing the need for human intervention in hazardous areas. However, a major challenge in this field is developing reliable communication networks, as underwater environments face limitations in bandwidth, range, and signal attenuation, hindering real-time data transmission. This paper presents a simple marine robot prototype based on the Raspberry Pi Model 4B, utilizing Electronic Speed Controllers (ESCs) and brushless motors for efficient movement. The robot's body is manually designed using 3D printing technology, with PETG (polyethylene terephthalate glycol) material chosen for its water resistance, durability, and buoyancy. The design ensures the robot's stability and functionality underwater, offering a cost-effective solution for marine robotics while underscoring the need for improved underwater communication technologies. © 2025 IEEE.

关键词： Marine communication

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Forecasting Depression and Anxiety in University students 1

引用

8th International Conference on Information and Communication technology for Competitive Strategies, ICTCS 2023

作者： Biswas, Tamal Bhattacharya, Diptendu Rudrapal, Dwijen Roy, Srijan National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India M Tech Student National Institute of Technology Agartala Department of Computer Science and Engineering Tripura Agartala India

ISBN: (数字)9789819702107

ISBN: (纸本)9789819702091

The timely identification of mental health issues enables experts to more effectively provide treatment and enhance the well-being of patients. Mental health pertains to an individual’s emotional, mental, and interpersonal state, influencing their thoughts, emotions, and behaviors. It remains crucial across all life phases, spanning childhood, adolescence, and adulthood. Historically, categorizing mental health problems among college students demanded significant effort and time from psychologists. This research engaged five machine learning methods to classify such issues swiftly. The effectiveness of these methods was evaluated based on different standards. The five methods included logistic regression, KNN classification, decision tree classification, random forest, and stacking. A comparison and implementation of these methods revealed that stacking yielded the highest accuracy, predicting 82.20. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： students

来源：评论

学校读者我要写书评

暂无评论

Gene Disease Classification from Biomedical Text via Ensemble Machine Learning 16

Gene Disease Classification from Biomedical Text via Ensembl...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

作者： Ghazi, Rabea F. Abd, Dhafar Hamed Informatics Institute for Postgraduate Student Baghdad Iraq University of Anbar College of Computer Science and Information Technology Ramadi Iraq

ISBN: (纸本)9798350381344

Detecting connections between genes and diseases is a vital endeavor in bioinformatics and genomics, carrying significant implications for the entire comprehension of the molecular underpinnings of various diseases. The rapid increase in the number of documents in the field of biomedicine has resulted in a significant burden and time requirement for manually curating relationships within this literature. In order to tackle this particular difficulty, the present study introduced a resilient ensemble machine-learning methodology that aimed at automating the classification of gene-disease relationships through the analysis of biomedical text. The proposed model was meant to leverage ensemble learning capabilities by integrating different base classifiers which are Decision Trees, Random Forest, AdaBoost, Bagging, CatBoost, Extra Trees and XGBoost with two feature extraction TF and TF-IDF. This ensemble architecture aimed to enhance the accuracy and dependability of gene-disease association predictions by utilizing a wide range of variables obtained from biomedical literature, including abstracts and various ensemble configurations and evaluating performance using standard metrics which are precision, recall, and F1-score, AUC, and accuracy. The study findings provided evidence supporting the efficacy of the ensemble methodology in enhancing both accuracy and resilience when compared to the performance of individual classifiers. The highest accuracy was achieved with XGBoost and TF 0.979%. © 2023 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Binary Dataset using Dragonfly Algorithm 16

Feature Selection for Binary Dataset using Dragonfly Algorit...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

作者： Raouf, Zaid Tariq Abd, Dhafar Hamed Informatics Institute for Postgraduate Student Baghdad Iraq University of Anbar College of Computer Science and Information Technology Ramadi Iraq

ISBN: (纸本)9798350381344

In contemporary times, the proliferation of data dimensionality has introduced many challenges within the realm of machine learning. Consequently, identifying and selecting pertinent features have assumed paramount importance. Consequently, a diverse array of techniques for feature selection has been proffered. Among them, Metaheuristic techniques are particularly significant within this milieu, with a focus on the dragonfly algorithm garnering notable attention. Metaheuristic algorithms are rooted in the emulation of swarm intelligence, drawing inspiration from the collective behaviors exhibited by insects. This scholarly inquiry aims to enhance the efficacy of classification outcomes by leveraging the dragonfly algorithm to select the most salient features. In this paper, the proposed approach is rigorously evaluated across three distinct datasets, namely, 'Ansur,' 'Predict 5-Year Career Longevity for NBA Rookies,' and 'Chronic Kidney Disease,' all of which were procured from the Kaggle repository. The study used four machine learning classifiers, namely, XGBoosting, K-Nearest Neighbors (KNN), Decision Tree, and Gaussian Naive Bayes (Gaussian-NB), for classification and evaluation. The empirical findings unveiled a notable enhancement in classification performance. Notably, the accuracy metrics exhibit substantial improvements across all classifiers. For instance, within chronic kidney disease classification, both XGBoost and Decision Tree classifiers yielded a remarkable accuracy rate of 100%, thereby underscoring the efficacy of the proposed dragonfly algorithm-based feature selection technique in augmenting the predictive capabilities of machine learning models. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Applying Dragonfly Algorithm for Feature Selection Optimizing in Machine Learning Classification 16

Applying Dragonfly Algorithm for Feature Selection Optimizin...

引用

16th International Conference on Developments in eSystems Engineering, DeSE 2023

作者： Raouf, Zaid Tariq Abd, Dhafar Hamed Informatics Institute for Postgraduate Student Baghdad Iraq University of Anbar College of Computer Science and Information Technology Ramadi Iraq

ISBN: (纸本)9798350381344

Feature selection plays a crucial role in the domain of machine learning, serving as an essential mission. Eliminating redundant and irrelevant attributes can enhance the learning process by increasing the learning rate, improving accuracy, and enhancing classifier performance. The primary objectives of feature selection encompass the creation of models that are more understandable and user-friendly, the enhancement of data mining efficiency, and the facilitation of data cleaning and organization for subsequent analysis. Metaheuristic algorithms have garnered considerable attention due to their prowess in solving many optimization problems such as feature section, in this paper using Dragonfly algorithm. The effectiveness of the proposed methodologies is evaluated on three benchmark datasets obtained from the Kaggle repository: the heart disease dataset, the Vehicle-Coupon-Recommendation dataset, and the Predict Diabetes dataset. Three machine learning classifiers - namely, Light Gradient Boosting Machine (LightGBM), AdaBoost, and Bagging - are utilized in this assessment. This approach yields an impressive accuracy rate of 85.71%. In contrast, when all features are included in the training process, the accuracy drops to a lower value of 83.51%. © 2023 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

An Enhanced Stress based Hairfall Detection and Prevention using KNN and Machine Learning Techniques 7

An Enhanced Stress based Hairfall Detection and Prevention u...

引用

7th International Conference on Trends in Electronics and Informatics, ICOEI 2023

作者： Srinivasan, L. Jeevika, A. Navina, R.K. Priyadharshini, S. Dr.N.G.P Institute of Technology Cse Computer Science and Engineering Coimbatore India Dr.N.G.P Institute of Technology STUDENT/CSE Computer Science and Engineering Coimbatore India

ISBN: (纸本)9798350397284

Numerous factors might affect a person's stress level, which results in hair loss. Due to variables such as increased employee dominance, job pressure, and work overload, among others employees in IT sectors are more prone to experience stress. Depression, anxiety, somatization, and attention deficit disorder are just a few of the mental health issues that stress can lead to, and even mortality. As a result, it's critical to recognize human stress early so that the proper treatments may be given and tension can be reduced. Numerous studies have been conducted on stress prediction. An extension of the skin, hair is an essentialcomponent of a person's facial beauty. The outcomes of some learning algorithms, like KNN, are superior. Other intelligent methods such as ML algorithms can be used to diagnose the diseases. © 2023 IEEE.

关键词： Machine 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：