检索结果-内蒙古大学图书馆

Review on application progress of federated learning model and security hazard protection

Digital Communications and Networks 2023年第1期9卷 146-158页

作者： Aimin Yang Zezhong Ma Chunying Zhang Yang Han Zhibin Hu Wei Zhang Xiangdong Huang Yafeng Wu Hebei Engineering Research Center for the Intelligentization of Iron Ore Optimization and Ironmaking Raw Materials Preparation Processes North China University of Science and TechnologyTangshanHebeiChina Hebei Key Laboratory of Data Science and Application North China University of Science and TechnologyTangshanHebeiChina The Key Laboratory of Engineering Computing in Tangshan City North China University of Science and TechnologyTangshanHebeiChina Tangshan Intelligent Industry and Image Processing Technology Innovation Center North China University of Science and TechnologyTangshanHebeiChina College of Science North China University of Science and TechnologyTangshanHebeiChina College of Artificial Intelligence North China University of Science and TechnologyTangshanHebeiChina

Federated learning is a new type of distributed learning framework that allows multiple participants to share training results without revealing their data *** data privacy becomes more important,it becomes difficult to collect data from multiple data owners to make machine learning predictions due to the lack of data *** is forced to be stored independently between companies,creating“data silos”.With the goal of safeguarding data privacy and security,the federated learning framework greatly expands the amount of training data,effectively improving the shortcomings of traditional machine learning and deep learning,and bringing AI algorithms closer to our *** the context of the current international data security issues,federated learning is developing rapidly and has gradually moved from the theoretical to the applied *** paper first introduces the federated learning framework,analyzes its advantages,reviews the results of federated learning applications in industries such as communication and healthcare,then analyzes the pitfalls of federated learning and discusses the security issues that should be considered in applications,and finally looks into the future of federated learning and the application layer.

关键词： data silos machine learning Federated learning Privacy protection learning framework

来源：评论

学校读者我要写书评

暂无评论

4th international conference on machine learning, Optimization, and data science, LOD 2018

4th International Conference on Machine Learning, Optimizati...

引用

4th international conference on machine learning, Optimization, and data science, LOD 2018

ISBN: (纸本)9783030137083

The proceedings contain 46 papers. The special focus in this conference is on machine learning, Optimization, and data science. The topics include: Adaptive dimensionality reduction in multiobjective optimization with multiextremal criteria;REFINE: Representation learning from diffusion events;augmented design-space exploration by nonlinear dimensionality reduction methods;classification and survival prediction in diffuse large B-cell lymphoma by gene expression profiling;learning consistent tree-augmented dynamic bayesian networks;designing ships using constrained multi-objective efficient global optimization;a new approach to measuring distances in dense graphs;ant colony optimization for markov blanket-based feature selection. Application for precision medicine;Average performance analysis of the stochastic gradient method for online PCA;simple learning with a teacher via biased regularized least squares;Improving traditional dual ascent algorithm for the uncapacitated multiple allocation hub location problem: A RAMP approach;supervised learning approach for surface-mount device production;crawling in Rogue’s dungeons with (partitioned) A3C;decision of neural networks hyperparameters with a population-based algorithm;strong duality of the kantorovich-rubinstein mass transshipment problem in metric spaces;evolutionary construction of convolutional neural networks;improving clinical subjects clustering by learning and optimizing feature weights;a framework to automatically extract funding information from text;Speeding up budgeted stochastic gradient descent SVM training with precomputed golden section search;an unsupervised learning classifier with competitive error performance;feature based multivariate data imputation;A GRASP/VND heuristic for the max cut-clique problem;a modelica-based simulation method for black-box optimal control problems with level-set dynamic programming;a clonal selection algorithm for multiobjective energy reduction multi-depot vehicle r

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Third Workshop on applied machine learning Management 24

The Third Workshop on Applied Machine Learning Management

引用

30th ACM SIGKDD conference on Knowledge Discovery and data Mining

作者： Goldenberg, Dmitri Lador, Shir Meir Sokolova, Elena Cheong, Lin Lee Sukhwani, Mohak Potdar, Saloni Booking Com Tel Aviv Israel Intuit Mountain View CA USA Amazon London England Amazon Santa Clara CA USA Myntra Bangalore Karnataka India Apple Siri & Informat Intelligence Team Seattle WA USA

ISBN: (纸本)9798400704901

machine learning applications are rapidly adopted by industry leaders in any field. The growth of investment in AI-driven solutions,including the emerging field of General AI (GenAI), has created new challenges in managing data science and ML resources, people and projects as a whole. The discipline of managing applied machine learning teams, requires a healthy mix between agile product development tool-set and a long term research oriented mindset. The abilities of investing in deep research while at the same time connecting the outcomes to significant business results create a large knowledge based on management methods and best practices in the field. The Third KDD Workshop on applied machine learning Management brings together applied research managers from various fields to share methodologies and case-studies on management of ML teams, products, and projects, achieving business impact with advanced AI-methods.

关键词： machine learning Management data science Management ML Product development GenAI and compliance

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of machine learning Algorithms on Imbalanced datasets Using SMOTE Technique 5th

Performance Analysis of Machine Learning Algorithms on Imbal...

引用

5th international conference on data science, machine learning and Applications

作者： Kumar, Bala Santhosh Yadav, Pasupula Praveen Prasad, P. Penchala G Pulla Reddy Engn Coll Comp Sci & Engn Dept Kurnool India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

This research paper aims to investigate the impact of using the Synthetic Minority Over-Sampling Technique (SMOTE) on the performance of several machine learning algorithms on imbalanced dataset. Imbalanced datasets are a common problem in many real-world applications, where one class is much more prevalent than the other class. This imbalance can lead to biased models, where the majority class dominates the model's predictions, and the minority class is often misclassified. To address this problem, we applied the SMOTE algorithm to generate synthetic data for the minority class. We evaluated the performance of several popular machine learning algorithms including logistic regression, decision trees, ensemble learning, support vector machines, Neural networks and Auto ML approach on both the original imbalanced dataset and the SMOTE-augmented dataset. The experimental results demonstrate that using SMOTE significantly improves the accuracy of the machine learning algorithms on imbalanced datasets. In conclusion, our research highlights the importance of considering the impact of imbalanced datasets on machine learning algorithm's performance and demonstrates the effectiveness of SMOTE in addressing this issue. Our results can be useful to practitioners working on imbalanced datasets to choose an appropriate machine-learning algorithm and to decide whether to use SMOTE to improve their model's performance.

关键词： machine learning SMOTE Accuracy

来源：评论

学校读者我要写书评

暂无评论

A Tool for the Implementation of an Educational data Mining Model applied to Universities

A Tool for the Implementation of an Educational Data Mining ...

引用

international conference on Communication and applied Technologies (ICOMTA)

作者： Novillo-Rangone, G. A. Montejano, G. A. Garis, A. G. Molina, W. R. Natl Univ Villa Mercedes Villa Mercedes Argentina Natl Univ San Luis San Luis Argentina

ISBN: (纸本)9789811963469;9789811963476

This work proposes a tool for the implementation of an educational data mining model that applies automated machine learning and machine learning interpretability. Starting from the selection between different types of educational problems, the tool: allows semi-automatically building the data set, obtaining an optimized machine learning model using automated machine learning and enabling the explanation of results with machine learning interpretability methods. The proposal allows university institutions to draw conclusions on complex problems, requiring a minimum number of experts in data science and providing a framework for both end users and legal entities to inform themselves about results.

关键词： AutoML data science Educational data mining Educational data mining tool IML

来源：评论

学校读者我要写书评

暂无评论

Forecasting the Emergence of a Dominant Design by Classifying Product and Process Patents Using machine learning and Text Mining

引用

international JOURNAL OF ADVANCED COMPUTER science AND APPLICATIONS 2025年第1期16卷 42-48页

作者： Masuda, Koji Hayashi, Yoshinori Haruyama, Shigeyuki Yamaguchi Univ Grad Sch Sci & Technol Innovat Ube Japan Yamaguchi Univ Grad Sch Innovat & Technol Management Ube Japan

Forecasting the emergence of a dominant design in advance is important because the emergence of the dominant design can provide useful information about the external environment for the product launch. Although the emergence of the dominant design can only be determined as a result of the introduction of the product into the market, it may be possible to predict the emergence of the dominant design in advance by applying a solution based on patent analysis. In the newly proposed technique of separating patents, we can capture changes in the state of technological innovation and analyze the emergence of the dominant design, but there is a problem that it requires processing of large amounts of patent data, and that the processing involves subjective judgments by experts. This study focuses on analyzing technological innovation trends using an approach that separates product patents from process patents, investigates whether this approach can be applied to machine learning, and aims to develop a learning model that automatically classifies patents. We applied text mining to patent information to create structured data sets and compared nine different machine learning classification algorithms with and without dimensionality reduction. The approach was effectively applied to machine learning, and the Random Forest, AdaBoost and Support Vector machine models achieved high classification performance of over 95%. By developing these learning models, it is possible to objectively forecast the emergence of a dominant design with high accuracy.

关键词： Dominant design patent analysis technological innovation machine learning text mining classification classification

来源：评论

学校读者我要写书评

暂无评论

Deep learning based Cloud Microphysics Parameterization Scheme for Numerical Weather Prediction with 1DD-CNN 7

Deep Learning based Cloud Microphysics Parameterization Sche...

引用

7th international conference on Artificial Intelligence and Big data (ICAIBD)

作者： Shu, Ting Zhou, Xiyuan Xie, Yuanfu Zhao, Huan Chen, Xunlai Wang, Rui Shenzhen Inst Meteorol Innovat Shenzhen Peoples R China Chinese Univ Hong Kong Shenzhen Peoples R China Hong Kong Polytech Univ Hong Kong Peoples R China Shenzhen Meteorol Bur Shenzhen Key Lab Severe Weather South China Shenzhen Peoples R China

ISBN: (纸本)9798350385113;9798350385106

machine learning methods, represented by deep learning, are rapidly changing and enhancing the process and results of the Numerical Weather Prediction (NWP) model. To better explore the application potential of the machine learning method in the Microphysical Parameterization Schemes (MPS) for NWP model, this study introduces a deep learning based cloud microphysical processes scheme. The scheme includes two steps: data processing and machine learning. The data process step in our scheme is to prepare data for the machine learning method, where the data is extracted and refined from NWP outputs. Subsequent to this process, a one-dimensional dense convolutional neural network (1DD-CNN) is applied to rigorously analyze the data and boost the predictive precision and computational speed of cloud microphysical processes. Empirical results validate the scheme's efficacy in advancing meteorological predictive capabilities.

关键词： numerical weather prediction deep learning microphysical parameterization scheme convolutional neural network precipitation prediction

来源：评论

学校读者我要写书评

暂无评论

5th international conference on applied machine learning and data Analytics, AMLDA 2022

5th International Conference on Applied Machine Learning and...

引用

5th international conference on applied machine learning and data Analytics, AMLDA 2022

ISBN: (纸本)9783031342219

The proceedings contain 20 papers. The special focus in this conference is on applied machine learning and data Analytics. The topics include: RU-Net: A Novel Approach for Gastro-Intestinal Tract Image Segmentation Using Convolutional Neural Network;a Credit Card Fraud Detection Model Using machine learning Methods with a Hybrid of Undersampling and Oversampling for Handling Imbalanced datasets for High Scores;Implementation of YOLOv7 for Pest Detection;online Grocery Shopping: - Key Factors to Understand Shopping Behavior from data Analytics Perspective;a Novel Approach: Semantic Web Enabled Subject Searching for Union Catalogue;how People in South America is Facing Monkeypox Outbreak?;multilevel Classification of Satellite Images Using Pretrained AlexNet Architecture;handwriting Recognition for Predicting Gender and Handedness Using Deep learning;retrieval of Weighted Lexicons Based on Supervised learning Method;univariate Feature Fitness Measures for Classification Problems: An Empirical Assessment;performance Evaluation of Smart Flower Optimization Algorithm Over Industrial Non-convex Constrained Optimization Problems;securing Advanced Metering Infrastructure Using Blockchain for Effective Energy Trading;keratoconus Classification Using Feature Selection and machine learning Approach;Semantic Segmentation of the Lung to Examine the Effect of COVID-19 Using UNET Model;SMDKGG: A Socially Aware Metadata Driven Knowledge Graph Generation for Disaster Tweets;Brain MRI Image Classification Using Deep learning;a Real-Time Face Recognition Attendance Using machine learning;towards Abalone Differentiation Through machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EdDSA Shield: Fortifying machine learning Against data Poisoning Threats in Continual learning 5th

EdDSA Shield: Fortifying Machine Learning Against Data Poiso...

引用

5th international conference on data science, machine learning and Applications

作者： Nageswari, Akula Sanjeevulu, Vasundra Jawaharlal Nehru Technol Univ Ananthapur Ananthapuramu India JNTUA Coll Engn Ananthapuramu India

ISBN: (纸本)9789819780334;9789819780310;9789819780303

Continual learning in machine learning systems requires models to adapt and evolve based on new data and experiences. However, this dynamic nature also introduces a vulnerability to data poisoning attacks, wheremaliciously crafted input can lead to misleading model updates. In this research, we propose a novel approach utilizing theEdDSAencryption system to safeguard the integrity of data streams in continual learning scenarios. By leveraging EdDSA, we establish a robust defense against data poisoning attempts, maintaining the model's trustworthiness and performance over time. Through extensive experimentation on diverse datasets and continual learning scenarios, we demonstrate the efficacy of our proposed approach. The results indicate a significant reduction in susceptibility to data poisoning attacks, even in the presence of sophisticated adversaries.

关键词： Continual learning machine learning EdDSA data poisoning Defense

来源：评论

学校读者我要写书评

暂无评论

machine learning for power transformer SFRA based fault detection

引用

international JOURNAL OF ELECTRICAL POWER & ENERGY SYSTEMS 2024年 156卷

作者： Bjelic, Milos Brkovic, Bogdan Zarkovic, Mileta Miljkovic, Tatjana Univ Belgrade Sch Elect Engn Bulevar Kralja Aleksandra 73 Belgrade 11000 Serbia

This paper presents machine learning methods for health assessment of power transformer based on sweep frequency response analysis. The paper presents an overview of monitoring and diagnostics based on statistical Sweep Frequency Response Analysis (SFRA) based indicators that are used to evaluate the state of the power transformer. Experimental data obtained from power transformers with internal short-circuit faults is used as a database for applying machine learning. machine learning is implemented to achieve more precise asset management and condition-based maintenance. Unsupervised machine learning was applied through the k-means cluster method for classifying and dividing the examined power transformer state into groups with similar state and probability of failure. Artificial neural network (ANN) and Adaptive Neuro Fuzzy Inference System (ANFIS) as part of supervised machine learning are created in order to detect fault severity in tested power transformers of different lifetime. The presented machine learning methods can be used to improve health assessment of power transformers.

关键词： Power transformer machine learning SFRA ANN ANFIS

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：