检索结果-内蒙古大学图书馆

data augmentation for fault diagnosis of oil-immersed power transformer

ENERGY REPORTS 2023年 9卷 1211-1219页

作者： Li, Ke Li, Jian Huang, Qi Chen, Yuhui Univ Elect Sci & Technol China Sch Mech & Elect Engn Sichuan Prov Key Lab Power Syst Wide Area Measurem Chengdu 611731 Sichuan Peoples R China Chengdu Univ Technol Coll Nucl Technol & Automation Engn Chengdu 610059 Sichuan Peoples R China

110 kV oil immersed transformer is a key part of the power transmission and transformation system, which determines the power quality and transmission efficiency. Its fault diagnosis can greatly reduce the maintenance cost and improve the economy. At present, the methods of transformer fault diagnosis have a strong dependence on the original data, and the size of the original data directly affects the effect of fault diagnosis. In order to change this situation and achieve higher accuracy of transformer fault diagnosis, this paper firstly uses the Conditional Variational Automatic Encoder (CVAE) composed of full connection layers to expand the original samples under each fault category. After data augmentation, the convolutional neural network (CNN) with strong feature extraction ability is selected as the classifier. Finally, the CVAE-CNN model is validated using public dataset and the result is compared to other machine learning algorithms. (c) 2023 The Authors. Published by Elsevier Ltd. This is an open access article under the CCBY license (http://***/licenses/by/4.0/).

关键词： Fault diagnosis Convolution neural network Conditional variational auto-encoder data augmentation

来源：评论

学校读者我要写书评

暂无评论

Distracted Driving Behavior Detection Based on CNN And Multi-Model Fusion 3

Distracted Driving Behavior Detection Based on CNN And Multi...

引用

3rd international conference on machine learning and Computer Application, ICMLCA 2022

作者： Song, Liye Cui, Hao Zhao, Xiaoxuan Sun, Mengyu Faculty of Electrical and Control Engineering Liaoning Technical University Huludao China

ISBN: (纸本)9781510664814

In view of the low monitoring accuracy of drivers' dangerous behaviors, tired driving and distracted driving in traffic safety, and the inability to accurately and timely give early warning, in order to make-up for the shortcomings of existing detection methods and improve the accuracy of identification, in this paper, a novel distracted driving behavior detection method (CF-Net) based on CNN and multi-model fusion is proposed for intelligent cockpit environment. Firstly, a distracted driving detection model was built through the classification network, and the influences of different parameter values and classification networks on the model were analyzed on the open source data set of distracted driving. The XGBoost learning tool is added to the Stacking training mode to optimize the model. By comparing various models, the multi-model fusion network (CF-Net) distraction detection model is further applied to the driving environment, and the model's overall generalization ability and effectiveness are verified. The experimental results show that the detection performance based on a multi-model fusion network (CF-Net) is better, the test accuracy reaches 93.45%, the verification loss is reduced to the minimum, for the current intelligent cockpit environment, the driver distraction detection has a significant advantage. © 2023 SPIE.

关键词： learning systems

来源：评论

学校读者我要写书评

暂无评论

1st EAI international conference on Intelligent Systems and machine learning, ICISML 2022

1st EAI International Conference on Intelligent Systems and ...

引用

1st EAI international conference on Intelligent Systems and machine learning, ICISML 2022

ISBN: (纸本)9783031350771

The proceedings contain 75 papers. The special focus in this conference is on Intelligent Systems and machine learning. The topics include: Mining Ancient Medicine Texts Towards an Ontology of Remedies – A Semi-automatic Approach;a Novel Oversampling Technique for Imbalanced Credit Scoring datasets;a Blockchain Enabled Medical Tourism Ecosystem;Measuring the Impact of Oil Revenues on Government Debt in Selected Countries by Using ARDL Model;diagnosis of Plant Diseases by Image Processing Model for Sustainable Solutions;face Mask Detection: An Application of Artificial Intelligence;a Critical Review of Faults in Cloud Computing: Types, Detection, and Mitigation Schemes;video Content Analysis Using Deep learning Methods;prediction of Cochlear Disorders Using Face Tilt Estimation and Audiology data;F2PMSMD: Design of a Fusion Model to Identify Fake Profiles from Multimodal Social Media datasets;quantum data Management and Quantum machine learning for data Management: State-of-the-Art and Open Challenges;multivariate Analysis and Comparison of machine learning Algorithms: A Case Study of Cereals of America;competitive Programming Vestige Using machine learning;machine learning Techniques for Aspect Analysis of Employee Attrition;AI-Enabled Automation Solution for Utilization Management in Healthcare Insurance;Real-Time Identification of Medical Equipment Using Deep CNN and Computer Vision;design of a Intelligent Crutch Tool for Elders;an Approach to New Technical Solutions in Resource Allocation Based on Artificial Intelligence;gesture Controlled Power Window Using Deep learning;novel Deep learning Techniques to Design the Model and Predict Facial Expression, Gender, and Age Recognition;a Novel Model to Predict the Whack of Pandemics on the international Rankings of Academia.

关键词：

来源：评论

学校读者我要写书评

暂无评论

The Advance of Reinforcement learning and Deep Reinforcement learning

The Advance of Reinforcement Learning and Deep Reinforcement...

引用

IEEE international conference on Electrical engineering, Big data and Algorithms (EEBDA)

作者： Lyu, Le Shen, Yang Zhang, Sicheng Guangdong Shunde Desheng Sch Int Guangzhou 528300 Guangdong Peoples R China Emory Univ Comp Sci 201 Dowman Dr Atlanta GA 30322 USA Univ Florida Coll Liberal Arts & Sci Gainesville FL 32611 USA

ISBN: (纸本)9781665416061

Reinforcement learning is one of the leading research fields of artificial intelligence. Unlike other machine learning methods, reinforcement learning is learning from the environment to action mappings. Thus, the chosen action could maximize the accumulated reward value from the environment and develop an optimal strategy via trial-and-error. In recent years, the achievements of deep reinforcement learning represented by AlphaGo have attracted wide attention from researchers. This paper first introduces the development of reinforcement learning, including classic reinforcement learning methods and deep reinforcement learning methods. Then, this paper discusses the advanced reinforcement learning work at present, including distributed deep reinforcement learning algorithms, deep reinforcement learning methods based on fuzzy theory, Large-Scale Study of Curiosity-Driven learning, and so on. Finally, this essay discusses the challenges faced by reinforcement learning.

关键词： Reinforcement learning Deep learning Qlearning Distributed System Neural Network

来源：评论

学校读者我要写书评

暂无评论

machine learning Methods for Phenotype Prediction from High-Dimensional, Low Population Aquaculture data

Machine Learning Methods for Phenotype Prediction from High-...

引用

18th international Joint conference on Biomedical engineering Systems and Technologies, BIOSTEC 2025

作者： Faldani, Giovanni Rossignolo, Enrico Signor, Eleonora Longo, Alessio Faggion, Sara Bargelloni, Luca Comin, Matteo Pizzi, Cinzia Department of Information Engineering University of Padova Padova35131 Italy Department of Comparative Biomedicine and Food Science University of Padova PD Legnaro35020 Italy

Recent research has increasingly focused on classification rules within the big data framework, yet many bioin formatics applications still address prediction problems that involve small-sample, high-dimensional data. In phenotype prediction, especially with the rise of large-scale genomic data, a central challenge arises from han dling high-dimensional datasets where the number of genetic features (such as SNPs) far exceeds the sample size. A significant example of such high-dimensional, low-sample datasets is found in aquaculture, a rapidly growing sector within global food production and a crucial source of high-quality protein. This study uses data from an experiment performed on European seabass as a test case, focusing on predicting resistance to Viral Nervous Necrosis (VNN) as a specific phenotype of interest. We explore a range of machine learning tech niques to address the complexities of high-dimensional data, from established methods like gradient boosting, SVM, and deep learning to newer approaches. This paper evaluates various methods for associating SNPs with phenotypic traits, benchmarking their performance on challenging aquaculture genomic data to provide insight into the effectiveness of these techniques. © 2025 by SCITEPRESS– Science and Technology Publications, Lda.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

1st EAI international conference on Intelligent Systems and machine learning, ICISML 2022

1st EAI International Conference on Intelligent Systems and ...

引用

1st EAI international conference on Intelligent Systems and machine learning, ICISML 2022

ISBN: (纸本)9783031350801

关键词：

来源：评论

学校读者我要写书评

暂无评论

How machine learning identifies handwritten numbers

How machine learning identifies handwritten numbers

引用

2022 international conference on machine learning and Knowledge engineering, MLKE 2022

作者： Wang, Zihua Shanghai Shangde Experimental School Shanghai201315 China

ISBN: (纸本)9781665495677

The work mainly shows a way to identify handwritten numbers from machine learning method. Given the importance of changing human workforce into machinery, the machine learning is inevitable a topic to develop [1]. The popularity of the anime "Gundam", the highly rated movie "Pacific Rim: Uprising", and even the various tests of human exoskeleton armor all explain this "theorem". Therefore, the first step of human-computer interconnection - handwritten font input was born. The researchers use k-nearest neighbor letting machine learn handwritten numbers in order to give orders to the machines. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Effective Prediction of Coronary Heart Disease Using Hybrid machine learning 4th

Effective Prediction of Coronary Heart Disease Using Hybrid ...

引用

4th international conference on data, engineering, and Applications, IDEA 2022

作者： Lenka, Swathi Palo, Sangeeta Ponugupati, Venkata Satya Sri Department of Information Technology GMRIT Srikakulum India Department of CSE Lendi Institute of Engineering and Technology Vizianagaram India

ISBN: (纸本)9789819700363

Coronary in the world, coronary heart disease (CHD) is the major cause of death. The number of people diagnosed with heart disease is increasing at an alarming rate, and it is critical and significant to predict these diseases in advance. A major challenge in clinical data research is predicting cardiovascular disease. At this point in time, one person dies from heart disease per minute. As a result, early identification of CHD can aid in the reduction of these rates. When it comes to using traditional methods to anticipate data, the difficulty lies in the data’s complexity and correlations. machine learning (ML) algorithms, on the other side, showed tremendous possibilities in outperforming conventional illness diagnosis methods and assisting medical practitioners in the early identification of high disorders. Therefore, this paper demonstrates how effectively predicting coronary heart disease may be done using hybrid machine learning. The prediction concept is explained utilizing various combinations of characteristics and a number of well-known categorization techniques. The suggested study uses a Hybrid Random Forest (RF) with Linear Model, Naive Bayes (NB), and Logistic Regression (LR) classifiers are used to identify the patient’s severity and estimate the probability of coronary heart disease. The prediction approach for CHD that utilizes a combination of Random Forest with Linear model, SVM (Support Vector machine), and NB can achieve improved performance and accuracy. In this paper, the accuracy, precision, F1-score, and recall of the presented model are utilized to determine its performance. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Advanced machine learning Approaches for Improving Traffic Flow Predictions in Smart Transportation Systems 1

引用

8th international conference on Computers, Management and Mathematical Sciences, ICCM 2022

作者： Kanakaprabha, S. Ganeshkumar, G. Sureshkumar, A. Udhayakumar, T. Nisha, M. Poornaprakash, P. Department of Computer Science and Engineering Rathinam Technical Campus Anna University Coimbatore India Department of Information Technology Rathinam Technical Campus Anna University Coimbatore India Department of Computer Science and Engineering Dhanalakshmi Srinivasan College of Engineering Anna University Coimbatore India

ISBN: (数字)9783031511677

ISBN: (纸本)9783031511660

Traffic flow extrapolation is a vital aspect of intellectual transportation systems, as it facilitates the smooth and efficient management of traffic. However, traditional traffic flow prediction methods have several limitations, including a lack of accuracy and the inability to handle large and complex data. In this study, advanced machine learning techniques are suggested for enhancing the precision and efficiency of traffic flow predictions in intelligent transportation systems. We collect and preprocess a large and diverse dataset of historical traffic flow data, and use techniques such as feature engineering, model selection, model evaluation, model tuning, and model ensemble to develop a robust-based traffic flow prediction system. The system suggested in this research integrates KNN, Random Forest, and ARIMA machine learning algorithms to forecast traffic flow considering various factors including weather, road conditions, and traffic volume. The outcomes show that the projected system significantly enhances the accuracy of traffic flow predictions compared to traditional methods and can handle a wide range of traffic scenarios and conditions. This research demonstrates the potential of advanced machine learning approaches for improving traffic flow predictions in smart transportation systems. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

machine learning Algorithms on COVID-19 Prediction Using CpG Island and AT-CG Feature on Human Genomic data 1st

Machine Learning Algorithms on COVID-19 Prediction Using CpG...

引用

1st international conference on machine Intelligence and Emerging Technologies, MIET 2022

作者： Manik, Md. Motaleb Hossen Habib, Md.Ahsan Ahmed, Tanim Department of Computer Science and Engineering Khulna University of Engineering and Technology Khulna Bangladesh

ISBN: (纸本)9783031346217

A pandemic has broken out throughout the world since December 2019 and later it has been named COVID-19. The flow of normal life has collapsed due to this pandemic, especially in the economic, public health, and education sectors. The number of infected people is increasing daily. So, the identification of COVID-19 patients is a crying need in the health sector to stop the spread of this virus. Recently, machine learning algorithms have shown fascinating results in the prediction of medical data. In this study, we have proposed an approach to predict COVID-19 on human genomic data using the CpG Island feature and the newly introduced AT-CG feature by machine learning algorithms. Our proposed system produces an impressive result of the highest 99.91% accuracy on the Naïve Bayes algorithm. © 2023, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Coronavirus

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：