检索结果-内蒙古大学图书馆

Investigation of the Necessity of Past Input/output Information in Reinforcement Learning based Robust control

Transactions of the Korean Institute of Electrical Engineers 2021年第12期70卷 1953-1957页

作者： Shim, Hyungbo Kim, Jeong Woo Park, Jooyoung Dept. of Electrical and Computer Engineering Seoul National University Korea Republic of Dept. of Control & Instrumentation Engineering Korea University Korea Republic of

Reinforcement learning yields a feedback controller that achieves specific control goal (which is often translated as a reward function). However, it often suffers from the Sim2Real gap, and domain randomization is known to be a method to overcome this issue. In this paper, we demonstrate necessity of input/outpu history when domain randomization is employed by a formal example and a simulation result. This is equivalent to the necessity of dynamic feedback controller in terms of control theory. © The Korean Institute of Electrical Engineers

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Detection of Electric Motor Damage Through Analysis of Sound Signals Using Bayesian Neural Networks

Detection of Electric Motor Damage Through Analysis of Sound...

引用

Annual Conference of Industrial Electronics Society

作者： Waldemar Bauer Marta Zagórowska Jerzy Baranowski Dept. of Automatic Control & Robotics AGH University of Krakow Krakow Poland Dept. of Engineering Cybernetics Norwegian University of Science and Technology Trondheim Norway

ISBN: (数字)9781665464543

ISBN: (纸本)9781665464550

Fault monitoring and diagnostics are important to ensure reliability of electric motors. Efficient algorithms for fault detection improve reliability, yet development of cost-effective and reliable classifiers for diagnostics of equipment is challenging, in particular due to unavailability of well-balanced datasets, with signals from properly functioning equipment and those from faulty equipment. Thus, we propose to use a Bayesian neural network to detect and classify faults in electric motors, given its efficacy with imbalanced training data. The performance of the proposed network is demonstrated on real life signals, and a robustness analysis of the proposed solution is provided.

关键词： Accuracy Fault detection Neural networks Training data Robustness Bayes methods Wind turbines Signal representation Time-domain analysis Electric motors

来源：评论

学校读者我要写书评

暂无评论

Detection of Electric Motor Damage Through Analysis of Sound Signals Using Bayesian Neural Networks

arXiv

引用

arXiv 2024年

作者： Bauer, Waldemar Zagórowska, Marta Baranowski, Jerzy Dept. of Automatic Control & Robotics AGH University of Krakow Krakow Poland Dept. of Engineering Cybernetics Norwegian University of Science and Technology Trondheim Norway

关键词： Electric motors

来源：评论

学校读者我要写书评

暂无评论

Transfer and Bayesian Learning Approaches for Land Use and Land Cover Classification

Transfer and Bayesian Learning Approaches for Land Use and L...

引用

Emerging Smart Computing and Informatics (ESCI), Conference on

作者： Zainab Malik Aisha Sir Elkhatem Gokhan Bilgin Dept. of Computer Engineering Yildiz Technical University Istanbul Turkey Dept. of Control and Automation Engineering Yildiz Technical University Istanbul Turkey

ISBN: (数字)9798331515683

ISBN: (纸本)9798331515690

Land use and land cover (LULC) classification is essential for understanding the impact of both human activities and natural processes on the Earth’s surface. This classification plays a critical role in deforestation, urban planning, and damage assessment. However, traditional machine learning techniques often face challenges in achieving consistent accuracy in diverse datasets. In this study, we implement transfer learning and Bayesian learning approaches to enhance the accuracy and robustness of LULC classification. Transfer learning leverages knowledge from previous classification problems, while Bayesian learning addresses uncertainties in the classification process. Using the Remote Sensing Image Classification Benchmark (RSI-CB128) dataset, the study evaluates the performance of Bayesian Convolutional Neural Networks (CNN), Mobile Neural Networks (MobileNet), Inception Neural Networks (InceptionNet), Densely Connected Convolutional Networks (DenseNet) and Efficient Neural Networks (EfficientNet). The study also investigates the impact of varying the Bayesian layers on model performance, finding that a medium number of layers optimally captures model uncertainty. The results indicate that the transfer learning models, particularly MobileNet, achieved the highest accuracy of 97. 48% compared to 90. 33% for Bayesian CNN. These findings suggest that transfer learning techniques are highly effective for LULC classification, providing a reliable method for practical applications in remote sensing.

关键词： Deforestation Accuracy Uncertainty Computational modeling Transfer learning Neural networks Urban planning Land surface Bayes methods Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

SB-AGT: A stochastic beam search-enhanced attention-based Gumbel tree framework for drug-drug interaction extraction from biomedical literature

引用

computers in Biology and Medicine 2025年 189卷 110011-110011页

作者： Saad, Eman Kishk, Sherif Ali-Eldin, Amr Saleh, Ahmed I. Communication and Information Technology Center Mansoura University Egypt Electronics and Communication Engineering Dept. Mansoura University Egypt Computer Engineering & Control Systems Dept. Mansoura University Egypt

Drug-Drug Interactions (DDI) and Chemical-Protein Interactions (CPI) detection are crucial for patient safety, as unidentified interactions may lead to severe Adverse Drug Reactions (ADRs). While extensive DDI and CPI information exists within biomedical literature, manual extraction by experts proves time-intensive and resource-demanding. This study presents SB-AGT: Stochastic Beam Search-enhanced Attention-based Gumbel Tree an innovative approach to automated DDI and CPI extraction through an attention-based architecture incorporating a modified Gumbel-Tree method with stochastic beam search optimization. SB-AGT leverages multi-head attention mechanisms and enhanced latent tree structures to effectively capture complex syntactic features and drug relationship patterns. Also, the methodology includes comprehensive preprocessing protocols and addresses dataset imbalance through hybrid sampling techniques. Experimental validation on the DDIExtraction 2013 and CHEMPROT datasets demonstrates the model's effectiveness, achieving precision, surpassing traditional approaches and showing competitive performance compared to contemporary pre-trained models. Through parametric analysis, we establish optimal beam search configurations that maximize the model's extraction accuracy. © 2025 Elsevier Ltd

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Radiomics-based classification in imbalanced datasets: complexity or interpretability

Radiomics-based classification in imbalanced datasets: compl...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Simone Boesso Lorenzo Farina Manuela Petti Dept. of Computer Control and Management Engineering Sapienza University of Rome Rome Italy

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Radiomics represents a specialized branch of medical imaging where quantitative features are extracted from images. Performing a classification using radiomics means solving two common problems: the imbalanced setting, and the large number of features that would increase the risk of overfitting. Moreover, since its main application and impact are in clinical field, there is the need of interpretable models for explaining their results. The aim of this study is to compare two modelling approaches: one based on a logistic regression model, known for its simplicity and interpretability, and RUSBoost, an ensemble method designed to handle class imbalance with potentially higher complexity, in order to answer the question whether higher complexity and lower interpretability are justified when dealing with radiomics data. Additionally, due to the large literature suggesting it, we analyze the impact of a feature selection step applied to these two classifiers. Test performances measured across 20 repeated splits on two datasets show how the RUSBoost approach is able to capture more detailed patterns of the data but this is highly dependent on the dataset at hand.

关键词： Logistic regression Analytical models Feature extraction Oncology Data models Complexity theory Mutual information Radiomics Overfitting Tumors

来源：评论

学校读者我要写书评

暂无评论

Optimization of Neural Networks using Swarm Intelligence Techniques for Achieving Energy Efficiency in Smart Building Architecture 1

Optimization of Neural Networks using Swarm Intelligence Tec...

引用

1st IEEE International Conference on Cognitive Robotics and Intelligent Systems, ICC - ROBINS 2024

作者： Raja, M. Karthick Shermatova, Makhbuba Al Ansari, Mohammed Saleh Abdufattokhov, Shokhjakhon Rao, Vuda Sreenivasa Raj, I. Infant Sri Eshwar College of Engineering Department of Computer Science and Engineering Coimbatore India Turin Polytechnic University in Tashkent Civil Engineering and Architecture Department Tashkent Uzbekistan University of Bahrain College of Engineering Department of Chemical Engineering Bahrain Turin Polytechnic University Automatic Control and Computer Engineering Dept Italy Tashkent Intl. University of Education Dept of Information Technologies Tashkent Uzbekistan Koneru Lakshmaiah Education Fou. Green Fields Department of Computer Science and Engineering A.P Vaddeswaram522302 India K. Ramakrishnan College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy621 112 India

ISBN: (纸本)9798350372748

The increasing prevalence of smart building architectures, driven by the integration of Internet of Things (IoT) devices and automation systems, has led to a surge in energy consumption. This research explores the application of swarm intelligence techniques as an innovative approach to optimize neural networks, aiming to strike a balance between maintaining the desired performance levels and minimizing energy consumption. The study investigates the integration of swarm-based optimization algorithms, such as Particle Swarm Optimization (PSO) into the training and operation of neural networks. These algorithms enable the networks to dynamically adapt and optimize their parameters in response to changing environmental conditions and user requirements. The research focuses on developing a comprehensive framework that considers the specific challenges posed by smart building architectures, including real-time data processing, sensor integration, and adaptive control. The proposed approach aims to achieve optimal neural network configurations that minimize energy consumption while ensuring reliable and responsive operation of smart building systems. The results demonstrate the potential of swarm intelligence to significantly improve the energy efficiency of neural network-enabled smart building architectures, providing a promising avenue for sustainable and intelligent infrastructure. The proposed model has an accuracy of 98.23% which is 7.64% higher than that of the traditional approaches. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Process-Model-Free Design of MPC via a Reference-Model-Based PI controller for the Gas Turbine 9

Process-Model-Free Design of MPC via a Reference-Model-Based...

引用

9th International Conference on Electrical engineering, control and Robotics, EECR 2023

作者： Shi, Gengjin Dai, Chengbo Ma, Miaomiao Li, Donghai Ding, Yanjun Tsinghua University State Key Lab of Power Systems Dept. of Energy & Power Engineering Beijing China North China Electric Power University School of Control & Computer Engineering Beijing China

ISBN: (纸本)9781665491204

Model predictive control (MPC) is a modern advanced control strategy which has great reputation because of its excellent reference tracking performance and the ability to deal with process constraints, time delay and multivariable problems. However, the gas turbine is difficult to model accurately and unmeasurable disturbances are unavoidable, which limits the application of MPC to the gas turbine. To solve these problems, a process-model-free design method for MPC via a reference-model (RM)-based proportional-integral (PI) controller-desired dynamic equational (DDE)-PI controller (MPC-DDE) is proposed in this paper. The DDE-PI provides the design model for the MPC and handle with unmeasurable disturbances while MPC provides a rolling optimized set point for DDE-PI. Simulation results illustrate the superiorities of the proposed hierarchical control strategy in reference tracking, disturbance rejection and robustness, which indicates the promising prospect of practical application of MPC-DDE to the gas turbine. © 2023 IEEE.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

Identification of Cancer Biomarkers for Multi-class Diagnostics through Network Analysis of RNAseq Data of Tumor-Educated Platelets

Identification of Cancer Biomarkers for Multi-class Diagnost...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Toccacieli, Ali Petti, Manuela Sapienza University of Rome MSc Program in Engineering in Computer Science Rome Italy Sapienza University of Rome Dept. of Computer Control and Management Engineering Rome Italy

ISBN: (纸本)9781665468190

Tumor-educated platelets (TEPs) are circulating blood cells with a distinct tumor-driven phenotype and act as carriers and protectors of metastases. To date, some studies have shown that the TEPs transcriptome can be used for cancer diagnostics. The objective of this study is to propose a procedure based on differential gene expression and differential gene co-expression analyses to identify a set of key genes for multi-class cancer diagnostics. To reach this aim, we analyzed RNA-seq data (57736 genes) of 130 subjects, of whom 40 patients with glioblastoma multiforme (GBM), 35 patients with pancreatic adenocarcinoma (PAAD), and 55 healthy donors (HC). We focused our analysis on the subset of differentially expressed genes (DEGs), and we used these genes to build and analyze the differential co-expression networks, identifying the hub genes. With this procedure, we obtained a restricted set of DEGs that maximize the accuracy in classifying patients according to their conditions (GBM, PAAD, or HC). Indeed, we validated our results by comparing the achieved classification accuracy with that resulting from random selections of DEGs and we obtained that genes selected by differential co-expression (DCE) network analysis have greater predictive power than any other set of differentially expressed genes, including using all of them. © 2022 IEEE.

关键词： Platelets

来源：评论

学校读者我要写书评

暂无评论

Monitoring and Forecasting Quality Indicators of Predough Production in the Bakery Industry 5

Monitoring and Forecasting Quality Indicators of Predough Pr...

引用

5th IEEE KhPI Week on Advanced Technology, KhPIWeek 2024

作者： Lutska, Nataliia Zaiets, Nataliia Vlasenko, Lidiia Zhyltsov, Andrii Dept. of Automation and Computer Technologies of Control Systems National University of Food Technologies Kyiv Ukraine dept. of Automation and Robotic Systems National University of Life and Environmental Sciences of Ukraine Kyiv Ukraine Dept. of Software Engineering and Cyber Security State University of Trade and Economics Kyiv Ukraine Dept. of Electromagnetic Systems The Institute of Electrodynamics The National Academy of Sciences of Ukraine Kyiv Ukraine

ISBN: (纸本)9798350384499

The work demonstrates the process of developing a machine learning model for a system for monitoring and controlling the quality of predough at a bakery. This system will provide continuous analysis of the predough parameters, such as temperature, humidity, lifting force and titranic acidity, which will ensure timely detection of deviations in the quality of the predough and avoid production problems. In addition, it will help automate the quality control process and ensure the stability of production processes. Analysis and forecasting of dough parameters will improve the quality of produced bread or other bakery products. Management based also on the predicted values of technological indicators of the predough will allow the enterprise to avoid unnecessary costs of materials and energy and increase economic efficiency. As part of the study, seven machine learning models were created and reviewed, including three linear and four varieties of binary decision trees. An analysis of the best model - a regression decision tree - was carried out, confirming its effectiveness and the validity of the resulting hierarchical structure, in particular, the prediction of important indicators of predough with a high degree of reliability, which indicates its importance in practical applications in production. The created model can be used to monitor and control product quality in real time, allowing operators to quickly identify and correct any deviations in process performance. Also, by analyzing changes in the variables of the predough production process, it is possible to identify precursors of possible production accidents or deviations in product quality, which will allow timely measures to be taken to avoid them. ©2024 IEEE.

关键词： Bakeries

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：