检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Big Data, Big Data 2022

作者： Eldeeb, Hassan Amashukeli, Shota Elshawi, Radwa University of Tartu Institute of Computer Science Tartu Estonia Tanta University Faculty of Engineering Computers and Automatic Control Department Tanta Egypt

ISBN: (纸本)9781665480451

Feature engineering is a crucial step in building well-performing machine learning pipelines. However, manually constructing highly predictive features is time-consuming and requires domain knowledge. Although the research area of automated feature engineering has attracted much interest lately, both in academia and industry, the scalability and efficiency of the existing systems and tools are still practically unsatisfactory. This paper presents a scalable and interpretable automated feature engineering framework, BigFeat, that optimizes input features' quality to maximize the predictive performance according to a user-defined metric. BigFeat employs a dynamic feature generation and selection mechanism that constructs a set of expressive features that improve the prediction performance while retaining interpretability. Extensive experiments are conducted, and the results show that BigFeat provides superior performance compared to the state-of-the-art automated feature engineering framework, AutoFeat, on a wide range of datasets. We show that BigFeat significantly improves the F1-Score of 8 classifiers by 4.59%, on average. In addition, the performance improvement achieved by integrating BigFeat into different AutoML frameworks is higher than that achieved by integrating AutoFeat into the same frameworks. Besides, the scalability of BigFeat is confirmed by its linear complexity, parallel design, and execution time which is, on average, 22x faster than AutoFeat. © 2022 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Identification for control by Using HARMAX Models

Nonlinear Identification for Control by Using HARMAX Models

引用

International Conference on control, Decision and Information Technologies (CoDIT)

作者： Janetta Culita Dan Stefanoiu Andreea-Maria Nica Department of Automatic Control and Systems Engineering University “Politehnica” of Bucharest Romania Faculty of Automatic Control and Computers University “Politehnica” of Bucharest Romania

The purpose of this article is to perform a comparison between two identification models: a nonlinear one referred to as HARMAX and a classical linear one, of Box-Jenkins (BJ) type. The first model modifies a classical ARMAX model by applying Hammerstein polynomials on input, output, and noise signals. Identification of models was performed by means of Multi-Step Least Squares Method, as described into the article. The simulations on a real-world plant, namely ASTANK2, a fluidic system with two inputs, two outputs and nonlinear static characteristic, have proven that the HARMAX model performs better than the BJ model and provides more accurate useful models to be integrated into closed loop configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Configurable Dynamics of Electromagnetic Suspension by Fuzzy Takagi-Sugeno controller 21st

Configurable Dynamics of Electromagnetic Suspension by Fuzzy...

引用

21st Polish control Conference, PCC 2023

作者： Pilat, Adam Krzysztof Milanowski, Hubert Bieszczad, Rafal Sikora, Bartiomiej Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Automatic Control and Robotics AGH-University of Science and Technology Krakow Poland

ISBN: (纸本)9783031351693

This elaboration presents the synthesis of the Takagi-Sugeno type Fuzzy Logic controller realizing the programmable parameters of the state feedback controller together with the steady state current for the active magnetic levitation system. Closed-loop dynamics was calculated precisely with respect to the requested dynamics. Two cases were considered: fixed-and variable-closed-loop dynamics. The Fuzzy Logic controller was considered under four scenarios with linear, nonlinear, and constant in-range output. The study was supported by simulations and experimental investigations. The position of the levitating sphere stands as an illustration of the system in operation. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Dynamics

来源：评论

学校读者我要写书评

暂无评论

STGNN: a new self-trained generalized neural networks task space control for robot manipulators

引用

Neural Computing and Applications 2025年 1-26页

作者： Elmogy, Ahmed Elawady, Wael El-Ghaish, Hany Computer Engineering Department Prince Sattam Ibn Abdelaziz University Alkharj16273 Saudi Arabia Computers and Automatic Control Department Faculty of Engineering Tanta University Tanta31527 Egypt

The inherent uncertainties in the dynamic and kinematic parameters of robot manipulators pose significant challenges for their control in task space. This paper introduces an innovative adaptive sliding mode control strategy, leveraging self-trained generalized neural networks to enhance the precision and robustness of robot manipulator control. The proposed framework called STGNN integrates deep neural networks for the real-time estimation and adjustment of dynamics’ and kinematics’ parameters. Key contributions of this work include the development of semi-supervised learning models for adaptive dynamics and kinematics estimation. By training the generalized neural network on different trajectories, the same models can be utilized to operate on a variety of tasks, significantly improving the robustness, scalability, and adaptability of the control system. The STGNN approach allows the models to leverage both labeled and unlabeled data, incorporating a self-training mechanism that enhances their ability to generalize and adapt to diverse operational scenarios. This capability is particularly beneficial for real-time applications, where the ability to learn and adapt on the fly is crucial. Simulation results demonstrate the superior performance of the STGNN framework in controlling robot manipulators in operational space, showcasing its potential for real-world applications. The proposed method significantly advances the adaptability, accuracy, and efficiency of robot control systems, offering notable improvements over conventional approaches. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Self adjusting control systems

来源：评论

学校读者我要写书评

暂无评论

Texture Analysis of Breast US Images Using Morphological Transforms, Hausdorff Dimension and Bagging Ensemble Method 32

Texture Analysis of Breast US Images Using Morphological Tra...

引用

32nd Mediterranean Conference on control and Automation, MED 2024

作者： Tabacaru, Gigi Moldovanu, Simona Barbu, Marian 'Dunarea de Jos' University of Galati Faculty of Automation Computers Electrical Engineering and Electronics Department of Automatic Control and Electrical Engineering Romania 'Dunarea de Jos' University of Galati Computer Science and Information Technology Faculty of Automation Computers Electrical Engineering and Electronics Romania Dunarea de Jos University of Galati The Modelling & Simulation Laboratory Galati800008 Romania

ISBN: (纸本)9798350395440

In this work, an attempt is made for the first time to use the measurement pattern generated by morphological transformation quantified by Hausdorff fractal dimension (HFD) and classified with ensemble learning based on bagging. The proposed work uses three morphological transformations for image preprocessing: hit-and-miss transform (HMT), white (WHT), and black top-hat (BHT). The pattern texture of US breast images is described by extracting the HFD from the regions of interest (ROI) after the ultrasound (US) images have been preprocessed. The main objective of this study was achieved by comparatively analyzing the classification performance of features using the Random Forest (RF), Extra Trees (ET) classifier, and bagging ensemble method based on XGBoot classifier. In presented study, the XGBoost classifier and BHT image processing method give an accuracy of 89.8% in a binary classification, benign versus malignant breast cancer. © 2024 IEEE.

关键词： Fractal dimension

来源：评论

学校读者我要写书评

暂无评论

A Multi-party Asymmetric Self-play Algorithm and Its Application in Multi-USV Adversarial Game Simulations 24

A Multi-party Asymmetric Self-play Algorithm and Its Applica...

引用

2024 International Conference on Machine Learning, Pattern Recognition and Automation engineering, MLPRAE 2024

作者： Rao, Jinjun Wang, Cong Liu, Mei Lei, Jingtao Giernacki, Wojciech Department of Precision Mechanical Engineering School of Mechatronic Engineering and Automation Shanghai University China Institute of Robotics and Machine Intelligence Faculty of Automatic Control Robotics and Electrical Engineering Poznan University of Technology Poland

ISBN: (纸本)9798400709876

Aiming at the problem that the combination of self-play (SP) and deep reinforcement learning (DRL) only involves two-party games and the policy learning of each party is limited, a multi-party asymmetric self-play algorithm (MASP) is proposed. Firstly, by improving the ELO scoring system, the ELO scoring takes into account each party of the unmanned surface vehicle (USV) clusters, and the imbalance of the number of USV clusters, so that the frequency of exchanging strategies of all USV clusters in the confrontation process is equal. Secondly, it ensures that USV clusters have a balanced combat ability, and at the same time ensures that the combat ability of all parties is strong and weak and the gap is not too wide. In addition, the parameters are dynamically set to reduce the update frequency of the policy of the stronger party. The experimental results show that the MASP can make the USV clusters learn more effective policies, have a shorter game time, and obtain higher rewards and ELO scores in the simple 2v2 adversarial game scenario and the three-party game scenario of a warship escort mission. © 2024 ACM.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning Method for control of Mixed Autonomy Traffic systems

Deep Reinforcement Learning Method for Control of Mixed Auto...

引用

2024 IEEE International Conference on Multisensor Fusion and Integration for Intelligent systems, MFI 2024

作者： Liu, Xingyu Apriaskar, Esa Mihaylova, Lyudmila University of Sheffield Department of Automatic Control and Systems Engineering SheffieldS1 3JD United Kingdom Universitas Negeri Semarang Faculty of Engineering Department of Electrical Engineering Semarang50229 Indonesia

ISBN: (纸本)9798350368031

The introduction of autonomous vehicles (AVs) presents a novel approach to regulating and optimising traffic flow through the automated control of AVs. In this context, the AV is defined as the actuator and an optimal control policy is desired to make control decisions. Deep Reinforcement Learning (DRL) is a novel method which aims to maximize the cumulative rewards given by the predefined reward function by making sequential decisions in a stochastic environment. In light of the above, we propose a DRL-based vehicular control method to train an optimal policy for the control of AV in a model-free fashion, and consequently improve the traffic efficiency with the obtained control policy. A single-lane circular road environment with both AV and human-driven vehicles is selected to serve as the mixed autonomy traffic system in the Simulation of Urban MObility (SUMO) [1] traffic simulator, and the Proximal Policy Optimization (PPO) algorithm is applied for the policy improvement. Simulation results demonstrate that our strategy is effective in mitigating the unstable stop-and-go waves, increasing 67.7% of the average driving speed and reducing 19.3% of the average energy consumption in a closed-ring road environment. © 2024 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Security issues in MCPS when using Wireless Sensor Networks

Security issues in MCPS when using Wireless Sensor Networks

引用

E-Health and Bioengineering Conference (EHB)

作者： Balaban Béatrix-May Sacală Ioan Ştefan Petrescu-Niţă Alina-Claudia Simen Radu Department of System Engineering Faculty of Automatic Control and Computers UPB Bucharest Romania

ISBN: (数字)9781665485579

ISBN: (纸本)9781665485586

Considering the evolution of technology, the need to secure data is growing fast. When we turn our attention to the healthcare field, securing data and assuring privacy are critical conditions that must be accomplished. The information is sensitive and confidential, and the exchange rate is very fast. Over the years, the healthcare domain has gradually seen a growth of interest regarding the interconnectivity of different processes to optimize and improve the services that are provided. Therefore, we need intelligent complex systems that can collect and transport sensitive data in a secure way. These systems are called cyber-physical systems. In healthcare domain, these complex systems are named medical cyber physical systems. The paper presents a brief description of the above-mentioned intelligent systems. Then, we focus on wireless sensor networks and the issues and challenges that occur in securing sensitive data and what improvements we propose on this subject. In this paper we tried to provide a detailed overview about cyber-physical systems, medical cyber-physical systems, wireless sensor networks and the security issues that can appear.

关键词： Wireless sensor networks Privacy Exchange rates Data privacy Medical services Cyber-physical systems Security

来源：评论

学校读者我要写书评

暂无评论

A Neural PID End-effector controller for Robotic Manipulator with Joint Position Constraints

A Neural PID End-effector Controller for Robotic Manipulator...

引用

2023 International Conference on system Science and engineering, ICSSE 2023

作者： Nguyet, Nguyen Tran Minh Ba, Dang Xuan Faculty of Electrical and Electronics Engineering Ho Chi Minh City Viet Nam Department of Automatic Control Ho Chi Minh City Viet Nam

ISBN: (纸本)9798350322941

We present a novel efficient method to control the end- effector of robotic manipulators without solving the inverse kinematics problem in the presence of the hard bound on the joint space motion. The basic Proportional-Integral-Derivative (PID) controller is combined with a nonlinear law to track the position and control the joint move within physical limits. To provide the adaptive ability of such the controller, a neural control signal is integrated to compensate for the internal and external disturbances in the robot dynamic. Stability of the closed-loop system is guaranteed by Lyapunov constraints. The proposed controller is validated in intensive simulation results. © 2023 IEEE.

关键词： End effectors

来源：评论

学校读者我要写书评

暂无评论

Consideration on RT software implementation for algorithm switching in MM structures 27

Consideration on RT software implementation for algorithm sw...

引用

27th International Conference on system Theory, control and Computing, ICSTCC 2023

作者： Lupu, Ciprian Secuianu, Catinca Lich, Luu Duch Faculty of Automatic Control and Computers University POLITEHNICA Bucharest Bucharest Romania Faculty of Chemical Engineering and Biotechnologies University POLITEHNICA Bucharest Bucharest Romania Faculty of Transportation Mechanical Engineering University of Science and Technology The University of Danang Da Nang550000 Viet Nam

ISBN: (纸本)9798350337983

Real-time (RT) implementation of control systems for non-linear processes raises numerous theoretical and practical challenges. Multi-model structures (MM) represent one of the successful solutions for these processes. However, switching of control algorithms constitutes the specific problem of MM structures. Even if reducing the sampling period can increase the precision in the control of some processes, for the case of algorithms switching in the MM structures is not improving significantly. The tests carried out in this work confirm this behavior for some numeric PIDs algorithms. Moreover, these tests can be an example for reducing the computational effort by changing the sampling period up to a maximum limit, specific to the process. However, superior performances in switching control algorithms can be obtained by using a common database for all switched algorithms in the respective MM structure. The architecture proposed in the paper and the tests performed on a laboratory implementation prove these solutions. © 2023 IEEE.

关键词： Real time systems

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：