检索结果-内蒙古大学图书馆

6th International Conference on Intelligent control, Measurement and Signal Processing, ICMSP 2024

作者： Zhang, Zhaozhao Li, Bofan Zhu, Yingqin Xi'an University of Science and Technology College Computer Science and Technology Xi'an China CINVESTAV-IPN National Polytechnic Institute Department of Control Automatic Mexico City Mexico

ISBN: (纸本)9798331516550

To overcome the limitations of conventional echo state networks (ESN), such as redundant connections and insufficient frequency-domain feature extraction, this paper proposes a frequency-domain feature architecture search-based ESN (FS-ESN). Leveraging a frequency response fitness function, FS-ESN dynamically optimizes reservoir structures and incorporates frequency-domain features aligned with target tasks. Experimental results demonstrate that FS-ESN significantly improves feature extraction, adaptability, and predictive performance, outperforming traditional ESN models in task-specific applications. © 2024 IEEE.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Energy Efficient Hardware Acceleration of Neural Networks with Power-of-Two Quantisation

Energy Efficient Hardware Acceleration of Neural Networks wi...

引用

International Conference on Computer Vision and Graphics, ICCVG 2022

作者： Przewlocka-Rus, Dominika Kryjak, Tomasz Embedded Vision Systems Group Computer Vision Laboratory Department of Automatic Control and Robotics AGH University of Science and Technology Krakow Poland

ISBN: (纸本)9783031220241

Deep neural networks virtually dominate the domain of most modern vision systems, providing high performance at a cost of increased computational complexity. Since for those systems it is often required to operate both in real-time and with minimal energy consumption (e.g., for wearable devices or autonomous vehicles, edge Internet of Things (IoT), sensor networks), various network optimisation techniques are used, e.g., quantisation, pruning, or dedicated lightweight architectures. Due to the logarithmic distribution of weights in neural network layers, a method providing high performance with significant reduction in computational precision (for 4-bit weights and less) is the Power-of-Two (PoT) quantisation (and therefore also with a logarithmic distribution). This method introduces additional possibilities of replacing the typical for neural networks Multiply and ACcumulate (MAC—performing, e.g., convolution operations) units, with more energy-efficient Bitshift and ACcumulate (BAC). In this paper, we show that a hardware neural network accelerator with PoT weights implemented on the Zynq UltraScale + MPSoC ZCU104 SoC FPGA can be at least 1.4x more energy efficient than the uniform quantisation version. To further reduce the actual power requirement by omitting part of the computation for zero weights, we also propose a new pruning method adapted to logarithmic quantisation. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： System-on-chip

来源：评论

学校读者我要写书评

暂无评论

Deep reinforcement learning for optimal denial-of-service attacks scheduling

引用

Science China(Information Sciences) 2022年第6期65卷 98-106页

作者： Fangyuan HOU Jian SUN Qiuling YANG Zhonghua PANG State Key Laboratory of Intelligent Control and Decision of Complex Systems Beijing Institute of Technology Key Laboratory of Fieldbus Technology and Automation of Beijing North China University of Technology

We consider an optimal denial-of-service(DoS) attack scheduling problem of N independent linear time-invariant processes, where sensors have limited computational capability. Sensors transmit measurements to the remote estimator via a communication channel that is exposed to DoS attackers. However,due to limited energy, an attacker can only attack a subset of sensors at each time step. To maximally degrade the estimation performance, a DoS attacker needs to determine which sensors to attack at each time step. In this context, a deep reinforcement learning(DRL) algorithm, which combines Q-learning with a deep neural network, is introduced to solve the Markov decision process(MDP). The DoS attack scheduling optimization problem is formulated as an MDP that is solved by the DRL algorithm. A numerical example is provided to illustrate the efficiency of the optimal DoS attack scheduling scheme using the DRL algorithm.

关键词： optimal denial-of-service attack scheduling optimization limited energy deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Designing a Robust control System Based on Sliding Mode control for Two-axis Gimbal systems

Designing a Robust Control System Based on Sliding Mode Cont...

引用

2024 Conference of Young Researchers in Electrical and Electronic Engineering, ElCon 2024

作者： Phuong, Nguyen Viet Tuyen, Nguyen Trong Khanh, Nguyen Duy Hung, Nguyen Ngoc Academy of Military Science and Technology Department of Aerospace Control Systems Hanoi Viet Nam Le Quy Don Technical University Department of Biomedical Engineering Hanoi Viet Nam Saint Petersburg State Electrotechnical University Department of Automatic Control Systems Hanoi Viet Nam Le Quy Don Technical University Department of Aerospace Control Systems Hanoi Viet Nam

ISBN: (纸本)9798350360646

Two-axis gimbals are used in stabilizing and controlling the aiming of optical systems. The main task is to isolate the angular motion of the payload and the disturbances affecting the optical axis of the camera while maintaining the camera's orientation locked onto the target. Currently, two commonly used gimbal structures are the Yaw-Pitch type and the Roll-Swing type. In this paper, we delve into an in-depth study to develop the full mathematical models for both types, thereby analyzing and evaluating the influence of the cross-channel noise moment effects caused by gimbal imbalance on the stability and aiming control quality under complex angular motion conditions of the payload. Simulation results conducted using MATLAB/SIMULINK with the two-axis gimbal model demonstrate that employing a robust control system significantly reduces the impact of disturbances and enhances the quality of control and stability of the transmission system. © 2024 IEEE.

关键词： adaptive inertially stabilized platform self-driving transmission sliding mode control two-axis gimbal

来源：评论

学校读者我要写书评

暂无评论

Modeling of Electro-Hydraulic Servo-Drive for Advanced control System Design 15th

Modeling of Electro-Hydraulic Servo-Drive for Advanced Contr...

引用

15th International Conference Dynamical systems: Theory and Applications, DSTA, 2019

作者： Możaryn, Jakub Winnicki, Arkadiusz Suski, Damian Institute of Automatic Control and Robotics Warsaw University of Technology Warsaw Poland

ISBN: (纸本)9783030773052

The paper describes the synthesis of a mathematical model of the electro-hydraulic servo-drive. Because of the complexity of the electro-hydraulic servo-drive system and the difficulty in determining all system’s coefficients, the simplification of the mathematical model is proposed. The model includes different non-linearities such as the friction or the pressure-dependent oil bulk module. The simulation results are presented, and the comparison with the data collected from the real servo drive is discussed. With the proposed method it was possible to choose the values of physical parameters such that the real electro-hydraulic servo-drive is modeled with the accuracy suitable for the fast prototyping and design of the advanced control system. © 2022, Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Research on the behaviour of Bluetooth Low Energy protocol in the heart rate monitoring application 27

Research on the behaviour of Bluetooth Low Energy protocol i...

引用

27th International Conference on Knowledge Based and Intelligent Information and Engineering Sytems, KES 2023

作者： Balas, Zuzanna Tokarz, Krzysztof Zielinski, Bartlomiej Guzniczak, Tomasz Department of Graphics Computer Vision and Digital Systems Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland

In the paper, the authors check the behaviour of Bluetooth Low Energy protocol in a popular smart wristband and a microcontroller in the heart rate monitoring application. The measurements were collected using a development board with the ESP32 System on Chip. The authors tested measurement period stability and measurement reliability in various conditions. © 2023 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (https://***/licenses/by-nc-nd/4.0)

关键词： Bluetooth Low Energy Health monitoring Internet of Things Smart wristband Wireless data transmission

来源：评论

学校读者我要写书评

暂无评论

Real-time Data Feature for Health Based on State Change Rate 3

Real-time Data Feature for Health Based on State Change Rate

引用

3rd International Conference on Computing, Communication, Perception and Quantum technology, CCPQT 2024

作者： Wen, Yudi Wang, Xin Zhang, Ying Quality Manage Department Beijing Aerospace Automatic Control Institute Beijing China Project Command Office International Business Department China Academy of Launch Vehicle Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligent Beijing Aerospace Automatic Control Institute Peking University Beijing China

ISBN: (纸本)9798331528386

This paper uses PSLOC (Predictive Sliding Local Outlier Correction) to remove random fluctuations and noise interference. The time series prediction of the system's signals over a period of time is performed based on the least squares support vector machine (LSSVM). The adaptive state change rate is used to detect the prediction starting point. The system's full life cycle signal is divided into several windows, and the state change rate of the signal in each window is calculated. The threshold is determined by calculating the state change rate of the full life cycle signal. Compared with the traditional denoising and smoothing algorithm for non-time series, the algorithm used is more suitable for outlier detection of time series whose trends change over time. The method used in this paper is compared with the traditional wavelet packet threshold denoising method. It is found that the method used in this paper can retain the degradation information of the system to the maximum extent while removing outliers, and is more suitable for data preprocessing for remaining life prediction. The algorithm can not only remove the interference of random fluctuations on state division and remaining life prediction, but also preserve the complete degradation trend of the system adjusted over time. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

A WE-OSELM Online Prediction Algorithm to Engine control 3

A WE-OSELM Online Prediction Algorithm to Engine Control

引用

3rd International Conference on Computing, Communication, Perception and Quantum technology, CCPQT 2024

作者： Gao, Jie Wang, Xin Zhang, Ying Quality Manage Department Beijing Aerospace Automatic Control Institute Beijing China Project Command Office International Business Department China Academy of Launch Vehicle Beijing China National Key Laboratory of Science and Technology on Aerospace Intelligent Beijing Aerospace Automatic Control Institute Peking University Beijing China

ISBN: (纸本)9798331528386

Based on the time series online prediction model, this paper proposes a WE-OSELM online prediction algorithm, which can control the product life and performance in real time in the field of engine, and effectively manage huge system engineering. The prediction model is closely related to the actual application of system engineering product modules and has great operability. This paper proposes the IPW-OSELM algorithm and error compensation algorithm with information perception weight as the core point, and relies on a dual parallel single hidden layer feedforward neural network to efficiently integrate related algorithms to form a WE-OSLEM algorithm. Among them, the information perception weight clarifies the relationship between point similarity and regional similarity in the case of fluctuations in the effectiveness of the data characteristics of the prediction object or mutations in a limited range, so that the online prediction algorithm has a more acute data characteristic perception ability in the process of responding to changes in data characteristics. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

SMTC-CL: Continuous Learning via Selective Multi-Task Coordination for Adaptive Signal Classification

引用

IEEE Transactions on Cognitive Communications and Networking 2024年第3期11卷 1664-1681页

作者： Hao, Xiaoyang Yang, Shuyuan Liu, Ruoyu Feng, Zhixi Peng, Tongqing Huang, Bincheng Xidian University Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education School of Artificial Intelligence Xi'an710071 China Avic Xi'an Flight Automatic Control Research Institute China MeiTuan China China Electronics Technology Group Corporation Institute of Information Science and Technology China

Continuously adaptive signal classification in complex electromagnetic environments is a desired property of realistic intelligent systems. However, the limitation of most existing signal processing tasks and methods lies in their assumption of fixed categories and invariant distributions. In contrast, humans naturally acquire knowledge continuously from data streams, enhancing their capabilities through cross-task knowledge integration and learning from the past. Inspired by this, we propose a continuous learning (CL) method based on selective multi-task coordination (SMTC) to deal with ever-changing task categories and distributions in practical electromagnetic environments (denoted as SMTC-CL). Firstly, we propose a signal task distribution comparison (TDC) method that leverages intra-domain density and inter-domain divergence. TDC selectively activates multiple old tasks to collaboration with the current incremental new task. Secondly, we propose the SMTC method. By revisiting potential collaborative tasks from the past using TDC and formulating different selection strategies based on the context, continuous learners can achieve mutual benefits between past and current tasks in SMTC learning. SMTC can partially alleviate catastrophic forgetting and enable continuous learners to adapt to the changing electromagnetic environment. Based on the signal automatic modulation classification (AMC) and real-world specific emitter identification (SEI) datasets, extensive experimental results validate the effectiveness of our proposed method on a variety of CL scenarios, including varying signal task categories, distributions, and their combinations. © 2015 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PITD3-based Autonomous Evasion Decision-making Method for Aircraft 43

PITD3-based Autonomous Evasion Decision-making Method for Ai...

引用

43rd Chinese control Conference, CCC 2024

作者： Liu, Chang Dou, Liqian Zhang, Ruilong Tang, Yifan Ren, Mengyuan Zhang, Lun School of Electrical Engineering and Automation Tianjin300072 China Beijing Aerospace Automatic Control Institute China Tianjin Aerospace Institute of Computing Technology Tianjin300308 China

ISBN: (纸本)9789887581581

Outstanding autonomous evasion decision-making capability has an important significance for ensuring flight safety and enhancing the autonomy of the aircraft. In this paper, a prediction information-based TD3 (PITD3) evasion decision-making algorithm for aircraft is proposed, which can autonomously evade the interceptors' attack in an antagonistic environment. Firstly, an antagonistic environment is described according to environmental constraints and the dynamics of the aircraft and interceptor. Secondly, the autonomous decision-making process of the aircraft facing the threat target is modelled as a Markov decision process to describe the state information of the aircraft and interceptor. Finally, an autonomous evasion decision-making method based on the twin delayed deep deterministic policy gradient (TD3) is designed to find the optimal strategy, and the effectiveness of the proposed autonomous evasion decision-making method is demonstrated by simulation results and comparative experiments. © 2024 Technical Committee on control Theory, Chinese Association of Automation.

关键词： Markov processes

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：