检索结果-内蒙古大学图书馆

IEEE International Conference on Industrial Informatics (INDIN)

作者： Kuan Li Weijie Su Xingyong Li Yang He Minchang Huang Hao Luo Shanghai Aerospace Control Technology Institute Shanghai China Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798331527471

ISBN: (纸本)9798331527488

This paper presents the parameter identification based on generalized orthonormal basis function (GOBF) without persistent excitation via two learning-based paradigms. The problem is formulated as a two-stage identification of poles and weight coefficients of GOBFs. The GOBF is designed based on the two-parameter Kautz basis function for the compatiblity with complex poles. The two learning-based paradigms are established on the nature-inspired meta-heuristic optimization and deep reinforcement learning, respectively. The ability of identification without strict persistent excitation is discussed as well. The effectiveness of the two paradigms are verified through a simulation study on a 4-order transfer function model.

关键词： Parameter estimation Metaheuristics Transfer functions Optimization methods Deep reinforcement learning Informatics Convergence

来源：评论

学校读者我要写书评

暂无评论

Augmenting Vision with Radar for All-weather Geo-localization without a Prior HD Map

Augmenting Vision with Radar for All-weather Geo-localizatio...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Can Dong Ziyang Hong Siru Li Liang Hu Huijun Gao Department of Automation School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Department of Control Science and Engineering Harbin Institute of Technology Harbin China

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Accurate and robust geo-localization in all-weather conditions is essential for enabling autonomous vehicles and delivery robots to offer uninterrupted mobility services in the real world. In this paper, we propose the first camera and radar fusion based geo-localisation method that is robust to all-weather conditions. The core of the proposed method is to leverage the rich semantics information in images and sensing consistency in radars across all-weather. Our proposed method surpasses the state of the art camera-based and LiDAR-camera based methods in inclement weather conditions, shown by extensive comparative experiments. Notably, our approach requires only an open accessible map, eliminating the need for high-definition maps and offering a cost-effective solution for geo-localizing or globally localizing autonomous vehicles in any weather condition. Our code and trained model will be released publicly.

关键词： Accuracy Robot vision systems Radar Radar imaging Cameras Feature extraction Sensor systems Sensors Autonomous vehicles Meteorology

来源：评论

学校读者我要写书评

暂无评论

Investigating Deep Watermark Security: An Adversarial Transferability Perspective

arXiv

引用

arXiv 2024年

作者： Qi, Biqing Gao, Junqi Luo, Yiang Liu, Jianxing Wu, Ligang Zhou, Bowen Department of Control Science and Engineering Harbin Institute of Technology Harbin China Department of Electronic Engineering Tsinghua University Bejing China School of Mathematics Harbin Institute of Technology Harbin China

The rise of generative neural networks has triggered an increased demand for intellectual property (IP) protection in generated content. Deep watermarking techniques, recognized for their flexibility in IP protection, have garnered significant attention. However, the surge in adversarial transferable attacks poses unprecedented challenges to the security of deep watermarking techniques—an area currently lacking systematic investigation. This study fills this gap by introducing two effective transferable attackers to assess the vulnerability of deep watermarks against.erasure and tampering risks. Specifically, we initially define the concept of local sample density, utilizing it to deduce theorems on the consistency of model outputs. Upon discovering that perturbing samples towards high sample density regions (HSDR) of the target class enhances targeted adversarial transferability, we propose the Easy Sample Selection (ESS) mechanism and the Easy Sample Matching Attack (ESMA) method. Additionally, we propose the Bottleneck Enhanced Mixup (BEM) that integrates information bottleneck theory to reduce the generator’s dependence on irrelevant noise. Experiments show a significant enhancement in the success rate of targeted transfer attacks for both ESMA and BEM-ESMA methods. We further conduct a comprehensive evaluation using ESMA and BEM-ESMA as measurements, considering model architecture and watermark encoding length, and achieve some impressive findings. Copyright © 2024, The Authors. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Robust Deep 3D Convolutional Autoencoder for Hyperspectral Unmixing with Hypergraph Learning

引用

Journal of harbin inst.tute of technology(New Series) 2021年第5期28卷 1-8页

作者： Peiyuan Jia Miao Zhang Yi Shen Department of Control Science and Engineering Harbin Institute of TechnologyHarbin 150001China

Hyperspectral unmixing aims to acquire pure spectra of distinct substances(endmembers)and fractional abundances from highly mixed *** this paper,a deep unmixing network framework is designed to deal with the noise *** contains two parts:a three⁃dimensional convolutional autoencoder(denoising 3D CAE)which recovers data from noised input,and a restrictive non⁃negative sparse autoencoder(NNSAE)which incorporates a hypergraph regularizer as well as a l2,1⁃norm sparsity constraint to improve the unmixing *** deep denoising 3D CAE network was constructed for noisy data retrieval,and had strong capacity of extracting the principle and robust local features in spatial and spectral domains efficiently by training with corrupted ***,a part⁃based nonnegative sparse autoencoder with l2,1⁃norm penalty was concatenated,and a hypergraph regularizer was designed elaborately to represent similarity of neighboring pixels in spatial *** experiments were conducted on synthetic and real⁃world data,which both demonstrate the effectiveness and robustness of the proposed network.

关键词： deep learning unsupervised unmixing convolutional autoencoder hypergraph hyperspectral data

来源：评论

学校读者我要写书评

暂无评论

Ca2+ homeostasis: a potential target for cancer therapies

引用

Biophysics Reports 2024年第5期10卷 283-292页

作者： Min Su Shanliang Zheng Hao Liu Tie-Shan Tang Ying Hu School of Life Science and Technology Harbin Institute of Technology Key Laboratory of Science and Engineering for the Multi-modal Prevention and Control of Major Chronic Diseases Ministry of Industry and Information Technology Department of Medicine and Health Zhengzhou Research Institute of Harbin Institute of Technology State Key Laboratory of Membrane Biology Institute of Zoology Chinese Academy of Sciences Beijing Institute for Stem Cell and Regenerative Medicine University of Chinese Academy of Sciences Chinese Academy of Sciences

Calcium ions(Ca2+) play a crucial role as secondary messengers in both excitable and non-excitable cells.A complex system of proteins and molecules involved in calcium handling allows Ca2+signals to be *** cancer cells,mutations,aberrant expression,and dysregulation of these calcium handling toolkit proteins disrupt the normal Ca2+flux between extracellular space,cytosol,endoplasmic reticulum and mitochondria,as well as the spatio-temporal patterns of Ca2+*** leads to the dysregulation of calcium-dependent effectors that control key signaling pathways involved in cancer cell proliferation,survival and *** there has been progressing in understanding the remodelling of calcium homeostasis in cancer cells and identifying key calcium transport molecules that promote malignant phenotypes,much work remains to be done to translate these fundamental findings into new tools for diagnosing and treating cancer by targeting Ca2+homeostasis.

关键词： Calcium homeostasis Cancer Therapy

来源：评论

学校读者我要写书评

暂无评论

An Obstacle Avoidance control Strategy for DELTA Parallel Manipulator via Improved Genetic Algorithm 37

An Obstacle Avoidance Control Strategy for DELTA Parallel Ma...

引用

37th Youth Academic Annual Conference of Chinese Association of Automation, YAC 2022

作者： Zheng, Hao Xu, Yihang Li, Yuantao Ran, Guangtao Liu, Jian Southeast University School of Automation Nanjing210018 China Harbin Institute of Technology Department of Control Science and Engineering Harbin150001 China

ISBN: (纸本)9781665465366

Aiming at the requirement of the DELTA parallel manipulator for performing grasping operations, a method for obstacle avoidance based on a genetic algorithm is proposed. Firstly, the classical DELTA parallel manipulator is analyzed mathematically, and its model is simplified. Then, the motion space and inverse kinematics solutions of the DELTA parallel manipulator are solved by using the spatial geometry method. Secondly, a cylindrical envelope surface is added to the manipulator's end for distance calculation. This envelope surface ensures that obstacles do not collide with the manipulator during obstacle avoidance. Thirdly, an improved genetic algorithm is proposed for obstacle avoidance. Finally, the simulation results are given to verify the effectiveness and reliability of the proposed algorithm. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Cascaded Extended State Observer-Based Sliding Mode control for DC-DC Converter with Time- Varying Power Fluctuation

引用

IEEE Transactions on Industry Applications 2022年 1-6页

作者： Xu, Liangcai Liu, Jianxing Zhuo, Shengrong Huangfu, Yigeng Gao, Fei School of Automation Northwestern Polytechnical University Xi'an China Department of Control Science and Engineering Harbin Institute of Technology Harbin China FEMTO-ST Institute Univ. Bourgogne Franche-Comte UTBM CNRS Belfort France

In this paper, a cascaded extended state observer- based sliding mode control (SMC) is proposed for the typical microgrid (MG) interfaced dc-dc boost converter. For a given MG system, the power fluctuation is unpredictable, which may cause an unstable dc-bus voltage. In that situation, all the dc-bus connected electronic loads cannot work normally. In order to maintain a stable dc-bus voltage, additional power sources with a suitable power converter and the advanced controller are necessary. Especially, the controller for the power converter plays a crucial role in reducing the power fluctuation and regulating the dc-bus voltage. In this paper, to improve the ability of the converters to reject external power disturbance, a cascaded extended state observer is designed to estimate the lumped disturbance more accurately. Besides, the continuous SMC method is adopted to provide a feedback control loop. The corresponding simulation results could highly validate the effectiveness of the proposed control method. IEEE

关键词： Sliding mode control

来源：评论

学校读者我要写书评

暂无评论

Using Image Pre-Processing to Improve Navigation Line Extraction Based on Pix2Pix Net on Small-size Datasets

Using Image Pre-Processing to Improve Navigation Line Extrac...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Hao Zheng Qiang Wang Department of Control Science and Engineering Harbin Institute of Technology Harbin China

Autonomous navigation of the machine in the farm is an essential part of an automatic farm. GNSS(Global Navigation Satellite System) is an effective navigation technology, but it lacks sufficient precision in agricultural applications and is limited in price and range of use. Traditional image processing is difficult to deal with the changeable outside environment. Deep neural networks are becoming more effective for navigation, but it is time-consuming work to produce datasets and train. In this paper, we proposed a navigation line extraction method for agriculture based on Pix2Pix net with image pre-processing. We first separated the crops from the background to remove useless information. Then the binary image would go through the Pix2Pix net that would draw a red line following the crop row near the middle of the image. After that, we extracted the red line and used the least square to calculate the angle to guide the robot along the crops. The experiments indicated that image pre-processing could decline useless data in the picture, leading to a better neural network performance in navigation line extraction. At the same time, data optimization could reduce the requirements of neural network datasets, and make the model more adaptable to similar environments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improvement of Steering Performance for Autonomous Vehicles Based on Preview Model

Improvement of Steering Performance for Autonomous Vehicles ...

引用

Chinese control Conference (CCC)

作者： Zipeng Yang Linhui Zhao Xinyi Zhao Haifeng Liu Department of Control Science and Engineering Harbin Institute of Technology Harbin China

This paper presents an approach to traveling along a reference path and evading obstacles with smooth steering angle for autonomous vehicles when trajectory planner and control run asynchronously. Trajectory in this paper is composed of position and time information, which is produced through decision maker, reference line calculator, trajectory smoother and speed planner. In order to restrain possible oscillation of steering angle, a vehicle dynamic model with preview is applied. It is transformed into a standard form of state space and can be directly used in control. Considering the control runs at a higher frequency than planning, a progression method coordinating these two parts is applied, which bases on time points on the trajectory and matches points with vehicle position after preview. The simulation results demonstrate improvement on the smoothness of steering angle. And vehicle's lateral error on tracking trajectory is kept small.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Time-Domain Frequency Estimation Approach for Intelligent control Systems

Time-Domain Frequency Estimation Approach for Intelligent Co...

引用

IEEE International Conference on Industrial technology (ICIT)

作者： Mingyi Huo Xinyu Qiao Hao Wang Yuchen Jiang Hao Luo Department of Control Science and Engineering Harbin Institute of Technology Harbin China

Health status of components of equipments in intelligent control systems affects the operation of systems and the quality of products. In the process of monitoring intelligent control systems, signal frequency analysis is often used to determine whether the equipment is faulty. Therefore, it is crucial to estimate the frequency of the operating signals effectively. Considering the disturbance and noise, a time-domain robust frequency estimation approach is proposed in this paper. Different from the frequency-domain methods, the proposed approach can estimate the frequencies of signal by constructing the subspace of disturbance and using the eigenvalue identification, which avoids the spectral leakage problem caused by the traditional frequency-domain method and has the advantage of simple calculation. Furthermore, the proposed approach can also reconstruct the original signal through the oblique projection. Finally, the effectiveness and feasibility of the approach are verified, which has a certain reference value.

关键词：

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：