检索结果-内蒙古大学图书馆

第三十九届中国控制会议

作者： Feng Liu Chang Chen Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In this paper, to avoid the problem of local optimization and slow convergence in complex environment, a reinforcement learning algorithm is proposed to solve the problem. A robot path planning model is built and its feasibility is verified by simulation. In addition, this paper proposes a deep environment to neural network for robot camera to establish a deep reinforcement learning path planning model, and establishes a deep recursive Q-network（DRQN） and Deep Dueling Q-network（DDQN）respectively. In the comparison of the final simulation results, DRQN needs to consume more computation time, but can achieve better results with higher accuracy.

关键词： Reinforcement learning path planning robots deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review

arXiv

引用

arXiv 2021年

作者： Wu, Dongrui Xu, Jiaxin Fang, Weili Zhang, Yi Yang, Liuqing Xu, Xiaodong Luo, Hanbin Yu, Xiang The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China The College of Public Administration Huazhong University of Science and Technology Wuhan430074 China The University of Michigan Ann ArborMI48109 United States The School of Management and Sino European Institute for Intellectual Property Huazhong University of Science and Technology Wuhan430074 China

Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, adaptive automation, health informatics, and physiological signal based biometrics. Physiological computing increases the communication bandwidth from the user to the computer, but is also subject to various types of adversarial attacks, in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output, leading to possible user confusion, frustration, injury, or even death. However, the vulnerability of physiological computing systems has not been paid enough attention to, and there does not exist a comprehensive review on adversarial attacks to them. This paper fills this gap, by providing a systematic review on the main research areas of physiological computing, different types of adversarial attacks and their applications to physiological computing, and the corresponding defense strategies. We hope this review will attract more research interests on the vulnerability of physiological computing systems, and more importantly, defense strategies to make them more secure. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A Fast Compression Algorithm Based on the Variable Block for 3D Point Cloud Data

A Fast Compression Algorithm Based on the Variable Block for...

引用

International Conference on Advanced Robotics and Mechatronics (ICARM)

作者： Zunran Wang Chenguang Yang Long Cheng Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

In this paper, a fast compression algorithm based on the variable block for 3D point cloud data is proposed, the key of the method is to reduce the temporal redundancy through finding the temporal correlation between the two consecutive frames. The first, the macroblock is generated by voxelizing the point cloud data. Then, the two consecutive frames are aligned, and the corresponding macroblocks inside the two consecutive frames are preliminarily judged whether they are consistent according to the point number of the macroblock and the color variance. Finally, the ICP algorithm is exploited to further match the two macroblocks. When the result of the ICP algorithm is lower than the Threshold, the macroblock in the current frame is replaced by the motion vectors for compressing the point cloud data. The motion vectors are acquired by the ICP algorithm applied for the corresponding macroblock between two consecutive frames. The Predicted-frame (P frame) consists of the motion vectors and no matched macroblock in the current frame while the Intra-frame (I frame) is the point cloud data. In our method, in order to improve the compression ratio, the size of the macroblock is set as a variable parameter. The experimental results demonstrate that the time delay will be decreased, meantime the compression ratio will be increased in our method. The visual result of our method also will be more smooth and the performance of our method is better than the state-of-the-art method.

关键词： Three-dimensional displays Octrees Image color analysis Iterative closest point algorithm Prediction algorithms Encoding Transforms

来源：评论

学校读者我要写书评

暂无评论

Robust Integrated optimization of Active Distribution Network Based on System Risk Index

Robust Integrated optimization of Active Distribution Networ...

引用

IEEE Student Conference on Electric Machines and Systems

作者： Yumin Zhang Haishu Gao Xingquan Ji Qi Liu Yixiao Yu College of Electrical Engineering and Automation Shandong University of Science and Technology Qingdao China Key Laboratory of Smart Grid of Ministry of Education Tianjin University Tianjin China Key Laboratory of Power System Intelligent Dispatch and Control Shandong University Jinan China

ISBN: (数字)9781728156224

ISBN: (纸本)9781728156231

This paper presents a comprehensive distribution robust optimization model based on the distribution network risk index to address the distributional uncertainties of distributed generations (DGs) and loads. To analyze the security of active distribution network (ADN) systematically, a risk assessment method based on improved semi-invariant method and clustering technique is proposed. The risk assessment method is performed on the integrated dynamic reconfiguration and reactive power optimization model. This method can consider the correlation between distributed power sources, and when the injected power is large, the calculation results with higher accuracy can be obtained Case studies on the PG&E 69-bus system verify the robustness and feasibility of the proposed model.

关键词： Uncertainty Power supplies Computational modeling Risk management Indexes Optimization Load modeling

来源：评论

学校读者我要写书评

暂无评论

Effects of cultivar selection, cultivation region and harvest timing on the structure and properties of carbohydrates from Saccharina japonica

引用

Algal Research 2025年 89卷

作者： Tian, Mingjie Kong, Yueqi Duan, Delin Shim, Soon-Mi Fu, Xiaoting State Key Laboratory of Marine Food Processing & Safety Control College of Food Science and Engineering Ocean University of China 1299th Sansha Road Qingdao 266000 China Key Lab of Breeding Biotechnology & Sustainable Aquaculture Shandong Province Key Laboratory of Experimental Marine Biology Institute of Oceanology Chinese Academy of Sciences Qingdao 266071 China Functional Lab for Marine Biology and Biotechnology National Laboratory for Marine Science and Technology Qingdao 266071 China Department of Food Science and Biotechnology Sejong University 209 Neungdong-Ro Kwangjin-Gu Seoul 05006 South Korea

The study aimed to explore the difference of yields, structures, and functions of three carbohydrates in Saccharina japonica (S. japonica), considering the differences of cultivars of Haiza (the northern cultivar) and Puke (the southern cultivar), cultivation regions (the north, the south, and the transplanted Puke from south to north), and harvesting times during their whole cultivation. The yield of mannitol was significantly higher in samples cultivated in the north region (5.07–27.82 %) compared to those from the south (2.34–3.37 %), and for both cultivars the optimal yield was in May and June. The molecular weight of alginate was lower in Puke but higher in both Haiza and the transplanted Puke. The mannuronate/guluronate ratio of alginate noticeably deceased from levels of 2.28–2.40 to levels of 1.68–1.93 after transplantation Puke from the south to north, which indicated the possible upregulation of the expression of genes encoding mannuronate C5-epimerases in colder temperature cultivation. Meanwhile, different fucoidan samples showed diverse monosaccharide composition, sulfate content, sulfation positions, and antioxidant activities. Fucoidans from Haiza showed better ABTS and hydroxyl radical scavenging ability. The correlation analysis indicated that the fucose content was positively correlated with ABTS radical scavenging ability (R = 0.576), while fucose and sulfate group contents were negatively correlated with the hydroxyl radical scavenging ability (R = 0.581 and R = 0.829). Overall, this study deepened the understanding of carbohydrates diversity in S. japonica and provided a scientific foundation for optimizing its cultivation strategies. © 2025

关键词： Antioxidant activity Carbohydrates Chemical characteristics Cultivation Diversity Saccharina japonica

来源：评论

学校读者我要写书评

暂无评论

Intelligent survey method of rice diseases and pests using AR glasses and image-text multimodal fusion model

引用

Computers and Electronics in Agriculture 2025年 237卷

作者： Chen, Xiangfu Yang, Baojun Liu, Yongjian Feng, Zelin Lyu, Jun Luo, Ju Wu, Jian Yao, Qing Liu, Shuhua School of Computer Science and Technology Zhejiang Sci-Tech University Hangzhou310018 China State Key Laboratory of Rice Biology and Breeding China National Rice Research Institute Hangzhou311401 China School of Information and Control Keyi College of Zhejiang Sci-Tech University Hangzhou310018 China School of Information Science and Engineering Zhejiang Sci-Tech University Hangzhou310018 China

The timely and accurate detection of the occurrence types and dynamics of rice diseases and insect pests in the field is a fundamental requirement for effective scientific prevention and control. Currently, survey methods rely heavily on the expertise and experience of surveyors, leading to challenges such as limited data traceability, high labor demands, and low efficiency. The complex environmental conditions in rice fields, coupled with the diversity of pests and diseases—many of which coexist and exhibit significant intraspecies variation and interspecies similarities—further complicate detection efforts. When identification models are trained using only a limited set of image samples, they often suffer from poor generalization, undermining the accuracy of pest and disease forecasts. To overcome these challenges, a rapid, efficient, and precise intelligent survey method using AR glasses and image-text multimodal fusion model to detect rice pests and diseases was proposed. The AR glasses have advantages of wearable, hands-free, voice-control functions, which is very convenient to collect rice images in paddy fields. An image-text multimodal fusion model with two stages, RDP-Detector, was developed to improve the detection accuracy rates of rice pest and disease lesions in the images. In the first stage, the improved YOLOv5X model with AF-FPN, Decoupled Head and Soft-NMS post-processing achieved improvements in detection ability. In the second stage, text modalities are introduced, and Prompt tuning is used to perform transfer learning for downstream tasks on the basis of the CLIP model. To improve the accuracy of pest detection, the detection boxes with low confidence in the first stage are subjected to reidentification in the second stage. Compared with the state of the art models, the RDP-Detector achieved an precision, recall, and mAP of 82.3 %, 86.5 %, and 87.4 %, respectively, on the detection of seven rice pests and diseases. Compared with the object detect

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Triple-Atom Sites Combined with Oxygen Vacancy for Selective Photocatalytic Conversion of CO2to Propionic Acid

引用

Angewandte Chemie 2025年

作者： Haiwei Su Haibo Yin William Orbell Yuqing Li Guoliang Wang Yunlong Wang Kohsuke Mori Zhen Chen Hexing Li Hiromi Yamashita Junhua Li State Key Joint Laboratory of Environment Simulation and Pollution Control School of Environment Tsinghua University Beijing 100084 P. R. China School of Resources and Environmental Engineering Wuhan University of Technology Wuhan 430070 P. R. China Division of Materials and Manufacturing Science Graduate School of Engineering Osaka University Osaka 565-0871 Japan Key Laboratory of Resource Chemistry of Ministry of Education College of Chemistry and Materials Science Shanghai Normal University Shanghai 200234 P. R. China

Photocatalytic CO 2 reduction to multicarbon products is an emerging approach for achieving carbon neutrality; however, the design of active sites that effectively promote multistep C−C coupling remains a challenge. Here, we propose a straightforward defect engineering approach to construct asymmetric triple-atom sites (Cu-Cu δ+ -W δ+ ) on CuWO 4 with oxygen vacancies (OVs) (named CWO-OVs). The optimized CWO-OVs achieve a photochemical synthesis rate of propionic acid (C 3 H 6 O 2 , PA) of 86.46±2.92 μmol g −1 h −1 , with an electron-based selectivity of 89.27 %, which exhibits a remarkable advantage in the field of photocatalytic CO 2 reduction to C 2+ products. Experimental results and density functional theory calculations corroborate the prominent role of OVs in inducing the triple-atom sites: (1) the asymmetric Cu-Cu δ+ triggers the first step of C 1 -C 1 coupling to form *CH 2 CH 3 ; (2) Cu δ+ -W δ+ facilitates subsequent C 2 -C 1 bonding, ultimately leading to PA production. This charge-asymmetric cascade reaction system offers new insights into the design of efficient photocatalysts for the synthesis of multi-carbon products.

关键词： Photocatalytic CO2 reduction Oxygen vacancies Asymmetry sites Triple-atom sites Propionic acid

来源：评论

学校读者我要写书评

暂无评论

Neural network control using composite learning for USVs with output error constraints

Neural network control using composite learning for USVs wit...

引用

2019 IEEE International Conference on Unmanned Systems and Artificial Intelligence, ICUSAI 2019

作者： Xu, Puyong Yang, Chenguang Dai, Shi-Lu Mao, Zhaoyong Key Laboratory of Autonomous Systems and Networked Control College of Automation Science and Engineering South China University of Technology Guangzhou China Unmanned System Research Institute Northwestern Polytechnical University Xi'an China

ISBN: (纸本)9781728158594

In this paper, by focusing on trajectory tracking control of unmanned surface vessel (USV), we present a control method considering uncertain dynamics and output error constrains. Firstly, by using the properties of tan-type barrier Lyapunov function (BLF), the output tracking error can be constrained. Secondly, we use radical basis function neural network (RBF NN) to approximate the uncertain dynamics. Considering that the estimated parameters convergence cannot be achieved in the absence of persistent excitation (PE) conditions, the composite learning update law of the weight matrix in the NN is adopted to guarantee the parameters convergence under interval excitation (IE) conditions which is easier to reach. In simulation studies, it is proven that the USV have good ability to follow the pre-designed trajectory with small tracking error and the parameters convergence can be ensured. © 2019 IEEE.

关键词： Lyapunov functions

来源：评论

学校读者我要写书评

暂无评论

Improved potential field method path planning based on genetic algorithm

Improved potential field method path planning based on genet...

引用

第三十九届中国控制会议

作者： Feng Liu Hualing He Zhihua Li Zhi-Hong Guan Hua O Wang School of Automation China University of Geosciences Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems College of Automation Huazhong University of Science and Technology Department of Mechanical Engineering Boston University

In order to overcome the problem of path planning failure in traditional potential field method, an improved potential field path planning method based on genetic algorithm is proposed in this paper. Firstly, for the problem of inaccessibility of the target, a factor method is added to the traditional gravity function to solve it;then the local minimum point problem of the traditional artificial potential field method is solved to ensure that the robot can reach the target point. At the same time, in order to get the optimal path, genetic algorithm is used to optimize the combined potential field function of gravity and repulsion, to find the lowest point of potential energy directly, so as to determine the step size and moving direction of the robot. Simulation is carried out to verify the effectiveness of the method.

关键词： Path planning artificial potential field gravitation function genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Gas sensor fault diagnosis based on Convolutional Neural Network

Gas sensor fault diagnosis based on Convolutional Neural Net...

引用

第三届材料科学应用与能源材料国际研讨会

作者： Yongyi Sun Yangyang Liu Fang Ji Gang Li Yanjun Ma Jin Li Lixin Yang Hongquan Zhang Key Laboratory of Electronics Engineering College of Heilongjiang Province Heilongjiang University Department of Public security information Liaoning Police Collage School of Information Technology Guangxi Police College School of electrical and control engineering Heilongjiang University of Science & Technology School of Automation Harbin Engineering University

Gas sensor often fails due to the influence of temperature, humidity, lighting, dust and toxic gases, and causes unreliable phenomena. Therefore, the fault diagnosis of gas sensors is considered as a weak link. Feature extraction and classification play an important role in gas sensor fault diagnosis. However, there are many problems in traditional feature extraction methods. For example, 1) requirements for expert experience, 2) sensitivity of changes in mechanical systems, 3) limitations of new feature extraction. Therefore, it is meaningful and attractive to develop a method that can discover and learn fault-sensitive features of gas sensors from the original data and classify them effectively according to the sensitive features. Convolutional neural network(CNN) has been widely applied in image analysis and voice recording, and has achieved great success. However, gas sensor fault diagnosis is rarely applied. This paper focuses on using CNN to learn fault features from data, extract features automatically, and then classify them effectively. Experiments show that the CNN method provides a effective solution for gas sensor fault diagnosis.

关键词： Gas sensor fault diagnosis based on Convolutional Neural Network

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：