检索结果-内蒙古大学图书馆

Chinese automation Congress (CAC)

作者： Qiang Li Xiwei Liu Xiaoyan Gong Sifeng Jing The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Institute of Smart Education Systems Qingdao Academy of Intelligent Industries BeiJing China

In recent years, with the rapid development of computer technology, facial expression recognition technology has gradually been applied to primary and secondary schools. This article first introduces the application of facial expression recognition in education. Then the development of facial expression recognition and the four basic processes of facial expressions are described. After that, the methods and algorithms used in face detection and localization of face expression recognition and classification are summarized, feature extraction and classification are summarized. Finally, the current application of facial expression recognition technology in education and the existing problems and future development are pointed out.

关键词： Face recognition Classification algorithms Feature extraction Education Hidden Markov models Face detection Face

来源：评论

学校读者我要写书评

暂无评论

GPO: Global plane optimization for fast and accurate monocular SLAM initialization

arXiv

引用

arXiv 2020年

作者： Du, Sicong Guo, Hengkai Chen, Yao Lin, Yilun Meng, Xiangbing Wen, Linfu Wang, Fei-Yue PA2R2T Group State Key Laboratory of Complex System Management and Control Institute of Automation Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing10049 China ByteDance AI Lab Beijing100089 China

Initialization is essential to monocular Simultaneous Localization and Mapping (SLAM) problems. This paper focuses on a novel initialization method for monocular SLAM based on planar features. The algorithm starts by homography estimation in a sliding window. It then proceeds to a global plane optimization (GPO) to obtain camera poses and the plane normal. 3D points can be recovered using planar constraints without triangulation. The proposed method fully exploits the plane information from multiple frames and avoids the ambiguities in homography decomposition. We validate our algorithm on the collected chessboard dataset against baseline implementations and present extensive analysis. Experimental results show that our method outperforms the fine-tuned baselines in both accuracy and real-time. Copyright © 2020, The Authors. All rights reserved.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

Capsule Network-Based Text Sentiment Classification

引用

IFAC-PapersOnLine 2020年第5期53卷 698-703页

作者： Bingyang Chen Zhidong Xu Xiao Wang Long Xu Weishan Zhang School of Computer Science and Technology China University of Petroleum Qingdao 266580 China School of security National Defence University PLA China Beijing 100091 China Beijing 100091 China Qingdao Academy of Intelligent Industries Shandong Qingdao 266109 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China

To improve text sentiments classification issues, such as information loss and insensitivity to spatial information, this paper proposes a text sentiment classification model based on the capsule network (T-Caps), which uses the Transformer to extract low-level text features. The method iteratively updates capsule network parameters through optimized dynamic routing algorithms and global parameter sharing, and it obtains the relationship between local features of the text and the overall emotional polarity to save the information integrity of text features. By comparing with multiple models, we find that the Transformer has the strongest feature extraction capability. The experimental results show that our model is capable of extracting more discriminative semantic features and yields a significant performance gain compared to other baseline methods.

关键词： Sentiment classification Capsule network Transformer Deep learning Attention

来源：评论

学校读者我要写书评

暂无评论

SmartPV-AIoT: an AIoT-integrated framework for fault diagnosis and remote monitoring in photovoltaic systems

引用

Energy Conversion and management: X 2025年

作者： Ehtisham Lodhi Xiaoli Liu Gang Xiong M. Adil Khan Zeeshan Lodhi Tahir Nawaz Adil Dilawar Sasu Tarkoma Feiyue Wang Zhejiang University-University of Illinois Urbana-Champaign Institute International Campus Haining 314400 China The SKL for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Computer Science University of Helsinki Helsinki 00560 Finland School of Transportation Fujian University of Technology Fuzhou China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China Department of Computer Science COMSATS University Islamabad Abbottabad Campus 22060 Pakistan Department of Electronics Technology University of Technology Nowshera 24100 Pakistan Department of Mechatronics Engineering National University of Sciences and Technology H-12 Islamabad 44000 Pakistan The SKL of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources Research Chinese Academy of Sciences Beijing 100101 China The Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Chinese Academy of Sciences Beijing 100190 China

This paper presents SmartPV-AIoT, a cost-effective and edge-computing-based framework for real-time fault detection and environmental monitoring in photovoltaic (PV) systems. Addressing the challenges faced in remote or intermittently connected environments, the proposed system integrates electrical and environmental sensor data using a Raspberry Pi 4 and NodeMCU microcontroller. A lightweight Res-BiLSTM model, combining residual learning and bidirectional long short-term memory (BiLSTM) layers, is deployed at the edge to perform local fault classification by analyzing seven key parameters derived from I to V curve measurements and ambient conditions. Additionally, the framework employs multi-sensor data fusion by integrating voltage, current, irradiance, and temperature measurements to support comprehensive fault detection and predictive maintenance. The framework was validated on a 4.56  kW PV installation using a dataset of 2400 labeled samples representing normal operation, open-circuit, short-circuit, and partial shading conditions. The classifier achieved a fault detection accuracy of 96.67 %, with a maximum inference latency of 290  ms and low power overhead, making it suitable for real-time, on-site diagnostics. The system supports offline operation with automatic data synchronization upon connectivity restoration and includes mobile-based monitoring for remote accessibility. The proposed framework is designed for modular deployment and scales linearly with array size. Overall, SmartPV-AIoT offers a scalable, resilient, and practical solution for intelligent PV monitoring, particularly in resource-constrained or off-grid environments.

关键词： Photovoltaic (PV) Artificial Intelligence of Things (AIoT) Green energy resources Deep learning Fault detection Fault classification Monitoring system Edge intelligence

来源：评论

学校读者我要写书评

暂无评论

Robust Graph Neural Networks Against Adversarial Attacks via Jointly Adversarial Training

引用

IFAC-PapersOnLine 2020年第5期53卷 420-425页

作者： Hu Tian Bowei Ye Xiaolong Zheng Desheng Dash Wu The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Department of Statistics University of Illinois in Urbana-Champaign Illinois USA School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China Stockholm Business School Stockholm University SE-106 91 Stockholm Sweden

Graph neural networks (GNNs) are powerful tools for analyzing graph-structured data. However, recent studies have shown that GNNs are vulnerable to small but intentional perturbations of input features and graph structures in the node classification task. Existing researches focus on enhancing the robustness of GNNs for a single type of perturbation such as graph structure perturbation or node feature perturbation. An ideal graph neural networks model should be able to resist the two kinds of perturbations. For this purpose, we propose a new adversarial training method for graph-structured data named Graph Jointly Adversarial Training (GJAT) which incorporates Graph Structure Adversarial Training (GSAT) and Graph Feature Adversarial Training (GFAT) two components and can resist perturbations from the topological structure and node attribute. Extensive experimental results demonstrate that our proposed method combining two kinds of adversarial training strategies can effectively improve the robustness of graph convolutional networks (GCNs) which is an important subset of GNNs.

关键词： Graph neural networks Robustness Adversarial Attack Adversarial Training Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced rolling horizon evolution algorithm with opponent model learning: Results for the fighting game ai competition

arXiv

引用

arXiv 2020年

作者： Tang, Zhentao Zhu, Yuanheng Zhao, Dongbin Lucas, Simon M. State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100049 China Queen Mary University of London LondonE1 4NS United Kingdom

The Fighting Game AI Competition (FTGAIC) provides a challenging benchmark for 2-player video game AI. The challenge arises from the large action space, diverse styles of characters and abilities, and the real-time nature of the game. In this paper, we propose a novel algorithm that combines Rolling Horizon Evolution Algorithm (RHEA) with opponent model learning. The approach is readily applicable to any 2-player video game. In contrast to conventional RHEA, an opponent model is proposed and is optimized by supervised learning with cross-entropy and reinforcement learning with policy gradient and Q-learning respectively, based on history observations from opponent. The model is learned during the live gameplay. With the learned opponent model, the extended RHEA is able to make more realistic plans based on what the opponent is likely to do. This tends to lead to better results. We compared our approach directly with the bots from the FTGAIC 2018 competition, and found our method to significantly outperform all of them, for all three character. Furthermore, our proposed bot with the policygradient-based opponent model is the only one without using Monte-Carlo Tree Search (MCTS) among top five bots in the 2019 competition in which it achieved second place, while using much less domain knowledge than the winner. Copyright © 2020, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Energy Analysis of a CPG-controlled Miniature Robotic Fish

引用

Journal of Bionic Engineering 2018年第2期15卷 260-269页

作者： Junzhi Yu Shifeng Chen Zhengxing Wu Xingyu Chen Ming Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China School of lnformation and Electrical Engineering Shandong Jianzhu University Jinan 250101 China

Bionic robotic fish has a significant impact on design and control of innovative underwater robots capable of both rapid swimming and high maneuverability. This paper explores the relationship between Central Pattern Generator （CPG） based locomotion control and energy consumption of a miniature self-propelled robotic fish. To this end, a real-time energy measurement system compatible with the CPG-based locomotion control is firstly built on an embedded system. Then, tests are conducted on the untethered actual robot. The results indicate that different CPG feature parameters involving amplitude, frequency, and phase lag play distinct roles in energy consumption under different swimming gaits. Specifically, energy consumption is positively correlated with the changes in the amplitude and frequency of CPGs, whereas the phase lag of CPGs has little influence on the energy consumption. It may offer important inspiration for improving energy efficiency and locomotion performance of versatile swimming gaits.

关键词： bionic robotic fish energy analysis Central Pattern Generator （CPG） swimming motion control

来源：评论

学校读者我要写书评

暂无评论

Security Assessment of a Partially Decentralized Blockchain System

Security Assessment of a Partially Decentralized Blockchain ...

引用

2019 IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2019

作者： Liu, Yiwen Ji, Qingqing Zheng, Quankai Wu, Huaiyu Wang, Zhihai Xiong, Gang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing University of Technology Faculty of Information Beijing China University of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Economics Finance and Management University of Bristol Bristol United Kingdom Beijing University of Technology Faculty of Information Beijing China

ISBN: (纸本)9781728128535

As a new technology with subversive significance in the Internet field, blockchain has received extensive attention from research and applications sector in recent years. Its decentralized structure and unchangeable data nature have a wide application prospect in Internet transactions. However, it is difficult to implement supervision in a partially decentralized system. Therefore, a blockchain system with a single or a few central nodes has emerged during the development of blockchain. For such special partially decentralized blockchain systems, more scientific development is needed. This paper takes X insurance trading chain as an example to study this partially decentralized blockchain system, to make a more scientific security assessment of this kind of system, and put forward corresponding countermeasures to improve the security of this kind of system. © 2019 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Path Planning for Surgery Robot with Bidirectional Continuous Tree Search and Neural Network

Path Planning for Surgery Robot with Bidirectional Continuou...

引用

2019 IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Rui-Jian Huang Gui-Bin Bian Chen Xin Zhen Li Zeng-Guang Hou The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing China Beijing Tongren Eye Center Beijing Tongren Hospital Beijing Institute of Ophthalmology

Solving a thorny issue of real-time path planning for surgery robot in uncertain environments, a novel algorithm named bidirectional continuous tree search (BCTS) is proposed. Most partially observable markov decision process (POMDP) planners address challenges of unknown environments with discrete states, observations and actions, which are fail to automate the operative procedure. However, the BCTS method addresses the issue by handling POMDPs in continuous state, observation and action spaces. The proposed approach has a bidirectional search structure with the intent of greatly improving the calculation efficiency. Meanwhile, Bayesian optimization (BO) algorithm is considered to dynamically sample promising actions while we construct a belief tree. In view of the speed of BO process, the upper and lower bounds of the optimal action values given by fast informed bound (FIB) and point-based value iteration (PBVI) limit the search scope, so we can improve the speed of BO. In addition, we apply an optimal path planning generator, radial basis function neural network (RBFNN), to obtain a smoother trajectory. Finally, simulation of glaucoma surgery has been carried out to explore the best surgical approach. The results show that the introduced structure can effectively guide the surgery robot to perform surgical procedures and receive a real-time as well as smooth path.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ordinal Optimization for Optimal Orientation Problems in 3D Printing

引用

IFAC-PapersOnLine 2020年第5期53卷 97-102页

作者： Can Luo Gang Xiong Zhishuai Li Zhen Shen Li Wan MengChu Zhou Fei-Yue Wang State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Chinese Academy of Sciences Donggguan China Ten Dimensions (Guangdong) Technology Co. Ltd. Foshan China Macau University of Science and Technology Taipa Macau

Compared with a traditional manufacturing process, 3D printing has advantages of performance and cost in personalized customization and has been applied in many fields. The problem of 3D model orientation optimization is a crucial one in practice. In this paper, based on the mathematical relationship between model orientation and printing time, surface quality, and supporting area, the model orientation problem is transformed into a multi-objective optimization problem with goal of minimizing printing time, surface quality, and supporting area. Ordinal Optimization (OO) is not only applicable to problems with random factors, but also to solve complex deterministic problems. The model orientation is a complex deterministic problem. We solve it with OO in this paper and use linear weighting to convert the multi-objective optimization problem into single-objective one. Finally, we compare the experimental results of solving 3D model orientation problems solved by OO and Genetic Algorithm (GA). The results show that OO requires less calculation time than GA while achieving comparable performance.

关键词： Digital Manufacturing Genetic Algorithm Intelligent Optimization Machine Learning Ordinal Optimization Orientation Optimization 3D Printing

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：