检索结果-内蒙古大学图书馆

Inductive Representation Learning on Dynamic Stock Co-Movement Graphs for Stock Predictions

INFORMS JOURNAL ON COMPUTING 2022年第4期34卷 1940-1957页

作者： Tian, Hu Zheng, Xiaolong Zhao, Kang Liu, Maggie Wenjing Zeng, Daniel Dajun Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Chinese Acad Sci Sch Artificial Intelligence Beijing 100190 Peoples R China Univ Iowa Tippie Coll Business Dept Business Analyt Iowa City IA 52242 USA Tsinghua Univ Sch Econ & Management Beijing 100084 Peoples R China

Co-movement among individual firms' stock prices can reflect complex inter-firm relationships. This paper proposes a novel method to leverage such relationships for stock price predictions by adopting inductive graph representation learning on dynamic stock graphs constructed based on historical stock price co-movement. To learn node representations from such dynamic graphs for better stock predictions, we propose the hybrid-attention dynamic graph neural network, an inductive graph representation learning method. We also extended mini-batch gradient descent to inductive representation learning on dynamic stock graphs so that the model can update parameters over mini-batch stock graphs with higher training efficiency. Extensive experiments on stocks from different markets and trading simulations demonstrate that the proposed method significantly improves stock predictions. The proposed method can have important implications for the management of financial portfolios and investment risk.

关键词： graph representation learning deep learning predictive models business intelligence

来源：评论

学校读者我要写书评

暂无评论

Parallel-Data-Based Social Evolution Modeling

引用

Tsinghua Science and Technology 2021年第6期26卷 878-885页

作者： Weishan Zhang Zhaoxiang Hou Xiao Wang Zhidong Xu Xin Liu Fei-Yue Wang China University of Petroleum Qingdao 266580China Qingdao Academy of Intelligent Industry Qingdao 266111China State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100049China Institute of National Security National Defense UniversityBeijing 100081China

Abnormal or drastic changes in the natural environment may lead to unexpected events,such as tsunamis and earthquakes,which are becoming a major threat to national ***,no effective assessment approach can deduce a situation and determine the optimal response strategy when a natural disaster *** this study,we propose a social evolution modeling approach and construct a deduction model for self-playing,self-learning,and self-upgrading on the basis of the idea of parallel data and reinforcement *** proposed approach can evaluate the impact of an event,deduce the situation,and provide optimal strategies for *** the breakage of a submarine cable caused by earthquake as an example,we find that the proposed modeling approach can obtain a higher reward compared with other existing methods.

关键词： paral el data reinforcement learning decision-making

来源：评论

学校读者我要写书评

暂无评论

Advanced Point Cloud Techniques for Improved 3D Object Detection: A Study on DBSCAN, Attention, and Downsampling

引用

WORLD ELECTRIC VEHICLE JOURNAL 2024年第11期15卷

作者： Zhang, Wenqiang Dong, Xiang Cheng, Jingjing Wang, Shuo Anhui Univ Sch Elect Engn & Automat Hefei 230601 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China

To address the challenges of limited detection precision and insufficient segmentation of small to medium-sized objects in dynamic and complex scenarios, such as the dense intermingling of pedestrians, vehicles, and various obstacles in urban environments, we propose an enhanced methodology. Firstly, we integrated a point cloud processing module utilizing the DBSCAN clustering algorithm to effectively segment and extract critical features from the point cloud data. Secondly, we introduced a fusion attention mechanism that significantly improves the network's capability to capture both global and local features, thereby enhancing object detection performance in complex environments. Finally, we incorporated a CSPNet downsampling module, which substantially boosts the network's overall performance and processing speed while reducing computational costs through advanced feature map segmentation and fusion techniques. The proposed method was evaluated using the KITTI dataset. Under moderate difficulty, the BEV mAP for detecting cars, pedestrians, and cyclists achieved 87.74%, 55.07%, and 67.78%, reflecting improvements of 1.64%, 5.84%, and 5.53% over PointPillars. For 3D mAP, the detection accuracy for cars, pedestrians, and cyclists reached 77.90%, 49.22%, and 62.10%, with improvements of 2.91%, 5.69%, and 3.03% compared to PointPillars.

关键词： autonomous vehicles attention mechanism DBSCAN CSPNet PointPillars

来源：评论

学校读者我要写书评

暂无评论

Robotic Autonomous Grasping Technique: A Survey 5

Robotic Autonomous Grasping Technique: A Survey

引用

5th Asian Conference on Artificial Intelligence Technology, ACAIT 2021

作者： Wang, Lili Zhang, Zhen Su, Jianhua Gu, Qipeng School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China State Key Lab. of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665426305

This paper provides a comprehensive survey of robotic autonomous grasping techniques. We summarize three key tasks: grasp detection, affordance detection, and model migration. Grasp detection determines the graspable area and grasping posture of the manipulator, so that the robot can successfully perform the grasps. The grasp detection methods based on deep learning are divided into 3DoF grasp and 6DoF grasp. The object affordances based grasping methods can further improve the robot's understanding of objects and environment, thereby improving the robot's intelligence and autonomy. Methods for object affordances detection are classified as learning-based, knowledge-based, and simulation-based. Model migration means that when the grasping model is migrated to other scenes where lightness and background changes, only little or no label data is required, so that the grasping model can be used in the target scene quickly and efficiently. This paper focuses on domain adaptation (DA) methods in model migration. © 2021 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

controlling the depth of a gliding robotic dolphin using dual motion control modes

引用

Science China(Information Sciences) 2020年第9期63卷 217-230页

作者： Jian WANG Zhengxing WU Min TAN Junzhi YU State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences University of Chinese Academy of Sciences State Key Laboratory for Turbulence and Complex System Department of Mechanics and Engineering ScienceBIC-ESAT College of Engineering Peking University

This paper investigates the performance of the dual mode, namely flipper mode and central pattern generator(CPG) mode, for controlling the depth of a gliding robotic dolphin. Subsequent to considering the errors in dynamic models, we propose a depth control system that combines the line-of-sight(LOS)method with an adaptive control approach(ACA) to deal with uncertainties in the model parameters. First,we establish a full-state dynamic model to conduct simulations and optimize the parameters used in later aquatic experiments. Then, we use the LOS method to transform the control target from the depth to the pitch angle and employ the ACA to calculate the control signal. In particular, we optimize the ACA’s control parameters using simulations based on our dynamic model. Finally, our simulated and experimental results demonstrate not only that we can successfully control the robotic dolphin’s depth, but also that its performance was better than that of the CPG-based control, thus indicating that we can achieve three-dimensional motion by combining flipper-based and CPG-based control. The results of this study suggest valuable ideas for practical applications of gliding robotic dolphins.

关键词： gliding robotic dolphin depth control dual motion adaptive control approach

来源：评论

学校读者我要写书评

暂无评论

Real-time In-situ Defect Detection in 3D Printing of Continuous Fiber-Reinforced Composites 4

Real-time In-situ Defect Detection in 3D Printing of Continu...

引用

4th IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2024

作者： Yue, Zhijian Shen, Zhen Dong, Xiangyang Fang, Qihang Wang, Weixing Dong, Xisong Xiong, Gang Wang, Fei-Yue University of Chinese Academy of Sciences School of Artificial Intelligence Beijing100049 China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing Engineering Research Center of Intelligent Systems and Technology Institute of Automation Beijing100190 China Qingdao Academy of Intelligent Industries Intelligent Manufacturing Center Qingdao266109 China Chinese Academy of Sciences Guangdong Engineering Research Center of 3D Printing and Intelligent Manufacturing Cloud Computing Center Dongguan523808 China Chinese Academy of Sciences State Key Laboratory for Management and Control for Complex Systems Institute of Automation Beijing100190 China

ISBN: (纸本)9798350349252

With the development of continuous fiber-reinforced composites (CFRCs) 3D printing technology, timely, efficient and accurate detection of fiber path defects is essential for ensuring product quality and performance. However, challenges still need to be addressed in this field, such as inadequate training data coverage and the complexity of fiber path structures. These factors hinder the capability of traditional methods to accurately assess the status of printed products. Therefore, developing accurate and robust fiber path defect detection techniques is crucial for CFRCs 3D printing technology. In this paper, we propose a precise detection method for fiber path defects in CFRCs 3D printing using the YOLOv7 object detection model combined with a Squeeze-and-Excitation (SE) attention mechanism. By introducing the SE attention mechanism, we enhance the perception capability of the YOLOv7 model for crucial features, thereby improving the accuracy of fiber path defect detection. The experimental results show that the YOLOv7 model, when augmented with an attention mechanism, achieves an average accuracy of 93.9% in identifying fiber path defects during the printing process. Compared to models without this attention mechanism, the results show that there is 10.7% increase, with a notably enhanced learning capacity during the training phase, which substantiates the efficacy and practicality of the proposed approach. © 2024 IEEE.

关键词： Fiber reinforced plastics

来源：评论

学校读者我要写书评

暂无评论

Point Cloud Completion by Larger Receptive Fields for Intelligent Vehicles 26

Point Cloud Completion by Larger Receptive Fields for Intell...

引用

IEEE 26th International Conference on Intelligent Transportation systems (ITSC)

作者： Zhang, Yunqing Liu, Kunhua Zhang, Xiaotong Lv, Yisheng He, Wei Chen, Long Sun Yat Sen Univ Sch Comp Sci & Engn Guangzhou 510275 Peoples R China Qingdao Univ Technol Sch Mech & Automot Engi neering Qingdao 266520 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing 100190 Peoples R China Univ Sci & Technol Beiing Sch Intelligence Sci & Technol Beijing 100083 Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Con trol Complex Syst Beijing 100864 Peoples R China Waytous Inc Beijing 100083 Peoples R China

ISBN: (纸本)9798350399462

Point cloud completion is a critical task for intelligent vehicles in the Intelligent Transportation systems (ITS). Due to the disordered nature of point clouds, current point-based point completion methods utilize max pooling operations and Convolutional Neural Networks (CNNs) with a convolution kernel size of 1 to extract point features. However, a network with a kernel size of 1 has a small receptive field and can only extract one point feature at a time;as a result, such a network struggles to precisely extract highly abstracted features. To address this issue, we propose a point cloud completion network with larger receptive fields, termed PLRF-Net, which is composed of two parts: a reconstruction network and a completion network. The reconstruction network focuses on repairing the structures of partial points and includes an offset-attention embedding module, a rearrangement module, several convolution layers with varying kernel sizes, a pooling and repeating layer, and transposed convolution layers with different kernel sizes. Meanwhile, the completion network strives to improve the precision of the completed point cloud and consists of several convolution layers, along with a downsampling and upsampling module. Experimental results indicate that our approach achieves superior quantitative and qualitative outcomes on both the Multiview Partial Point Cloud (MVP) and KITTI datasets.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Forming Circle Formations of Multi-agent systems Under Actuator Faults 5th

Forming Circle Formations of Multi-agent Systems Under Actu...

引用

5th Chinese Conference on Swarm Intelligence and Cooperative control, CCSICC 2021

作者： Liu, Jiajun Ru, Xinfeng Xia, Weiguo Wang, Chen China National Aeronautical Radio Electronic Research Institute and National Key Laboratory of Science and Technology on Avionics System Integration Shanghai China Key Laboratory of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education and School of Control Science and Engineering Dalian University of Technology Dalian China National Engineering Research Center of Software Engineering and the State Key Laboratory of Turbulence and Complex Systems Intelligent Biomimetic Design Lab College of Engineering Peking University Beijing China

ISBN: (纸本)9789811939976

A distributed fault-tolerant formation control law is designed in this paper for multi-agent systems under external disturbances and actuator faults including time-varying loss of effectiveness faults. The initial position of each agent is already on a circle and the control purpose is to form a desired formation on this circle. Based on this local information, a distributed adaptive formation control law is designed by employing the congelation of variables method to deal with time-varying actuator faults. Finally, a simulation example is given to verify the effectiveness of the adaptive fault-tolerant control design method. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection in digital twin model 1

Anomaly detection in digital twin model

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Wang, Yutong Cao, Yansong Wang, Fei-Yue Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China Macau Institute of Systems Engineering Macau University of Science and Technology China

ISBN: (纸本)9781665433372

As the simulation model of a physical system, digital twin has been widely used in many complicated control systems. Providing an effective way to perform simulation, digital twin makes the evaluation, prediction and optimization process cheaper and easier than on physical systems. For smart manufacturing, digital twin achieves high productivity with less operation and maintenance cost. However, the advantages of digital twin in anomaly detection during manufacturing are always neglected. Taking a two-speed transmission system as an example, we generate three kinds of faults on this digital twin model. After extracting features from the system output, we train an anomaly detection model on these features to classify each type of fault. By this digital twin model, we can find the fault in the whole system at the very beginning, and reduce the time and cost of debugging and diagnosing. © 2021 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Continuous grip force estimation from surface electromyography using generalized regression neural network

引用

TECHNOLOGY AND HEALTH CARE 2023年第2期31卷 675-689页

作者： Mao, He Fang, Peng Zheng, Yue Tian, Lan Li, Xiangxin Wang, Pu Peng, Liang Li, Guanglin Shenzhen Inst Adv Technol CAS Key Lab Human Machine Intelligence Synergy Sy Shenzhen Guangdong Peoples R China Univ Chinese Acad Sci Shenzhen Coll Adv Technol Shenzhen Guangdong Peoples R China Shenzhen Engn Lab Neural Rehabil Technol Shenzhen Guangdong Peoples R China Sun Yat Sen Univ Dept Rehabil Med Affiliated Hosp 7 Shenzhen Guangdong Peoples R China Chinese Acad Sci Inst Automat State Key Lab Management & Control Complex Syst Beijing Peoples R China

BACKGROUND: Grip force estimation is highly required in realizing flexible and accurate prosthetic control. OBJECTIVE: This study presents a method to accurately estimate continuous grip force from surface electromyography (sEMG) under three forearm postures for unilateral amputees. METHODS: Ten able-bodied subjects and a transradial amputee were recruited. sEMG signals were recorded from six forearm muscles on the dominant side of each able-bodied subject and the stump of amputee. Meanwhile, grip force was synchronously measured from the ipsilateral hands of able-bodied subjects and contralateral hand of amputee. Three force profiles (triangle, trapezoid, and fast triangle) were tested under three forearm postures (supination, neutral and pronation). Two algorithms (Generalized Regression Neural Network (GRNN) and Multilinear Regression Model (MLR)) were compared using several EMG features. The estimation performance was evaluated by coefficient of determination ( R2) and mean absolute error (MAE). RESULTS: The optimal regressor combining TD and GRNN achieved R-2 = 96.33 +/- 1.13% and MAE = 2.11 +/- 0.52% for the intact subjects, and R-2 = 86.86% and MAE = 2.13% for the amputee. The results indicated that multiple grip force curves under three forearm postures could be accurately estimated for unilateral amputees using mirrored bilateral training. CONCLUSIONS: The proposed method has the potential for precise force control of prosthetic hands.

关键词： Electromyography amputees rehabilitation machine learning

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：