检索结果-内蒙古大学图书馆

Chinese Control and Decision Conference, CCDC

作者： Lin Qiao Yuanqi Yu Qun Wang Yu Zhang Yueming Song Xiaosheng Yu Department Information Communication Branch of State Grid Liaoning Electric Power Co.Ltd. Shenyang China Faculty of Robot Science and Engineering Northeastern University Shenyang China

The accurate prediction of time series data in the industrial production process can provide important guidance for the scheduling and decision-making of industrial systems, and is also an important part of predictive control technology. In this paper, a time series prediction model which introduces the graph neural network (GCN) is proposed. This model mainly consists of a time series feature extraction module and a relational modeling module. In the time series feature extraction module, the Att-LSTM model is proposed to extract the feature information of time series data. In the relational modeling module, a novel M-GCN network is proposed to model the relevance among different time series nodes. In addition, based on the time series prediction model, a time series multi-classification model is also proposed. The proposed model can predict the energy consumption conditions of the data center accurately. The experimental results demonstrate that the propose model can provide a desirable performance superior to some traditional models in accuracy and robustness.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-person interaction action recognition based on co-occurrence graph convolutional network

Multi-person interaction action recognition based on co-occu...

引用

第34届中国控制与决策会议

作者： Zhongyu Bai Hongli Xu Haopeng Zhang Haitao Gu Faculty of Robot Science and Engineering Northeastern University State Key Laboratory of Robotics Shenyang Institute of AutomationChinese Academy of Sciences

Skeleton-based human action recognition has attracted more and more attention with the accessibility of depth sensors and the development of pose estimation *** recognition of multi-person interaction behavior with skeleton data has wide applications in real ***,the existing skeleton-based action recognition methods mainly focus on single-person actions,and lack the research on the semantic information of the skeleton co-occurrence relationship in the spatial ***,a two-stream co-occurrence graph convolutional network(2 s-CGCN) is proposed for multi-person interactive action *** topological connection structure of the proposed model establishes connections between the human limbs and the head to capture the co-occurrence *** addition,the coordinates and co-occurrence information of the joints are simultaneously input into the *** experiments of mutual actions in the NTU-RGB+D dataset show the effectiveness of the proposed model.

关键词： Action recognition Skeleton sequence Interactive information Graph convolution

来源：评论

学校读者我要写书评

暂无评论

A Propagation Condition Identification and Non-Line of Sight Error Mitigation Algorithm in Wireless Sensor Network 2

A Propagation Condition Identification and Non-Line of Sight...

引用

2019 2nd International Conference on Computer Information science and Artificial Intelligence, CISAI 2019

作者： Chu, Hao Lian, Siyi Yang, Hao Wu, Rongguang Faculty of Robot Science and Engineering Northeastern University Shenyang Liaoning110000 China

Node localization is one of key technologies in wireless sensor networks (WSN). In practice, the occlusion of obstacles often leads to large non-line-of-sight (NLOS) error. Therefore, the misidentification of LOS (line-of-sight)/NLOS conditions can seriously reduce the accuracy of localization algorithms in WSN. In this paper, we propose a novel localization algorithm based on hypothesis testing method, which combines the NLOS condition identification algorithm and the extended Kalman filter method to mitigate the NLOS error. Moreover, we introduce the false alarm rate fa to fuse the estimated values in the LOS/NLOS condition to obtain more accurate results. The simulations demonstrate that the proposed algorithm can effectively reduce the influence of NLOS error and improve the localization accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

PTT: Point-track-transformer module for 3D single object tracking in point clouds

arXiv

引用

arXiv 2021年

作者： Shan, Jiayao Zhou, Sifan Fang, Zheng Cui, Yubo The Faculty of Robot Science and Engineering Northeastern University Shenyang China

3D single object tracking is a key issue for robotics. In this paper, we propose a transformer module called Point-Track-Transformer (PTT) for point cloud-based 3D single object tracking. PTT module contains three blocks for feature embedding, position encoding, and self-attention feature computation. Feature embedding aims to place features closer in the embedding space if they have similar semantic information. Position encoding is used to encode coordinates of point clouds into high dimension distinguishable features. Self-attention generates refined attention features by computing attention weights. Besides, we embed the PTT module into the open-source state-of-the-art method P2B to construct PTT-Net. Experiments on the KITTI dataset reveal that our PTT-Net surpasses the state-of-the-art by a noticeable margin (∼10%). Additionally, PTT-Net could achieve real-time performance (∼40FPS) on NVIDIA 1080Ti GPU. Our code is open-sourced for the robotics community at https: //***/shanjiayao/PTT. © 2021, CC BY.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Capturing Contact Surfaces by a Frustrated Total Internal Reflection System Using a Curved Plate for Comparison of the Beginning of Touching Motions by Humanitude Experts and Novices

Capturing Contact Surfaces by a Frustrated Total Internal Re...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Yuguchi, Akishige Toyoda, Mayuki Cho, Sung-Gwi Nakazawa, Atsushi Takamatsu, Jun Yoshino, Koichiro Ogasawara, Tsukasa Tokyo University of Science Faculty of Advanced Engineering Katsushika-ku Tokyo125-8585 Japan Guardian Robot Project Riken Seika-cho Sorakugun Kyoto619-0288 Japan Nara Institute of Science and Technology Nara Ikoma630-0192 Japan School of Science and Engineering Tokyo Denki University Hatoyama-machi Saitama Hiki-gun350-0394 Japan Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayama University Okayama Kita-ku700-8530 Japan Applied Robotics Research Microsoft Corporation RedmondWA98052 United States

ISBN: (纸本)9781665410205

Analyzing time-series changes of the contact surface by touching is important to elucidate the touching skills of Humanitude as one of the pervasive multimodal comprehensive care methodologies. For the analysis, there is a frustrated total internal reflection (FTIR) method to capture contact surfaces on a transparent flat plate by a camera. However, this conventional flat plate is far from the actual surfaces of care receivers because the surfaces of humans consist of curved shapes. In this paper, we propose an FTIR sensing system using a transparent curved plate to capture more ideal contact states with a surface shape more similar to the human body. We collect the contact surface data of the beginning of touching motions by Humanitude experts and novices using the FTIR sensing system with the curved and flat plates. Then, we compare the data by the experts and novices in terms of time-series contact areas and the quantitative indices and subjective evaluation and discuss the analysis results. Through these experiments, we confirm that the proposed system has the potential for the novices to perform more correctly the beginning of Humanitude's touching motions. © 2024 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection of EMU trains based on line-scan image registration 7

Anomaly detection of EMU trains based on line-scan image reg...

引用

7th Global Intelligent Industry Conference, GIIC 2024

作者： Fang, Lei Shi, Zelin Xiao, Chuanmin Liu, Yunpeng Pang, Mingqi Zhao, Enbo Faculty of Robot Science and Engineering Northeastern University Shenyang110169 China Key Laboratory of Opto-Electronic Information Processing Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China Third Military Representative Room in Shenyang Area Air Force Equipment Shenyang110016 China

ISBN: (纸本)9781510682986

Anomaly detection based on template image registration is one of the methods used to detect anomalies of objects with similar structures. However, the imaging device of the Electronic Multiple Units (EMU) train is a line-scan camera, and the geometric transformation law between its image and the area-scan image is different. The conventional image registration method of the area-scan image cannot accurately align the line-scan image. Moreover, the line-scan image of the EMU train collected in uncontrollable environmental scenes exhibits significant grayscale changes, and the registered images cannot detect differences by directly comparing grayscale. To address these two challenges, this paper proposes a two-stage anomaly detection method based on line-scan image registration and edge comparison. In the registration stage, a coarse-to-fine line-scan image registration method was designed. First, the feature-based registration method was used to achieve coarse position of the EMU train template image in the target image. Then, the direct registration method based on the line-scan image geometric transformation model achieved precise geometric alignment. In the anomaly detection stage, edge information is extracted from the template image and the registered target image, and anomaly detection of EMU trains is achieved through edge comparison, edge expansion, and edge connection. The experimental results on the line-scan image of EMU trains show that the two-stage method proposed in this paper can achieve the registration of line-scan images of EMU trains, and on this basis, achieve detection and segmentation of abnormal areas of EMU trains. © 2024 SPIE.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Vision-Based Indoor Positioning System for Connected Vehicles in Small-scale Testbed Environments

Vision-Based Indoor Positioning System for Connected Vehicle...

引用

IEEE Symposium on Intelligent Vehicle

作者： Mahmoud S. Hamza Omar M. Shehata Elsayed I. Morgan Catherine M. Elias Multi-Robot Systems (MRS) Research Group Cairo Egypt Mechatronics Department Faculty of Engineering and Materials Science German University Cairo Egypt Mechatronics Department Faculty of Engineering Ain Shams University Cairo Egypt Science Department Faculty of Media Engineering and Technology German University Cairo Egypt

ISBN: (数字)9798350348811

ISBN: (纸本)9798350348828

In this paper, we present an innovative indoor positioning system designed for computing the position and orientation of multiple model-scale vehicles. Our system, equipped with four cameras, utilizes a novel image-stitching technique to stitch the images from these cameras into a single output image. We explore diverse methodologies for detecting and estimating the position and orientation of the model-scale vehicles, demonstrating robust detection within the plane. Through rigorous testing with vehicles of varying dimensions, our system achieves an accuracy ranging from approximately 0.5cm to 3cm on both axes. This establishes the system’s potential applicability in scenarios involving model-scale autonomous vehicles, where precise knowledge of each vehicle’s position is critical.

关键词： Connected vehicles Accuracy Computational modeling Cameras Distance measurement Indoor positioning systems Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

FATL: Frozen-feature augmentation transfer learning for few-shot long-tailed sonar image classification

引用

Neurocomputing 2025年

作者： Zhongyu Bai Hongli Xu Qichuan Ding Xiangyue Zhang Faculty of Robot Science and Engineering Northeastern University Shenyang 110819 China

Current deep learning-based approaches for sonar image classification have demonstrated effectiveness in scenarios with abundant and balanced samples. However, real-world applications often face challenges such as few-shot learning and long-tailed distribution due to the inherent limitations of underwater sonar image acquisition. In this work, a Frozen-feature Augmentation Transfer Learning (FATL) framework is proposed for few-shot long-tailed sonar image classification. The feature extractor and classifier are independently frozen during training to improve generalization capability. A frozen-feature augmentation module with contrastive learning is introduced to enrich the representational capacity of the feature space in both value and channel dimensions. In addition, a balanced sampling strategy that divides the training set into multiple balanced subsets is employed to mitigate sample bias during classifier training. Extensive experiments conducted on the three public sonar image datasets (KLSG, FLSMDD, and NKSID) indicate that the proposed FATL framework achieves superior performance and outperforms existing approaches in the few-shot long-tailed sonar image classification task.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperative obstacle avoidance method of multiple unmanned underwater vehicles based on improved artificial potential field method

Cooperative obstacle avoidance method of multiple unmanned u...

引用

Chinese Control and Decision Conference, CCDC

作者： HongLi Xu Kuo Luan BenQing Jia HaiTao Gu Dept. Faculty of Robot Science and Engineering Northeastern University Shenyang China Dept. State Key Laboratory of Robotics Shenyang Institute of Automation Chinese Academy of Sciences Shenyang China

Aiming at the obstacle avoidance problem of multiple unmanned underwater vehicles (UUV) formation in different obstacle avoidance scenarios, the collaborative collision avoidance algorithm of multiple UUV formation was studied. In terms of obstacle avoidance algorithm, an algorithm combining artificial potential field method and consistent formation control algorithm is proposed. A variety of obstacle scenes are set by using the information of forward looking sonar, and different weights are set for the fusion of control instructions of the two algorithms. The problems of formation recovery time and formation error caused by formation "grouping" in the course of UUV obstacle avoidance are solved. Finally, in the underwater simulation platform, the effectiveness and advantages of the collaborative obstacle avoidance algorithm in multiple scenes are verified by experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Imperceptible and Sparse Adversarial Attacks via a Dual-Population-Based Constrained Evolutionary Algorithm

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2023年第2期4卷 268-281页

作者： Tian, Ye Pan, Jingwen Yang, Shangshang Zhang, Xingyi He, Shuping Jin, Yaochu Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education Institutes of Physical Science and Information Technology Hefei230601 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230088 China Anhui University School of Computer Science and Technology Hefei230601 China Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Artificial Intelligence Hefei230601 China Anhui University Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and Automation Hefei230601 China Bielefeld University Faculty of Technology Bielefeld33619 Germany

The sparse adversarial attack has attracted increasing attention due to the merit of a low attack cost via changing a small number of pixels. However, the generated adversarial examples are easily detected in vision since the perturbation to each pixel is relatively large. To achieve imperceptible and sparse adversarial attacks, this article formulates a bi-objective constrained optimization problem, simultaneously minimizing the 0 and 2 distances to the original image, and proposes a dual-population-based constrained evolutionary algorithm to solve it. The proposed method solves the optimization problem by evolving two populations, where one population is responsible for finding feasible solutions (i.e., successful attacks) and the other one is to minimize both the 0 and 2 distances. Moreover, a population initialization strategy and two genetic operators are customized to accelerate the convergence speed. Experimental results indicate that the proposed method can achieve high success rates with low attack costs, and strikes a better balance between the 0 and 2 distances than state-of-the-art methods. © 2020 IEEE.

关键词： Evolutionary algorithms

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：