检索结果-内蒙古大学图书馆

Transverse Velocity Field Measurements in High-resolution Solar Images Based on Deep Learning

Research in Astronomy and Astrophysics 2023年第6期23卷 86-97页

作者： Zhen-Hong Shang Si-Yu Mu Kai-Fan Ji Zhen-Ping Qiang Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China Yunnan Key Laboratory of Artificial Intelligence Kunming University of Science and TechnologyKunming 650500China Yunnan Observatories Chinese Academy of SciencesKunming 650216China College of Big Data and Intelligent Engineering Southwest Forestry UniversityKunming 650224China

To address the problem of the low accuracy of transverse velocity field measurements for small targets in highresolution solar images,we proposed a novel velocity field measurement method for high-resolution solar images based on *** method transforms the transverse velocity field measurements into an optical flow field prediction *** evaluated the performance of the proposed method using the Hαand TiO data sets obtained from New Vacuum Solar Telescope *** experimental results show that our method effectively predicts the optical flow of small targets in images compared with several typical machine-and deeplearning *** the Hαdata set,the proposed method improves the image structure similarity from 0.9182 to0.9587 and reduces the mean of residuals from 24.9931 to 15.2818;on the TiO data set,the proposed method improves the image structure similarity from 0.9289 to 0.9628 and reduces the mean of residuals from 25.9908 *** optical flow predicted using the proposed method can provide accurate data for the atmospheric motion information of solar *** code implementing the proposed method is available on https://***/lygmsy123/transverse-velocity-field-measurement.

关键词： methods:data analysis techniques:image processing Sun:fundamental parameters

来源：评论

学校读者我要写书评

暂无评论

Iterative Methods for Solving Sylvester Transpose Tensor Equation A⋆NX⋆MB+C⋆M^XT⋆ND=E

引用

Operations Research Forum 2021年第4期2卷 64页

作者： Dehdezi, Eisa Khosravi Department of Mathematics Faculty of Intelligent Systems Engineering and Data Science Persian Gulf University Bushehr Iran

In recent years, solving tensor equations has attracted the attention of mathematicians in applied mathematics. This paper investigated the gradient-based and gradient-based least-squares iterative algorithms to solve the Sylvester transpose tensor equation A⋆ _NX⋆ _MB+ C⋆ _MX^T⋆ _ND= E. These algorithms use tensor computations with no matricizations involved which includes the Sylvester transpose matrix equation as special case. The first algorithm is applied when the tensor equation is consistent. Error convergence analysis of the proposed methods has been discussed. For inconsistent Sylvester transpose tensor equation, the gradient-based least-squares iterative method is presented. Modified versions of these algorithms are obtained by little changes. Also, it is showed that for any initial tensor, a solution of related problems can be obtained within finite iteration steps in the absence of round-off errors. In addition, the computational cost of the methods is obtained. The effectiveness of these procedures are illustrated by several numerical examples. Finally, some concluding remarks are given. © 2021, The Author(s), under exclusive licence to Springer Nature Switzerland AG.

关键词： Einstein product Gradient based Iterative methods Tensor

来源：评论

学校读者我要写书评

暂无评论

Enhancing LoRaWAN Localization in Industrial Environments: Merging Path-Loss Modeling, Extended Kalman Filtering and Map-Matching

引用

IEEE Access 2025年 13卷 84765-84778页

作者： Moradbeikie, Azin Keshavarz, Ahmad Ivan Lopes, Sergio CiTin-Centro de Interface Tecnológico Industrial Arcos de Valdevez4970-786 Portugal Persian Gulf University Faculty of Intelligent Systems Engineering and Data Science Electrical Engineering Department Bushehr*** Iran Instituto Politécnico de Viana do Castelo ADiT-Lab Viana do Castelo4900-347 Portugal IT-Instituto de Telecomunicações Campus Universitário de Santiago Aveiro3810-193 Portugal

In industrial environments, accurate location information is crucial for enabling the seamless operation of technologies. Localization based on the signal features of the implemented network (such as RSSI) is becoming an appropriate substitute to solve its problems, such as low power consumption and cost. LoRaWAN, a contemporary LPWAN technology, can provide long-range coverage, an important requirement for several industrial application domains. RSSI-based localization in LoRaWAN is a widely used low-cost method, but it is susceptible to environmental changes and noise, leading to low performance and accuracy, especially in industrial environments. So, applying an adoptable noise-filtering method based on the environment to make measured RSSI usable in industrial applications, such as asset management localization and tracking, is essential. This paper proposes a novel method that merges an Extended Kalman Filter (EKF) with Path-Loss Modeling (PLM) for noise filtering in LoRaWAN systems. Unlike the previous approaches that just use EKF as a noise filtering method on RSSI and use achieved RSSI to provide distance estimation using PLM, our method uses EKF as a location estimation method that gets RSSI as an input. Additionally, we incorporate map-matching to further improve the accuracy of location estimation by leveraging geographical constraints. For the evaluation step, the proposed method is implemented and tested in a harbor in a highly dynamic and harsh industrial environment. The detailed evaluation demonstrates that the proposed approach leads to an improvement between 15% and 46% compared to normal PLM. In addition, adding map-matching leads to a 36% improvement in location estimation. © 2013 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Postural Synergy Analysis of Continuous Hand Movements for Application to Prosthetic Hands 17

Postural Synergy Analysis of Continuous Hand Movements for A...

引用

17th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2024

作者： Jiang, Hai Yamanoi, Yusuke Chen, Peiji Yong, Xu Li, Guanglin Yokoi, Hiroshi Jing, Xiaobei Shenzhen518055 China The Univiersity of Electro-Communications Department of Mechanical Engineering and Intelligent Systems Tokyo 182-8585 Japan Tokyo University of Science Faculty of Engineering Department of Elecrical Engineering Tokyo 125-8585 Japan

ISBN: (纸本)9798331507398

This paper focuses on exploring the coordinated movements used to control dexterous myoelectric prosthetic hands by hand motion analysis inspired by the motor synergy theory of the human hand. Recently, prosthetic hands have become multi-degree-of-freedom, and simultaneous proportional control of each finger is the most required challenge. In response to this problem, motor synergy is expected to play a key role in constructing the control method because it reduces the amount of information on the control object. In the experiment, we used a Leap Motion Controller to measure 60 continuous hand movement data from four healthy individuals, analyzed based on principal component analysis methods, and extracted several principal component data used by humans to control various grasping movements. We produced a hand model with 19 degrees of freedom for visualizing the principal component data. The results of the visualization showed similarities in postural synergies among the four healthy individuals used to control continuous hand movements. Based on the acquired synergies, the number of learning data for the control method of myoelectric prosthetic hands will be greatly reduced. © 2024 IEEE.

关键词： Degrees of freedom (mechanics)

来源：评论

学校读者我要写书评

暂无评论

A Player Position Tracking Method Based on a Wide-Area Pan-Tilt-Zoom Video 12

A Player Position Tracking Method Based on a Wide-Area Pan-T...

引用

Proceedings of the 12th International Conference on Sport sciences Research and Technology Support, icSPORTS 2024

作者： Yamagishi, Shunzo Xie, Chun Shishido, Hidehiko Kitahara, Itaru Master's and Doctoral Program in Intelligent Mechanical Interaction Systems University of Tsukuba Ibaraki Japan Center for Computational Sciences University of Tsukuba Ibaraki Japan Faculty of Science and Engineering Department of Information Systems Engineering Soka University Tokyo Japan

ISBN: (纸本)9789897587191

This paper proposes a method to estimate the posture of an athlete moving on a vast field in a sporting event using a pan-tilt-zoom camera. In order to estimate the posture of an athlete on a sports field from a dynamic video sequence, our method extracts image features to search correspondence points among successive frames and computes the homography transformation matrix that compensates for changes the camera parameters (e.g., angle of view and posture). The effectiveness of this method is qualitatively verified using MLB TV broadcast video. The accuracy and error factors are also quantitatively verified by CG simulation. Copyright © 2024 by SCITEPRESS - science and Technology Publications, Lda.

关键词： Pan-Tilt-Zoom Camera Player Tracking Sports Analytics Video Processing Wide-Area

来源：评论

学校读者我要写书评

暂无评论

Analysis of Typical Features Using an Angle-to-sEMG Decoder Model 17

Analysis of Typical Features Using an Angle-to-sEMG Decoder ...

引用

17th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2024

作者： Liu, Zehao Jiang, Hai Yamanoi, Yusuke Chen, Peiji Jing, Xiaobei Li, Guanglin Yokoi, Hiroshi Yong, Xu Shenzhen518055 China Univiersity of Electro-Communications Department of Mechanical Engineering and Intelligent Systems Tokyo182-8585 Japan Tokyo University of Science Faculty of Engineering Department of Elecrical Engineering Tokyo125-8585 Japan

ISBN: (纸本)9798331507398

Current prosthetic control methods mainly rely on extensive data collection and the training of classification models. Nevertheless, achieving a balance between learning efficiency and classification accuracy remains a persistent challenge. In this paper, we introduce a novel prosthetic control approach that divides the processing of surface electromyography (sEMG) signals into two stages to predict corresponding joint angles. Initially, a pretrained model is utilized to infer the associated joint angles based on typical features. This methodology necessitates the mapping of individual sEMG signals to these typical features through a compact mapping network during application. we think that it will enhance hand motion recognition accuracy while minimizing learning duration though a pre-training approach. This study represents the initial phase, which involves the acquisition and evaluation of the similarity among typical features linked to joint angles. To this end, we constructed angle-to-sEMG models (decoders) and input the same unprocessed continuous joint angle data into the decoders of five participants. Subsequently, we utilized the resultant typical features as inputs for the encoders of different individuals. The findings indicate that, notwithstanding interindividual variability, there exists a degree of resemblance in the typical features associated with joint angles, thus enabling the generation of angle data resembling the true angles even across diverse subjects. © 2024 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Recognition of American sign language using modified deep residual CNN with modified canny edge segmentation

引用

Multimedia Tools and Applications 2025年 1-28页

作者： Hariharan, U. Devarajan, Devikanniga Kumar, P. Santhosh Rajkumar, K. Meena, M. Akilan, T. Department of Computer Science and Engineering Apex Institute of Technology Chandigarh University Punjab Mohali140413 India Department of Computer Science and Engineering GITAM University Karnataka Bengaluru561203 India Department of Information Technology Faculty of Engineering and technology SRM Institute of Science and Technology Ramapuram Tamil Nadu Chennai600089 India Department of Data Science and Business Systems School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai603203 India Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Tambaram602109 India Research Coordinator Dept. of IQAC Amity University Kolkata West Bengal 700135 India

American Sign Language (ASL) recognition aims to recognize hand gestures, and it is a crucial solution to communicating between the deaf community and hearing people. However, existing sign language recognition algorithms still have some drawbacks, such as difficulty recognizing hand movements and low recognition accuracy for most sign language recognition. A Modified Convolutional Neural Network (MCNN) deep residual 101 classifier-based American Sign Language identification system has been developed to address this problem. There are three main parts presents in the method. The first part is pre-processing the images to remove the noise, enhance the contrast of the picture, adjust the contrast level and smoothen the picture using various filters. The second part is the segmentation, and it’s used to partition the image using a modified canny edge detection method by removing all weak edges present in the image. Finally, classification will be done using the Modified CNN deep residual 101 classifiers. By classifying the image, the American Sign Language is accurately identified. This process is conducted through images. The outcome shows that the suggested approach has a 0.97% accuracy and a 0.05% False Positive Rate. Other CNN architectures such as resNet 50 and resNet 18 reached 0.90% and 0.80% accuracy, respectively, which is lower than our proposed method. In addition, the resNet 101 classifier effectively recognizes the difficult hand gestures through the image data. It obtains high recognition accuracy for 36 signs is 0 to 9 numbers and a to z alphabets from American Sign Language. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A novel deep domain-adversarial method based on DRN-DATL for rolling bearing 43

A novel deep domain-adversarial method based on DRN-DATL for...

引用

43rd Chinese Control Conference, CCC 2024

作者： Li, Zhuorui Wang, Xiaodong Ma, Bao Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming650500 China Yunnan University Yunnan Key Laboratory of Intelligent Systems and Computing Kunming650500 China

ISBN: (纸本)9789887581581

In recent years, a variety of rolling bearing fault diagnosis methods based on deep learning has become an emerging research orientation. However, there is still a gap between the existing diagnostic model and the practical application, i.e., 1) due to the variability of working conditions, the domain shift problem between source domain and the target domain have led to the obvious degradation of the diagnostic performance. 2) It is time-consuming and expensive to label a mass of monitoring data in practical situation. To address this problem, a domain-adversarial transfer learning method based on deep residual network (DRN-DATL) for rolling bearing fault diagnosis is proposed. Firstly, DRN is designed to extract features from raw vibration signal, which can avoid gradient problems. Then, the APReLU activation function is adopted to improved diagnostic accuracy under different working conditions. Meanwhile, domain-adversarial training is utilized to minimize distribution differences between source domain and target domain. Finally, seven comparison methods are selected for systematic analysis, and the results show that the proposed method can effectively improve the overall performance of the diagnosis model, which has achieved higher classification accuracy. © 2024 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

A language for graph database evolution and its implementation in Neo4j 42

A language for graph database evolution and its implementati...

引用

42nd International Conference on Conceptual Modeling: ER Forum, 7th Symposium on Conceptual Modeling Education, SCME 2023, Project Exhibitions, Posters and Demos, and Doctoral Consortium, ER-Companion 2023

作者： Hausler, Dominique Klettke, Meike Störl, Uta University of Regensburg Data Engineering Group Faculty of Informatics and Data Science Bajuwarenstrasse 4 Regensburg93053 Germany University of Hagen Chair of Databases and Information Systems Faculty of Mathematics and Computer Science Universitätsstrasse 1 Hagen58084 Germany

In this article, we present an evolution language for graph databases and a method to realize evolution operations on graph databases and their schema. Graph database management systems like Neo4j can be used for different scenarios: they can store graphs where no semantic constraints are checked. It is also possible to use them to store graphs where the structure of nodes and relationships is regular, for example, because the nodes and relationships of a graph have been generated by an application. In the latter case, these structures may change, that means they can undergo evolution. Currently, there is no established evolutionary language for graphs. However, evolution operations (such as add, rename, delete, merge, copy, split and move) have already been developed for other database models. In this article, we will not only use the established evolution operations but additionally extend the operations appropriated. After analyzing evolution operators explicitly in the context of graph databases, we also created a new graph-specific operation: transform. Moreover, we suggest an evolution language to graph data and show how it can be executed on the graph database schema as well as on the instances (i.e. the graphs themselves). In doing so, some operations can be implemented native based on Cypher, others non-native using the APOC library for Neo4j. © 2023 CEUR-WS. All rights reserved.

关键词： evolution graph databases evolution graph evolution language graph schema description

来源：评论

学校读者我要写书评

暂无评论

Facial expression recognition under occlusion conditions based on multi-feature cross-attention

引用

Journal of intelligent and Fuzzy systems 2024年第4期46卷 9841-9856页

作者： Guo, Sheng Tan, Mian Cai, Shan Zhang, Zaijun Liang, Yihui Feng, Hongxi Zou, Xue Wang, Lin School of Data Science and Information Engineering Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guizhou Minzu University Guiyang China School of Mathematics and Statistics Qiannan Normal University for Nationalities Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Province Duyun China Zhongshan Institute University of Electronic Science and Technology of China Zhongshan China Guizhou Aerospace Tianma Electromechanical Technology Co LTD Zunyi China

Although facial expression recognition (FER) has a wide range of applications, it may be difficult to achieve under local occlusion conditions which may result in the loss of valuable expression features. This issue has motivated the present study, as a part of which an effective multi-feature cross-attention network (MFCA-Net) is proposed. The MFCA-Net consists of a two-branch network comprising a multi-feature convolution module and a local cross-attention module. Thus, it enables decomposition of facial features into multiple sub-features by the multi-feature convolution module to reduce the impact of local occlusion on facial expression feature extraction. In the next step, the local cross-attention module distinguishes between occluded and unoccluded sub-features and focuses on the latter to facilitate FER. When the MFCA-Net performance is evaluated by applying it to three public large-scale datasets (RAF-DB, FERPlus, and AffectNet), the experimental results confirm its good robustness. Further validation is performed on a real FER dataset with local occlusion of the face. © 2024 – IOS Press.

关键词： Convolution

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：