检索结果-内蒙古大学图书馆

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Two-Stage Multi-Camera Constrain Mapping Pipeline for Large-Scale 3D Reconstruction 42

Two-Stage Multi-Camera Constrain Mapping Pipeline for Large-...

引用

42nd Chinese Control Conference, CCC 2023

作者： Han, Fuzhang Jia, Shenhan Jiao, Yanmei Huang, Wenjun Wang, Yue Xiong, Rong Zhejiang University State Key Laboratory of Industrial Control and Technology Hangzhou China School of Information Science and Engineering Hangzhou Normal University Hangzhou China

ISBN: (纸本)9789887581543

Over the last decade, Augmented reality (AR) has witnessed a significant increase in popularity largely. Consequently, as a central component of these applications, large-scale 3D reconstruction has gained more and more attention. One of the promising solutions is using the camera and the Structure from Motion(SfM) method, especially with the advent of multi-camera devices. However, most of these methods are susceptible to failure in some high-traffic commercial street scenarios due to lots of moving objects and texture-free scenes. Besides, these methods treat each image as a separate source of information, which significantly degrades the performance of the multi-camera acquisition systems now commonly used. Hence, this paper presents a two-stage reconstruction pipeline to obtain an accurate large-scale 3D map in the central business district with multi-camera devices. In the first stage, we enhance the robustness of the incremental SfM method by using the pose prior obtained from the multi-camera visual-inertial system(VINS) and advance the accuracy of the reconstruction result in the second stage by performing the global optimization considering the multi-camera extrinsic constraints. Experiments show that our method yields more complete and accurate maps than its counterpart. © 2023 Technical Committee on Control Theory, Chinese Association of Automation.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

GP-Net: Global Perceptual Network with Adaptive Gradient Clipping for Emotional Image Classification 8

GP-Net: Global Perceptual Network with Adaptive Gradient Cli...

引用

8th International Conference on Intelligent Computing and Signal Processing, ICSP 2023

作者： Wang, Xiaohua Yang, Jie Hu, Min Wu, Xia Hefei University of Technology Anhui Province Key Laboratory of Affective Computing and Advanced Intelligent Machine School of Computer Science and Information Engineering Hefei China

ISBN: (纸本)9798350302455

Traditional image emotion recognition focuses only on the emotion information embedded in the subject or part of the image, while ignoring the global emotion information. In this paper, we propose a new network based on Vision Transformer: a global perception network, containing a main module and a background module. The main module enhances the weighting of objects by showing the interdependencies between modelled channels. The background module further searches for emotional information in the background. In addition, we employ multi-task learning and Adaptive Gradient Clipping to improve the network. Extensive experiments show that our proposed method outperforms the state-of-the-art methods for image sentiment analysis. © 2023 IEEE.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Method for Detecting and Resolving Inconsistencies Between Contour Lines and Double-Line Rivers by Excavating Morphological Features

引用

Journal of Geo-information science 2025年第5期27卷 1129-1143页

作者： Zhao, Binbin Liu, Guang Zhu, Zhe Xie, Jianxiang College of Transportation Engineering Changsha University of Science & Technology Changsha410114 China Engineering Laboratory of Spatial Information Technology of Highway Geological Disaster Early Warning in Hunan Province Changsha University of Science & Technology Changsha410114 China Changsha Urban Planning Information Service Center Changsha410221 China

[Objectives] Inconsistencies between contour lines and rivers are a common challenge in updating and maintaining geospatial databases. Most existing studies focus on single-line rivers, with few addressing double-line rivers. To address this gap, this study proposes a method for detecting and resolving inconsistencies between contour lines and double-line rivers by analyzing their morphological features. [Methods] First, the DTW algorithm is used to establish a mapping relationship between the target nodes on both sides of the river's shoreline, and the Morphing transform is applied to extract the centerline of the double-line river. Second, contour valley points are identified based on bending feature parameters, and approximate valley lines are extracted using the DTW algorithm. Third, using the centerline of the double-line river as a reference, comprehensive judgment rules are established to assess inconsistencies between valley points and double-line rivers, as well as between valley lines and double-line rivers. Finally, the detected inconsistencies are corrected through contour transformation, river displacement, and contour collaborative transformation. Additionally, an affine transformation is applied to resolve cases where local contour lines fall into the water. [Results] This study conducts experiments in three different terrain areas. After correction, all valley points are positioned within the double-line river, and the average path difference between the valley line and the double-line river is significantly reduced. The overall average path differences corrected using contour similarity transformation combined with collaborative transformation are 2.417, 0.033, and 2.783 m, respectively. The overall average path differences corrected using river displacement combined with contour collaborative transformation are 2.667, 0.057, and 0.042 m, respectively, all of which remain within the consistency threshold. [Conclusions] This study thoroughly explores

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

High-brightness and high-efficiency diode laser module based on a coherent-spectral beam combining external cavity

引用

Chinese Optics Letters 2024年第12期22卷 70-73页

作者： Lingqian Meng Weiqiao Zhang Jing Liu Peng Cao Yufei Wang Xuyan Zhou Wanhua Zheng Laboratory of Solid State Optoelectronics Information Technology Institute of SemiconductorsChinese Academy of SciencesBeijing 100083China Center of Materials Science and Optoelectronics Engineering University of Chinese Academy of SciencesBeijing 100049China Weifang Academy of Advanced Opto-Electronic Circuits Weifang 261071China State Key Laboratory on Integrated Optoelectronics Institute of SemiconductorsChinese Academy of SciencesBeijing 100083China College of Future Technology University of Chinese Academy of SciencesBeijing 101408China

A hybrid cavity structure based on individual laser diode integrating coherent beam combining(CBC)and spectral beam combining(SBC)is *** CBC structure is used to enhance laser output power while optimizing beam quality,and the SBC structure is employed to further increase laser output *** output power of 1.42 W was obtained at 0.55 A,with a high combining efficiency of 87.2%.Additionally,the brightness of this structure is 58.65 MW·cm^(-2)·sr^(-1),which is 3.66times that of a single laser *** entire structure provides a new approach for increasing the output power and optimizing the beam quality of the laser diode.

关键词： high brightness coherent beam combining spectral beam combining

来源：评论

学校读者我要写书评

暂无评论

A thermally reversible dynamic bond as a magnetic and nonlinear optical switch

引用

science China Chemistry 2025年

作者： Xue-Li Cao Jin Liu Chuan-Qi Shen Shu-Qi Wu Zi-Shuo Yao Qing Li Zhong-Min Cao Lu-Yao Liu Fu-Lin Lin Zi-Ang Nan Zhu Zhuo Wei Wang Osamu Sato You-Gui Huang State Key Laboratory of Structure Chemistry Fujian Institute of Research on the Structure of Matter Chinese Academy of Sciences Fujian Science & Technology Innovation Laboratory for Optoelectronic Information of China Xiamen Key Laboratory of Rare Earth Photoelectric Functional Materials Xiamen Institute of Rare Earth Materials Haixi InstitutesChinese Academy of Sciences Institute for Materials Chemistry and Engineering & IRCCS Kyushu University Key Laboratory of Cluster Science (Beijing Institute of Technology) Ministry of Education School of Chemistry and Chemical EngineeringBeijing Institute of Technology

In general,flexible metal-organic frameworks （MOFs） change their structures via framework breathing in response to external stimuli （usually guest adsorption and desorption）.Here,we show a dynamic coordination bond in a flexible MOF driving a thermo-induced diffuse phase transition occurring in a wide temperature range of 130-270 K （centered at～200 K）,which enables the switching of magnetism and second-harmonic generation （SHG） *** specific,a solvent-free CoII-based flexible MOF Co2（TPY）2（BPTC）(1),bearing biphenyl-3,3′,5,5′-tetracarboxylic acid （H4BPTC） and 2,2′:6′,2′′-terpyridine （TPY）ligands,exhibits a reversible thermo-responsive coordination-mode switching between five-and *** dynamic bond results in the reversible transformation between a distorted polar framework and a regular nonpolar framework,and therefore leads to the subtle change of the magnetic property and substantial change of the nonlinear optical property of 1.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on the Influence of Sealing and Ventilation on the Fire Characteristics Near the Wall of Utility Tunnel

引用

IAENG International Journal of Applied Mathematics 2024年第5期54卷 866-870页

作者： Bai, Zhenpeng Yu, Yueyang Zhang, Yang Gao, Zihe Yao, Haowei Zhang, Jin Department of Zhengzhou Key Laboratory of Electric Power Fire Safety College of Building Environment Engineering Zhengzhou University of Light Industry China Department of College of Building Environment Engineering Zhengzhou University of Light Industry China Department of School of Electrical and Information Engineering Henan University of Engineering China Department of School of Civil Engineering China Department of College of Building Environment Engineering Zhengzhou University of Light Industry Zhengzhou450002 China Department of Beijing Key Laboratory of Control Technology for City Toxic and Combustible Major Hazards Institute of Urban Safety and Environmental Science Beijing Academy of Science and Technology Beijing100054 China

In this paper, the temperature rise in the longitudinal direction, the heat release rate (HRR), the endless area temperature under the ceiling of the utility tunnel, and the root of HRR (oil and fuel type), cable type, number of cable layers and and cables per layer. The effects of airtightness, natural ventilation, and longitudinal ventilation on the fire characteristics of cable compartments were compared. The results showed that the effects of enclosed cable tunnels and natural ventilation on fire behavior near walls in cable tunnels were compared. Compared with the natural ventilation state, when placing RVVR type cables, the fire duration of the enclosed cable compartment was shorter, the ceiling temperature rise was greater. And the time that was necessary to increase the ceiling temperature to its maximum value was shorter. The HRR inside the enclosed cable compartment was very high and could almost reach its peak quickly. The contribution of this article is to reduce the social and economic costs of utility tunnels by preventing tunnel fires. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Ventilation

来源：评论

学校读者我要写书评

暂无评论

Metaheuristic Optimization Algorithm for Signals Classification of Electroencephalography Channels

引用

Computers, Materials & Continua 2022年第6期71卷 4627-4641页

作者： Marwa M.Eid Fawaz Alassery Abdelhameed Ibrahim Mohamed Saber Department of Communications and Electronics Delta Higher Institute of Engineering and TechnologyMansoura35111Egypt Department of Computer Engineering College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia Computer Engineering and Control Systems Department Faculty of EngineeringMansoura UniversityMansoura35516Egypt Department of Electronics and Communications Engineering Faculty of EngineeringDelta University for Science and TechnologyMansoura11152Egypt

Digital signal processing of electroencephalography(EEG)data is now widely utilized in various applications,including motor imagery classification,seizure detection and prediction,emotion classification,mental task classification,drug impact identification and sleep state *** the increasing number of recorded EEG channels,it has become clear that effective channel selection algorithms are required for various *** Whale Optimization Method(Guided WOA),a suggested feature selection algorithm based on Stochastic Fractal Search(SFS)technique,evaluates the chosen subset of *** may be used to select the optimum EEG channels for use in Brain-Computer Interfaces(BCIs),the method for identifying essential and irrelevant characteristics in a dataset,and the complexity to be *** enables(SFS-Guided WOA)algorithm to choose the most appropriate EEG channels while assisting machine learning classification in its tasks and training the classifier with the ***(SFSGuided WOA)algorithm is superior in performance metrics,and statistical tests such as ANOVA and Wilcoxon rank-sum are used to demonstrate this.

关键词： Signals metaheuristics optimization feature selection multilayer perceptron support vector machines

来源：评论

学校读者我要写书评

暂无评论

An Analog Front-End with Automatic Gain Control for Galvanic-Coupled Human Body Communication

An Analog Front-End with Automatic Gain Control for Galvanic...

引用

2023 Cross Strait Radio science and Wireless technology Conference, CSRSWTC 2023

作者： Zhao, Wenxiang Li, Dongming Wang, Jiamei Pun, Sio Hang Vai, Mang I. Gao, Yueming College of Physics and Information Engineering Fuzhou University China Fuzhou University The International Joint Laboratory on Health Intelligent Monitoring Systems China University of Macau State Key Laboratory of Analog and Mixed-Signal VLSI China Faculty of Science and Technology University of Macau China

ISBN: (纸本)9798350358971

The channel loss of galvanic-coupled human body communication (GC-HBC) is greatly affected by human body activities or individual differences, which will cause large changes in the amplitude of the input signal received by the receiver. This requires the analog front-end to have the ability to adaptively adjust the circuit gain to ensure stable output of the amplified signal. In this regard, this paper proposes an analog front-end with automatic gain control for GC-HBC. This circuit uses a differential preamplifier circuit with high input impedance and a rear-stage automatic gain control circuit that uses voltage feedback to control gain. While achieving amplification of weak signals, it also meets the requirements for stable signal output. The measurement results show that it has an input impedance of > 100 M Ω, a maximum gain of 74dB, and a sensitivity of - 76dBm, effectively meeting the needs for capturing and amplifying weak signals. The loop stabilization time is 156μs, and the input dynamic range is 34dB, which can ensure stable output of the amplified signal amplitude when the input signal amplitude changes. © 2023 IEEE.

关键词： analog front-end automatic gain control GC-HBC stable output

来源：评论

学校读者我要写书评

暂无评论

Multi-dimensional controllability analysis of precision ball bearing integrity

引用

Advances in Manufacturing 2023年第4期11卷 682-693页

作者： Lai Hu Jun Zha Wei-Hua Zhao Xiao-Fei Peng Yao-Long Chen School of Mechanical Engineering Xi’an Jiaotong UniversityXi’an710049People’s Republic of China State Key Laboratory for Manufacturing Systems Engineering Xi’an Jiaotong UniversityXi’an710054People’s Republic of China Luoyang Bearing Science and Technology Co. Ltd.Luoyang471039HenanPeople’s Republic of China

Many factors affect the integrity of precision ball *** this study,the multi-dimensional controllability of precision ball bearings produced in different company brands(bearing A and bearing B)were studied and *** geometric errors(flatness,parallelism,roundness and cylindricity of inner and outer rings,roundness,groove and roughness of inner and outer rings)and vibration errors of bearings were ***,the residual stress,residual austenite content,element content ratio,metamorphic layer and temperature-vibration displacement coupling test were also *** on the above analysis conclusion,the bearing fatigue life test was carried out for 2150 *** reliability of the conclusion is proved again as *** the residual austenite content in the raceway of precision ball bearing is 10%,the axial residual stress is 877.4 MPa;the tangential residual stress is 488.1 MPa;the carbon content is 6%;the test temperature of bearing is the lowest;and the service life is prolonged.

关键词： Precision ball bearing Controllability Geometric errors Carbon content Residual austenite Residual stress

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：