检索结果-内蒙古大学图书馆

2023 International Conference on Artificial Intelligence and Automation Control, AIAC 2023

作者： Wang, Xiangjie Jing, Zhiyong Shi, Lei Cheng, Guozhen Gao, Yufei Hao, Bing Zhengzhou University School of Cyber Science and Engineering Zhengzhou China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou China Information Engineering University Institute of Information Technology Zhengzhou China Songshan Laboratory Zhengzhou China

ISBN: (纸本)9798350383805

The current vehicle detection models are inadequate for deployment on edge computing devices due to limited computing capabilities. Therefore, this paper proposes a novel lightweight vehicle detection method called MA-YOLO (MobileNet Attention YOLO). In order to reduce the number of parameters and computational requirements, the depthwise separable convolution and inverse residual structure is used to instead of conventional convolution. Additionally, the SELayer and CALayer module of attention mechanism is embedded into Backbone module, to improve the correlation of inter-channel and inter-space features, respectively. The experimental results demonstrate that the MA-YOLO has achieved a mean average precision (mAP) of 90.7% for vehicle detection under normal weather conditions. In comparison to YOLOv8s, MA-YOLO has compressed the number of parameters by 40.5% and computation by 52.4%, while experiencing only a decrease of 0.1% in mAP. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Workspace Mapping Method Based on Edge Drifting for the Teleoperation System 4

Workspace Mapping Method Based on Edge Drifting for the Tele...

引用

2022 4th International Symposium on Robotics and Intelligent Manufacturing technology, ISRIMT 2022

作者： Gou, Songlin Zhou, Jian Zhang, Hua Liu, Manlu Yang, Shunyao Zhang, Xinglang School of Information Engineering Southwest University of Science and Technology Mianyang Sichuan China School of Information Engineering Southwest University of Science and Technology Special Environment Robot Technology Key Laboratory of Sichuan Province Sichuan Mianyang China

The workspace mapping method for master-slave isomeric robots is a key research direction. In order to enhance the safety and stability of the operation of such robots, a position-joint hybrid mapping method based on edge drifting is proposed in this paper. First, teleoperation is divided into two phases, that is, task approach and task operation. During the task approach, the edge drifting algorithm is adopted to largely cover the workspace of a robot. Rate mapping is used to quickly control the movement of the slave robot to the target position. During task operation, a hybrid mapping algorithm integrating the Cartesian space and the joint space highly precisely maps both the position and pose of the slave robot to accurately follow the control command of the master end and achieve precise control. Lastly, the proposed method is validated on the experimental platform for master-slave isomeric teleoperation. The experimental results indicate that this mapping method allows the master-slave isomeric teleoperation system to cover a large workspace precisely with desirable precision in position and pose following. © Published under licence by IOP Publishing Ltd.

关键词： Slave robots

来源：评论

学校读者我要写书评

暂无评论

SVDFed: Enabling Communication-Efficient Federated Learning via Singular-Value-Decomposition 42

SVDFed: Enabling Communication-Efficient Federated Learning ...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Wang, Haolin Liu, Xuefeng Niu, Jianwei Tang, Shaojie Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing China Zhongguancun Laboratory Beijing China Zhengzhou University Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou China Naveen Jindal School Management University of Texas at Dallas Richardson United States

ISBN: (纸本)9798350334142

Federated learning (FL) is an emerging paradigm of distributed machine learning. However, when applied to wireless network scenarios, FL usually suffers from high communication cost because clients need to transmit their updated gradients to a server in every training round. Although many gradient compression techniques like sparsification and quantization are proposed, they compress clients' gradients independently, without considering the correlations among gradients. In this paper, we propose SVDFed, a collaborative gradient compression framework for FL. SVDFed utilizes Singular Value Decomposition (SVD) to find a few basis vectors, whose linear combination can well represent clients' gradients at a certain round. Due to the correlations among gradients, these basis vectors can still well approximate new gradients in many subsequent rounds. With the help of basis vectors, clients only need to upload the coefficients of the linear combination to the server, which greatly reduces communication cost. In addition, SVDFed leverages the classical PID (Proportional, Integral, Derivative) control to determine the proper time to update basis vectors to maintain their representation ability. Through experiments, we demonstrate that SVDFed outperforms existing gradient compression methods in FL. For example, compared to a popular gradient quantization method QSGD, SVDFed can reduce the communication overhead by 66 % and pending time by 99 %. © 2023 IEEE.

关键词： Singular value decomposition

来源：评论

学校读者我要写书评

暂无评论

Phase of Multivariable systems: A Revisit via H2T-Dissipativity 62

Phase of Multivariable Systems: A Revisit via H2T-Dissipativ...

引用

62nd IEEE Conference on Decision and Control, CDC 2023

作者： Wang, Dan Chen, Wei Johansson, Karl H. Kth Royal Institute of Technology Division of Decision and Control Systems Stockholm Sweden Peking University State Key Laboratory for Turbulence and Complex Systems Department of Mechanics and Engineering Science Beijing China

ISBN: (纸本)9798350301243

A new notion of phase of multi-input multi-output (MIMO) systems was recently defined and studied, leading to new understandings in various fronts including a formulation of small phase theorem, a performance criterion named H∞ phase sector, and a sectored real lemma, etc. In this paper, we define a new notion of H2T-dissipativity and show the connection between the phase of a multivariable linear time-invariant (LTI) system and the H2T-dissipativity. The H2T-dissipativity, roughly speaking, is dissipativity restricted to the time-domain H2 space which consists of L2 signals with only positive frequency components. In addition, by exploiting the newly defined H2T- dissipativity, we also study the phase of a feedback system and provide a physical interpretation of the sectored real lemma. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recurrence Plot and Quantification of Glottal Signal for Pathological Voice Analysis 12

Recurrence Plot and Quantification of Glottal Signal for Pat...

引用

2024 12th International Conference on systems and Control, ICSC 2024

作者： Dahmani, M. Bettayeb, N. Laboratory of Speech Communication and Signal Processing University of Science and Technology Houari Boumediene Electrical Engineering Faculty Algeria Faculté des News Technologies of Information and Communications University Kasdi Merbah Algeria

ISBN: (纸本)9798331531812

In this work, the information obtained from plotting the Recurrence Plot (RP) diagram and Recurrence Quantification Analysis (RQA), referring to the glottal signal waveform, is explored for the diagnosis and assessment of human voice disorders. For that, the glottal signal was initially obtained from the vocal signal through the use of an inverse filtering algorithm : Iterative Adaptive Inverse Filtering (IAIF). RP tracing and RQA were applied to the glottal signal to evaluate the dynamic process and vibration of Vocal Folds (VFs). the normal or healthy voice is considered as a reference. Visual inspection of the RPs and parametric analysis reveals a valuable information about the state of vocal folds under pathologies. © 2024 IEEE.

关键词： Quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

Process capability analysis for simple linear profiles

引用

Quality and Quantity 2024年第3期58卷 2183-2211页

作者： Pakzad, Aylin Adibfar, Saeed Razavi, Hamideh Noorossana, Rassoul Department of Industrial Engineering Kosar University of Bojnord Bojnord Iran Industrial Engineering Department Iran University of Science and Technology Tehran Iran Department of Industrial Engineering Faculty of Engineering Ferdowsi University of Mashhad Mashhad Iran Information Systems and Operations Management Department College of Business University of Central Oklahoma Edmond OK United States

When a process is under statistical control, one is usually interested in evaluating process performance based on specification limits (SLs) provided by customer. This evaluation is referred to as process capability analysis. This study provides a new method to measure process capability index (PCI) for a simple linear profile based on its parameters. In this regard, the SLs for the proposed PCIs (SLs for the profile parameters) are presented based on SLs of the response variable while considering the in-control profiles. Simulation results reveal satisfactory performance for the proposed method considering absolute percentage error criterion. In addition, the minimum number of profile samples for estimation of the proposed PCIs are determined. A real case in calibration application is also considered to show the applicability of the proposed method in practice. © The Author(s), under exclusive licence to Springer Nature B.V. 2023.

关键词： Loss-based capability index Phase I and phase II analysis Process capability analysis Simple linear profile Statistical process control

来源：评论

学校读者我要写书评

暂无评论

United Domain Cognition Network for Salient Object Detection in Optical Remote Sensing Images

arXiv

引用

arXiv 2024年

作者： Sun, Yanguang Yang, Jian Luo, Lei The PCA Laboratory Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Recently, deep learning-based salient object detection (SOD) in optical remote sensing images (ORSIs) have achieved significant breakthroughs. We observe that existing ORSIs-SOD methods consistently center around optimizing pixel features in the spatial domain, progressively distinguishing between backgrounds and objects. However, pixel information represents local attributes, which are often correlated with their surrounding context. Even with strategies expanding the local region, spatial features remain biased towards local characteristics, lacking the ability of global perception. To address this problem, we introduce the Fourier transform that generate global frequency features and achieve an image-size receptive field. To be specific, we propose a novel United Domain Cognition Network (UDCNet) to jointly explore the global-local information in the frequency and spatial domains. Technically, we first design a frequency-spatial domain transformer block that mutually amalgamates the complementary local spatial and global frequency features to strength the capability of initial input features. Furthermore, a dense semantic excavation module is constructed to capture higher-level semantic for guiding the positioning of remote sensing objects. Finally, we devise a dual-branch joint optimization decoder that applies the saliency and edge branches to generate high-quality representations for predicting salient objects. Experimental results demonstrate the superiority of the proposed UDCNet method over 24 state-of-the-art models, through extensive quantitative and qualitative comparisons in three widely-used ORSIs-SOD datasets. The source code is available at: https://***/CSYSI/UDCNet. © 2024, CC BY.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Highly sensitive vector magnetic fiber sensor based on hyperbolic metamaterials

引用

science China(Physics,Mechanics & Astronomy) 2022年第11期65卷 115-124页

作者： Shiqi Hu Junhao Liang Jiayao Chen Hongda Cheng Qianyu Lin Weicheng Shi Jinming Yuan Gui-Shi Liu Lei Chen Zhe Chen Norhana Arsad Yaofei Chen Yunhan Luo Guangdong Provincial Key Laboratory of Optical Fiber Sensing and Communications Department of Optoelectronic EngineeringCollege of Science and EngineeringJinan UniversityGuangzhou510632China Key Laboratory of Optoelectronic Information and Sensing Technologies of Guangdong Higher Education Institutes Jinan UniversityGuangzhou510632China Department of Electrical Electronic and Systems EngineeringFaculty of Engineering and Built EnvironmentUniversiti Kebangsaan MalaysiaBangi43600Malaysia

Hyperbolic metamaterials(HMMs) are novel artificial materials that excite the surface plasmon resonance(SPR) because of their unique hyperbolic dispersion properties. Herein, to the best of our knowledge, we propose the first HMM-based fiber SPR(HMM-SPR) sensor for vector magnetic detection. By selecting the composite materials and structural parameters of the HMM dispersion management, HMM-SPR sensors can achieve a high refractive index sensitivity of 14.43 μm/RIU. Vector magnetic field detection was performed with the HMM-SPR sensor encapsulated with a magnetic fluid. Compared with other ferrofluidbased magnetic field fiber sensors, the proposed sensor shows pronounced advantages in intensity and direction sensitivity of 1.307 nm/Oe and 7.116 nm/°, respectively. The sensor design approach presented in this paper provides an excellent demonstration of HMM-SPR sensors in various applications.

关键词： hyperbolic metamaterials(HMMs) vector magnetic detection surface plasmon resonance(SPR) direction sensitivity intensity sensitivity

来源：评论

学校读者我要写书评

暂无评论

Frequency Increments Optimization Based on IPSO to Extend Beam Dwell Time for Frequency Diverse Array 3

Frequency Increments Optimization Based on IPSO to Extend Be...

引用

2021 3rd International Conference on Computer, Communications and Mechatronics engineering, CCME 2021

作者： Pan, Yuwen Yang, Yuanwang Jiao, Libin Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China Science and Technology on Communication Networks Laboratory Shijiazhuang China

Compared with traditional phased array radar, frequency diverse array (FDA) can form a range-dependent beampattern and overcome the shortcoming that the traditional phased array radar cannot effectively control the range direction of the transmit beam. Nonuniform linear frequency increments has been widely applied in FDA to promote the performance of FDA. However, few methods can effectively extend the beam dwell time. In this paper, we propose an improved particle swarm optimization algorithm (IPSO) that can adjust the frequency increment of every array element to extend the dwell time of the beam within a period of time. Numerical simulation results show that our method can outperform other existing methods, which implies that a more stable and flexible FDA communication system can be achieved for the proposed method. © Published under licence by IOP Publishing Ltd.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Atmospheric correction for microwave remote sensing with Considering clouds and precipitation profiles 5

Atmospheric correction for microwave remote sensing with Con...

引用

5th International Conference on Geology, Mapping, and Remote Sensing, ICGMRS 2024

作者： Liu, Xuan Ji, Dabin Chen, Chao Tang, Rugang Marine Science and Technology College Zhejiang Ocean University Zhoushan China Key Laboratory of Remote Sensing and Digital Earth Aerospace Information Research Institute Chinese Academy of Sciences Beijing100101 China School of Geography Science and Geomatics Engineering Suzhou University of Science and Technology Suzhou China

ISBN: (纸本)9781510681712

The microwave brightness temperature observed in areas covered by clouds and rain is strongly influenced by the atmosphere. In order to obtain accurate surface information, atmospheric correction is required. Most studies cannot achieve atmospheric correction for areas covered by rainfall. This article develops an atmospheric correction method based on the radiative transfer model. Through analyzing the impact of clouds and rain on microwave radiation transmission, it was found that clouds and rain are not sensitive to the low-frequency bands of 6.9 GHz, 7.3 GHz, and 10.7 GHz, while they have varying degrees of attenuation at 18.7 GHz, 23.8 GHz, 36.5 GHz, and 89.0 GHz. Based on this, both cloud and rain information are added to the model for atmospheric correction. By comparing the results before and after atmospheric correction, it was found that this algorithm can achieve atmospheric correction in the 18.7GHz, 23.8GHz, 36.5GHz, and 89.0GHz bands. However, it is not suitable for areas with strong water vapor absorption in the 23.8GHz band and rainfall areas in the 89.0GHz band. © 2024 SPIE.

关键词： Rain

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：