检索结果-南通市图书馆

Structured Sparse Coding With the Group Log-regularizer for Key Frame Extraction

在线全文

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1818-1830页

作者： Zhenni Li Yujie Li Benying Tan shuxue ding Shengli Xie the School of Automation Guangdong University of TechnologyGuangzhou 510006 the Guangdong-Hong Kong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangdong University of Technology(GDUT)Guangzhou 510006China the School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China the National Institute of Advanced Industrial Science and Technology TsukubaIbaraki 305-8560Japan IEEE the Key Laboratory of Intelligent Information Processing and System Integration of Io T(GDUT) Ministry of Education Guangdong Key Laboratory of IoT Information Technology(GDUT) Guangzhou 510006China

Key frame extraction based on sparse coding can reduce the redundancy of continuous frames and concisely express the entire ***,how to develop a key frame extraction algorithm that can automatically extract a few frames with a low reconstruction error remains a *** this paper,we propose a novel model of structured sparse-codingbased key frame extraction,wherein a nonconvex group log-regularizer is used with strong sparsity and a low reconstruction *** automatically extract key frames,a decomposition scheme is designed to separate the sparse coefficient matrix by *** rows enforced by the nonconvex group log-regularizer become zero or nonzero,leading to the learning of the structured sparse coefficient *** solve the nonconvex problems due to the log-regularizer,the difference of convex algorithm(DCA)is employed to decompose the log-regularizer into the difference of two convex functions related to the l1 norm,which can be directly obtained through the proximal ***,an efficient structured sparse coding algorithm with the group log-regularizer for key frame extraction is developed,which can automatically extract a few frames directly from the video to represent the entire video with a low reconstruction *** results demonstrate that the proposed algorithm can extract more accurate key frames from most Sum Me videos compared to the stateof-the-art ***,the proposed algorithm can obtain a higher compression with a nearly 18% increase compared to sparse modeling representation selection(SMRS)and an 8% increase compared to SC-det on the VSUMM dataset.

关键词： Difference of convex algorithm(DCA) group logregularizer key frame extraction structured sparse coding

Stress evolution and support mechanism of a bolt anchored in a rock mass with a weak interlayer

在线全文

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2017年第3期27卷 573-580页

作者： ding shuxue Jing Hongwen Chen Kunfu Xu Guo'an Meng Bo State Key Laboratory for Geomechanics & Deep Underground Engineering School of Mechanics and Civil Engineering China University of Mining & Technology Xuzhou 221116 China

By applying experimental method, the bolt stress and supporting mechanism is studied during the deformation process of a rock mass containing a weak interlayer. The force measuring bolt is installed manually and instrumented five pairs of symmetrical strain gauges. The experimental results show that the fully grouted bolt suffers tensile, compressive, bending and shear stress at the same time. The bolt stress evolution is closely related to the deformation stages of the rock mass which are very gradually varying stage, gradually varying stage at the pre-peak and suddenly varying stage at the post peak *** axial compressive stress in the bolt is mainly induced by the moment. Thus, in most cases the axial compressive stress is distributed on one side of the bolt. For axial stresses, induced by the axial force and the bending moment at the post-peak stage, three types of changing are observed, viz. increasingincreasing type, decreasing-increasing type and increasing-decreasing type. The stress characteristics of the bolt section in the weak interlayer are significantly different from those in the hard rock. The failure models of the anchored bolt are tensile failure and shear failure, respectively. The bolt not only provides constraints on the free surface of the rock mass, but also resists the axial and lateral loading by the bending moment. This study provides valuable guidelines for bolting support design and its safety assessment.

关键词： Fully grouted bolt Stress evolution Support mechanism Weak interlayer Deformation process

夯实矸石压缩-固结蠕变成岩过程及等价采高模型分析

在线全文

学校读者我要写书评

暂无评论

河南理工大学学报（自然科学版） 2024年第6期43卷 27-37页

作者：许磊王思雨 ELMO Davide 丁书学刘洪林李文峰洪紫杰河南理工大学土木工程学院河南焦作454000 河南省地下空间开发及诱发灾变防治国际联合实验室河南焦作454000 英属哥伦比亚大学NBK矿业工程研究所温哥华V6T 1Z4加拿大新疆大学地质与矿业工程学院新疆乌鲁木齐830046 洛斯阿拉莫斯国家试验室洛斯阿拉莫斯87545新墨西哥美国

目的为了研究被夯实矸石压缩-固结蠕变成岩过程及其等价采高模型,方法以亭南煤业公司1102矸石充填工作面为工程背景,采用理论分析、数值模拟、室内试验、现场实测等方法进行研究。结果结果表明:矸石充填工作面最大控顶距=端面距+截割深... 详细信息

目的为了研究被夯实矸石压缩-固结蠕变成岩过程及其等价采高模型,方法以亭南煤业公司1102矸石充填工作面为工程背景,采用理论分析、数值模拟、室内试验、现场实测等方法进行研究。结果结果表明:矸石充填工作面最大控顶距=端面距+截割深度+顶梁长度+架后触矸距离;顶板回转下沉量等于最大控顶距乘以支架后倾角度正弦值;架后可充填空间高度等于采高减去顶板回转下沉量、欠接顶量、架后底鼓量。被夯实矸石在可充填空间内压缩-固结蠕变成岩的4个阶段及可充压缩率分别为骨架调整段(7.42%),缓慢压缩段(5.39%),固结沉降段(0.34%),蠕变成岩段(12.38%)。由该等价采高模型可知,1102工作面4阶段等价采高为骨架调整段0.94 m,缓慢压缩段1.10 m,固结沉降段1.11 m,蠕变成岩段1.48 m。结论通过概率积分法预测、数值模拟和沉陷观测对比可知,1102工作面走向和倾向主断面地表下沉曲线均为碗形。前两阶段地表下沉曲线平缓,后两阶段地表下沉曲线陡峭。

关键词：矸石充填等价采高矸石压实固结成岩

Motion artifact correction for MR images based on convolutional neural network

在线全文

学校读者我要写书评

暂无评论

Optoelectronics Letters 2022年第1期18卷 54-58页

作者： ZHAO Bin LIU Zhiyang ding shuxue LIU Guohua CAO Chen WU Hong College of Electronic Information and Optical Engineering Nankai UniversityTianjin 300350China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Nankai UniversityTianjin 300350China School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China Department of Medical Imaging Tianjin Huanhu HospitalTianjin 300350China

Magnetic resonance imaging(MRI)is a common way to diagnose related ***,the magnetic resonance(MR)images are easily defected by motion artifacts in their acquisition process,which affects the clinicians’*** order to correct the motion artifacts of MR images,we propose a convolutional neural network(CNN)-based method to solve the *** method achieves a mean peak signal-to-noise ratio(PSNR)of(35.212±3.321)dB and a mean structural similarity(SSIM)of 0.974±0.015 on the test set,which are better than those of the comparison methods.

关键词： neural methods. problem.

Indoor Positioning Using Public FM and DTMB Signals Based on Compressive Sensing

在线全文

学校读者我要写书评

暂无评论

China Communications 2019年第5期16卷 171-180页

作者： Menghuan Yang Hong Wu Zhiyang Liu shuxue ding Hongzhao Peng College of Electronic Information and Optical Engineering Nankai UniversityTianjin 300350China Tianjin Key Laboratory of Optoelectronic Sensor and Sensing Network Technology Tianjin 300350China School of Computer Science and Engineering University of AizuAizu-Wakamatsu 9658580Japan

Location-Based Services have become an indispensable part of our daily life, the sparsity of location finding makes it possible to estimate specific position by Compressive Sensing(CS). Using public Frequency Modulation(FM) broadcasting and Digital Television Terrestrial Multimedia Broadcasting(DTMB) signals, this paper presents an indoor positioning scheme, which is consisted of an offline stage and an online stage. In the offline stage, the Received Signal Strength(RSS) at the Reference Points(RPs) is measured, including the average and variance of public FM broadcasting and DTMB signals. In the online stage, the K-Weighted Nearest Neighbor algorithm is used to fulfill coarse positioning, which is able to narrow the selection scope of locations and choose partial RPs for accurate positioning. Then, the accurate positioning is implemented through CS. Experiment shows that the average positioning error of the proposed scheme is 1.63 m. What’s more, a CS-based method has been proposed in this paper to reduce the labor cost when collecting data. Experiment shows the average positioning error is 2.04 m, with the advantage of a 34% labor cost reduction. Experiment results indicate that the proposed system is a practical indoor positioning scheme.

关键词： indoor positioning compressive sensing FM broadcasting DTMB

Visual Positioning of Nasal Swab Robot Based on Hierarchical Decision

在线全文

学校读者我要写书评

暂无评论

Journal of Shanghai Jiaotong university(Science) 2023年第3期28卷 323-329页

作者：李国志邹水中丁数学 School of Artiﬁcial Intelligence Guilin University of Electronic TechnologyGuilin 541004GuangxiChina School of Electronic Engineering and Automation Guilin University of Electronic TechnologyGuilin 541004GuangxiChina

This study focuses on a robot vision localization method for coping with the operational task ofautomatic nasal swab sampling. The application is important in the detection and epidemic prevention of CoronaVirus Disease 2019 (COVID-19) to alleviate the large-scale negative impact of individuals suffering from pneumoniaowing to COVID-19. In this method, the idea of a hierarchical decision network is used to consider the stronginfectious characteristics of the COVID-19, which is followed by processing the robot behavior constraint *** visual navigation and positioning method using a single-arm robot for sampling is also planned, whichconsiders the operation characteristics of medical staff. In the decision network, the risk factor for potentialcontact infection caused by swab sampling operations is established to avoid the spread among personnel. A robotvisual servo control with artiﬁcial intelligence characteristics is developed to achieve a stable and safe nasal swabsampling operation. Experiments demonstrate that the proposed method can achieve good vision positioning forthe robots and provide technical support for managing new major public health situations.

关键词： surgical robot nasal swab sampling vision servo hierarchical decision

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

有机朗肯-蒸汽压缩复合式热泵系统性能研究

低温与超导 2017年第1期45卷 74-79页

作者：黄成达马国远许树学丁若晨北京工业大学环境与能源工程学院北京100124

建立了采用一种工质的有机朗肯-蒸汽压缩复合式热泵系统,给出了系统性能计算模型。基于此计算模型,比较筛选出复合系统最适宜的工质;研究了复合系统随发生器温度、蒸发温度、冷凝温度的变化特性。有关结论可为设计有机朗肯-蒸汽压缩式... 详细信息

建立了采用一种工质的有机朗肯-蒸汽压缩复合式热泵系统,给出了系统性能计算模型。基于此计算模型,比较筛选出复合系统最适宜的工质;研究了复合系统随发生器温度、蒸发温度、冷凝温度的变化特性。有关结论可为设计有机朗肯-蒸汽压缩式热泵系统提供理论指导。

关键词：有机朗肯热泵工质 COP

基于RBF网络逆辨识的LF炉电极系统控制策略

在线全文

学校读者我要写书评

暂无评论

采矿与安全工程学报 2017年第6期34卷 1094-1102页

作者：丁书学靖洪文齐燕军许国安张力杨利军龙景奎中国矿业大学深部岩土力学与地下工程国家重点实验室力学与土木工程学院江苏徐州221116

针对LF炉电极控制系统存在的非线性、模型不确定性、多输入多输出耦合的现象,通过可逆性分析,构造了网络辨识的逆模型;由于三相电极电流存在强耦合,因此通过逆控制器将其解耦成三个相互独立的伪线性控制回路.通过实验仿真,结果表明该控... 详细信息

针对LF炉电极控制系统存在的非线性、模型不确定性、多输入多输出耦合的现象,通过可逆性分析,构造了网络辨识的逆模型;由于三相电极电流存在强耦合,因此通过逆控制器将其解耦成三个相互独立的伪线性控制回路.通过实验仿真,结果表明该控制策略对电弧炉电极的解耦性能、跟踪性能和抗干扰能力起到较好的作用,能达到预期的效果.

关键词： RBF神经网络逆辨识 LF炉电极控制解耦控制

在线全文

学校读者我要写书评

暂无评论

深部应力集中区巷道变形规律的模拟研究

金属矿山 2009年第11期38卷 119-123页

作者：宋锦虎贺瑞霞白哲丁书学河南城建学院中国矿业大学

针对深部应力集中区巷道,采用物理模拟和数值模拟方法,研究其在高应力集中荷载作用下的变形特点。在物理模拟试验中采用数字照相量测技术进行变形分析,获得了巷道变形随时间的变化过程,以及动压作用对巷道变形的影响。在数值分析中采用... 详细信息

针对深部应力集中区巷道,采用物理模拟和数值模拟方法,研究其在高应力集中荷载作用下的变形特点。在物理模拟试验中采用数字照相量测技术进行变形分析,获得了巷道变形随时间的变化过程,以及动压作用对巷道变形的影响。在数值分析中采用多线性随动强化材料模型,针对试验结果进行对比计算分析,获得了动压情况下巷道变形、围岩塑性区的变化过程。综合分析得知深部高应力集中区巷道随时间会发生显著的收敛变形;当荷载增大时,围岩塑性区范围随之扩大,帮部围岩由于应力集中程度较高,其变形较顶底板更为显著。

关键词：深部巷道应力集中变形物理模拟数值模拟