检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Rasti, Behnood Hong, Danfeng Hang, Renlong Ghamisi, Pedram Kang, Xudong Chanussot, Jocelyn Benediktsson, Jon Atli Machine Learning Group Exploration Division Helmholtz Institute Freiberg for Resource Technology Helmholtz-Zentrum Dresden-Rossendorf Freiberg09599 Germany Univ. Grenoble Alpes CNRS Grenoble INP GIPSAlab Grenoble38000 France Jiangsu Key Laboratory of Big Data Analysis Technology School of Automation Nanjing University of Information Science and Technology Nanjing210044 China Machine Learning Group Exploration Division Helmholtz Institute Freiberg for Resource Technology Helmholtz-Zentrum Dresden-Rossendorf Freiberg09599 Germany College of Electrical and Information Engineering Hunan University Changsha410082 China Key Laboratory of Visual Perception and Artificial Intelligence of Hunan Province Changsha410082 China Univ. Grenoble Alpes Inria CNRS Grenoble INP LJK GrenobleF-38000 France Faculty of Electrical and Computer Engineering University of Iceland Reykjavik101 Iceland Faculty of Electrical and Computer Engineering University of Iceland Reykjavik107 Iceland

The final version of the paper can be found in IEEE Geoscience and Remote Sensing Magazine. Hyperspectral images provide detailed spectral information through hundreds of (narrow) spectral channels (also known as dimensionality or bands) with continuous spectral information that can accurately classify diverse materials of interest. The increased dimensionality of such data makes it possible to significantly improve data information content but provides a challenge to the conventional techniques (the so-called curse of dimensionality) for accurate analysis of hyperspectral images. Feature extraction, as a vibrant field of research in the hyperspectral community, evolved through decades of research to address this issue and extract informative features suitable for data representation and classification. The advances in feature extraction have been inspired by two fields of research, including the popularization of image and signal processing as well as machine (deep) learning, leading to two types of feature extraction approaches named shallow and deep techniques. This article outlines the advances in feature extraction approaches for hyperspectral imagery by providing a technical overview of the state-of-the-art techniques, providing useful entry points for researchers at different levels, including students, researchers, and senior researchers, willing to explore novel investigations on this challenging topic. In more detail, this paper provides a bird's eye view over shallow (both supervised and unsupervised) and deep feature extraction approaches specifically dedicated to the topic of hyperspectral feature extraction and its application on hyperspectral image classification. Additionally, this paper compares 15 advanced techniques with an emphasis on their methodological foundations in terms of classification accuracies. Furthermore, to push this vibrant field of research forward an impressive amount of codes and libraries is shared at: https://***/Behnoo

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “An Optimized RBF Neural Network Based on Beetle Antennae Search Algorithm for Modeling the Static Friction in a Robotic Manipulator Joint”

引用

Mathematical Problems in engineering 2020年第1期2020卷

作者： Yuxiang Wang Zhangwei Chen Hongfei Zu Xiang Zhang State Key Laboratory of Fluid Power and Mechatronics Systems Zhejiang University Hangzhou 310000 *** Faculty of Mechanical Engineering and Automation Zhejiang Sci-Tech University Hangzhou 310000 *** Institute of Computer Science Hangzhou Dianzi University Hangzhou 310000 ***

来源：评论

学校读者我要写书评

暂无评论

Sunspot Umbral Oscillation Analysis Using Wavelet Transform 29

Sunspot Umbral Oscillation Analysis Using Wavelet Transform

引用

第29届中国控制与决策会议

作者： Zeyuan Du Song Feng Yunnan Key Laboratory of Computer Technology Application/Faculty of Information Engineering and Automation Kunming University of Science and Technology

ISBN: (纸本)9781509046584

Umbral oscillation is one kind of basic phenomena appearing in *** measurement the oscillation period is quiet important for understanding the structure and evolution of sunspot.A long line of work indicates that there are two kinds of typical oscillations in sunspot umbral area:3-minute oscillations and 5-minute *** high quality observational sunspot data set obtained with the HINODE/Solar Optical Telescope in the Ca II H line on 20 August 2013 was employed to study the oscillation period of the chromosphere above a *** this paper,we used two kinds of wavelet transform methods to analyze sunspot umbral *** method based on continuous wavelet transform(CWT) was applied to analyze umbral oscillation period and frequency changing over *** other method based on cross wavelet transform(XWT) was used to analyze phase relationship between the two time *** outcomes demonstrate the viability and efficiency of the wavelet transform as a analyzing tool by accurately calculating period and studying phase difference.

关键词： Sunspot Umbral oscillation period Phase relationship Continuous wavelet transform Cross wavelet transform

来源：评论

学校读者我要写书评

暂无评论

A method of calculating the mean life-time of solar granules 29

A method of calculating the mean life-time of solar granules

引用

第29届中国控制与决策会议

作者： Jianshu Wang Song Feng Yunnan Key Laboratory of Computer Technology Application Faculty of Information Engineering and Automation Kunming University of Science and Technology

ISBN: (纸本)9781509046584

Solar granulation is a kind of morphological characteristics of solar photosphere caused by convective *** of the mechanism of convective motion,when we calculated the mean life-time of solar granules,we can get the time of convective *** are many methods based on the classification of solar granules and tracking solar granules to calculate the mean life-time of solar *** a result of the existence time of solar granules is very short and the evolution is more complex,identifying the fragmentation and merging of solar granules will get us into *** this paper,we present a power spectrum analysis based on periodic analysis method to calculate the mean life-time of solar ***,we use the κ-ω filter to remove the 5-minute *** removing the 5-minute oscillations can we more accurately calculate the mean life-time of solar ***,we use gradient transformation to remove the direct current component(DC component) and reduce spectral energy leakage with the Hamming ***,using the function of Periodogram calculates the mean life-time of solar *** order to verify the accuracy of the method,we set three data to calculate the mean life-time of solar *** final results of calculating the mean life-time of solar granules are 9.24 min,9.04 min and 10.67 min *** our method is effective and accurate compared with the results of other literature.

关键词： Solar granules k-ω filter Power spectrum The mean life-time

来源：评论

学校读者我要写书评

暂无评论

The Intelligent Search Method of Ambiguity Function Main Ridge Based on the Adaptive Differential Evolution Algorithm

The Intelligent Search Method of Ambiguity Function Main Rid...

引用

IEEE Information Technology and Mechatronics engineering Conference (ITOEC)

作者： Yunwei Pu Lanyu Ma Wentai Hou Yuanpu Guo Computer Center Kunming Univ. of Science and Tech. Kunming China Faculty of Information Engineering and Automation Kunming Univ. of Science and Tech.

ISBN: (纸本)9781538653746

The ambiguity function is an effective tool to solve the problem of radar emitter signals sorting in complex systems. To improve the real-time and accuracy of the ambiguity function main ridge (AFMR), this paper proposes an intelligent method to search AFMR based on adaptive differential evolution algorithm. The signal is pre-identified by the instantaneous frequency (IF) features to reduce the AFMR search range and the complexity of the problem. In this way, the differential evolution algorithm parameters can be adaptively adjusted according to the pre-recognition results to accelerate the convergence of the algorithm. Then the statistical hypothesis testing theory is used to analyze and test the search results. The experiment results show that the proposed method reduces the time of searching AFMR to about 4% compared with the exhaustive method with higher accuracy and stability.

关键词： Radar emitter signal Adaptive differential evolution algorithm Ambiguity function main ridge Signal sorting and recognition differential evolution algorithms Antiferromagnetic resonance ambiguity function evolutionary algorithm ambiguity Intelligent retrieval instantaneous frequency ridges Crest

来源：评论

学校读者我要写书评

暂无评论

Progressive LiDAR adaptation for road detection

arXiv

引用

arXiv 2019年

作者： Chen, Zhe Zhang, Jing Tao, Dacheng UBTECH Sydney Artificial Intelligence Centre School of Computer Science Faculty of Engineering and Information Technologies University of Sydney 6 Cleveland St DarlingtonNSW2008 Australia School of Software and Advanced Analytics Institute University of Technology Sydney 15 Broadway UltimoNSW2007 Australia School of Automation Hangzhou Dianzi University

Despite rapid developments in visual image-based road detection, robustly identifying road areas in visual images remains challenging due to issues like illumination changes and blurry images. To this end, LiDAR sensor data can be incorporated to improve the visual image-based road detection, because LiDAR data is less susceptible to visual noises. However, the main difficulty in introducing LiDAR information into visual image-based road detection is that LiDAR data and its extracted features do not share the same space with the visual data and visual features. Such gaps in spaces may limit the benefits of LiDAR information for road detection. To overcome this issue, we introduce a novel Progressive LiDAR Adaptation-aided Road Detection (PLARD) approach to adapt LiDAR information into visual image-based road detection and improve detection performance. In PLARD, progressive LiDAR adaptation consists of two subsequent modules: 1) data space adaptation, which transforms the LiDAR data to the visual data space to align with the perspective view by applying altitude difference-based transformation;and 2) feature space adaptation, which adapts LiDAR features to visual features through a cascaded fusion structure. Comprehensive empirical studies on the well-known KITTI road detection benchmark demonstrate that PLARD takes advantage of both the visual and LiDAR information, achieving much more robust road detection even in challenging urban scenes. In particular, PLARD outperforms other state-of-the-art road detection models and is currently top of the publicly accessible benchmark leader-board. Copyright © 2019, The Authors. All rights reserved.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

The use of cognitive maps in product development

The use of cognitive maps in product development

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Robert Demeter Attila Kovari Jozsef Katona Ilona Heldal Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania CogInfoCom Based LearnAbility Research Team Institute of Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Faculty of Psychology and Educational Sciences Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The aim of this study is to view product traceability using graph-based simulation software, which gives us a cognitive map of a product's path. In this paper, we present a method for manufacturers to efficiently and automatically visualize all components of their products, allowing for multiple changes or fault event in the supply chain.

关键词： Conferences Cognition Education Tools Product development Informatics

来源：评论

学校读者我要写书评

暂无评论

Examination of Gaze Fixations Recorded during the Trail Making Test

Examination of Gaze Fixations Recorded during the Trail Maki...

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Attila Kovari Jozsef Katona Ilona Heldal Carsten Helgesen Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Robert Demeter CogInfoCom Based LearnAbility Research Team Institute of Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Faculty of Psychology and Educational Sciences Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The continuous visual tracking of activity performed in perception and action activities requires continuous eye motion. The visual computer monitoring, recording and evaluation of human motion provides many opportunities in the development of human-computer interfaces. In most activities performed by humans, eye-hand coordination plays a significant role. From the eye-hand coordination aspect, the fixation's direction is an essential factor, since before touching an object, the look is aimed at the object to be touched for a longer period. In this paper, the fixation playing a major role in eye-hand coordination is being analyzed during the Trail Making Test. The test primarily aims to measure visual searching or scanning, visual-spatial sequencing; however, the eye-hand coordination's speed plays a key role in the quick and accurate execution of the test. During the test, eye motion parameters were recorded and determined, where further analyses make certain human cognitive factors indirectly able to be analyzed.

关键词： Tracking Task analysis Conferences Visualization Software Testing Cognition

来源：评论

学校读者我要写书评

暂无评论

Failure modes and effects analysis for an automatic level control system

Failure modes and effects analysis for an automatic level co...

引用

IEEE International Conference on automation, Quality and Testing, Robotics, AQTR

作者： Claudiu Bâlc Alexandru Cretu Dan Iudean Horaţiu Laslo Szilárd Enyedi Radu Munteanu Faculty of Electrical Engineering Technical University of Cluj-Napoca Cluj-Napoca Romania Faculty of Automation and Computer Science Technical University of Cluj-Napoca Cluj-Napoca Romania

An Automatic Level Control System is an important process that needs to be properly designed and monitored in order to determine and eliminate the critical failures that could result in the loss of the system. Water resource availability is an important problem and in a water distribution process the level and flow must be always known and monitored to keep the system running at full capacity and with minimal disruptions. If the systems are properly designed and the critical failures eliminated the process availability increases considerably. This paper presents a Failure Modes and Effects Analysis for an automatic level control system. This analysis gives an overview on the critical components of the system.

关键词： Level control Reliability Standards Sensor systems Manufacturing processes Process control

来源：评论

学校读者我要写书评

暂无评论

A quantitative study of using Cisco Packet Tracer simulation software to improve IT students’ creativity and outcomes

A quantitative study of using Cisco Packet Tracer simulation...

引用

International Conference on Cognitive Infocommunications (CogInfoCom)

作者： Robert Demeter Attila Kovari Jozsef Katona Ilona Heldal Cristina Costescu Adrian Rosan Andrea Hathazi Serge Thill Department of Automation and Information Technology Faculty of Electrical Engineering and Computer Science Transilvania University of Brasov Brasov Romania CogInfoCom Based LearnAbility Research Team Institute of Engineering Engineering University of Dunaujvaros Dunaujvaros Hungary Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Computing Mathematics and Physics Western Norway University of Applied Sciences Bergen Norway Special Education Department Babes-Bolyai University Cluj-Napoca Romania Donders Centre for Cognition Donders Institute for Brain Cognition and Behaviour Radboud University Nijmegen Netherland

ISBN: (数字)9781728147932

ISBN: (纸本)9781728147949

The continued development of ICT technologies has led to new ways of information communication. As is well known, the success of any new training or communication technology incorporates disseminating information, timeliness and efficiency and often incorporates simulation and virtual reality technologies. This paper presents the results of a quantitative study showing that simulation-based training strategies are more effective than traditional methods. The current case is for applying didactic teaching methodologies for learning ICT concepts for complex systems. The paper also compares the results of this study with previous studies and recommends strategies for using virtual reality elements to streamline learning process of engineering students.

关键词： computer networks Software Tools Education Hardware Intelligent sensors

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：