检索结果-内蒙古大学图书馆

Rolling element bearing fault diagnosis using convolutional neural network and vibration image

COGNITIVE systems RESEARCH 2019年 53卷 42-50页

作者： Hoang, Duy-Tang Kang, Hee-Jun Univ Ulsan Grad Sch Elect Engn Ulsan South Korea Univ Ulsan Sch Elect Engn Ulsan South Korea

Detecting in prior bearing faults is an essential task of machine health monitoring because bearings are the vital components of rotary machines. The performance of traditional intelligent fault diagnosis methods depend on feature extraction of fault signals, which requires signal processing techniques, expert knowledge, and human labor. Recently, deep learning algorithms have been applied widely in machine health monitoring. With the capacity of automatically learning complex features of input data, deep learning architectures have great potential to overcome drawbacks of traditional intelligent fault diagnosis. This paper proposes a method for diagnosing bearing faults based on a deep structure of convolutional neural network. Using vibration signals directly as input data, the proposed method is an automatic fault diagnosis system which does not require any feature extraction techniques and achieves very high accuracy and robustness under noisy environments. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Bearing fault diagnosis Convolutional neural network Deep learning Machine learning

来源：评论

学校读者我要写书评

暂无评论

Petascale XCT: 3D image Reconstruction with Hierarchical Communications on Multi-GPU Nodes

Petascale XCT: 3D Image Reconstruction with Hierarchical Com...

引用

International Conference on High Performance Computing, Networking, Storage and Analysis (SC)

作者： Hidayetoglu, Mert Bicer, Tekin de Gonzalo, Simon Garcia Ren, Bin De Andrade, Vincent Gursoy, Doga Kettimuthu, Raj Foster, Ian T. Hwu, Wen-mei W. Univ Illinois Champaign IL 61820 USA Argonne Natl Lab Lemont IL USA Barcelona Supercomp Ctr Barcelona Spain Coll William & Mary Williamsburg VA 23187 USA

ISBN: (纸本)9781728199986

X-ray computed tomography is a commonly used technique for noninvasive imaging at synchrotron facilities. Iterative tomographic reconstruction algorithms are often preferred for recovering high quality 3D volumetric images from 2D Xray images, however, their use has been limited to smalUmedium datasets due to their computational requirements. In this paper, we propose a high-perl4mance iterative reconstruction system for terabyte(s)-scale 31) volumes. Our design involves three novel optimizations: (1) optimization of (back)projection operators by extending the 2D memory -centric approach to 3D;(2) performing hierarchical communications by exploiting "fat -node" architecture with many GPUs;(3) utilization of mixed -precision types while preserving convergence rate and quality. We extensively evaluate the proposed optimizations and scaling on the Summit supercomputer. Our largest reconstruction is a mouse brain volume with 9Kx 11Kx 11K voxels, where the total reconstruction time is under three minutes using 24,576 GPUs, reaching 65 PELOPS: 34% of Summit's peak performance.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

Fast estimation of optical properties of pear using a single snapshot technique combined with a least-squares support vector regression model based on spatial frequency domain imaging

引用

APPLIED OPTICS 2019年第15期58卷 4075-4084页

作者： He, Xueming Li, Tingwei Fu, Xiaping Jiang, Xu Gao, Yingwang Rao, Xiuqin Zhejiang Univ Coll Biosyst Engn & Food Sci 866 Yuhangtang Rd Hangzhou 310058 Zhejiang Peoples R China Minist Agr Key Lab Site Proc Equipment Agr Prod Hangzhou 310058 Zhejiang Peoples R China Zhejiang Sci Tech Univ Fac Mech Engn & Automat Xiasha Higher Educ Zone 928 Second Ave Hangzhou 310018 Zhejiang Peoples R China

Spatial frequency domain imaging has great potential in agricultural produce quality control due to its advantage of wide-field mapping of absorption (mu(a)) and reduced scattering (mu(s)') parameters. However, it is not widely adopted in real applications due to the large time cost during image acquisition and inversion calculation processes. In this study, a single snapshot technique was used to obtain ac and dc components (R-d_ac, R-d _dc) of diffuse reflectance of turbid media (phantoms and pears). The validation results for the snapshot method indicate that at the spatial frequency of 1000/3 m(-1), it achieved the optimal demodulation, by comparison with the results obtained by the commonly used time-domain amplitude demodulation method. Diffusion approximation, artificial neural network, least-squares support vector machine regression (LSSVR), and LSSVR combined with a genetic algorithm (LSSVR + GA) were then used to predict mu(a) and mu(s)' from the obtained R-d_ac, R-d_dc at the f(x) of 1000/3 m(-1). Validation results indicated that the LSSVR method took the least time to calculate mu(a) and mu(s)' with high performance. The proposed imaging system and algorithm were implemented for the inspection of a pear bruise. Results indicated that the bruise, which is not obviously distinguishable in original gray maps, can show obvious contrast in calculated mu(a) and mu(s)' maps, especially mu(a )maps. Further, the contrast becomes more obvious with the passage of time. In summary, this study developed a low-cost spatial frequency imaging system and matching software that could realize fast detection of optical properties for a pear with the proposed snapshot and LSSVR algorithms. (C) 2019 Optical Society of America

关键词： Genetic algorithms image processing Imaging systems Laser imaging Spatial frequency Turbid media

来源：评论

学校读者我要写书评

暂无评论

Data collection and preliminary results on turbulence characterisation and mitigation techniques 16

Data collection and preliminary results on turbulence charac...

引用

Conference on Electro-Optical and Infrared systems - Technology and Applications XVI

作者： Velluet, M. -T. Bell, C. Daigle, J. -F. Dijk, J. Gladysz, S. Kanaev, A. Lambert, A. Lemaster, D. Potvin, G. Vorontsov, M. Off Natl Etud & Rech Aerosp French Aerosp Lab F-92322 Chatillon France Dstl Ft Halstead Sevenoaks TN14 7BP Kent England DRDC Valcartier Res Ctr 2459 Bravoure Rd Quebec City PQ Canada TNO POB 96864 NL-2509 JG The Hague Netherlands Fraunhofer Inst Optron Syst Technol & Image Explo Gutleuthausstr 1 D-76275 Ettlingen Germany NRL 4555 Overlook Av Washington DC 20375 USA UNSW Canberra Canberra ACT Australia US Air Force Res Lab 2241 Avion Circle Wright Patterson AFB OH 45433 USA Univ Dayton Sch Engn Intelligent Opt Lab 300 Coll Pk Dayton OH 45469 USA

ISBN: (数字)9781510630222

ISBN: (纸本)9781510630222

In the framework of NATO task group SET 226 on turbulence mitigation techniques for OA systems, a trial was conducted in the premises of RDDC-Valcartier, using indoor and outdoor facilities in September 2016. images data sets were collected under various turbulence conditions, both controllable (indoor) and natural (outdoor). The imagery of this trial was used in the Grand Challenge, where different experts were asked to process identical input data with state-of-the-art algorithms. The trial also provided a data-base to validate theoretical and numerical models. The paper will give an overview of the experiment set-up (target, sensors, turbulence screens generators.) and present some preliminary results obtained with the collected data in terms of effectiveness of image processing techniques, new methods for turbulence characterisation, modelling of laser beam propagation.

关键词： Turbulence propagation experiments image processing laser beam delivery adaptive optics

来源：评论

学校读者我要写书评

暂无评论

Key-Point Based Distribution Probability Optimization for Object Detection in Remote Sensing images

Key-Point Based Distribution Probability Optimization for Ob...

引用

International Conference on Computer and Communications (ICCC)

作者： Xiaoke Zhu Yufei Wang Xiaopan Chen Danyang Li Jitong Zhang Yulong Cai School of Computer and Information Engineering Henan University Kaifeng China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China

ISBN: (纸本)9781665409513

Recently, object detection in remote sensing images has been an important topic in computer vision. As a mainstream approach to detectors, single-stage detectors usually compute the important points of the bounding box to get the location of the target, and optimize them by Focal Loss. One of the development trends for one-stage detectors is to combine with Localization Quality Estimation (LQE), which can provide accurate ranking scores, and thus bring benefits to the Non-Maximum Suppression as well as the following detection results. In this paper, we propose a one-stage detector, named Key-point based Distribution Probability Optimization (KDPO), for remote sensing object detection. Specially, we first classify and locate the object through five key points. Then, we merge the quality estimation into the class prediction vector to form a joint representation of localization quality and classification. Next, we utilize a vector to represent arbitrary distribution of box locations. The improved representations avoid the inconsistency risk and accurately describe the flexible distribution of the data. Meanwhile, we use the improved Focal Loss for the succeed optimization. The proposed method is tested on two popular aerial image datasets, including HRSC2016 and DOTA. In all experiments, our approach achieves promising performance comparing to the state-of-the-art detectors.

关键词： Location awareness Heating systems Computer vision Estimation Detectors Object detection Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

Aerial Monitoring of Rice Crop Variables using an UAV Robotic System 16

Aerial Monitoring of Rice Crop Variables using an UAV Roboti...

引用

16th International Conference on Informatics in Control, Automation and Robotics (ICINCO)

作者： Devia, C. Rojas, J. Petro, E. Martinez, C. Mondragon, I Patino, D. Rebolledo, C. Colorado, J. Pontificia Univ Javeriana Sch Engn Bogota Colombia Int Ctr Trop Agr CIAT Agrodivers Palmira Colombia CIRAD AGAP Pam Montpellier France

ISBN: (纸本)9789897583803

This paper presents the integration of an UAV for the autonomous monitoring of rice crops. The system integrates image processing and machine learning algorithms to analyze multispectral aerial imagery. Our approach calculates 8 vegetation indices from the images at each stage of rice growth: vegetative, reproductive and ripening. Multivariable regressions and artificial neural networks have been implemented to model the relationship of these vegetation indices against two crop variables: biomass accumulation and leaf nitrogen concentration. Comprehensive experimental tests have been conducted to validate the setup. The results indicate that our system is capable of estimating biomass and nitrogen with an average correlation of 80% and 78% respectively.

关键词： UAV Precision Agriculture image processing Vegetative Indices Multispectral imagery Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Generation of Raman images through spectral mappings

引用

JOURNAL OF INTELLIGENT & FUZZY systems 2019年第5期36卷 4991-4999页

作者： Martinez-Espinosa, J. C. Cordova-Fraga, T. Guzman-Cabrera, R. Inst Politecn Nacl UPIIG Ind Puerto Interior Mineral Valenciana N 200 Silao De La Victoria Gto Mexico Univ Guanajuato Dept Ingn Fis Campus Leon Leon Gto Mexico Univ Guanajuato Dept Ingn Elect DICIS Campus IrapuatoSalamanca Km 3-5 Carretera Salama Leon Gto Mexico

In this work, we propose a practical approach to access and visualize relevant information on the spatial distribution on the anything sample about its biochemical composition. In order to carry out this analysis, we use a Raman spectroscopy technique to obtain spectral maps with specific spatial resolution (1 and 5 micrometers) over a selected region of the sample. Our study relies on the application of a Principal Component Analysis on the cross-correlations between the spectral blocks measured, within a certain spectral window of interest. The associated values of these principal components are used to build low-resolution images (with the same spatial resolution of the Raman scan) in which the relevant information on the chemical composition is already encoded. Finally, the spatial resolution of the principal components images was numerically enhanced in the post-processing through standard linear interpolation algorithms. In this way, we can map and visualize, simultaneously, the spatial and spectral information. The results suggest that the Raman spectroscopy imaging is a powerful tool for determining the biochemistry of organic and inorganic samples based on spectral scanning and thus determine compounds concentrations of medical interest. The proposed methodology is rather general and it could be extended to other spectroscopic measurement techniques where the spatial mapping of the spectral information is needed.

关键词： Raman spectroscopy principal components analysis spectral maps image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A robust image segmentation approach using fuzzy C-means clustering with local coefficient of variation

A robust image segmentation approach using fuzzy C-means clu...

引用

International Conference on Intelligent Computing, Communication and Devices, ICCD 2017

作者： Jiang, Xiaoliang Zhang, Dongsong Lin, Huan Li, Xin Xiao, Junjian Li, Bailin College of Mechanical Engineering Quzhou University Quzhou324000 China Southwest Jiaotong University Chengdu610031 China

ISBN: (纸本)9789811089435

image segmentation is a fundamental component in image processing, object tracking, and clinical research. Many scholars have proposed various techniques;however, fuzzy c-means (FCM) algorithms have been proven effectively. In order to retain more image details as well as canceling image noise, a novel clustering algorithm based on the local coefficient of variation is presented in this paper, termed as LCVFCM. The major characteristics of LCVFCM are: firstly, the local gray similarity matrix is modified based on the differences between median pixel and neighborhood pixels to reduce the impact of noise on image pixels, and secondly, a new fuzzy factor is established by introducing local coefficient of variation to improve the performance of LCVFCM. The corresponding experiments with a large number of synthetic and real images prove our model achieves excellent segmentation capability and has stronger anti-noise ability, as compared with other segmentation methods. © Springer Nature Singapore Pte Ltd. 2019.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

A component-driven distributed framework for real-time video dehazing

引用

MULTIMEDIA TOOLS AND APPLICATIONS 2018年第9期77卷 11259-11276页

作者： Wang, Meihua Mai, Jiaming Liang, Yun Cai, Ruichu Fu, Tom Zhengjia Zhang, Zhenjie South China Agr Univ Coll Math & Informat Guangzhou Guangdong Peoples R China Guangdong Univ Technol Sch Comp Sci & Technol Guangzhou Guangdong Peoples R China Illinois Singapore Pte Ltd Adv Digital Sci Ctr Singapore Singapore

Traditional dehazing techniques, as a well studied topic in image processing, are now widely used to eliminate the haze effects from individual images. However, the state-of-the-art dehazing algorithms may not provide sufficient support to video analytics, as a crucial pre-processing step for video-based decision making systems (e.g., robot navigation), due to poor coherence and low processing efficiency of the present algorithms. This paper presents a new framework, particularly designed for video dehazing, to output coherent results in real time, with two novel techniques. Firstly, we decompose the dehazing algorithms into three generic components, namely transmission map estimator, atmospheric light estimator and haze-free image generator. They can be simultaneously processed by multiple threads in the distributed system, such that the processing efficiency is optimized by automatic CPU resource allocation based on the workloads. Secondly, a cross-frame normalization scheme is proposed to enhance the coherence among consecutive frames, by sharing the parameters of atmospheric light from consecutive frames in the distributed computation platform. The combination of the above three components enables our framework to generate highly consistent and accurate dehazing results in real-time, by using only 5 PCs connected by Ethernet.

关键词： Video dehazing image restoration image enhancement Distributed computing

来源：评论

学校读者我要写书评

暂无评论

Secure Surveillance Framework for IoT systems Using Probabilistic image Encryption

引用

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 2018年第8期14卷 3679-3689页

作者： Muhammad, Khan Hamza, Rafik Ahmad, Jamil Lloret, Jaime Wang, Haoxiang Baik, Sung Wook Sejong Univ Digital Contents Res Inst Intelligent Media Lab Seoul 143747 South Korea Univ Batna 2 Dept Comp Sci Batna 05078 Algeria Univ Politecn Valencia Inst Inves Gest Integrada Zonas Costeras E-46022 Valencia Spain GoPercept Lab Ithaca NY USA Cornell Univ Ithaca NY 14853 USA

This paper proposes a secure surveillance framework for Internet of things (IoT) systems by intelligent integration of video summarization and image encryption. First, an efficient video summarization method is used to extract the informative frames using the processing capabilities of visual sensors. When an event is detected from keyframes, an alert is sent to the concerned authority autonomously. As the final decision about an event mainly depends on the extracted keyframes, their modification during transmission by attackers can result in severe losses. To tackle this issue, we propose a fast probabilistic and lightweight algorithm for the encryption of keyframes prior to transmission, considering the memory and processing requirements of constrained devices that increase its suitability for IoT systems. Our experimental results verify the effectiveness of the proposed method in terms of robustness, execution time, and security compared to other image encryption algorithms. Furthermore, our framework can reduce the bandwidth, storage, transmission cost, and the time required for analysts to browse large volumes of surveillance data and make decisions about abnormal events, such as suspicious activity detection and fire detection in surveillance applications.

关键词： Industrial Internet of things (IoT) information security lightweight image encryption surveillance networks video summarization

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：