检索结果-内蒙古大学图书馆

3rd ieee symposium on computational intelligence in Control and Automation (CICA)

作者： Pitel', Jan Mizak, Jozef Tech Univ Kosice Fac Mfg Technol Dept Math Informat & Cybernet Presov Slovakia

ISBN: (纸本)9781467358934

Artificial intelligence techniques have been used for carbon monoxide and oxygen low cost sensors signal processing in biomass combustion. Considering a large scatter of the measured data two approximation tools using artificial neural networks have been tested for approximation of carbon monoxide emissions dependence on oxygen concentration in the flue gas: AForge. Neuro library and Neural Network Fitting Tool of Matlab. The comparable results of approximation have been obtained by testing of both approximation tools on the off-line measured data.

关键词： arificial neural networks biomass combustion carbon monoxide emissions oxygen concentration

来源：评论

学校读者我要写书评

暂无评论

A PARALLEL ARCHITECTURE FOR DISCRETE RELAXATION ALGORITHM

引用

ieee TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE intelligence 1987年第6期9卷 816-831页

作者： GU, J WANG, W HENDERSON, TC UNIV UTAH DEPT ELECT ENGNSALT LAKE CITYUT 84112

Discrete relaxation techniques have proven useful in solving a wide range of problems in digital signal and digital image processing, artificial intelligence, operations research, and machine vision. Much work has been devoted to finding efficient hardware architectures. This paper shows that a conventional hardware design for a Discrete Relaxation Algorithm (DRA) suffers from O(n2m3) time complexity and O(n2m2) space complexity. By reformulating DRA into a parallel computational tree and using a multiple tree-root pipelining scheme, time complexity is reduced to O(nm), while the space complexity is reduced by a factor of 2. For certain relaxation processing, the space complexity can even be decreased to O(nm). Furthermore, a technique for dynamic configuring an architectural wavefront is used which leads to an O(n) time highly concurrent DRA3 architecture.

关键词： Parallel architectures Hardware signal processing Digital images Artificial intelligence Operations research Machine vision Computer architecture Algorithm design and analysis Concurrent computing

来源：评论

学校读者我要写书评

暂无评论

Why Ricker Wavelets Are Successful in processing Seismic Data: Towards a Theoretical Explanation

Why Ricker Wavelets Are Successful in Processing Seismic Dat...

引用

ieee symposium Series on computational intelligence

作者： Gholamy, Afshin Kreinovich, Vladik Univ Texas El Paso Computat Sci Program El Paso TX 79968 USA

ISBN: (纸本)9781479945092

In many engineering applications ranging from engineering seismology to petroleum engineering and civil engineering, it is important to process seismic data. In processing seismic data, it turns out to be very efficient to describe the signal's spectrum as a linear combination of Ricker wavelet spectra. In this paper, we provide a possible theoretical explanation for this empirical efficiency. Specifically, signal propagation through several layers is discussed, and it is shown that the Ricker wavelet is the simplest non-trivial solution for the corresponding data processing problem, under the condition that the described properties of the approximation family are satisfied.

关键词： seismic waves signal processing wavelet transforms Ricker wavelet spectra seismic data processing signal propagation signal spectrum Approximation methods Convolution Earthquakes Fourier transforms Probability density function Random variables Seismic waves seismic waves Seismic data processing signal spectrum Approximation method Random variable Fourier Transform Probability density function wavelet transforms Convolution Earthquakes signal processing seismic data wavelets seismology engineering sciences

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Networks Improve Vein image Quality 17

Deep Convolutional Neural Networks Improve Vein Image Qualit...

引用

17th ieee International symposium on computational intelligence and Informatics (CINTI)

作者： Kashihara, Koji Tokushima Univ Grad Sch Sci & Technol 2-1 Minamijyousanjima Tokushima 7708506 Japan

ISBN: (纸本)9781509039098

Analysis of near-infrared images has a possibility to simply find vein disease. If super-resolution (SR) techniques improve the quality of near-infrared images with a low signal-to-noise ratio, they could detect abnormal veins at an early stage. Deep convolutional neural networks (DCNNs) as a SR technique were applied to downgraded images, and the effectiveness was investigated. The DCNNs with the optimal structure and parameters improved the vein image quality, although the target images contained complicated shapes of veins. Furthermore, the DCNN may estimate the hidden information on actual veins. In future, creating of an e-healthcare system with SR techniques will be useful for the quick evaluation of abnormal veins.

关键词： Veins Convolution image resolution Shape Kernel Cameras image quality Veins image quality image resolution Convolution Cameras mineral dyke target image Kernel Vein Disorder SAVANNAH RIVER OPERATIONS OFFICE Strontium Infrared imaging Shape Neural network

来源：评论

学校读者我要写书评

暂无评论

X-ray image segmentation using active contour model with global constraints

X-ray image segmentation using active contour model with glo...

引用

ieee symposium on computational intelligence in image and signal processing

作者： Jiang, Y. Meng, J. Babyn, P. Ryerson Univ Dept Comp Sci 350 Victoria St Toronto ON M5B 2K3 Canada Hosp Sick Children 555 Univ Ave Toronto ON M5G 1X8 Canada

ISBN: (纸本)9781424407071

This paper presents an image segmentation method that outlines fractured bones in an X-ray image of a patient's arm within cast materials, and displays the alignment between the fractured bones. The cast material overlaying on the fractured bones creates extra noises to the X-ray image and provides challenges to the segmentation method. Our segmentation method aims on outlining the objects from a low contrast and high noise ratio of the X-ray images. A geodesic active contour model with global constraints is applied to this segmentation task. A prior shape is collected and embedded into the active contour model as a global constraint. A maximum-likelihood function is derived and used as a feedback system for each evolving process to a decision making procedure. Mutual Information is employed to measure the difference or the likelihood between the prior shape and the evolving curve. Experimental results show that the method produces the outlines of the fractured bones on the low contrast X-ray images robustly and accurately. The computation of our segmentation method is fast and efficient.

关键词： bone diagnostic radiography feature extraction image segmentation maximum likelihood estimation medical image processing X-ray image segmentation cast materials fractured bone alignment geodesic active contour model maximum-likelihood function patient ar image segmentation diagnostic radiography casting material Medical image processing maximum likelihood estimation Feature extraction Feedback X-rays

来源：评论

学校读者我要写书评

暂无评论

Tilt-Then-Blur or Blur-Then-Tilt? Clarifying the Atmospheric Turbulence Model

引用

ieee signal processing LETTERS 2022年 29卷 1833-1837页

作者： Chan, Stanley H. Purdue Univ Sch Elect & Comp Engn W Lafayette IN 47907 USA

Imaging at a long distance often requires advanced image restoration algorithms to compensate for the distortions caused by atmospheric turbulence. However, unlike many standard restoration problems such as deconvolution, the forward image formation model of the atmospheric turbulence does not have a simple expression. Thanks to the Zernike representation of the phase, one can show that the forward model is a combination of tilt (pixel shifting due to the linear phase terms) and blur (image smoothing due to the high order aberrations). Confusions then arise between the ordering of the two operators. Should the model be tilt-then-blur, or blur-then-tilt? Some papers in the literature say that the model is tilt-then-blur, whereas more papers say that it is blur-then-tilt. This paper clarifies the differences between the two and discusses why the tilt-then-blur is the correct model. Recommendations are given to the research community.

关键词： Atmospheric modeling image restoration Mathematical models Phase distortion computational modeling Refractive index Optical distortion Atmospheric turbulence image restoration forward model simulation convolution signal processing

来源：评论

学校读者我要写书评

暂无评论

Fast Cube Matching Using Orthogonal Tree-Structured Haar Transform for Multispectral images 11

Fast Cube Matching Using Orthogonal Tree-Structured Haar Tra...

引用

11th International symposium on image and signal processing and Analysis (ISPA)

作者： Ito, Izumi Pizurica, Aleksandra Tokyo Inst Technol Informat & Communicat Engn Tokyo Japan Univ Ghent Telecommun & Informat Proc Ghent Belgium

ISBN: (纸本)9781728131405

Multispectral images contain several wavelength bands and hence have rich information. All the methods for grayscale images can be applied to multispectral images by processing each band separately. However, it requires a vast computational time, especially for the task of looking for overlapping patches that are similar to a given query patch. To address this problem, we propose cube matching using orthogonal tree-structured Haar transform (OTSHT) for multispectral images. By using three-dimensional integral images, we reduce computational complexity significantly. We demonstrate superior performance of the proposed cube matching.

关键词： Haar transform matching multispectral image

来源：评论

学校读者我要写书评

暂无评论

Optimising the performance of soft computing agents for classification of unstained mammalian cell images

Optimising the performance of soft computing agents for clas...

引用

ieee International symposium on computational intelligence for Measurement Systems and Applications

作者： Khosla, R Lai, C Mitsukura, Y La Trobe Univ Business Sys & Knowledge Modelling Lab Sch Business Melbourne Vic 3086 Australia

ISBN: (纸本)0780377834

Most existing approaches for determining serious pathological conditions involve analysis of stained images of human tissue. In this paper we describe a multi-agent distributed control system model for image processing of unstained human (mammalian) cell images. The control system model develops a symbiotic relationship between soft computing agents like neural networks and water immersion and morphological agents for segmentation and classification of cells in unstained Chinese hamster ovarian image samples.

关键词： Computer networks Control system synthesis Distributed control Humans image analysis image processing image segmentation Neural networks Pathology Symbiosis

来源：评论

学校读者我要写书评

暂无评论

computational Measuring Approach for the Identification of Probable Intestinal System Pathologies through the Human Iris Parameters

Computational Measuring Approach for the Identification of P...

引用

22nd symposium on image, signal processing and Artificial Vision (STSIVA)

作者： Miranda, Julian D. Salinas, Sergio A. Pontifical Bolivarian Univ Fac Syst & Informat Engn Bucaramanga Colombia Pontifical Bolivarian Univ Fac Elect & Elect Engn Bucaramanga Colombia

ISBN: (纸本)9781728114910

Iridology is the science that aims to identify certain human pathologies through human iris by using manual visual methods. These methods, although they are less invasive, are cumbersome. In this paper, a detailed description of the results obtained by applying an algorithmic approach for the automatic identification, calculation, and computation measurements of the key internal parameters of the human eye iris and specific organic pathologies related to the intestinal system is presented. Results evidence that using composition and basic segmentation of human iris, it is possible to execute propitious computational procedures for the determination of organic anomalies in the intestinal system.

关键词： Iris recognition Iris Pathology Colon Diseases Tools image color analysis

来源：评论

学校读者我要写书评

暂无评论

Lung segmentation on x-ray images with neural validation

Lung segmentation on x-ray images with neural validation

引用

ieee symposium Series on computational intelligence (ieee SSCI)

作者： Polap, Dawid Wozniak, Marcin Silesian Tech Univ Inst Math Kaszubska 23 PL-44100 Gliwice Poland

ISBN: (纸本)9781538627266

Lung segmentation on x-ray images is an important part in the process of feature extraction for recognition purposes. Using it we can extract specific data from the input image. Segmentation allows to remove unnecessary elements such as bones and spine, leaving in the image only the lungs. This solution reduces the area of the image subjected to further analysis in terms of disease detection. In this paper, segmentation technique based on graphics processing methods and swarm algorithm was presented. A swarm methodology was used for extraction of particular portions of the information for which we have applied convolutional neural network as a detector. For the composed method we have performed tests to show and discuss the results.

关键词： medical image processing image segmentation convolutional neural network

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：