检索结果-内蒙古大学图书馆

A method for classification accuracy evaluation for a precipitation-oriented classifier

INTERNATIONAL JOURNAL OF REMOTE SENSING 2005年第21期26卷 4785-4800页

作者： Anthis, AI Cracknell, AP Reg Meteorol Ctr Hellen Tact Air Force Hellen Natl Meteorol Serv Larisa Greece Univ Dundee Div Elect Engn & Phys Dundee Scotland

A method of classification accuracy evaluation for a cloud and precipitation classifier applied to geostationary meteorological satellite data is presented. The method has been developed to evaluate the accuracy of a rather precise classification algorithm. The algorithm produces nine classes, four of which involve precipitation. The classes are: (1) clear or insignificant cloud, (2) low thin cloud with no rain, (3) low or middle thin cloud with no rain, (4) low or middle thick cloud with no rain, (5) middle or high cloud with no rain, (6) middle or high cloud with the possibility of rain, (7) middle or high cloud with light-moderate precipitation, (8) middle-high cloud with moderate-heavy precipitation, (9) heavy thunderstorm. The evaluation classifier has been tested for its accuracy (ground truth) using comparison between actual meteorological weather reports and classification results derived from the algorithm applied. For the estimation of classification accuracy, the omission/commission method is applied between the observed and the classification-produced values. The classifier used has proved to be very reliable for classifying major cloud types and precipitation, tested during the synoptic situation of depression systems approaching the south Balkan Peninsula from the west. In that synoptic situation, different intensities of rainfall as well as heavy thunderstorm were present, and the results are very satisfactory. The method can be used to evaluate classification results produced by algorithms applied to meteorological satellite data, classifying precipitation areas as well as the heaviness of precipitation.

关键词： Classifiers Cloud Types algorithms mean point rain Satellite Imagery sorting algorithm

来源：评论

学校读者我要写书评

暂无评论

Video Behavior Analysis Using Topic Models and Rough Sets

引用

IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE 2013年第1期8卷 56-67页

作者： Zhao, Liang Shang, Lin Gao, Yang Yang, Yubin Jia, Xiuyi Nanjing Univ Nanjing Jiangsu Peoples R China Nanjing Univ Sci & Technol Nanjing Jiangsu Peoples R China

Video behavior analysis is both meaningful and challenging in computer vision. As the monitoring equipment become readily cheaper and available, massive video data have been generated. As abnormal behaviors are rare, manual surveillance may drastically increase the chances of false positives or false negatives. It is hence useful to achieve automatic surveillance. Abnormal behaviors are usually complex and short. It is however difficult to completely list the abnormal behaviors. We can view abnormalities as outliers. Sometimes abnormalities co-occur with normalities, which cannot be distinguished in some feature space.

关键词： Analytical models Classification algorithms Computational modeling Computer vision Data models Feature extraction Rough sets Rough sets Feature extraction ANALYSIS MODELS monitoring equipment data models Eigenvector behavioral research abnormal behavior computer vision sorting algorithm Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Brownian Motus and Clustered Binary Insertion Sort methods: An efficient progress over traditional methods

引用

FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2018年 86卷 266-280页

作者： Goel, Shubham Kumar, Ravinder Thapar Inst Engn & Technol Comp Sci & Engn Dept Patiala 147004 Punjab India

sorting is the basic operation in every application of computer science. The paper proposes two novel sorting algorithms based on the concept of traditional Insertion Sort (IS). Firstly, Brownian Motus Insertion Sort (BMIS) based on IS is proposed. It is followed by Clustered Binary Insertion Sort (CBIS) based on the principles of Binary Insertion Sort (BIS). BIS is a binary search enhancement of IS which is a quite famous variant of it. Average case time complexity of BMIS is 0((0.54)root n);and that of CBIS is 0(n log n). The scenario which results into the worst case of IS is with the complexity of 0(n(2));and BIS with 0(n log n) is the best case scenario for BMIS and CBIS with complexity of 0(n). The probability of getting a worst case scenario for BMIS and CBIS is approximately zero. Comparison of proposed algorithms with IS and BIS has been performed at 25%, 50%, 75% and 100% level of randomness in the initial dataset. These results lead to prove our claim of devising efficient enhancements of IS. The results further reveal that performance of BMIS and CBIS will increase with a decrease in randomness level of the dataset in comparison to its counterparts. The number of comparisons required by BMIS and CBIS will approach to 0(n) with randomness level approach to zero. So, for nearly sorted datasets, our proposed BMIS and CBIS are the best choice. Both BMIS and CBIS are in-place, stable and online sorting algorithm. (C) 2018 Elsevier B.V. All rights reserved.

关键词： Brownian Motus insertion sort Clustered Binary Insertion Sort Insertion sort Binary insertion sort sorting algorithm Online algorithm

来源：评论

学校读者我要写书评

暂无评论

A comparison of classification algorithms for the identification of smoke plumes from satellite images

引用

STATISTICAL METHODS IN MEDICAL RESEARCH 2011年第2期20卷 131-156页

作者： Wan, V. Braun, W. J. Dean, C. B. Henderson, S. Simon Fraser Univ Dept Stat & Actuarial Sci Burnaby BC V5A 1S6 Canada Univ Western Ontario Dept Stat & Actuarial Sci London ON N6A 5B7 Canada Univ British Columbia Sch Environm Hlth Vancouver BC V5Z 1M9 Canada

Obtaining accurate measures of exposure to forest fire smoke is important for the assessment of health risk. Estimating exposure from air quality monitors is challenging because of the sparseness of the monitoring networks in remote areas. However, satellite imagery offers a novel and data-rich tool to provide visual information on smoke plumes. We will discuss statistical techniques for obtaining estimates of forest fire smoke plumes using classification algorithms on data from satellite imagery in order to develop automated processes for identifying exposure. The aim is to identify whether such methods may offer a high-resolution approach that provides a reliable estimate of smoke and a more thorough caption of the spatial distribution of smoke from fires than is currently available.

关键词： Health risk assessment Smoke visual information statistical techniques sorting algorithm

来源：评论

学校读者我要写书评

暂无评论

Single-Molecule Study of Ribosome Hierarchic Dynamics at the Peptidyl Transferase Center

引用

BIOPHYSICAL JOURNAL 2010年第9期99卷 3002-3009页

作者： Altuntop, Mediha Esra Ly, Cindy Tu Wang, Yuhong Univ Houston Dept Biol & Biochem Houston TX 77004 USA

During protein biosynthesis the ribosome moves along mRNA in steps of precisely three nucleotides. The mechanism for this ribosome motion remains elusive. Using a classification algorithm to sort single-molecule fluorescence resonance energy transfer data into subpopulations, we found that the ribosome dynamics detected at the peptidyl transferase center are highly inhomogeneous. The pretranslocation complex has at least four subpopulations that sample two hybrid states, whereas the posttranslocation complex is mainly static. We observed transitions among the ribosome subpopulations under various conditions, including 1), in the presence of EF-G;2), spontaneously;3), in different buffers, and 4), bound to antibiotics. Therefore, these subpopulations represent biologically active ribosomes. One key observation indicates that the Hy2 hybrid state only exists in a fluctuating ribosome subpopulation, which prompts us to propose that ribosome dynamics are hierarchically arranged. This proposal may have important implications for the regulation of cellular translation rates.

关键词： Peptidyl Transferases Subpopulations Ribosomes sorting algorithm

来源：评论

学校读者我要写书评

暂无评论

On automatic cloud detection over ocean

引用

INTERNATIONAL JOURNAL OF REMOTE SENSING 2001年第15期22卷 3047-3052页

作者： Kärner, O Di Girolamo, L Tartu Astrophys Observ EE-61602 Toravere Estonia Univ Illinois Urbana IL 61801 USA

An automatic cloud classification algorithm is proposed for the Advanced Very High Resolution Radiometer (AVHRR), based on a 5-D histogram technique. The technique determines three-level (high, medium, low) cloud amount and the average cloud-top brightness temperature (BT) and reflectance for 128 x 128 pixel areas. Comparison of the products for NOAA-11 AVHRR measurements during 14 orbits over oceans with the International Satellite Cloud Classification Project DX products for the same AVHRR data set is presented.

关键词： oceans Reflectance international satellite sorting algorithm

来源：评论

学校读者我要写书评

暂无评论

Detecting bruises on 'Golden Delicious' apples using hyperspectral imaging with multiple wavebands

引用

BIOSYSTEMS ENGINEERING 2005年第1期90卷 27-36页

作者： Xing, J Bravo, C Jancsók, PT Ramon, H De Baerdemaeker, J Catholic Univ Louvain Dept Agro Engn & Econ Lab Agr Machinery & Proc B-3001 Louvain Belgium

In this research, the potential of using a multi-spectral imaging system was investigated for detecting bruises on 'Golden Delicious' apples. For this purpose, a hyperspectral imaging system has been built in the spectral region between 400 and 1000nm. Based on the principal components analysis for the hyperspectral images, four wavebands were selected for a multi-spectral imaging test. The principal components analysis on the multi-spectral images gave very similar results as on the hyperspectral images. The second and third principal components scores images were found to be suitable for identifying the presence of bruises. An image processing and classification algorithm based on moments thresholding was developed. The classification results indicated that, for the sample population used in this experiment, about 93% of the non-bruised apples were recognised as sound. An accuracy of about 86% was achieved for detecting bruises, although all the bruised regions were found to remain in the images after moments thresholding. (C) 2004 Published by Elsevier Ltd. on behalf of Silsoc Research Institute.

关键词： multispectral imagery sorting algorithm spectral region component analysis multi-spectral image Contusions Moment of force hyperspectral imagery Crab Apple

来源：评论

学校读者我要写书评

暂无评论

Trigger processing using reconfigurable logic in the CMS calorimeter trigger

引用

NUCLEAR INSTRUMENTS & METHODS IN PHYSICS RESEARCH SECTION A-ACCELERATORS SPECTROMETERS DETECTORS AND ASSOCIATED EQUIPMENT 2001年第1-3期461卷 505-506页

作者： Brooke, JJ Cussans, DG Heath, GP Maddox, AJ Newbold, DM Rabbetts, PD Univ Bristol HH Wills Phys Lab Bristol BS8 1TL Avon England Rutherford Appleton Lab Didcot OX11 0QX Oxon England

We plc sent the design of the Global Calorimeter Trigger processor for the CMS detector at LHC. This is a fully pipelined processor system which collects data from all the CMS calorimeters and produces summary information used in forming the Level-1 trigger decision for each event. The design in based on the use of state-of-the-art reconfigurable logic devices (FPGAs) and fast data links. We present the results of device testing using a low-latency pipelined sort algorithm, which demonstrate that an FPGA can be used to perform processing previously foreseen to require custom ASICs. Our design approach results in a powerful, flexible and compact processor system. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： sorting algorithm PROCESSOR Reconfigurable logic Meltdown Field programmable gate arrays Large Hadron Collider device test Calorimeters

来源：评论

学校读者我要写书评

暂无评论

Partially distributed representations of objects and faces in ventral temporal cortex

引用

JOURNAL OF COGNITIVE NEUROSCIENCE 2005年第4期17卷 580-590页

作者： O'Toole, AJ Jiang, F Abdi, H Haxby, JV Univ Texas Sch Behav & Brain Sci Richardson TX 75083 USA Princeton Univ Princeton NJ 08544 USA

Object and face representations in ventral temporal (VT) cortex were investigated by combining object confusability data from a computational model of object classification with neural response confusability data from a functional neuroimaging experiment. A pattern-based classification algorithm learned to categorize individual brain maps according to the object category being viewed by the subject. An identical algorithm learned to classify an image-based, view-dependent representation of the stimuli. High correlations were found between the confusability of object categories and the confusability of brain activity maps. This occurred even with the inclusion of multiple views of objects, and when the object classification model was tested with high spatial frequency "line drawings" of the stimuli. Consistent with a distributed representation of objects in VT cortex, the data indicate that object categories with shared image-based attributes have shared neural structure.

关键词： Temporal Lobe Computational modeling sorting algorithm representations brain activity spatial frequency

来源：评论

学校读者我要写书评

暂无评论

Development of a Hyperspectral Imaging System for the Early Detection of Apple Rottenness Caused by Penicillium

引用

JOURNAL OF FOOD PROCESS ENGINEERING 2015年第5期38卷 499-509页

作者： Zhang, Bao-Hua Li, Jiang-Bo Zheng, Ling Huang, Wen-Qian Fan, Shu-Xiang Zhao, Chun-Jiang Meng, Qing-Da Beijing Acad Agr & Forestry Sci Beijing Res Ctr Intelligent Equipment Agr Beijing 100097 Peoples R China Shanghai Jiao Tong Univ State Key Lab Mech Syst & Vibrat Shanghai 200240 Peoples R China

Automatic detection of early rottenness caused by Penicillium is still a challenge due to the high similarity between the rotten region and sound tissue, and the large variations in surface background color of apples. A hyperspectral reflectance imaging system and a systematic approach were developed to detect the early rottenness caused by Penicillium on Fuji apples. The principal component analysis of the hyperspectral reflectance images in the full region (400-1,000nm) of spectra was used to develop hyperspectral image analytical algorithm and select the efficient wavelengths. Independent component analysis (ICA) based on the selected efficient wavelengths (810 and 970nm, respectively) and simple thresholding methods were used to segment and classify the rottenness from the sound tissue. Finally, ICA-based image processing and classification algorithm was developed based on the images at 810 and 970nm to realize the fast inspection of early rottenness. The detection result with 97% overall accuracy indicated that the proposed system and algorithm were efficient and suitable for the detection of the early rottenness caused by Penicillium on Fuji apples. This study was the first attempt to use hyperspectral imaging system to detect the early rottenness caused by Penicillium on Fuji apples and would lay a foundation for the development of multispectral imaging system for fast inspection of rottenness. The limitation of our research is the limited inspection view of the samples. Future work will be focused on simultaneous whole surface inspection using multispectral imaging system. Practical ApplicationsThe algorithm and results in our paper can provide a foundational basis to develop a real-time inspection system to detect rottenness on apples in the postharvest processing line, or develop a monitoring system to monitor the quality changes in storage shelf.

关键词： hyperspectral imagery automatic detection Imaging Crab Apple Early Diagnosis surface inspection Fujiyama Penicillium sorting algorithm

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：