检索结果-内蒙古大学图书馆

第32届中国控制与决策会议

作者： Zhu Haijie Li Jiafeng Cheng Sifan Qin Linlin Department of Automation University of Science and Technology of China

The ORB,SIFT,and SURF algorithms are currently common feature matching *** three algorithms have certain differences in execution speed and matching *** this paper,the data sets provided by Mikolajczyk and Schmid are used to compare the algorithms in terms of execution speed,image transformation robustness,and noise *** conclusion of this paper is that the ORB algorithm is the fastest,the SURF algorithm is the most robust,and the SIFT algorithm has the most feature points.

关键词： ORB SIFT SURF Feature Matching algorithm comparison

来源：评论

学校读者我要写书评

暂无评论

CROSS-comparison OF THREE SAR SOIL MOISTURE RETRIEVAL algorithmS USING SYNTHETIC AND EXPERIMENTAL DATA 38

CROSS-COMPARISON OF THREE SAR SOIL MOISTURE RETRIEVAL ALGORI...

引用

38th IEEE International Geoscience and Remote Sensing Symposium (IGARSS)

作者： Balenzano, A. Satalino, G. Lovergine, F. Mattia, F. Cartus, O. Davidson, M. Al-Khaldi, M. Johnson, J. CNR ISSIA Bari Italy Gamma Remote Sensing Res & Consulting AG GAMMA Gumlingen Switzerland Estec ESA NL-2201 Noordwijk Netherlands Ohio State Univ Dept Elec & Comp Eng Columbus OH 43210 USA

ISBN: (纸本)9781538671504

The objective of this study is to cross-compare three algorithms for retrieving surface soil moisture (SSM) from ESA's Sentinel-1 (S-1) data. The context is provided by the large scientific and application interest in SSM products at high resolution and regional/continental scale that can be retrieved from S-1 data alone or in combination with other missions such as NASA/SMAP and ESA/SMOS. Of the three investigated algorithms, one inverts a scattering model exploiting a Bayesian approach, whereas the other two are change detection approaches. The cross-comparison is carried out by using both simulated and experimental data. Strengths and weaknesses of the three algorithms are identified and discussed.

关键词： Soil Moisture Sentinel-1 algorithm comparison Validation

来源：评论

学校读者我要写书评

暂无评论

Ethylene-vinyl acetate foam as a new lung substitute in radiotherapy

引用

MEDICAL PHYSICS 2018年第4期45卷 1715-1723页

作者： Marques, Enrique Mancha, Pedro J. Virgen del Puerto Hosp Dept Med Phys Plasencia 10600 Caceres Spain Infanta Cristina Hosp Dept Med Phys Badajoz 06006 Spain

PurposeThe purpose of this study was to evaluate ethylene-vinyl acetate (EVA) foam as a new lung substitute in radiotherapy and to study its physical and dosimetric characteristics. MethodsWe calculated the ideal vinyl acetate (VA) content of EVA foam sheets to mimic the physical and dosimetric characteristics of the ICRU lung tissue. We also computed the water-to-medium mass collision stopping power ratios, mass attenuation coefficients, CT numbers, effective atomic numbers and electron densities for: ICRU lung tissue, the RANDO commercial phantom, scaled WATER and EVA foam sheets with varying VA contents in a range between the minimum and maximum values supplied by the manufacturer. For all these substitutes, we simulated percent depth-dose curves with EGSnrc Monte Carlo (MC PDDs) in a water-lung substitute-water slab phantom expressed as dose-to-medium and dose-to-water for 3x3- and 10x10-cm(2) field sizes. PDD for the 10x10-cm(2) field size was also calculated with the MultiGrid Superposition algorithm (MGS PDD) for a relative electron density to water ratio of 0.26. The latter was compared with the MC PDDs in dose-to-water for scaled WATER and EVA foam sheets with the VA content that was most similar to the calculated ideal content that is physically achievable in practice. ResultsWe calculated an ideal VA content of 55%;however, the maximum physically achievable content with current manufacturing techniques is 40%. The physical characteristics of the EVA foam sheets with a VA content of 40% (EVA40) are very close to those of the ICRU lung reference. The physical densities of the EVA40 foam sheets ranged from 0.030 to 0.965g/cm(3), almost covering the entire physical density range of the inflated/deflated lung (0.260-1.050g/cm(3)). Its mass attenuation coefficient at the effective energy of a 6-MV photon beam agrees within 0.8% of the ICRU reference value, and its CT number agrees within 6HU. The effective atomic number for EVA40 varies by less than 0.42 of the

关键词： algorithm comparison dosimetric characteristics ethylene-vinyl acetate foam lung substitute physical characteristics

来源：评论

学校读者我要写书评

暂无评论

Infrared image segmentation algorithm for defect detection based on FODPSO

引用

INFRARED PHYSICS & TECHNOLOGY 2019年 102卷

作者： Tang, Qingju Gao, Shuaishuai Liu, Yongjie Yu, Fengyun Heilongjiang Univ Sci & Technol Sch Mech Engn Harbin 150022 Heilongjiang Peoples R China

To address the problems of high noise and fuzzy edges of acquired infrared images when detecting debonding defective components of SiC thermal barrier coating structure by pulsed infrared thermal waves, an image segmentation method based on fractional Darwin particle swarm optimization algorithm (FODPSO) is adopted to reconstruct infrared image sequences. This algorithm adopts fractional calculus to control the convergence of the system, and can perform n - 1 threshold optimization calculation on n - 1 level images. Experimental results show that FODPSO algorithm effectively overcomes the shortcomings of traditional algorithm such as easy to enter local optimal and slow convergence speed, and can realize the edge identification of SiC coating defects. The processed image improves the contrast and signal-to-noise ratio.

关键词： Fractional order Fractional-order Darwin particle swarm algorithm Infrared image Edge detection Multi-scale segmentation algorithm comparison SiC coating

来源：评论

学校读者我要写书评

暂无评论

Optimal Combination of Predictors and algorithms for Forest Above-Ground Biomass Mapping from Sentinel and SRTM Data

引用

REMOTE SENSING 2019年第4期11卷

作者： Chen, Lin Wang, Yeqiao Ren, Chunying Zhang, Bai Wang, Zongming Chinese Acad Sci Northeast Inst Geog & Agroecol Key Lab Wetland Ecol & Environm Changchun 130102 Jilin Peoples R China Univ Chinese Acad Sci Beijing 100049 Peoples R China Univ Rhode Isl Dept Nat Resources Sci 1 Greenhouse Rd Kingston RI 02881 USA

Accurate forest above-ground biomass (AGB) mapping is crucial for sustaining forest management and carbon cycle tracking. The Shuttle Radar Topographic Mission (SRTM) and Sentinel satellite series offer opportunities for forest AGB monitoring. In this study, predictors filtered from 121 variables from Sentinel-1 synthetic aperture radar (SAR), Sentinal-2 multispectral instrument (MSI) and SRTM digital elevation model (DEM) data were composed into four groups and evaluated for their effectiveness in prediction of AGB. Five evaluated algorithms include linear regression such as stepwise regression (SWR) and geographically weighted regression (GWR);machine learning (ML) such as artificial neural network (ANN), support vector machine for regression (SVR), and random forest (RF). The results showed that the RF model used predictors from both the Sentinel series and SRTM DEM performed the best, based on the independent validation set. The RF model achieved accuracy with the mean error, mean absolute error, root mean square error, and correlation coefficient in 1.39, 25.48, 61.11 Mgha(-1) and 0.9769, respectively. Texture characteristics, reflectance, vegetation indices, elevation, stream power index, topographic wetness index and surface roughness were recommended predictors for AGB prediction. Predictor variables were more important than algorithms for improving the accuracy of AGB estimates. The study demonstrated encouraging results in the optimal combination of predictors and algorithms for forest AGB mapping, using openly accessible and fine-resolution data based on RF algorithms.

关键词： optimal predictors algorithm comparison Sentinel-1 SAR Sentinel-2 MSI SRTM DEM forest AGB mapping

来源：评论

学校读者我要写书评

暂无评论

Model Prediction of Defects in Sheet Metal Forming Processes 1

引用

19th International Conference on Engineering Applications of Neural Networks (EANN)

作者： Dib, Mario Ribeiro, Bernardete Prates, Pedro Univ Coimbra Ctr Informat & Syst Univ Coimbra CISUC Coimbra Portugal Univ Coimbra Ctr Mech Engn Mat & Proc CEMMPRE Coimbra Portugal

ISBN: (数字)9783319982045

ISBN: (纸本)9783319982045;9783319982038

Predicting defects is a challenge in many processing steps during manufacturing because there is a great number of variables involved in the process. In this paper, we take a machine learning perspective to choose the best model for defects prediction of sheet metal forming processes. An empirical study is presented with the objective to choose the best machine learning algorithm that will be able to perform accurately this task. For building the model, three distinct datasets were created using numerical simulation for three mild steel materials: mild steel, DH600, HSLA340. The numerical simulation was performed on the basis of sixteen input features representing characteristics of the materials. Moreover, two kinds of defects, springback and maximum thinning, each one is binary with 1 (defects) and 0 (non-defects) were considered in the simulator. The experimental setup consists of running MLP, CART, NB, RF and SVM algorithms using cross-validation for correctly choosing model parameters. The results were averaged in 30 runs and the standard deviations recorded. The initial conclusion is that the learning algorithm scores differently depending on the type of defect and conditions of the experiment. Although the preliminary results show good performance of the algorithms in simulated environment, a further study with real data will be addressed in future work.

关键词： Machine learning Manufacturing process Predictive model Defect prediction algorithm comparison

来源：评论

学校读者我要写书评

暂无评论

Unveiling the development of intracranial injury using dynamic brain EIT: an evaluation of current reconstruction algorithms

引用

PHYSIOLOGICAL MEASUREMENT 2017年第9期38卷 1776-1790页

作者： Li, Haoting Chen, Rongqing Xu, Canhua Liu, Benyuan Tang, Mengxing Yang, Lin Dong, Xiuzhen Fu, Feng Fourth Mil Med Univ Dept Biomed Engn Xian 710032 Shaanxi Peoples R China Imperial Coll London Dept Biomed Engn London SW7 2AZ England

Objective: Dynamic brain electrical impedance tomography (EIT) is a promising technique for continuously monitoring the development of cerebral injury. While there are many reconstruction algorithms available for brain EIT, there is still a lack of study to compare their performance in the context of dynamic brain monitoring. Approach: To address this problem, we develop a framework for evaluating different current algorithms with their ability to correctly identify small intracranial conductivity changes. Firstly, a simulation 3D head phantom with realistic layered structure and impedance distribution is developed. Next several reconstructing algorithms, such as back projection (BP), damped least-square (DLS), Bayesian, split Bregman (SB) and GREIT are introduced. We investigate their temporal response, noise performance, location and shape error with respect to different noise levels on the simulation phantom. The results show that the SB algorithm demonstrates superior performance in reducing image error. To further improve the location accuracy, we optimize SB by incorporating the brain structure-based conductivity distribution priors, in which differences of the conductivities between different brain tissues and the inhomogeneous conductivity distribution of the skull are considered. We compare this novel algorithm (called SB-IBCD) with SB and DLS using anatomically correct head shaped phantoms with spatial varying skull conductivity. Main results and Significance: The results showed that SB-IBCD is the most effective in unveiling small intracranial conductivity changes, where it can reduce the image error by an average of 30.0% compared to DLS.

关键词： dynamic electrical impedance tomography brain injury algorithm comparison inhomogeneous brain conductivity distribution

来源：评论

学校读者我要写书评

暂无评论

Best practices for comparing optimization algorithms

引用

OPTIMIZATION AND ENGINEERING 2017年第4期18卷 815-848页

作者： Beiranvand, Vahid Hare, Warren Lucet, Yves Univ British Columbia Dept Comp Sci Kelowna BC Canada Univ British Columbia Dept Math Kelowna BC Canada

Comparing, or benchmarking, of optimization algorithms is a complicated task that involves many subtle considerations to yield a fair and unbiased evaluation. In this paper, we systematically review the benchmarking process of optimization algorithms, and discuss the challenges of fair comparison. We provide suggestions for each step of the comparison process and highlight the pitfalls to avoid when evaluating the performance of optimization algorithms. We also discuss various methods of reporting the benchmarking results. Finally, some suggestions for future research are presented to improve the current benchmarking process.

关键词： Benchmarking algorithm comparison Guidelines Performance Software Testing Metric Timing Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Security algorithms for IoT devices 5

Performance Analysis of Security Algorithms for IoT devices

引用

5th IEEE-Region-10 Humanitarian Technology Conference (R10-HTC)

作者： Khan, Nuzhat Sakib, Nazmus Jerin, Ismot Quader, Shaela Chakrabarty, Amitabha BRAC Univ Dept Comp Sci & Engn Dhaka Bangladesh

ISBN: (纸本)9781538621752

Internet of things (IoT) has gained tremendous attention in today's world, IoT ecosystem is growing and showing us a glimpse of how the future will look in the coming days. However, the IoT sector is not impeccable, security is still a threat for the IoT devices as these devices are meant for low power usage for small scale setups. Security algorithms are not abrupt, but many of them don't fit the IoT systems as their compatibility can only rely on products with larger form factor (Which usually means better performance, storage etc.). In this paper, the main concern has been to investigate the performance of different security algorithms and compare them in terms of processing cycle and execution timein Raspberry Pi. The paper has worked with FLECC_IN_C and Crypto++(R), two different cryptographic libraries and measured their performance in a constrained environment. It is the first of its kind, to this paper's knowledge, to use raspberry pi which is established as black box device and implemented security algorithms on it. The paper in the end shows a summarised view of several key algorithms and decides which is better in the terms of IoT constraints.

关键词： IoT security algorithm cryptography Crypto plus plus (R) flecc_in_c algorithm comparison security analysis data security embedded device security

来源：评论

学校读者我要写书评

暂无评论

Is a comparison of results meaningful from the inexact replications of computational experiments?

引用

SOFT COMPUTING 2016年第1期20卷 223-235页

作者： Crepinsek, Matej Liu, Shih-Hsi Mernik, Luka Mernik, Marjan Univ Maribor SLO-2000 Maribor Slovenia Calif State Univ Fresno Fresno CA 93740 USA CALTECH Pasadena CA 91125 USA

The main objective of this paper is to correct the unreasonable and inaccurate criticism to our previous experiments using Teaching-Learning-Based Optimization algorithm and to quantify the amount of error that may arise due to incorrect counting of fitness evaluations. It is shown that inexact experiment replication should be avoided in comparisons between meta-heuristic algorithms whenever possible. Otherwise, an inexact replication and margin of error should be explicitly reported.

关键词： Teaching-learning-based optimization algorithm comparison Replication of experiments

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：