检索结果-内蒙古大学图书馆

Automatic Characterization of Benign and Malignant Masses in Mammography

Procedia computer science 2015年 46卷 1762-1769页

作者： K. Vaidehi T.S. Subashini Research Scholar Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University India Associate Professor Department of Computer Science and EngineeringFaculty of Engineering and Technology Annamalai University India

The paper aims to develop an automated breast mass characterization system for assisting the radiologist to analyze the digital mammograms. Mammographic Image Analysis Society (MIAS) database images are used in this study. Fuzzy C-means technique is used to segment the mass region from the input image. GLCM texture features namely contrast, correlation, energy and homogeneity are obtained from the region of interest. The texture features extracted from gray level co-occurrence matrix (GLCM) are computed at distance d=1 and θ=0 o , 45 o , 90 o , 135 o . These with three classifiers namely adaboost, back propagation neural network and sparse representation classifiers are used for characterizing the region containing either benign mass or malignant mass. The experimental results show the SRC classifier is more effective with an accuracy of 93.75% and with the Mathew's correlation coefficient (MCC) of 87.35%.

关键词： Benign and malignant mass classification Fuzzy C-Means clustering Sparse representation classifier Mathews correlation coefficient.

来源：评论

学校读者我要写书评

暂无评论

Approximate String Search in Large Spatial Database

引用

Procedia computer science 2015年 47卷 92-100页

作者： M. TamilSelvi R. Renuga PG Scholar Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore - 641014 India Associate Professor Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore - 641014 India

Applications are featured with both text and location information, which leads to a search like: spatial approximate string search (SAS). Mainly four issues are identified in the general area of SAS. They are: (i) Spatial approximate string search in Euclidean space (E sas ); (ii) Spatial approximate string search on road networks (R SAS ); (iii) Selectivity Estimation for E sas Range Queries; (iv) Multi-Approximate-Keyword Routing query on road networks. For efficiently answering spatial approximate string queries in Euclidean space, SAS propose a novel index structure, IR 2 -tree, which is based on the R-tree augmented with the min-wise signature and the linear hashing technique. Extensive experiments on large real data sets demonstrate the efficiency and effectiveness of the proposed approach.

关键词： Spatial Database Spatial Queries Min-wise signature Range Query Road Networks

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Parallel Computing Using Cuda for Chemical Process

引用

Procedia computer science 2015年 47卷 237-246页

作者： S. Sosutha D. Mohana PG Scholar Department of Computer Science and EngineeringCoimbatore Institute of Technology Coimbatore and 641014 India Associate Professor Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore and 641014 India

CUDA ( Compute Unified Device Architecture ) is a parallel computing platform and programming model created by NVIDIA and implemented by the graphics processing units (GPUs) that they produce. Using CUDA, the GPUs can be used for general purpose processing which involves parallel computation. CUDA has been used to accelerate non-graphical applications in computational biology, cryptography and other fields by an order of magnitude or more. Chemical processes need validation of their experimental data. It was found that Chemical process could become one such application where CUDA can be efficiently used. These validations of Chemical processes normally involve calculation of many coefficients. The chemical process that has been chosen for parallelizing is Heat Transfer process. This process involves calculation of coefficients for multiple iterations. As each of these iterations is independent of one another, CUDA was used to parallelize the calculation process. The execution time analysis shows that though CPU outperforms GPU when the numbers of iterations are less, when the number of iterations increase the GPU outperforms CPU greatly.

关键词： Heterogeneous Computing CUDA Heat transfer application

来源：评论

学校读者我要写书评

暂无评论

Automatic Classification of Cardiac Views in Echocardiogram Using Histogram and Statistical Features

引用

Procedia computer science 2015年 46卷 1569-1576页

作者： G.N. Balaji T.S. Subashini N. Chidambaram Research scholar Department of computer science and Engineering Faculty of Engineering and Technology Annamalai University India Associate professor Department of computer science and Engineering Faculty of Engineering and Technology Annamalai University India Professor and Head Department of Cardiology Faculty of Medicine Annamalai University India

Automatic classification cardiac views is the first step to automate wall motion analysis, computer aided disease diagnosis, measurement computation etc. In this paper a fully automatic classification of cardiac view in echocardiogram is proposed. The system is built based on a machine learning approach which characterizes two features 1) Histogram features and 2) Statistical features. In this system four standard views parasternal short axis (PSAX), parasternal long axis (PLAX), apical two chamber (A2C) and apical four chamber (A4C) views are classified. Experiments over 200 echocardiogram images show that the proposed method with an accuracy of 87.5% can be effectively used in cardiac view classification.

关键词： parasternal short axis (PSAX) parasternal long axis (PLAX) apical two chamber (A2C) and apical four chamber (A4C).

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Agent Based Framework

引用

Procedia computer science 2015年 47卷 37-44页

作者： K. Sindhuja A.V. Monisha S. Padmavathi Post Graduate Student Computer Science and Engineering Thiagarajar College of Engineering Madurai and 625015 India Under Graduate Student Computer Science and Engineering Thiagarajar College of Engineering Madurai and 625015 India Associate Professor Computer Science and Engineering Thiagarajar College of Engineering Madurai and 625015 India

Cloud computing is the delivery of on-demand computing resources – everything from applications to datacenters over the internet on pay per use basis. Service composition in cloud is an important mechanism usually done through several scheduling policies or by dynamic resource allocation techniques. Services delivered to the users lack Quality of Service during this composition phase. Hence, an Agent-based cloud computing paradigm for resource allocation is proposed that consist of designing and developing software agents for cloud service discovery, finding appropriate service and service composition. Here, two types of agents are created – consumer agent that process the user requirements and service provider agent that clusters the output from consumer agent. Finally, each user is mapped to each producer. Experimental results shows efficient execution of user requests using agent with 100% success execution rate in a parallel manner than that of using Hadoop.

关键词： Agent Hadoop Service discovery Service composition Consumer Agent Service Provider Agent

来源：评论

学校读者我要写书评

暂无评论

Fabrication of the Kinect Remote-controlled Cars and Planning of the Motion Interaction Courses

引用

Procedia - Social and Behavioral sciences 2015年 174卷 3102-3107页

作者： Ke-Yu Lee Jhih-Sian Jheng Shiang-Chih Chen Shi-Jer Lou Associate Professor Department of Computer Science and Information Engineering Cheng Shiu University Taiwan Professor Graduate Institue of Technological and Vocational Education National Pingtung University of Science and Technology Taiwan

This paper describes the fabrication of Kinect remote-controlled cars, using PC, Kinect sensor, interface control circuit, embedded controller, and brake device, as well as the planning of motion interaction courses. The Kinect sensor first detects the body movement of the user, and converts it into control commands. Then, the PC sends the commands to Arduino control panel via XBee wireless communication modules. The interface circuit is used to control movement and direction of motors, including forward and backward, left and right. In order to develop the content of Kinect motion interaction courses, this study conducted literature review to understand the curriculum contents, and invited experts for interviews to collect data on learning background, teaching contents and unit contents. Based on the data, the teaching units and outlines are developed for reference of curriculums.

关键词： Kinect motion interaction embedded control remote controlled cars

来源：评论

学校读者我要写书评

暂无评论

Unique Sense: Smart Computing Prototype

引用

Procedia computer science 2015年 50卷 223-228页

作者： S. Vijaykumar S.G. Saravanakumar M. Balamurugan Student School of Computer Science Engineering and Applications Bharathidasan University Trichy – 23 TamilNadu India Associate Professor School of Computer Science Engineering and Applications Bharathidasan University Trichy – 23 TamilNadu India

Unique sense: Smart computing prototype is a part of “unique sense” computing architecture, which delivers alternate solution for today's computing architecture. This computing is one step towards future generation needs, which brings extended support to the ubiquitous environment. This smart computing prototype is the light weight compact architecture which is designed to satisfy all the needs of this society. The proposed solution is based on the hybrid combination of cutting edge technologies and techniques from the various layers. In addition it achieves low cost architecture and eco-friendly to meet all the levels of people's needs.

关键词： Smart Computing HPC Prototype ARM Hadoop

来源：评论

学校读者我要写书评

暂无评论

Generic Feature Learning in computer Vision

引用

Procedia computer science 2015年 58卷 202-209页

作者： D. Kanishka Nithin P. Bagavathi Sivakumar M.TECH. Scholar Department of Computer Science and Engineering Amrita VishwaVidyapeetham(University) Coimbatore India 641112 Associate Professor Department of Computer Science and Engineering Amrita VishwaVidyapeetham(University) Coimbatore India 641112

Current Machine learning algorithms are highly dependent on manually designing features and the Performance of such algo- rithms predominantly depend on how good our representations are. Manually we might never be able to produce best and diverse set of features that closely describe all the variations that occur in our data. Understanding this, vision community is moving towards learning the optimum features itself instead of learning from the features. Traditional hand engineered features lack in generalizing well to other domains/Problems, are time consuming, expensive, requires expert knowledge on the problem domain and doesn’t facilitate learning from previous learnings/Representations(Transfer learning). All these issues are resolved in learning deep representations. Since 2006 a wide range of representation learning algorithms has been proposed but by the recent success and breakthroughs of few deep learning models, the representation learning algorithms have gained the spotlight. This paper aims to give short overview of deep learning approaches available for vision tasks. We also discuss their applicability (With respect to their properties) in vision field.

关键词： Feature learning Generic features Vision Recognition Supervised learning Unsupervised learning Deep learning Convolution Neural networks RBM Autoencoders

来源：评论

学校读者我要写书评

暂无评论

Analysis for Maximal Optimized Penalty for the Scheduling of Jobs with Specific Due Date on a Single Machine with Idle Time

引用

Procedia computer science 2015年 47卷 247-254页

作者： D. Jagan A.N. Senthilvel R. Prabhakar S. Uma Maheswari PG Scholar Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore - 641014 India Assistant Professor(SG) Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore - 641014 India Emeritus Professor Department of Computer Science and Engineering Coimbatore Institute of Technology Coimbatore - 641014 India Associate Professor Department of Electronics and Communication Engineering Coimbatore Institute of Technology Coimbatore641014 India

In the real world the Scheduling of Jobs in industries is provided without any idle time which is very tedious. Practically it becomes difficult when any of the spare part has started to malfunction and has to be changed in the machine then some idle time is needed in order to undergo the change. In this proposed work some amount of idle time is allotted to schedule the jobs in a single machine which includes three stages namely scheduling strategy, inserting idle time and optimizing the net penalty value of all the jobs.

关键词： Single machine scheduling Early/Tardy scheduling optimization techniques

来源：评论

学校读者我要写书评

暂无评论

Classification and Prediction of Stock Market Index Based on Fuzzy Metagraph

引用

Procedia computer science 2015年 47卷 214-221页

作者： Thirunavukarasu Anbalagan S. Uma Maheswari Teaching Fellow Department of Computer science and Engineering Anna University University College of Engineering Ramanathapuram-623513 Tamilnadu India Associate Professor Department of Electronics and Communication Engineering Coimbatore Institute of Technology Coimbatore641014 Tamilnadu India

Stock market price forecasting is one of the challenging tasks due to the difficulty in predicting the non-linear and non-stationary time series data. In this paper a Fuzzy Metagraph (FM) based stock market decision making, classification and prediction are proposed for short term investors of Indian stock market. Simple Moving Average (SMA), Exponential Moving Average (EMA), Moving Average Convergence Divergence (MACD) and Relative Strength Index (RSI) are some of the Technical Indicators which are used as input to train the system which is integrated with Fuzzy Metagraph. This approach of incorporating FM with SMA, MACD and RSI would be a new attempt in classification and prediction on share market investment. Stocks listed in Bombay Stock Exchange (BSE) in India are used to evaluate the performance of the system. The results obtained from the proposed FM based model are found to be satisfactory with very low risk error.

关键词： FIS Fuzzy Metagraph Stock Market Classification Stock Market Prediction RSI MACD SVM

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：