检索结果-内蒙古大学图书馆

Visualization and Classification of Diseases using Deep Learning Based Convolution Neural Network

IOP Conference Series: Materials Science and Engineering 2020年第1期937卷

作者： D.A Janeera P. Amudhavalli P Sherubha S.P Sasirekha P. Anantha Christu Raj R Sitharthan Assistant Professor Sri Krishna College of Engineering and Technology Coimbatore Assistant Professor Department of Computer Applications B S AbdurRahman Crescent Institute of Science and Technology Chennai Independent Researcher Coimbatore ORCID: 0000-0002-5945-2402 Research Scholar Karpagam Academy of Higher Education Coimbatore Assistant Professor Robotics Engineering Karunya Institute of Technology and Sciences Coimbatore School of Electrical Engineering Vellore Institute of Technology Vellore

In the contemporary phase of big data, data visualization is one of the challenging segment of the discovery process. For a classifier, the primary goal is to identify the hidden levels of big data. The performance of classifiers depends on the feature space, number of classes and size of the data. To improve the reliability, efficiency and accuracy of the classifiers, new algorithms are required for analysis. This paper enables classification and visualization of information on diseases using a Deep Learning based Convolution Neural Network classifier. For feature selection and handling massive data in analysis of multivariate data is performed using particle swarm optimization (PSO) and principal component analysis (PCA) techniques. Real-world datasets are utilized for demonstration of the proposed learning algorithm. Deep learning classifiers are scientifically higher and offers better performance when compared to other classifiers according to the comparative study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A rational cognitive architectural model of language generation

引用

Procedia computer Science 2018年 132卷 149-156页

作者： Meenakhi Sahu Hima Bindu Maringanti Assistant Prfessor North Orissa University Baripada Odisha 757003 India Professor Computer Science and Applications North Orissa University Baripada Odisha 757003 India

In this paper, a prototype model demonstrating the rationality in humans is developed. For queries to be answered, the internal knowledge representation mechanism is understood to be in the form of inter-related clusters permanently stored in the long term memory (LTM). In response to a query involving a single predicate (simplest case), only one cluster along with its various attributes and values may be retrieved. In contrast, a complex query involving multiple predicates requires the retrieval of multiple related chunks, forming a network of knowledge, often referred to as a concept map, from which the response is generated. An internal process that happens is the matching of predicate of the question with the facts in the knowledge-base and retrieval of the chunk(s) with the corresponding Attribute-Value pairs, through a process akin to unification, a substitution procedure. However, an unanswered query due to the absence of a specific knowledge generates a negative response.

关键词： Memory model Brain map ACT-R Knowledge representation Concept map Chunks Association rule Short Term Memory Language understanding generation

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Survey of Spam Profile Detection Methods in Online Social Networks

引用

Journal of Physics: Conference Series 2019年第1期1362卷

作者： R. Krithiga E. Ilavarasan Assistant Professor Department of Computer Applications Perunthalaivar Kamaraj Arts College Puducherry Professor Department of Computer Science & Engineering Pondicherry Engineering College Puducherry

Social networks have grown into a popular way for internet surfers to interact with friends in addition to family members, reading news, and also discuss events. Users spend more time on popular social platforms (e.g., Facebook, Twitter, etc.) storing and sharing their personal information. This fact together with the prospect of communicating thousands of users fascinates the concentration of malicious users. They exploit the implicit trust interactions concerning users with the purpose of accomplishing their malicious objectives, for instance, create malicious links inside the posts/tweets, spread fake news, send out unsolicited messages to genuine users and so on. In this paper, we reviewed various existing techniques on spam profile detection in online social networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dealing of Data Pre-processing with Computational Intelligence for Sampling and Analysis of Soil-Case Bidar District-Karnataka.

引用

Journal of Physics: Conference Series 2018年第1期1142卷

作者： Sangayya Gulledmath V Arulkumar Research Scholar Department of Computer Science and Applications Reva University Yelahanka Bangalore-560064 India Assistant Professor Department of Computer Science and Applications Reva University Yelahanka Bangalore-560064 India

Data Mining and Knowledge Discovery becomes buzzwords from last two decades. Data Mining as we all know its trending industry in Data Analytics and knowledge representation. This research article initiates novel approach of how Data Mining can be relatively used in Agricultural domain and their applications more dominant in the specified area of soil classification and soil fertility. Now Data Analysis is becoming part of our life why can't we consider our own farmers to empower them to use more knowledge-oriented techniques to yield the good crop. I have taken Bidar District in Karnataka for soil Sampling and Analysis of Soil. Data pre-processing is challenging, important and critical step in the data mining process and it has enormous scope and it directly impacts the success of data mining process. There are many pre-processing techniques but which one makes better selection for agricultural data sets is vital task of the computational challenges that needs to address and incorporate more suitable one for the better representation of knowledge in soil sampling and analysis.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Software Citations and the ACAT Community

引用

Journal of Physics: Conference Series 2018年第2期1085卷

作者： Daniel S. Katz Assistant Director for Scientific Software and Applications National Center for Supercomputing Applications (NCSA) Research Associate Professor Computer Science (CS) Research Associate Professor Electrical and Computer Engineering (ECE) Research Associate Professor School of Information Sciences (iSchool) University of Illinois Urbana-Champaign Urbana Illinois 61801 USA

Software is essential for the bulk of research today. It appears in the research cycle as infrastructure (both inputs and outputs, software obtained from others before the research is performed and software provided to others after the research is complete), as well as being part of the research itself (e.g., new software development). To measure and give credit for software contributions, the simplest path appears to be to overload the current paper citation system so that it also can support citations of software. A multidisciplinary working group built a set of principles for software citation in late 2016. Now, in ACAT 2017 and its proceedings, we want to experimentally encourage those principles to be followed, both to provide credit to the software developers and maintainers in the ACAT community and to try out the process, potentially finding flaws and places where it needs to be improved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Modified Frame Difference Method Using Correlation Coefficient for Background Subtraction

引用

Procedia computer Science 2016年 93卷 478-485页

作者： P. Ramya R. Rajeswari Phd Research Scholar Department of Computer Applications Bharathiar University Coimbatore and 641046 India Assistant Professor Department of Computer Applications Bharathiar University Coimbatore and 641046 India

Background subtraction is one of the most important step in video surveillance which is used in a number of real life applications such as surveillance, human machine interaction, optical motion capture and intelligent visual observation of animals, insects. Background subtraction is one of the preliminary stages which are used to differentiate the foreground objects from the relatively stationary background. Normally a pixel is considered as foreground if its value is greater than its value in the reference image. Hence, every pixel has to be compared to find the foreground and background pixel. This paper presents a technique which improves the frame difference method by first classifying the blocks in the frame as background and others using correlation coefficient. Further refinement is performed by performing pixel-level classification on blocks which are not considered as background. Experiments are conducted on standard data-sets and the performance measures shows good results in some critical conditions.

关键词： Background Subtraction Frame Difference Correlation Coefficient

来源：评论

学校读者我要写书评

暂无评论

Influence of Linear Features in Nonlinear Electroencephalography (EEG) Signals

引用

Procedia computer Science 2015年 47卷 229-236页

作者： P. Bhuvaneswari J. Satheesh Kumar Research Scholar Department of Computer Applications Bharathiar University Coimbatore-46 India Assistant Professor Department of Computer Applications Bharathiar University Coimbatore-46 India

Epilepsy is a critical brain disorder which can be detected through the signals captured from the brain. Electroencephalography is an efficient method used to capture signals from the brain. K nearest neighbor is one of the simplest methods used for classifying epilepsy patterns. Classification of the epilepsy signal from normal pattern will be primarily based on features extracted from brain signals. This paper discusses statistical based linear feature extraction methods such as Root Mean Square, Variance and Linear Prediction Coefficient. This paper also focuses influence of decision rules such as consensus and majority rule in the classification of epilepsy data set. Results show better classification with respect to increased k value.

关键词： Classifier EEG Majority rule RMS Variance LPC

来源：评论

学校读者我要写书评

暂无评论

Implementation Challenges of Mobile Commerce in Small and Mid-size Business

SEDME (Small Enterprises Development, Management & Extension...

引用

SEDME (Small Enterprises Development, Management & Extension Journal) 2013年第1期40卷 43 - 51页

作者： G. Naga Raja Prasad D.N.S. Bhaskar G Naga Raja Prasad is Associate Professor Department of Computer Applications CBIT and D.N.S. Bhaskar is Assistant Professor SMS CBIT Gandipet Hyderabad e-mail: .

来源：评论

学校读者我要写书评

暂无评论

A Hybrid k-DCI and Apriori Algorithm for Mining Frequent Itemsets

A Hybrid k-DCI and Apriori Algorithm for Mining Frequent Ite...

引用

International Conference on Circuits, Power and Computing Technologies

作者： S. Suriya S. P. Shantharajah Assistant Professor Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai Tamilnadu India. Professor Department of Master of Computer Applications Sona College of Technology Salem Tamilnadu India.

ISBN: (纸本)9781467349215

Data mining involves analysis, extraction, refining and representation of required data from large databases. kDCI (k Direct Count and Intersect) algorithm is one of the best scalable algorithms for identifying frequent items in huge repository of data. This algorithm uses a special kind of compressed data structure which helps in mining the datasets easily. Apriori algorithm, a realization of frequent pattern matching, is universally adopted for reliable mining. It is based on parameters namely support and confidence. kDCI algorithm is hybridized with Apriori algorithm for better performance than their individual contribution. The result proves scalability and mining speed effectively.

关键词： kDCI Apriori Scalability Support Confidence

来源：评论

学校读者我要写书评

暂无评论

Expected Completion Time based Scheduling Algorithm for Heterogeneous Processors

Expected Completion Time based Scheduling Algorithm for Hete...

引用

2011 International Conference on Information Communication and Management(ICICM 2011)

作者： R.Eswari S.Nickolas Assistant Professor Department of Computer Applications National Institute of Technology Trichy Tamilnadu India Associate Professor Department of Computer Applications National Institute of Technology Trichy Tamilnadu India

Effective scheduling of a distributed application is one of the major issues in distributed computing systems since scheduling algorithms are playing important role in achieving better performance. In this paper we proposed a static Expected Completion Time based Scheduling (ECTS) algorithm to effectively schedule application tasks onto the heterogeneous processors. The algorithm is mainly focused on minimizing the application execution time. It consists of two phases: First, the order of execution of tasks is computed in the task prioritization phase and secondly, the ordered tasks are assigned to the available processors in the processor selection phase. In comparison with the existing HEFT and PETS algorithms, the proposed ECTS algorithm offers better schedule length.

关键词： static task scheduling, heterogeneous distributed computing systems, Directed Acylic Graph, heuristic 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：