检索结果-内蒙古大学图书馆

Feature Selection of Gene Expression Data for Cancer Classification: A Review

Procedia computer science 2015年 50卷 52-57页

作者： Rabindra Kumar Singh M. Sivabalakrishnan Assistant Professor School of Computer Science and Engineering VIT Univeristy Chennai Campus Associate Professor School of Computer Science and Engineering VIT Univeristy Chennai Campus

The DNA microarray technology has capability to determine the levels of thousands of gene simultaneously in a single experiment. Analysis of gene expression is important in many fields of biological research in order to retrieve the required information. As time progresses, the illness in general and cancer in particular have become more and more complex and complicated, in detecting, analyzing and curing. We know cancer is deadly disease. Cancer research is one of the major area of research in medical field. Predicting precisely of different tumor types is a great challenge and providing accurate prediction will have great value in providing better treatment to the patients. To achieve this, data mining algorithms are important tools and the most extensively used approach to achieve important feature of gene expression data and plays an important role for gene classification. One of major challenges is to discover how to extract useful information from huge datasets. This paper presents recent advances in the machine learning based gene expression data analysis with different feature selection algorithms. Gene expression profiles, which represent the state of a cell at a molecular level, have great potential as a medical diagnosis tool. But compared to the number of genes involved, available training data sets generally have a fairly small sample size for classification. These training data limitations constitute a challenge to certain classification methodologies. Feature selection techniques can be used to extract the marker genes which influence the classification accuracy effectively by eliminating the un wanted noisy and redundant genes This paper presents a review of feature selection techniques that have been employed in micro array data based cancer classification and also the predominant role of SVM for cancer classification.

关键词： Gene Expression Cancer Classification Feature selection

来源：评论

学校读者我要写书评

暂无评论

Online Social Gaming and Social Networking Sites

引用

Procedia computer science 2016年 82卷 72-79页

作者： Linah Aburahmah Hajar AlRawi Yamamah Izz Liyakathunisa Syed Software Engineering student at Prince Sultan University – College of Women Riyadh Saudi Arabia Computer Science student at Prince Sultan University – College of Women Riyadh Saudi Arabia Information Systems student at Prince Sultan University – College of Women Riyadh Saudi Arabia Assistant Professor at Prince Sultan University – College of Women Riyadh Saudi Arabia

Online social games are becoming a significant component in today's social media sites. The social networking sites environment has provided a platform for online games to develop and expand in the virtual medium. Users are now able to play games online, compare scores, and challenge each other among many other things. Due to the diverse user demographics of social media sites, various motivations to playing social games emerge. The need for this present research was to answer the question whether the integration of social games within social networking sites and apps have increased the likelihood of playing those games. Therefore, the main objective of this research is to predict from the fact that will be used to decide whether to include games (Adventure, Fighting, Design\Art, Virtual Life…etc.) in the social media sites that still have not been implemented (such as Twitter, Tumblr, etc.). Also, we want to discover whether the inclusion of social games has improved the services offered by social sites and whether social gaming has effects on human behavior with regards to socializing and interacting with others. The aim of this study was to examine the relation between social media apps and games, and whether the former has increased users participation in online games. The primary setting for the quantitative method of research study was the online gamers regardless their age, gender, and interests. The data were collected by distributing an online survey, and were analyzed using WEKA data mining tool. Two popular classification algorithms were used to predict the answer of this research question. The resulting data were compared and tested for their accuracy using different metrics.

关键词： Online games Social sites Data Mining Random Forest Neural Networks

来源：评论

学校读者我要写书评

暂无评论

Symptoms Based Treatment Based on Personal Health Record Using Cloud Computing

引用

Procedia computer science 2015年 47卷 22-29页

作者： P. Dhivya S. Roobini A. Sindhuja Assistant Professor Department of Computer Science and Engineering Coimbatore India Student Department of Computer Science and Engineering SNS College of Technology Coimbatore India

Cloud architecture is used for maintaining the personal health record and provide symptoms based treatment to the patients. The details of a patient need to be stored in a secured manner. It is to create a cloud storage server for long term storage over the internet. The storage server will act as a database server. Uploaded data stored in the cloud server through proxy re-encryption method. A secured threshold proxy re-encryption server and integrates it with a decentralized erasure code such that a secure distributed storage system. To generate proxy re-encryption key for one-time data access. A proxy server will be created virtually for one time data access. We can achieve the symptoms based treatment by secure Personal Health Record in cloud storage when applying the proposed encryption algorithm.

关键词： PersonalHealth Record(PHR) Encryption proxy treatments cloud computing

来源：评论

学校读者我要写书评

暂无评论

SOA Based Secure Data Transmission over CMEA Protocol in MANET

引用

Procedia computer science 2015年 47卷 434-440页

作者： P. Dhivya S. Karthik T. Kalaikumaran Assistant Professor Department of Computer Science and Engineering SNS College of Technology Coimbatore India Professor & Dean Department of Computer Science and Engineering SNS College of Technology Coimbatore India Professor & HoD Department of Computer Science and Engineering SNS College of Technology Coimbatore India

Mobile Adhoc Networks is a self organizing network composed of mobile terminals connected by wireless links. Adhoc Networks are created dynamically without any preexisting network infrastructure Ad-hoc networks are very useful in situations like emergency search and reuse operations and meetings where people want to quickly share information. This network does not have any central administration, hence there are no designated routes, all the nodes can serve as routers for each other, and data packets are forwarded from node to node to node in multi hop fashion. Cluster based Mobility and Energy Aware (CMEA) routing protocols is used to find the reliable route in a cluster networks. The clustered network avoids path breaks and long path delay. When applying the energy and mobility aware metric over clustered network gives reliable route between Source and Destination. Service Oriented Architecture (SOA) is an evolution of past platforms, preserving successful characteristics of traditional architectures and bringing with it distinct principles that follow service orientation in support service oriented enterprise. It forces the network to improve the reliability, security, integrity etc. By applying the proposed XML technique for encrypting the secure data improves the content delivery over the CMEA network. Therefore SOA based secure data transmission over the reliable route improves the network performance.

关键词： Service Oriented Architecture (SOA) Mobile Adhoc Network (MANET) route discovery Cluster based Mobility and Energy Aware (CMEA) protocol Route Request (RREQ) Route Reply (RREP) Multi purpose Internet Mail Extension (MIME).

来源：评论

学校读者我要写书评

暂无评论

Proposal to Provide Security in MANET's DSRRouting Protocol

引用

Procedia computer science 2015年 48卷 440-446页

作者： Milan Kumar Dholey G.P. Biswas Assistant Professor Computer Science & Engineering Hooghly Engineering & Technology College Hooghly 712103 India Computer Science & Engineering Indian School of Mines Dhanbad 826004 India

Mobile Ad-hoc network (MANET) is infrastructure less, self-organizing bandwidth constraint on demand wireless network. MANET is a multi-hop wireless network therefore, needs an efficient routing protocol to transmit data packet from source to destination. MANET routing protocol can be divided as proactive, reactive and hybrid. In an ad-hoc network a node cannot identify the nodes that are beyond its radio range. The nodes in MANET are movable so, a fixed path cannot be defined in between source to a destination. In MANET's reactive routing protocol, like Dynamic Source Routing (DSR), a source node locate the destination before data transmission take place by broadcasting/flooding route request (RREQ) control message and establishes the path after receiving route reply (RREP) control message. During route discovery using DSR routing protocol a malicious node may enter in between source-destination path as an intermediate node or eavesdrop to the source by sending RREP control message before original RREPs (multiple path exists between source to destination) reach to the source with unexpected path information. As a result, without knowing anything source may deliver data packet to a different destination. In this paper, we identified the issues and proposed a solution to prevent to enter the malicious node in between source-destination path. In our proposal, initially we formed a group by considering neighbour nodes of an individual node from the original network and presented the way of communication by the group member using Diffie-Hellman group key (GDH) management scheme in the network through our proposed algorithm. Our proposed algorithm will prevent a malicious node to enter in between source-destination path during route discovery using DSR routing protocol. Further our technique prevents to gainaccess to any node in the network except the group member hence malicious node cannot identify the source to sent RREP control message with wrong path information.

关键词： MANET Routing Protocol DSR GDH

来源：评论

学校读者我要写书评

暂无评论

Frequent Subgraph Mining Algorithms – A Survey

引用

Procedia computer science 2015年 47卷 197-204页

作者： T. Ramraj R. Prabhakar Assistant Professor 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

Graphs are common data structures used to represent / model real-world systems. Graph Mining is one of the arms of Data mining in which voluminous complex data are represented in the form of graphs and mining is done to infer knowledge from them. Frequent sub graph mining is a sub section of graph mining domain which is extensively used for graph classification, building indices and graph clustering purposes. The frequent sub graph mining is addressed from various perspectives and viewed in different directions based upon the domain expectations. In this paper, a survey is done on the approaches in targeting frequent sub graphs and various scalable techniques to find them.

关键词： Candidate Graphs Support Apriori-based Pattern-growth.

来源：评论

学校读者我要写书评

暂无评论

Study on online community user motif using web usage mining

引用

Journal of Physics: Conference Series 2016年第1期710卷

作者： Meera Alphy Ajay Sharma PhD Scholar Department of Computer Science and Engineering SRM University Haryana India Assistant Professor Department of Computer Science and Engineering SRM University Haryana India

The Web usage mining is the application of data mining, which is used to extract useful information from the online community. The World Wide Web contains at least 4.73 billion pages according to Indexed Web and it contains at least 228.52 million pages according Dutch Indexed web on 6th august 2015, Thursday. It's difficult to get needed data from these billions of web pages in World Wide Web. Here is the importance of web usage mining. Personalizing the search engine helps the web user to identify the most used data in an easy way. It reduces the time consumption; automatic site search and automatic restore the useful sites. This study represents the old techniques to latest techniques used in pattern discovery and analysis in web usage mining from 1996 to 2015. Analyzing user motif helps in the improvement of business, e-commerce, personalisation and improvement of websites.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Refining of image using self-organizing map with clustering

引用

AIP Conference Proceedings 2016年第1期1715卷

作者： Neeraj Dahiya Surjeet Dalal Gundeep Tanwar 1)Assistant Professor Department of Computer Science & EngineeringSRM University Haryana India 2)Associate Professor Department of Computer Science & Engineering SRM University Haryana India 3)Associate Professor Department of Computer Science & Engineering BRCM College of Engineering & Technology BahalBhiwani Haryana India

Self Organization Map(SOM) is an automatic tool in data analysis in data mining,it is used to explore the multi-dimentional data which simplifies complexity and produce meaningful relation with each other or high dimentional into low dimentional .the powerful method of SOM i.e learning method results excellent performance .the SOM algorithum have various steps from starting stage to the final neuron and their weight updation and modification, these procedure resultant a lot of compplexity accoording to the parameters on the basis of experiments .this paper will compare and discuss various papameters and their result or factors that can improve and refine the image through varius process of SOM.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Single Sign on Mechanism Using Attribute Based Encryption in Distributed computer Networks

引用

Procedia computer science 2015年 47卷 441-451页

作者： M. Surya N. Anithadevi PG Student Computer Science and Engineering Coimbatore Institute of Technology Coimbatore- 641014 India Assistant Professor Computer Science and Engineering Coimbatore Institute of Technology Coimbatore- 641014

Single Sign On (SSO) is an authentication mechanism that enables legal user with a single credential to be authenticated by multiple service providers in a distributed computer networks. SSO obtains credential from trusted authorities i.e., Smart Card Producing Center (SCPC) and Trusted Credential Privacy (TCP) which is used for mutual authentication and authorization of legal users. Chang-Lee coined a new SSO scheme which makes use of SCPC for mutual authentication and session key establishment whereas Schnorr signature makes use of TCP which generates and verifies the signature for user's authentication. RSA algorithm and Attribute Based Encryption (ABE) is used for encryption and decryption of messages in which ABE tends to be more efficient than RSA based algorithm. ABE is a new public key based on one-to-many encryption that allows users to decrypt the message based on set of attributes and access policies. Decryption is an expensive process and this ABE system eliminates the decryption overhead using outsourced decryption. Integrity of data is maintained by verification of the cipher text which guarantees that the encrypted and decrypted files are same and original message is recovered using hash technique in case of any modifications in the file.

关键词： Encryption Decryption Ciphertext Trusted Authority Credential.

来源：评论

学校读者我要写书评

暂无评论

FIR3: A Fuzzy Inference based Reliable Replica Replacement Strategy for Cloud Data Centre

FIR3: A Fuzzy Inference based Reliable Replica Replacement S...

引用

International Conference on Computing and Network Communications

作者： D. VIJAYAKUMAR K. G. SRINIVASAGAN R. SABARIMUTHUKUMAR Assistant Professor (SG) Dept of Computer Science and Engineering National Engineering College Kovilpatti TamilNadu India Professor Dept of Computer Science and Engineering National Engineering College Kovilpatti TamilNadu India Assistant Professor Dept of Computer Science and Engineering National Engineering College Kovilpatti TamilNadu India

ISBN: (纸本)9781467373104

Cloud computing is the most fast driven computing technology in IT industry. Nowadays, due to increase in data intensive applications in various domains, usage of cloud also increases. Mainly in the medical domain, the Electronic Health records form the huge data. Efficient retrieval and management of those e-services is needed for immediate treatments and verification. EHRs are mostly available in multimedia formats and also an efficient multimedia based cloud service is needed. But the data management is the major issue in a cloud environment. Data loss or crash and data outages may happen frequently in this internet based computing. Data Replication is the appropriate solution to overcome these major issues in cloud environment. In this work, we have proposed a new data replication technique based on Fuzzy Inference System. The main idea is to maintain each replica of the data in the different availability zones. Our algorithm uses fuzzy inference to made decision about replacing the existing replicas by the newer ones in order to handle the space inconsistency problems. The synchronization among the replicas has been achieved with lesser error rate and data missing rate. The entire replication technology is deployed in the cloud stack environment. Thus the entire system fault tolerance will be enhanced by this replication technique.

关键词： replication replacement cloudstack data management Electronic Health care records

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：