Computer

If you order your custom term paper from our custom writing service you will receive a perfectly written assignment on Computer. What we need from you is to provide us with your detailed paper instructions for our experienced writers to follow all of your specific writing requirements. Specify your order details, state the exact number of pages required and our custom writing professionals will deliver the best quality Computer paper right on time.

Our staff of freelance writers includes over 120 experts proficient in Computer, therefore you can rest assured that your assignment will be handled by only top rated specialists. Order your Computer paper at affordable prices!

1. Abstract

The explosion of online scientific data resulted from DNA microarray experiments and other high-throughput techniques in molecular biology has threatened to overwhelm the ability of researchers to take full advantage of available information. This problem is particularly severe in the rapidly expanding area of gene and cancer research. The project is devoted to the document clustering of documents and papers regarding gene and breast cancer research. A few clustering algorithms will be explored and evaluated to determine the ¡§best¡¨ algorithm for use in clustering breast cancer related documents. With the clustering technique, it hopes to help researchers in gaining valuable information from the immense amount of textual documents.

. Introduction

Biologists and scientists need to know the most updated information of the gene-cancer research at any stage of their project or research. Although some popular bio-informatics web sites, such as OMIM and GeneCard, generate a subset of data that the scientists required, none of them could provide significant support for scientists. Help with essay on Computer

Currently, scientists need to put significant efforts on analysis and updating of the available information. However, the amount of information available on even a small subset of the published literature proved to be too large to review using conventional search methods. Moreover, in the process of integration of these data and documents, issues like data duplication, doubtful updating and inefficient summarizing etc. come in. In addressing the problems of the growth of biomedical information, artificial intelligent techniques that are capable of classifying the available documents, highlighting their relevant information in a well-organized and coherent manner and identifying new discoveries is required.

This project will focus on document clustering of gene and breast cancer related documents, which group large amount of textual document data, cluster and present them in a structural manner. By employing the technique, time and effort required in the literature survey will be significantly reduced. This effort can also be easily expanded and applied to other domain.

The problem description, scope and objective and the benefits and costs of the project will be discussed in chapter . While in chapter , user requirement specification is stated. In chapter 4, we cover the knowledge modeling. System description and system design is discussed in chapter 5 and 6 respectively. Our project plan is mentioned in chapter 7. The detail design of user interface, a weight simulation, and a sample knowledge based are attached as appendixes.

.1 Problem Description

Researchers from NCC are currently working on the projects concerning of cancer-gene co-relationship (e.g. Breast cancer), as the study of human gene has come to a new phase where new information come out everyday. In order to catch the latest technology, researchers need to access the information as soon as they are available as well as in an efficient way.

Currently, researchers from NCC refers to the following two websites OMIM and GeneCard as a tool to help to get useful information very frequently.

OMIM is a searchable database containing information about most known human genes and genetic diseases. Information is in the form of contains textual information, pictures, reference information, and links to Medline articles or GeneCard.

GeneCards, is a database of human genes, their products and their involvement in diseases. It offers concise information about the functions of all human genes that have an approved symbol.

Both websites are very useful, but each of them has its' own weakness. GeneCard, is better for non medical research, the updating of information is doubtful, the text data are not helpful as the size of the document are too large and not easy to differentiate, and for OMIM, it only contain genetic information, and it doesn't has the useful links that scientists want. Besides the above weakness, it has also other problems such as the duplication of information; trustiness or whether the information is up-to-date is a big concern.

Because of the above constraints, the information gathered from the above websites are only useful during the starting point of a project, it is very difficult for them to go back to refer during the intermediate stage of the research as the huge amount of information and the unuser-friendly representation.

Document Clustering, by grouping similar documents together, cluster them and present them in a structural and coherent manner, will help the user to quickly grasp the main topics without wading through thousands of pieces of data, can significantly improve the effectiveness of information retrieval.

. Scope and Objective

..1 Objectives

In the gene-Cancer research domain, the Document-clustering tool serve as an intelligent system, which can read the papers and look into the features, automatically cluster the papers into hierarchical trees.

The system will be able to group the relevant papers into clusters to the end users - the biologists in NCC.

.. System Scope and its limitations

„h Cluster representation

By using document-clustering technique{ an unsupervised learning AI technique, the result of the clustering is represented with keywords and the relationship among them, the representation may not be as clear as manual classification. However, since the end-users are experts in the research area so the ¡§keyword only¡¨ representation should not be a problem for the end users to understand.

„h None ¡V incremental /limited incremental ability

Most of the text clustering techniques has their inherent limitations of the incremental updating. When new articles are added to the document warehouse, the whole clustering process will have to be run again to generate new clustering tree.

„h Concept dictionary updating

The document-clustering tool uses domain-specific concept dictionary to enhance its ability in handling the scientific papers. But because almost everyday there are new findings, and the new terms are invented from time to time, so the concept dictionary should be kept up-to-date. This updating job will be done by the end-users after the system is handed over. The system is modularized designed, which means the concept dictionary is kept separately from the functionary software.

The updating job can be done via friendly UI.

. Benefit and Cost

..1 Benefits to NCC

„h Automatic grouping of articles can save time for the researchers.

The Document-clustering tool can considerably reduce the time and efforts of the researchers in grouping and searching the numerous relevant articles. The system can automatically group the scientific articles into hierarchical structure thus eliminate the process of the manual reading/grouping efforts.

Save time does not only means save of manpower but competence advantage to NCC. As we all know the competence of gene-related researching is fierce, any delay or waste of time can cause the efforts to be vain if the competitors can reach the same results in just one day in advance.

„h The system will also integrate some kind of summarization functions. But due to time constraint, the summarization function is considered as a bonus function, so the quality of the summarization is not guaranteed.

„h System re-usage

The object-oriented structure of the system makes it easy to adapt to new research field. By changing the concept dictionary and selection of the algorithms, the system can be adopted to other gene research fields.

.. Estimated Costs

Software and hardware

1. Hardware

LAN connected NT server, CPU PIII 700 or above, 1G ram, GB for OS, 0G free hard disk space for application.

. Software

„h JavaServer Page will be used for front-end GUI Representation.

„h Java will be used as the main back-end programming language.

„h Microsoft SQL 7.0 will be used as the database server.

„h Allaire JRun server is used as the web server.

Please note that this sample paper on Computer is for your review only. In order to eliminate any of the plagiarism issues, it is highly recommended that you do not use it for you own writing purposes. In case you experience difficulties with writing a well structured and accurately composed paper on Computer, we are here to assist you. Your cheap custom college paper on Computer will be written from scratch, so you do not have to worry about its originality.

Order your authentic assignment and you will be amazed at how easy it is to complete a quality custom paper within the shortest time possible!