Browsing by Author "S, MohanaPriya"

Now showing 1 - 4 of 4

AN EFFICIENT AND ENHANCED PATH SEQUENCE ALGORITHM FOR MISSING PAGES IN COMMUNITY WEB
(International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS), 2014-02) S, MohanaPriya
Web directory is a concept it lists web sites by category and subcategory. The Web content into thematic hierarchies these are known as Web Directories and correspond to listings of topics which are organized and overseen by humans. Web personalization is a technique websites are personalized based on the interests of an individual, group or organization. In context previous work the Web directory is viewed as a thematic hierarchy and personalization on the basis of usage data. In dissimilarity to most of the work on Web usage mining, the usage data that are analyzed here communicate to user navigation throughout the Web. Due to proxy servers and cached versions of the pages used by the client using ‘Back’, the sessions identified have many missed pages. In this work Enhanced Path Sequence Algorithm proposed there are chances of missing pages after constructing transactions due to proxy servers and caching problems. Three approaches used for this 1. Time Window: 2. Reference Length approach: 3. Maximal Forward Reference.
LUNG CANCER CLASSIFICATION
(International Journal of Computer Engineering and Applied Sciences, 2018-04) S, MohanaPriya
The main objective of this project is to assist clinicians to efficiently identify the Lung Cancer via forecasting analysis by using Morphological Neural Network (MNN) Classification with Image Pruning Methodology. In image processing domain, the complex task to analyze and rectify is cancer estimation and prediction. Compare to tumor estimations, Cancer estimations are more complex because these are purely cell based paradigms and visually not clear to analyze; especially this system focus on Lung cancer and its strategies. A new methodology is required to classify these kind of cancer with Image Pruning Scheme is introduced to efficiently classify the cancer cells and mark out the affected region more efficiently. Lung cancer is one of prevalent diseases in human, and can be diagnosed using several tests that include CT scans, MRI Scans, biopsy and so on. Over the years, the use of learning machine and artificial intelligence techniques has transformed the process of diagnosing lung Cancer. However, the accurate classification of cancer cells is still a medical challenge faced by researchers. Difficulties are routinely encountered in the search for sets of features that provide adequate distinctiveness required for classifying breast tissues into groups of normal and abnormal. Therefore, the aim of this approach is to prove that the MNN algorithm is more efficient for diagnosis, prognosis and prediction of lung abnormality, which is basically derived from two classical algorithms called Morphological Image Processing and Artificial Neural Network (ANN) with Image Pruning.
A STUDY ON ENHANCED PATH SEQUENCE ALGORITHM USING WEB DIRECTORIES
(PSGR Krishnammal College for Women, 2017-02) S, MohanaPriya
A web directory is not a search engine and does not display lists of web pages based on keywords; instead, it lists web sites by category and subcategory. The categorization is usually based on the whole web site rather than one page or a set of keywords, and sites are often limited to inclusion in only a few categories. Web directories often allow site owners to submit their site for inclusion, and have editors review submissions for fitness.In dissimilarity to most of the work on Web usage mining, the usage data that are analyzed here communicate to user navigation throughout the Web, to a certain extent than a particular Web site exhibit as a result a high amount of thematic diversity. Due to proxy servers and cached versions of the pages used by the client using ‘Back’ , the sessions identified have many missed pages. Enhanced Path Sequence Algorithm proposed there are chances of missing pages after constructing transactions due to proxy servers and caching problems. Three approaches used for this 1. Time Window: A time window transaction is framed from triplets of ip address, user identification, and time length of each webpage up to a limit called time window. 2. Reference Length approach: This approach is based on the assumption that the amount of time a user spends on a page correlates to whether the page is an auxiliary page or content page for that user. 3. Maximal Forward Reference: A transaction is considered as the set of pages from the visited page until there is a backward reference. Forward reference pages are considered as content pages and the path is taken as index pages. The primary usage to store sessions and pointers to secondary table which is having complete path navigation.
A STUDY ON PRECAUTION MEASURES FOR THEVULNERABILITIES IN CLOUD TECHNOLOGY
(PSGR Krishnammal College for Women, Coimbatore, 2015-01) S, MohanaPriya; T, Saranya
Today’s global village is getting equipped with more modern techniques. Various technologies have emerged and are being developed to fulfill the needs of the people. In this aspect, cloud computing technology has given its contribution over a large area especially in the field of networking and communication. Several companies have also developed their own search engines and other websites for communication where cloud computing plays a major role. However, some companies are facing some inconvenience in using this cloud technology which is mainly due to the threats and minute vulnerabilities. In this paper, we present an idea of reducing the problem of data breaches and denial of service which are contributing a major part in the usage of cloud as a worldwide technology. The proposed system will explain the usage of dual encryption technique and the technique of automated deletion of duplicated copies of the data present.