Classification of Encrypted Data with Elliptic Curve Cryptography

  Brindha.M,   Dr.R.Nedunchezhiyan

Data mining, the mining of hidden predictive information from huge databases, is a powerful new technology with grand latent to help companies focus on the most vital information in their data warehouses. Data mining tools expect future trends and behaviors, allowing businesses to make positive, knowledge-driven decisions. Text classification is the method of conveying text documents based on assured categories. Due to the rising trends in the field of internet and computers, billions of text data are processed at a known time and so there is a require for systematize these data to offer easy storage and accessing .Many text classification approaches were developed for efficiently solving the difficulty of identifying and classifying these data. During the data retrieval of the classified data, privacy, security, accuracy and time consuming is the challenging task. In this paper, classification after encryption has been applied for security issue and support vector machine classification has been compared with k Nearest Neighbor classification for accuracy and time consumption issue. A classifier is used to define the suitable class for each text document based on the input algorithm used for classification. Encryption is the procedure of encoding messages or information in such a way that only approved parties can read it, which provides high security and accuracy.

Keywords- privacy of data, classifier, encryption, k-NN, text document

Unique Identification Number - IJEDR1602325
Page Number(s) - 1850-1853
Pubished in - Volume 4 | Issue 2 | June 2016
DOI (Digital Object Identifier) -   
Publisher - IJEDR (ISSN - 2321-9939)

  Brindha.M,   Dr.R.Nedunchezhiyan,   "Classification of Encrypted Data with Elliptic Curve Cryptography", International Journal of Engineering Development and Research (IJEDR), ISSN:2321-9939, Volume.4, Issue 2, pp.1850-1853, June 2016, Available at :http://www.ijedr.org/papers/IJEDR1602325.pdf