Back-Propagation Neural Network Learning with PreservedPrivacy using Cloud Computing
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2015, Vol 17, Issue 2
Abstract
Abstract: Cloud computing facilitates the owners to share data. Multiple parties join the learning process byconducting joint Back propagation neural network algorithm on the union of their respective data sets. Duringthe learning process none of the party wants to disclose her/his private data to others. The limitations of theexisting schemes are learning process for only two parties or the few ways in which the data is arbitrarilypartitioned. The proposed solution allows two or more parties, each with an arbitrarily partitioned data set, tojointly conduct the learning. The solution is provided by the magnificent power of cloud computing. In theproposed scheme, each owner encrypts his/her private dataset locally through AES cryptography and uploadsthe cipher texts into the cloud. The cloud then executes most of the operations over cipher texts via BGNhomomorphic algorithm. The cloud is unaware of the original dataset. The Back propagation learning takesplace and the owners are benefited through collaborative learning. Thus the scalability of the learning processis improved and the privacy of the data is ensured
Authors and Affiliations
Mrs. Valli N, , Mr. H. Anwar Basha
Keywords
Related Articles
- EP ID EP137502
- DOI -
- Views 92
- Downloads 0
Comparative Study of RBFS & ARBFS Algorithm
RBFS is a best-first search that runs in space that is linear with respect to the maximum search depth, regardless of the cost function used. This algorithm allows the use of all available memory. One major ...
A study on Clustering Algorithms for XML Data Clustering
Abstract: Nowadays mining meaningful information from large scale web documents is more important to satisfy the user demand. XML and RDF documents are supporting the semantic information retrieval to interpret and extra...
Fuzzy mathematical models for the analysis of fuzzy systems with application to liver disorders
Abstract: The main objective of this model is to focus on how to use the model of fuzzy system to solve fuzzy mathematics problems. Some mathematical models based on fuzzy set theory, fuzzy systems and neural netwo...
Validation Experimentations of Local Alignment Parameters for Comparing DNA and Protein Sequences
Abstract : A basic issue in aligning DNA and protein sequences is to find similar characters between two or more sequences in order to detect relations between newly defined sequences and well-known sequences store...
Low-Cost Bus Tracking System Using Area-Trace Algorithm
This paper proposes a low-cost Bus Tracking System that uses GPS and allows the user to know the bus location on their mobile phone. It has an advantage that it does not use any internet data for the users to be,notified...