Biometric verified access control of critical data on a cloud

Abstract

The standalone computer machines are powerful with diverse applications. But the actual performance and utilization of these machines was achieved by interlinking them to form networks which will work in coordination and cooperation. Cloud computing, an application of computer networks, deserves a separate field for research due to its enormous applications and elegant performance. The basic intend to develop this technology was to enhance the efficiency, utilization and performance of the computer resources but despite the enormous potential that is promised by this discipline is still to be fulfilled because of the various security issues. Here, in this paper we address the issue of access control to the critical data on a cloud by the use the biometric iris verification and authentication for a controlled flow of data. In order to achieve the above goal we are using biometric iris verification for the purpose of authentication of users. MATLAB is used in the implementation for the proposed scheme where in iris textural features (gray level co-occurrence matrix) are extracted and later validated on the CASIA iris database.Index Terms-Cloud computing, security and privacy, access control, iris biometric, gray level co-occurrence matrix (GLCM).

Multi-banking automatic teller machine transaction system by utilizing GSM and biometric identification with one single touch

“…If customer wants to send the money or debit the money from bank account, he/she will get One Time Password on registered mobile phone number. The GSM system created One Time Password for enforce verify [13,14] transaction from the desire bank side. This OTP requires to be entered for the transaction deal to be execute.…”

Prediction of depression using Machine Learning and NLP approach

“…They tried to achieve higher performance improvements using various Natural Language Pro-cessing (NLP) techniques and text classification approaches. Some studies use single set features, such as bag of words (BOW) [3], [4], N-grams [5], LIWC [6] or LDA [7], [8] to identify depression in their posts. Some other papers compare the perfor-mance of individual features with various machine learning classifiers [9] - [12].…”