Search results for: N. Vijayarangan
2 ATM Service Analysis Using Predictive Data Mining
Authors: S. Madhavi, S. Abirami, C. Bharathi, B. Ekambaram, T. Krishna Sankar, A. Nattudurai, N. Vijayarangan
Abstract:
The high utilization rate of Automated Teller Machine (ATM) has inevitably caused the phenomena of waiting for a long time in the queue. This in turn has increased the out of stock situations. The ATM utilization helps to determine the usage level and states the necessity of the ATM based on the utilization of the ATM system. The time in which the ATM used more frequently (peak time) and based on the predicted solution the necessary actions are taken by the bank management. The analysis can be done by using the concept of Data Mining and the major part are analyzed based on the predictive data mining. The results are predicted from the historical data (past data) and track the relevant solution which is required. Weka tool is used for the analysis of data based on predictive data mining.
Keywords: ATM, Bank Management, Data Mining, Historical data, Predictive Data Mining, Weka tool.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 56131 Deterministic Random Number Generators for Online Applications
Authors: Natarajan Vijayarangan, Prasanna S. Bidare
Abstract:
Cryptography, Image watermarking and E-banking are filled with apparent oxymora and paradoxes. Random sequences are used as keys to encrypt information to be used as watermark during embedding the watermark and also to extract the watermark during detection. Also, the keys are very much utilized for 24x7x365 banking operations. Therefore a deterministic random sequence is very much useful for online applications. In order to obtain the same random sequence, we need to supply the same seed to the generator. Many researchers have used Deterministic Random Number Generators (DRNGs) for cryptographic applications and Pseudo Noise Random sequences (PNs) for watermarking. Even though, there are some weaknesses in PN due to attacks, the research community used it mostly in digital watermarking. On the other hand, DRNGs have not been widely used in online watermarking due to its computational complexity and non-robustness. Therefore, we have invented a new design of generating DRNG using Pi-series to make it useful for online Cryptographic, Digital watermarking and Banking applications.
Keywords: E-tokens, LFSR, non-linear, Pi series, pseudo random number.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2009