Farhana Javed Zareen

Farhana Javed Zareen, Suraiya Jabin

We are in the era of data analytics and data science which is on full bloom. There is abundance of all kinds of data for example biometrics based data, satellite images data, chip-seq data, social network data, sensor based data etc. from a variety of sources. This data abundance is the result of the fact that storage cost is getting cheaper day by day, so people as well as almost all business or scientific organizations are storing more and more data. Most of the real data is multi-dimensional, non-uniform, and big in size, such that it requires a unique pre-processing before analyzing it. In order to make data useful for any kind of analysis, pre-processing is a very important step. This paper presents a unique and novel pre-processing method for multi-dimensional and non-uniform data with the aim of making it uniform and reduced in size without losing much of its value. We have chosen biometric signature data to demonstrate the proposed method as it qualifies for the attributes of being multi-dimensional, non-uniform and big in size. Biometric signature data does not only captures the structural characteristics of a signature but also its behavioral characteristics that are captured using a dynamic signature capture device. These features like pen pressure, pen tilt angle, time taken to sign a document when collected in real-time turn out to be of varying dimensions. This feature data set along with the structural data needs to be pre-processed in order to use it to train a machine learning based model for signature verification purposes. We demonstrate the success of the proposed method over other methods using experimental results for biometric signature data but the same can be implemented for any other data with similar properties from a different domain.

Farhana Javed Zareen, Kashish Ara Shakil, Mansaf Alam et al.

With an exponential increase in number of users switching to mobile banking, various countries are adopting biometric solutions as security measures. The main reason for biometric technologies becoming more common in the everyday lives of consumers is because of the facility to easily capture biometric data in real time, using their mobile phones. Biometric technologies are providing the potential security framework to make banking more convenient and secure than it has ever been. At the same time, the exponential growth of enrollment in the biometric system produces massive amount of high dimensionality data that leads to degradation in the performance of the mobile banking systems. Therefore, in order to overcome the performance issues arising due to this data deluge, this paper aims to propose a distributed mobile biometric system based on a high performance cluster Cloud. High availability, better time efficiency and scalability are some of the added advantages of using the proposed system. In this paper a Cloud based mobile biometric authentication framework (BAMCloud) is proposed that uses dynamic signatures and performs authentication. It includes the steps involving data capture using any handheld mobile device, then storage, preprocessing and training the system in a distributed manner over Cloud. For this purpose we have implemented it using MapReduce on Hadoop platform and for training Levenberg-Marquardt backpropagation neural network has been used. Moreover, the methodology adopted is very novel as it achieves a speedup of 8.5x and a performance of 96.23%. Furthermore, the cost benefit analysis of the implemented system shows that the cost of implementation and execution of the system is lesser than the existing ones. The experiments demonstrate that the better performance is achieved by proposed framework as compared to the other methods used in the recent literature.