Kashish Ara Shakil

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.

Kashish Ara Shakil, Shadma Anis, Mansaf Alam

Dengue is a life threatening disease prevalent in several developed as well as developing countries like India.In this paper we discuss various algorithm approaches of data mining that have been utilized for dengue disease prediction. Data mining is a well known technique used by health organizations for classification of diseases such as dengue, diabetes and cancer in bioinformatics research. In the proposed approach we have used WEKA with 10 cross validation to evaluate data and compare results. Weka has an extensive collection of different machine learning and data mining algorithms. In this paper we have firstly classified the dengue data set and then compared the different data mining techniques in weka through Explorer, knowledge flow and Experimenter interfaces. Furthermore in order to validate our approach we have used a dengue dataset with 108 instances but weka used 99 rows and 18 attributes to determine the prediction of disease and their accuracy using classifications of different algorithms to find out the best performance. The main objective of this paper is to classify data and assist the users in extracting useful information from data and easily identify a suitable algorithm for accurate predictive model from it. From the findings of this paper it can be concluded that Naïve Bayes and J48 are the best performance algorithms for classified accuracy because they achieved maximum accuracy= 100% with 99 correctly classified instances, maximum ROC = 1, had least mean absolute error and it took minimum time for building this model through Explorer and Knowledge flow results

Shuchi Sethi, Kashish Ara Shakil, Mansaf Alam

This work is focused on attacks on confidentiality that require time synchronization. This manuscript proposes a detection framework for covert channel perspective in cloud security. This problem is interpreted as a binary classification problem and the algorithm proposed is based on certain features that emerged after data analysis of Google cluster trace that forms base for analyzing attack free data. This approach can be generalized to study the flow of other systems and fault detection. The detection framework proposed does not make assumptions pertaining to data distribution as a whole making it suitable to meet cloud dynamism.