In the last two decades, number of Engineering Institutes and Universities grows rapidly in India. This causes a tight competition among these institutions and Universities while attracting the student to get admission in these Institutions/Universities. Most of the institutions and courses opened in Universities are in self finance mode, so all time they focused to fill all the seats of the courses not on the quality of students. Therefore a large number of students drop the course after first year. This paper presents a data mining application to generate predictive models for student's dropout management of Engineering. Given new records of incoming students, the predictive model can produce accurate prediction list identifying students who tend to need the support from the student dropout program most. The results show that the machine learning algorithm is able to establish effective predictive model from the existing student dropout data.

The Bin Packing Problem (BPP) is one of the most known combinatorial optimization problems. This problem consists in packing a set of items into a minimum number of bins. There are several variants of this problem; the most basic problem is the one-dimensional bin packing problem (1-BPP). In this paper, we present a new approach based on the GRASP procedure to deal with the1-BPP problem. The first GRASP phase is based on a new random heuristics based on hybridization between First Fit and Best Fit heuristics. The second GRASP phase is based on Tabu search algorithm used for the enhancement of the solutions found in the first phase. The obtained results are very encouraging and show the feasibility and effectiveness of the proposed approach.

Nonlinear dynamics has been introduced to the analysis of biological data and increasingly recognized to be functionally relevant. The aim of this study is to evaluate nonlinear and chaotic dynamics of gait signals. For this purpose, we analyzed gait data in ten healthy subjects who walked for an hour at their usual, slow and fast paces. Poincare plots, Hurst Exponents and the Lyapunov Exponents of gait signals were calculated. The results show that the Hurst Exponents are significantly increased during slow and fast paces. For all subjects, the Lyapunov Exponents are increased during normal gait, which indicates that signals are more chaotic. This can be due to decreased nonlinear interaction of variables in slow and fast paces. The finite values of Hurst Exponents and positive values of Lyapunov Exponents suggest that all of gait signals have low dimensional chaos. In addition, the complexity of signals is decreased during slow and fast gait. Results are useful for the early diagnosis of common gait pathologies.

In digital image processing, edge detection of images is an important and difficult task. Also, if the images are corrupted by noise, it smears some details and thus resulting in inaccurate edge detection. Hence, a pre-processing step must be taken before the edge detection. In this paper a new approach for edge detection with noise filtering of digital images using Cellular Automata Game of Life is presented. This procedure can easily be generalized and used for any type of digital media. To illustrate the proposed method, some experiments have been performed on standard test images and compared with popular methods. The results reveal that the proposed method has relatively desirable performance.

There are multiple numbers of security systems are available to protect your computer/resources. Among them, password based systems are the most commonly used system due to its simplicity, applicability and cost effectiveness But these types of systems have higher sensitivity to cyber-attack. Most of the advanced methods for authentication based on password security encrypt the contents of password before storing or transmitting in the physical domain. But all conventional encryption methods are having its own limitations, generally either in terms of complexity or in terms of efficiency.
In this paper an enhanced password based security system has been proposed based on user typing behavior, which will attempt to identify authenticity of any user failing to login in first few attempts by analyzing the basic user behaviors/activities and finally training them through neural network and classifying them as genuine or intruder.

Satellite based communication is a way to transmit digital information from one geographic location to another by utilizing satellites. Satellite as communication medium to transfer data vulnerable various types of information security threat, and require a novel methodology for safe and secure data transmission over satellite. In this paper a methodology is proposed to ensure safe and secured transferred of data or information for satellite based communication using symmetric and asymmetric Cryptographic techniques.

A major challenge in biomedical studies in recent years has been the classification of gene expression profiles into categories, such as cases and controls. This is done by first training a classifier by using a labeled training set containing labeled samples from the two populations, and then using that classifier to predict the labels of new samples. Such predictions have recently been shown to improve the diagnosis and treatment selection practices for several diseases. This procedure is complicated, however, by the high dimensionality of the data. While microarrays can measure the levels of thousands of genes per sample, case-control microarray studies usually involve no more than several dozen samples. Standard classifiers do not work well in these situations where the number of features (gene expression levels measured in these microarrays) far exceeds the number of samples. Selecting only the features that are most relevant for discriminating between the two categories can help construct better classifiers, in terms of both accuracy and efficiency. This paper provides a comparison between dimension reduction technique, namely Partial Least Squares (PLS)method and a hybrid feature selection scheme, and evaluates the relative performance of four different supervised classification procedures such as Radial Basis Function Network (RBFN), Multilayer Perceptron Network (MLP), Support Vector Machine using Polynomial kernel function(Polynomial- SVM) and Support Vector Machine using RBF kernel function (RBF-SVM) incorporating those methods. Experimental results show that the Partial Least-Squares(PLS) regression method is an appropriate feature selection method and a combined use of different classification and feature selection approaches makes it possible to construct high performance classification models for microarray data.