M. Karnan

Review Article: Biometric personal authentication using keystroke dynamics: A review

Authentication is the process of determining whether someone or something is, in fact, who or what it is declared to be. As the dependence upon computers and computer networks grows, the need for authentication has increased. Biometrics is the science and technology of authentication by identifying the living individuals physiological or behavioral attributes. Keystroke dynamics is a behavioral measurement and it utilizes the manner and rhythm in which each individual types. The approaches in keystroke dynamics can be categorized by the selection of features and the classification methods employed. The objective of this review paper is to summarize the well-known approaches used in keystroke dynamics in the last two decades.

Diagnose brain tumor through MRI using image processing clustering algorithms such as Fuzzy C Means along with intelligent optimization techniques

Magnetic Resonance Imaging (MRI) is one of the best technologies currently being used for diagnosing brain tumor. Brain tumor is diagnosed at advanced stages with the help of the MRI image. Segmentation is an important process to extract suspicious region from complex medical images. Automatic detection of brain tumor through MRI can provide the valuable outlook and accuracy of earlier brain tumor detection. In this paper an intelligent system is designed to diagnose brain tumor through MRI using image processing clustering algorithms such as Fuzzy C Means along with intelligent optimization tools, such as Genetic Algorithm (GA), and Particle Swarm Optimization (PSO). The detection of tumor is performed in two phases: Preprocessing and Enhancement in the first phase and segmentation and classification in the second phase

Personal Authentication Based on Keystroke Dynamics Using Soft Computing Techniques

The need to secure sensitive data and computer systems from intruders, while allowing ease of access for authenticate user is one of the main problems in computer security. Traditionally, passwords have been the usual method for controlling access to computer systems but this approach has many inherent flaws. Keystroke dynamics is a promising biometric technique to recognize an individual based on an analysis of his/her typing patterns. In the experiment, we measure mean, standard deviation and median values of keystroke features such as latency, duration, digraph and their combinations and compare their performance. Particle swarm optimization (PSO), genetic algorithm (GA) and the proposed ant colony optimization (ACO) are used for feature subset selection. Back propagation neural network (BPNN) is used for classification. ACO gives better performance than PSO and GA with regard to feature reduction rate and classification accuracy. Using digraph as the feature for feature subset selection is novel and show good classification performance.

Bio password — Keystroke dynamic approach to secure mobile devices

The objective of the paper is to provide how a biopassword is using keystroke dynamics technology to deliver security for mobile devices to monitor and authenticate users. Mobile devices have outgrown their initial use for telephony and now have added functionality such web browsing and m-commerce. Depending on the specific area of usage of the device, the importance and hence the sensitivity of the data stored in it changes. As a result, there is a need to secure the data and to protect the devices from loss or theft. The users of these mobile devices have authentication method of PIN i.e. (Personal Identification Numbers). But, with the problems associated with using PIN is Easy to Crack passwords, Sharing the passwords, using the same password for different devices, the need for using sophisticated methods allowing only the legitimate users the access to data and identifying and preventing imposters manifolds many times as the mobility of the computing devices changes. In this paper we examine an emerging biometric technique that aims to identify users based on analyzing habitual rhythm patterns in the way they type.

Identity authentication based on keystroke dynamics using genetic algorithm and particle Swarm Optimization

Techniques based on biometrics have been successfully applied to personal identification systems. Keystroke dynamics is a promising biometric technique to recognize an individual based on an analysis of his/her typing patterns. In this work, Mean and Standard Deviation of Latency, Duration and Digraph is measured as keystroke features. Optimization techniques such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) are used for feature subset selection and their performance is compared. Particle Swarm Optimization gave moderate performance than Genetic Algorithm. Using the duration as the feature for feature subset selection is novel.

Improved implementation of brain MR image segmentation using Meta heuristic algorithms

Brain Image Segmentation is a complex and challenging part in the Medical Image Processing. This paper describes two new approaches for brain tumor detection using Meta heuristic algorithms. MRI scan has become a particularly useful medical diagnostic tool for cases involving brain tissue. The aim of this research is to develop an effective algorithm for the segmentation of brain MRI images. This paper is divided in to three phases, namely preprocessing, enhancement, segmentation. In first phase, film artifacts and unwanted portions of MRI Brain image are removed. Secondly, the noise and high frequency components are removed using weighted median filter (WM). Final one is segmentation phase. It has two different approaches like block based (non algorithmic) and ACO algorithm segmentation. Finally the performance of the above two approaches are evaluated.

Hybrid Markov Random Field with Parallel Ant Colony Optimization and Fuzzy C Means for MRI Brain Image segmentation

In this paper, a novel approach to MRI Brain Image segmentation based on the Hybrid Parallel Ant Colony Optimization (HPACO) with Fuzzy C-Means (FCM) Algorithm have been used to find out the optimum label that minimizes the Maximizing a Posterior (MAP) estimate to segment the image. There are M colonies, M-1 colonies treated as slaves and one colony for master. Each colonies visit all the pixels with out revisit. Initially, initialize the pheromone value for all the colonies. Posterior energy values or fitness values are computed by Markov Random Field. If this value is less than global minimum, the local minimum is assigned to global minimum. The pheromone of the Ant that generates the global minimum is updated. At the final iteration global minimum returns the optimum threshold value for select the initial clustering the FCM implementation in the brain Magnetic Resonance Image (MRI) segmentation.

Fuzzy Based Ant Miner Algorithm in Datamining for Hepatitis

Data mining or knowledge discovery in databases in simple words is the non-trivial extraction of implicit, previously unknown and potentially useful information from data. It deals with the discovery of hidden knowledge, unexpected patterns and new rules from large databases. Knowledge discovery in databases is the process of identifying a valid, potentially useful and ultimately understandable structure in data. Datasets of hepatitis are collected from the benchmark repository and training datasets are revealed. Data mining tasks including classification, clustering, regression etc., In order to discover the classification rules, ant miner algorithm is used. The ant miner algorithm is based on the behavior of ants in searching of food. The proposed method extracts the classified rules using Fuzzy Based Ant Miner Algorithm (FACO). The training set is taken and the FACO algorithm is applied initially for classifying the categorical attributes. Using heuristic functions, the best rules are generated. Next, rule pruning is performed to obtain the optimized rules based on quality functions. The accuracy of the designed system is determined using the test cases. FACO is used to bring out with better quality for the classified rules. The project aims at obtaining the best rules with maximum accuracy. It provides the secondary opinion for the doctors and it predicts the hepatitis in the earlier stage.

Identifying Masses in Mammograms Using Template Matching

This paper introduces a novel segmentation scheme based on the template-matching method is used for identifying cancerous part in the mammogram image. These templates are defined according to the shape, and brightness of the masses or micro calcifications. Earlier to template matching, median filtering enhances the mammogram images, Edge detection operators such as Sobel, Prewitts, Laplacian and Laplacian of Guassian masks are enhances and detect the edges and then edge detection is used to detect the shape of the cancerous part. In the template matching, the threshold is set for the calculated values of the crosscorrelation. Then the percentile method is used to set an overall threshold for each mammogram image. The segmentation accuracy is increased as the proposed scheme is more robust to noise and hence, it prevents over segmentation in final segmented images. It is exposed that, this method of template matching for identifying early stage cancerous parts gives considerably better detection results

Mammogram image enhancement and segmentation

This paper proposes a image enhancement and segmentation method for mammographic images, which is based on the pixel intensity transformation, spatial filtering, edge detection, and region growing techniques. This method consists of two approaches. The first approach is applying intensity transformation, logarithmic transformation, contrast stretching, histogram equalization and spatial filtering techniques separately to enhance the mammogram images. In the second approach is applying edge detection operators, local and global thresholding techniques used to extract the suspicious regions from back ground tissue.