Browsing by Author "Vasantha Kalyani David"
Now showing 1 - 20 of 66
Results Per Page
Sort Options
Item Airtel Information System(2005-05) Akilandeshwari, D; Vasantha Kalyani DavidItem Augmented Content Based Image Retrieval using FusioiiBased on Self Organizing Ma(2012) Vasantha Kalyani DavidContent Based Image Retrieval (CBIR) comprises the task of retrieving the image from a large database which matches the query image. The features like color, texture and shape are taken as multiple features and using fusion Self Organizing Map the matching process is carried out. Enhanced HSV-based Histograms for color, Active Contours for shape, DWT transformation for texture are applied and this work prove that the proposed CBIR system is an improved version in terms of precision, recall and speed of image retrieval.Item Augmented Content Based Image Retrieval using Fusion Based on Self Organizing Map(2012) Vasantha Kalyani DavidContent Based Image Retrieval (CBIR) comprises the task of retrieving the image from a large database which matches the query image. The features like color, texture and shape are taken as multiple features and using fusion Self Organizing Map the matching process is carried out. Enhanced HSV-based Histograms for color, Active Contours for shape, DWT transformation for texture are applied and this work prove that the proposed CBIR system is an improved version in terms of precision, recall and speed of image retrieval.Item Authentication Based on Finger Vein Recognition Using Neuro-Fuzzy Technique(2015) Vasantha Kalyani Davidvlany computational problems are achieved by Artificial ntelligence which is based on mathematical equations and irtifid-'i neurons. The main focus is on the implementation of Inge in recognition for personal authentication. Basically he finger vein patterns are captured by a device that can ransmit near infrared through the finger and record the jatterns. The proposed biometric system for verification lonsist of a combination of feature extraction using Genetic Principal Component Analysis(GPCA) technique to obtain the iptimized features and pattern classification using Neuromzzy technique which is a learning algorithm. To verify the Tfect of the proposed Neuro fuzzy system in the pattern ilassification, the Back Propagation Network(BPN) is lompared with the proposed system. The experimental results ndicated the proposed system using Neuro fuzzy has better rerformance than the BPN for personal identification using he finger-vein patterns. This paper shows the finger vein ramework with the parameter of false acceptance rate (FAR), alse rejection rate (FRR) and total execution time for the lystem.Item Backpropogation Neural Networks to Recognize Isolated Digits(2010-07) M Dharani; Vasantha Kalyani DavidOptical Character Recognition is a field of research that has attracted several researchers for the past several decades. Recognizing handwritten characters pose several challenges, like different style of writing, pen depth and thickness and quality of the scanned handwritten image. Digit recognition, a sub field of character recognition, is the art of recognizing numbers from handwritten images. They are used in various application areas like bank (cheque number recognifion), vehicle tracking (license plate recognition), and Postal Zipcode(post office).Item Business Manager(2005-05) Rekha.E.R; Vasantha Kalyani DavidItem Cancer Classification Using Fuzzy Neural Networiswith Anova Test Procedures(2010-07) S Kalaiarase; Vasantha Kalyani DavidBiological studies progress tiirough the expansion of the expertise technologies. A DNA microarray is a high throughput technology used in molecular biology and in medicine. DNA micro arrays can be used to measure changes in expression levels or to detect single nucleotide polymorphisms. One can analyze the expression o f many genes in a single reaction quickly and in an efficient manner.Item Classifiers for Gene Micro Array Data Analysis(2010) Vasantha Kalyani DavidResearchers aim to develop an automated system for robust and reliable cancer diagnosis based on gene micro array data. There are methods for evaluating and improving techniques for selecting infonnative genes from micro array data. The genes of interest are selected by ranking them using classical statistical techniques. Various statistical classifiers are applied to get the best classification model. By applying this procedure there is always a need fur two systems; a gene selection method and a classifier, and selection of an optimal gene selection algorithm-classifier pair are difficult. To solve this difficulty, from the study it is found that genetic programming act as a classifier as well as gene selection algorithm. [12].Item Cloud enabled Big Data Analytics(2015) Vasantha Kalyani DavidCloud computing is an innovative technology with intense implications not only for internet services but also fo r the important areas o f analytics and big data. This paper provides an architecture fo r finding gaps between the technology and to recommend solutions fo r research community on Cloud-supported big data computing and analytic solutions. This paper mainly focuses on four important areas in big data analytics which are data management and supporting architecture, model development and scoring, visualisation and user interaction and business models. Cloud computing is an effective technology for determining many o f the challenges enabling ubiquitous, convenient, on-demand network access to a shared pool o f configurable computing resources that can be rapidly provisioned and released with minimal management effort or service provider interaction.Item A Comparative Performance Study on Hybrid Swarm Model for Micro array Data(2010) Vasantha Kalyani DavidCancer classification based on microarray data is an important problem. Prediction models are used for classification which helps the diagnosis procedures to improve and aid in the physician’s effort. A hybrid swarm model for microarray data is proposed for performance evaluation based on Nature-inspired metaheuristic algorithms. Firefly Algorithm (FA) is the most powerful algorithms for optimization used for multimodal applications. In this paper a Flexible Neural Tree (FNT) model for microarray data is constructed using Nature-inspired algorithms. The FNT structure is developed using the Ant Colony Optimization (ACO) and the parameters embedded in the neural tree are optimized by Firefly Algorithm (FA). FA is superior to the existing metaheuristic algorithm and solves multimodal optimization problems. In this research, comparisons are done with the proposed model for evaluating its performance to find the appropriate model in terms of accuracy and error rate.Item A Comparative Performance Study on Hybrid Swarm Model for Micro array Data(2011) Vasantha Kalyani DavidCancer classification based on microarray data is an important problem. Prediction models are used for classification which helps the diagnosis procedures to improve and aid in the physician’s effort. A hybrid swarm model for microarray data is proposed for performance evaluation based on Nature-inspired metaheuristic ulgoi'itliiiis. Fiiefly Alguiilhu] (FA) is the most powerful algorithms^ for optimization used for multimodal applications. In this paper a Flexible Neural Tree (FNT) model for microarray data is constructed using Nature-inspired algorithms. The FNT structure is developed using the Ant Colony Optimization (ACO) and the parameters embedded in the neural tree are optimized by Firefly Algorithm (FA). FA is superior to the existing metaheuristic algorithm and solves multimodal optimization problems. In this research, comparisons are done with the proposed model for evaluating its performance to find the appropriate model in terms of accuracy and error rate.Item Constructing Models from Microarray Data with Swarm Algorithms(2010) Vasantha Kalyani DavidBuilding a model plays an important role in DNA microarray data. An essential feature of DNA microarray data sets is that the number of input variables (genes) is far greater than the number of samples. As such, most classification schemes employ variable selection or feature selection methods to pre-process DNA microarray data. In this paper Flexible Neural Tree (FNT) model for gene expression prordes classification is done. Based on the predefined instruction/operator sets, a flexible neural tree model can be created and evolved. This framework allows input variables selection, over-layer connections and different activation functions for the various nodes involved. The FNT structure is developed using the Ant Colony Optimization (ACO) and the free parameters embedded in the neural tree are optimized by Particle Swarm Optimization (PSO) algorithm and its enhancement (EPSO). The purpose of this research is to find the model which is an appropriate model for feature selection and tree-based ensemble models that are capable of delivering high performance classification models for microarray data.Item Continuous Neighbor Discovery in Asynchronous Sensor Networks(2012-04) Vaishnavee, R; Vasantha Kalyani DavidItem Crime Rate Prediction using K-Means Clustering Algorithm(2019-04) Tamilarasi, C; Vasantha Kalyani DavidItem Defensive Modeling of Fake News Through Online Social Networks(2022-05) Piruthvi, A; Vasantha Kalyani DavidItem Design of Power Gating Technique Using Neural Functions for Signal Compression and Decompression(2014-07-31) S Ponmalar; Vasantha Kalyani DavidThe goals for computational problems are achieved by Artificial Intelligence. This intelligence based on mathematical equation and artificial neurons. The main focus is on the implementation of chip layout design and this is trained using Power Gating (PG) Technique in analog domain with new technique to produce power to the CMOS board using VLSI application. The Analog components used are Gilbert Cell Multiplier (GCM), Neuron Activation Function (NAF) and Adders for the implementation. The Existing system consumes designing of Signal Compression and Decompression using Back Propagation (BP) Algorithm of Neural Networks (NN).Back Propagation uses a digital computer to calculate weights while the final network being hardware loses its plasticity. Moreover the calculation is slow and training speed is also slow. Hence Power consumption is high and overall delay is high. Compression and Decompression is done in lossy data and not to lossless data. The Proposed system consumes Power Gating Technique and this reduces power and overcomes the disadvantage of the existing system. Signal Compression and Decompression are designed using Power Gating Technique. Layout Design and Verification of the Power Gating Technique carried out using Micro wind 2.6 (Back-End tool).The Technology used in the designing layout is 0.12 Micrometer Technology.Item Distributed Data Mining In Credit Card Fraud Detection(2012-04) Mathivathani, S; Vasantha Kalyani DavidItem E-Mail Dispersion Tool(2007-04) Parvathi Mayil, A; Vasantha Kalyani DavidItem Emergency Alert System on Android Mobile Platform(2015-03) Tintu George; Vasantha Kalyani DavidItem Employee E-Exam Management System(2014-03) Baby Priyanka, G; Vasantha Kalyani David