Advances in Intelligent Systems and Computing | Year: 2016
Many business applications use data mining techniques. Small organizations collaborate with each other to develop few applications to run their business smoothly in competitive world. While developing an application the organization wants to share data among themselves. So, it leads to the privacy issues of the individual customers, like personal information. This paper proposes a method which combines Walsh Hadamard Transformation (WHT) and existing data perturbation techniques to ensure privacy preservation for business applications. The proposed technique transforms original data into a new domain that achieves privacy related issues of individual customers of an organization. Experiments were conducted on two real data sets. From the observations it is concluded that the proposed technique gives acceptable accuracy with K-Nearest Neighbour (K-NN) classifier. Finally, the calculation of data distortion measures were done. © Springer India 2016.
Mallaiah G.,KITS |
Kumar A.,National Institute of Technology Warangal |
Ravinder Reddy P.,CBIT |
Madhusudhan Reddy G.,Indian Defence Research And Development Laboratory
Materials and Design | Year: 2012
The effect of grain refining elements such as copper, titanium and aluminum on transverse tensile strength, ductility, impact toughness, microhardness and austenite content of AISI 430 ferritic stainless steel welds through Gas Tungsten Arc Welding (GTAW) process in as-welded condition was studied. Taguchi method was used to optimize the weight percentage of copper, titanium and aluminum for maximizing the mechanical properties and austenite content in the weld region of ferritic stainless steel welds. Based on Taguchi orthogonal array the regression equations were developed for predicting the mechanical properties of ferritic stainless steel welds within the range of grain refining elements. The observed mechanical properties and austenite content have been correlated with microstructure and fracture features. © 2011 Elsevier Ltd.
Vodithala S.,KITS |
Proceedings of the IEEE International Conference on Software Engineering and Service Sciences, ICSESS | Year: 2015
Software reuse is one of the major research area in component based software engineering (CBSE). It is an area which integrates all the other technical areas like data mining, soft computing, artificial intelligence etc. The major areas which are to be focused in software reuse are classification, clustering, searching, indexing and retrieval of software components. There are many techniques described in literature each with their advantages and limitations. In this paper, we propose a dynamic approach where the components are retrieved by using genetic algorithm. The proposed algorithm mainly focuses on the termination condition or stopping criteria of Genetic Algorithm, which changes dynamically based on the user query. Genetic Algorithm (GA) stops the evolution i.e., reaches convergence when the average fitness value of the population becomes equal to the fitness value of the user query. © 2015 IEEE.
Jyothi B.V.,CBIT |
ISMS 2010 - UKSim/AMSS 1st International Conference on Intelligent Systems, Modelling and Simulation | Year: 2010
In this paper, we describe two new approaches to content-based image retrieval (CBIR) based on preference information provided by the user interacting with an image search system. First, we present the existing methods of image retrieval with relevance feedback, which serve then as a reference for the new approaches. The first extension of the distance function-based CBIR approach makes it possible to apply this approach to complex objects .Next we discuss the second approach for image retrieval. That new algorithm is based on an approximation of user preferences by a neural network. Finally we discuss the advantages and disadvantages and further improvements and future scope in this particular area. © 2010 IEEE.
Chandra Mohan Reddy G.,CBIT |
Ravindra Reddy P.V.R.,CBIT |
Janardhan Reddy T.A.,Osmania University
Tribology International | Year: 2010
Drawability is a term commonly used to describe the ease with which the metal can be drawn into the cups. The various measures of drawability are limit drawing ratio and the limit strains which are influenced by the parameters like tooling configurations, blank configurations, material properties, and forming conditions. Generally the drawability is limited by tearing of the cup at the punch corners. Friction plays an important role in deciding drawability in such a situation. In this work, the effect of coefficient of friction on limit drawing ratio and the limit strains are studied using an explicit finite element code LSDYNA. The model is validated by comparing force obtained by the existing experimental setup with the one obtained in simulation. The limit strains obtained from the simulation are verified by the analytical equations developed using vortex theory. The results are tallying within 0.17-8.29% error. © 2009 Elsevier Ltd. All rights reserved.
Radhika K.,CBIT |
Reddy A.V.G.,Osmania University
ICECT 2011 - 2011 3rd International Conference on Electronics Computer Technology | Year: 2011
Next generation wireless networks are expected to exhibit heterogeneity in terms of wireless access technologies, services and application requirements. These heterogeneous wireless access networks consist of the integration of various wireless networks especially Wi-Fi (WLAN), Wi-Max and 3G/B3G cellular networks. One of the challenging problems is to choose the optimal network depending upon the type of the demanding application. Vertical handoff occurs when a mobile terminal decides to switch to the selected network from the current network. This paper mainly deals with a network selection algorithm based on Fuzzy Multiple Attribute Decision Making. The algorithm considers the factors of Received Signal Strength(RSS), Monetary cost(C), Band Width (BW), Velocity (V) and user preference (P). It finds the Network selection function (NSF) that measures the efficiency in utilizing radio resources by handing off to a particular network. The network that provides highest NSF is selected as the best network to hand off from the current access network. © 2011 IEEE.
Venu D.,Osmania University |
Proceedings of the 2016 IEEE International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2016 | Year: 2016
Passive radar detects and locates the target by using third-party transmitters like FM, Digital Broadcast Signals, or any other communications links. The cost of installation and operation is low for such passive radars. It is difficult to detect and jam these passive radars, since they do not use dedicated transmitters, known as transmitter-of-opportunity. Over the last few years these systems have led to growing interest as increasing maturity of passive radar systems. In this paper, FM broadcast based passive radar is used to determine the target range. An algorithm based on cross correlation is developed to determine the distance from the target to passive radar receiver separated by certain distance and a stationary target is available. In this paper we have used a dual antenna based passive radar receiver. Algorithm is developed to work even at very low SNR. Test results have clearly indicated the efficacy of the method and the computed parameter demonstrated the fact that the FM broadcast based passive radars serve the said purposes. © 2016 IEEE.
Tallapragada V.V.S.,C.B.I.T. |
Rajan E.G.,Pentagram Research Center
Proceedings - 1st International Conference on Integrated Intelligent Computing, ICIIC 2010 | Year: 2010
Iris biometric is considered to be one of the most efficient and trusted biometric method for authenticating users. This paper presents a method for iris recognition based on hybrid feature set of wavelet and GLCM features, a non-filter based technique, combined with Haar wavelet transform to increase the efficiency of the system. Here we combine frequency domain feature with spatial domain feature to increase overall efficiency of system. Probability neural Network is used to classify the features. Results show that the overall system efficiency is 94% with false rejection rate higher than false acceptance rate. The technique is tested on CASIA Iris database. © 2010 IEEE.
Sastry P.N.,CBIT |
Krishnan R.,Amrita University
Proceedings of the 2012 World Congress on Information and Communication Technologies, WICT 2012 | Year: 2012
This paper deals with the Palm leaf character recognition (PLCR) using Radon Transform applied to Telugu Characters. A large collection of these Palm leaf characters are available in the classical Indian languages like Sanskrit, Tamil, Pali etc as well as in more modern languages like Telugu. Manuscripts on Palm leaves in India are the most unique collection for Centuries pertaining to wisdom and knowledge containing religious texts and treaties on a host of subjects such as art, medicine, astronomy, astrology, mathematics, law and music in various traditional and modern languages. The palm leaves are natural organic products and are therefore very susceptible to deterioration due to climatic factors (relative humidity, temperature), light and insects. Hence, preservation and digitization of these palm leaves/manuscripts is important. These characters on the palm leaf have the additional properties like depth (which is proportional to the pen pressure applied by the scriber), an added feature which can be gainfully exploited in PLCR. This paper explores how these 3D features can be extracted and how they can be gainfully used in the recognition and classification process using Radon Transform and Nearest Neighborhood Classifier (NNC). The best percentage of accuracy obtained in the proposed method is 93%. © 2012 IEEE.
Kumar G.V.P.,CBIT |
Proceedings of IEEE International Conference on Circuit, Power and Computing Technologies, ICCPCT 2016 | Year: 2016
Cognitive Radio is relatively new standard for mobile communication, especially designed to meet the challenges of high spectrum demand for packet data. As spectrum is limited and expensive, unutilized spectrum is an economic constraint for the service provider. Cognitive radio provides a solution for this by providing means of reallocating the unused spectrum to secondary user (SU) when part of spectrum is unused by primary users (PU). Several past works have addressed this issue using various algorithm which ranges from statistical analysis to predictive analysis. In this paper we propose a novel solution for spectrum sensing using frequency domain analysis of the transmitted data. However one of the lesser addressed issues in this direction has been the consideration of PU emulation attack. If a SU has sufficient means of estimating void spectrum, then it can emulate a PU spectrum which then results is low accuracy in void spectrum detection. In this work we primarily focus on frequency domain analysis for void spectrum detection such that free spectrum can be padded up to prevent emulation attacks. We consider a cognitive radio network and adopt BPSK transmission. We assume that the access points are time synchronized and have preliminary knowledge of beginning of a transmission cycle. FFT of signal data in a time slot reveals the energy in the bands. By adaptive thresholding the energy of distinct bands we determine the free spectrum. Further we also demonstrate the means of reallocating this band by injecting secondary user data in the spectrum. We analyze the solution under AWGN channel. Comparison with QR based spectrum sensing technique reveals that the proposed work provides better sensing under high noise by triggering fewer false alarms and through more accurate prediction of the unused spectrum. © 2016 IEEE.