I. Ramesh Babu

Acharya Nagarjuna University, Гунтура, Andhra Pradesh, India

Are you I. Ramesh Babu?

Claim your profile

Publications (25)0 Total impact

  • Source
    Pokkuluri Kiran Sree · Inamupudi Ramesh Babu · SSSN Usha Devi N
    [Show abstract] [Hide abstract]
    ABSTRACT: Protein Structure Predication from sequences of amino acid has gained a remarkable attention in recent years. Even though there are some prediction techniques addressing this problem, the approximate accuracy in predicting the protein structure is closely 75%. An automated procedure was evolved with MACA (Multiple Attractor Cellular Automata) for predicting the structure of the protein. Most of the existing approaches are sequential which will classify the input into four major classes and these are designed for similar sequences. PSMACA is designed to identify ten classes from the sequences that share twilight zone similarity and identity with the training sequences. This method also predicts three states (helix, strand, and coil) for the structure. Our comprehensive design considers 10 feature selection methods and 4 classifiers to develop MACA (Multiple Attractor Cellular Automata) based classifiers that are build for each of the ten classes. We have tested the proposed classifier with twilight-zone and 1-high-similarity benchmark datasets with over three dozens of modern competing predictors shows that PSMACA provides the best overall accuracy that ranges between 77% and 88.7% depending on the dataset.
    01/2014; 2(3). DOI:10.1166/jbic.2013.1052
  • Source
    P. Kiran Sree · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Pattern recognition problem rely upon the features inherent in the pattern of images. Face detection and recognition is one of the challenging research areas in the field of computer vision. In this paper, we present a method to identify skin pixels from still and video images using skin color. Face regions are identified from this skin pixel region. Facial features such as eyes, nose and mouth are then located. Faces are recognized from color images using an RBF based neural network. Unsupervised Cellular Automata with K means clustering algorithm is used to locate different facial elements. Orientation is corrected by using eyes. Parameters like inter eye distance, nose length, mouth position, Discrete Cosine Transform (DCT) coefficients etc. are computed and used for a Radial Basis Function (RBF) based neural network. This approach reliably works for face sequence with orientation in head, expressions etc.
  • Source
    P. KIRAN SREE · I Ramesh Babu · J. V. R. Murty
    [Show abstract] [Hide abstract]
    ABSTRACT: Ad hoc wireless network with their changing topology and distributed nature are more prone to intruders. The network monitoring functionality should be in operation as long as the network exists with nil constraints. The efficiency of an Intrusion detection system in the case of an ad hoc network is not only determined by its dynamicity in monitoring but also in its flexibility in utilizing the available power in each of its nodes. In this paper we propose a hybrid intrusion detection system, based on a power level metric for potential ad hoc hosts, which is used to determine the duration for which a particular node can support a network- monitoring node. Power -aware hybrid intrusion detection system focuses on the available power level in each of the nodes and determines the network monitors. Power awareness in the network results in maintaining power for network monitoring, with monitors changing often, since it is an iterative power-optimal solution to identify nodes for distributed agent-based intrusion detection. The advantage that this approach entails is the inherent flexibility it provides, by means of considering only fewer nodes for re-establishing network monitors. The detection of intrusions in the network is done with the help of Cellular Automata (CA). The CA's classify a packet routed through the network either as normal or an intrusion. The use of CA's enable in the identification of already occurred intrusions as well as new intrusions.
  • ACM SIGSOFT Software Engineering Notes 05/2012; 37(3):1. DOI:10.1145/2180921.2180940
  • [Show abstract] [Hide abstract]
    ABSTRACT: Data preprocessing is an important activity for discovering behavioral patterns. The analysis of web logs is an essential task for System Administrators to safeguard adequate bandwidth and to maintain server capacity on their business websites. A web Log file represents user activities occurring over a period of time. Web log files offer valuable insight into the effective usage of the web site. It helps maintain an account of the actual usage in a regular working system as compared to the virtual setting of a usability lab. This research paper focuses on the preprocessing techniques implemented on a specially designed Web Sift (WebIS) tool on an IIS web server and also proposes some efficient heuristics and techniques
    ACM SIGSOFT Software Engineering Notes 01/2012; DOI:10.1145/180921.2180940
  • P. Kiran Sree · I. Ramesh Babu · S. Viswanadha Raju
    [Show abstract] [Hide abstract]
    ABSTRACT: Clustering has been widely applied to Information Retrieval (IR) on the grounds of its potential improved effectiveness over inverted file search. Clustering is a mostly unsupervised procedure and the majority of the clustering algorithms depend on certain assumptions in order to define the subgroups present in a data set.A clustering quality measure is a function that, given a data set and its partition into clusters, returns a non-negative real number representing the quality of that clustering. Moreover, they may behave in a different way depending on the features of the data set and their input parameters values. Therefore, in most applications the resulting clustering scheme requires some sort of evaluation as regards its validity. The quality of clustering can be enhanced by using a Cellular Automata Classifier for information retrieval. In this study we take the view that if cellular automata with clustering is applied to search results (query-specific clustering), then it has the potential to increase the retrieval effectiveness compared both to that of static clustering and of conventional inverted file search. We conducted a number of experiments using ten document collections and eight hierarchic clustering methods. Our results show that the effectiveness of query-specific clustering with cellular automata is indeed higher and suggest that there is scope for its application to IR. Key words: Cellular automata, information retrieval, clustering
  • Source
    P. Srinivasulu · J. Ranga Rao · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: In the faceless world of the Internet,online fraud is one of the greatest reasons of loss for web merchants.Advanced solutions are needed to protect e businesses from the constant problems of fraud.Many popular fraud detection algorithms require supervised training,which needs human intervention to prepare training cases.Since it is quite often for an online transaction database to ha e Terabyte level storage,human investigation to identify fraudulent transactions is very costly.This paper describes the automatic design of user profiling method for the purpose of fraud detection.We use a FP (Frequent Pattern) Tree rule learning algorithm to adaptively profile legitimate customer behavior in a transaction database.Then the incoming transactions are compared against the user profile to uncover the anomalies The anomaly outputs are used as input to an accumulation system for combining evidence to generate high confidence fraud alert value. Favorable experimental results are presented.
  • Source
    Srinivasulu P · R. Satya Prasad · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Security is becoming a critical part of organizational informationsystems. Network Intrusion Detection System (NIDS) is an importantdetection that is used as a countermeasure to preserve data integrity andsystem availability from attacks. The detection of attacks against computernetworks is becoming a harder problem to solve in the field of Networksecurity. Intrusion Detection is an essential mechanism to protectcomputer systems from many attacks. The success of an intrusiondetection system depends on the selection of the appropriate features indetecting the intrusion activity. In NIDS electing unnecessary featuresmay cause computational issues and decrease the accuracy of detection.This paper describes a technique of applying Genetic Algorithm (GA) tochoose features (attributes) of KDDCUP99 Dataset. We have chosen thestandard dataset KDDCUP from MIT, U.S.A, which is used for IDSresearch oriented projects. In this paper a brief overview of the IntrusionDetection System and genetic algorithm is presented. We used BayesNetwork (BN), and Decision Tree (DT) Tree approaches for classifyingthe network attacks for chosen attribute dataset. These models gave betterperformance compared with the all features of dataset.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Data mining also known as knowledge discovery in databases has been recognized as a promising newarea for database research. The proposed work in this paper is about optimizing the data with clusteringand fuzzy association rules using multi-objective genetic algorithms. This algorithm is implemented in twophases. In the first phase it optimizes the data to reduce the number of comparisons using clustering. Inthe second phase it is implemented with multi-objective genetic algorithms to find the optimum number offuzzy association rules using threshold value and fitness function.
  • Source
    P. Kiran Sree · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Network Intrusion Detection Systems (NIDS) are computer systems which monitor a network with the aim of discerning malicious from benign activity on that network. With the recent growth of the Internet such security limitations are becoming more and more pressing. Most of the current network intrusion detection systems relay on labeled training data. An Unsupervised CA based anomaly detection technique that was trained with unlabelled data is capable of detecting previously unseen attacks. This new approach, based on the Cellular Automata classifier (CAC) with Genetic Algorithms (GA), is used to classify program behavior as normal or intrusive. Parameters and evolution process for CAC with GA are discussed in detail. This implementation considers both temporal and spatial information of network connections in encoding the network connection information into rules in NIDS. Preliminary experiments with KDD Cup data set show that the CAC classifier with Genetic Algorithms can effectively detect intrusive attacks and achieve a low false positive rate. Training a NIDWCA (Network Intrusion Detection with Cellular Automata) classifier takes significantly shorter time than any other conventional techniques.
    Advanced Computer Theory and Engineering, 2008. ICACTE '08. International Conference on; 01/2009
  • Source
    P. Kiran Sree · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Adhoc wireless network with their changing topology and distributed nature are more prone to intruders. The efficiency of an Intrusion detection system in the case of an adhoc network is not only determined by its dynamicity in monitoring but also in its flexibility in utilizing the available power in each of its nodes. In this paper we propose a hybrid intrusion detection system, based on a power level metric for potential adhoc hosts, which is used to determine the duration for which a particular node can support a network-monitoring node. The detection of intrusions in the network is done with the help of Cellular Automata (CA). IDFADNWCA (Intrusion Detection for Adhoc Networks with Cellular Automata) focuses on the available power level in each of the nodes and determines the network monitors. Power Level Metric in the network results in maintaining power for network monitoring, with monitors changing often, since it is an iterative power optimal solution to identify nodes for distributed agent based intrusion detection. The advantage of this approach entails is the inherent flexibility it provides, by means of considering only fewer nodes for reestablishing network monitors.
    Advanced Computer Theory and Engineering, 2008. ICACTE '08. International Conference on; 01/2009
  • P Kiran Sree · I Ramesh Babu · N S S S N Usha Devi
    [Show abstract] [Hide abstract]
    ABSTRACT: Genes carry the instructions for making proteins that are found in a cell as a specific sequence of nucleotides that are found in DNA molecules. But, the regions of these genes that code for proteins may occupy only a small region of the sequence. Identification of the coding regions plays a vital role in understanding these genes. In this paper we have explored an Artificial Immune System (AIS) that can be used to strengthen and identify the protein coding regions in a genomic DNA system in changing environments and the CA technique for protein structure prediction of small alpha/beta proteins using Rosetta. From an initial round of Rosetta sampling, we learn properties of the energy landscape that guide a subsequent round of sampling toward lower-energy structures. Three different approaches to improve tertiary fold prediction using the genetic algorithm are discussed: refinement of the search strategy; combination of prediction and experiment; inclusion of experimental data as selection criteria into the genetic algorithm. It has been developed using a slight variant of genetic algorithm. Good classifiers can be produced, especially when the number of the antigens is increased. However, an increase in the range of the antigens somehow affects the fitness of the immune system. Experimental results confirm the scalability of the proposed AIS FMACA based classifier to handle large volume of datasets irrespective of the number of classes, tuples and attributes. We note an increase in accuracy of more than 5.2%, over any existing standard algorithms that address this problem. This was the first algorithm to identify protein coding regions in mixed and also non-overlapping exon-intron boundary DNA sequences. The accuracy of prediction of the structure of proteins was also found comparable.
    International Journal of Bioinformatics Research and Applications 01/2009; 5(6):647-62. DOI:10.1504/IJBRA.2009.029044
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Classification of iris templates based on their texture patterns is one of the most effective methods in iris recognition systems. This paper proposes a novel algorithm for automatic iris classification based on fractal dimensions of Haar wavelet transforms is presented. Fractal dimensions obtained from multiple scale features are used to characterize the textures completely. Haar wavelet is applied in order to extract the multiple scale features at different resolutions from the iris image. Fractal dimensions are estimated from these patterns and a classifier is used to recognize the given image from a data base. Performance comparison was made among different classifiers.
  • Source
    E. Srinivasa Reddy · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Blend of cryptography and biometrics results an emerging architecture known as Crypto-biometrics which produces high level security. Fuzzy vault is a cryptographic construction used to store iris biometric templates which are binded by a random key extracted from same iris textures. Though the fuzzy vault provides better security, it is affected by cross matching, non uniform nature of biometric data. To overcome these limitations, we propose a scheme that hardens both fuzzy vault and secret key using password based on iris textures. By using password an additional layer of security is embedded to achieve high level security.
    Computer and Information Technology Workshops, 2008. CIT Workshops 2008. IEEE 8th International Conference on; 08/2008
  • E. Srinivasa Reddy · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Crypto-biometrics is an emerging architecture where cryptography and biometrics are merged to achieve high level security systems. This paper explores the realization of cryptographic construction called fuzzy vault to store digital signature based on iris pseudo textures. Iris pseudo textures such as nodes and end points does not change through out the life period of user and can be used to extract minutiae to lock and unlock the fuzzy vault. The proposed algorithm aims to create a fuzzy vault to store secret key, based on iris pseudo textures. The algorithm has two phases: The first is to extract binary key (digital signature) from iris textures, and the second to generate fuzzy vault by using Lagrange interpolating polynomial projections, further which is projected by using data units extracted from iris minutiae.
    Modeling & Simulation, 2008. AICMS 08. Second Asia International Conference on; 06/2008
  • V. Srikanth · D. Swathi · M. Tabassum · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Wireless sensor networks are new type of emerging networks with bunch of applications in all fields due to their low cost and low power scheme. As these networks follow open wireless communication, they undergo dynamic node problems and fault node detection due to malicious node activities. In this paper we overcome these problems with the help of algorithms that will provide uninterrupted communication and also save node's energy and time.
    Wireless, Mobile and Multimedia Networks, 2008. IET International Conference on; 02/2008
  • P. Kiran Sree · Raju G.V.S · I. Ramesh Babu · S. Viswanadha Raju
    [Show abstract] [Hide abstract]
    ABSTRACT: Clustering has been widely applied to Information Retrieval (IR) on the grounds of its potential improved effectiveness over inverted file search. Clustering is a mostly unsupervised procedure and the majority of the clustering algorithms depend on certain assumptions in order to define the subgroups present in a data set .A clustering quality measure is a function that, given a data set and its partition into clusters, returns a non-negative real number representing the quality of that clustering. Moreover, they may behave in a different way depending on the features of the data set and their input parameters values. Therefore, in most applications the resulting clustering scheme requires some sort of evaluation as regards its validity. The quality of clustering can be enhanced by using a Cellular Automata Classifier for information retrieval. In this study we take the view that if cellular automata with clustering is applied to search results (query-specific clustering), then it has the potential to increase the retrieval effectiveness compared both to that of static clustering and of conventional inverted file search. We conducted a number of experiments using ten document collections and eight hierarchic clustering methods. Our results show that the effectiveness of query-specific clustering with cellular automata is indeed higher and suggest that there is scope for its application to IR.
    Journal of Computer Science 02/2008; 4(2). DOI:10.3844/jcssp.2008.167.171
  • Source
    Y. Dhanalakshmi · I. Ramesh Babu
    [Show abstract] [Hide abstract]
    ABSTRACT: Summary Intrusion Detection is one of the important area of research. Our work has explored the possibility of integrating the fuzzy logic with Data Mining methods using Genetic Algorithms for intrusion detection. The reasons for introducing fuzzy logic is two fold, the first being the involvement of many quantitative features where there is no separation between normal operations and anomalies. Thus fuzzy association rules can be mined to find the abstract correlation among different security features. We have proposed architecture for Intrusion Detection methods by using Data Mining algorithms to mine fuzzy association rules by extracting the best possible rules using Genetic Algorithms. .
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Genes carry the instructions for making proteins that are found in a cell as a specific sequence of nucleotides that are found in DNA molecules. But, the regions of these genes that code for proteins may occupy only a small region of the sequence. Identifying the coding regions play a vital role in understanding these genes. In this paper we have explored an artificial immune system can be used to strengthen and identify the protein coding regions in genomic DNA system in changing environments. It has been developed using a slight variant of genetic algorithm. Good classifier can be produced especially when the number of the antigens is increased. However, an increase in the range of the antigens had somehow affected the fitness of the immune system. Experimental results confirm the scalability of the proposed AIS FMACA based classifier to handle large volume of datasets irrespective of the number of classes, tuples and attributes. We note an increase in accuracy of more than 5.2%, over any existing standard algorithms for addressing this problem. This was the first algorithm to identify protein coding regions in mixed and non overlapping exon-inton boundary DNA sequences also. Keywords—Cellular Automata (CA), unsupervised learning Classifier, Genetic Algorithm (MGA), Artificial immune system, Coding Regions, Fuzzy Multiple Attractor Cellular Automata (FMACA), Pattern Classifier
  • I. Ramesh Babu · V.S. Raghav · S.V.L.N. Rao
    [Show abstract] [Hide abstract]
    ABSTRACT: The authors propose a new concept known as neighbourhood images to generate a sequence of images from dilation to erosion and from closing to that of opening on the basis of an algorithm presented by K. Vladimir (1986) in the morphologic domain. These generated images show a high correlation to each other. Basically, the morphologic procedures separate the border regions from those of the interior and as such, the image content and border component are affected in the morphologic transformation. The authors further utilised the dilated, the median and eroded images for decorrelation and generation of images which are ortho-normal to each other. Such decorrelated images can be utilised for the study of the borders separately from that of interior pixels. Based on this background, X-ray image of the neck and chest region displaying the malignancy near the neck region is studied. Neighbourhood images are selected and a set of three morphologic images are used for decorrelation. The first image shows enhancement with reduction of noise content. The second and the third image display the contours of the malignancy. X-ray images are routinely used, for the visual interpretation and analysis, and are not subject to rigorous procedures of image analysis
    Engineering in Medicine and Biology Society, 1995 and 14th Conference of the Biomedical Engineering Society of India. An International Meeting, Proceedings of the First Regional Conference., IEEE; 03/1995