IJCTA-Volume 5 Issue 3/ May-June 2014
Title/Author Name
Page No
Reinforcement Learning: Features and its Applications
-Jitisha R. Patel,Sunita S. Barve
This paper discusses some basic concepts of reinforcement learning, which is concerned with how software agents or learning agents ought to take actions in a complex and non-deterministic environment so as to maximize some notion of cumulative reward. The reinforcement learning (RL) approach has been applied in a variety of schemes such as routing, resource management, dynamic decision making, dynamic channel selection in wireless networks, etc. Here, an overview of classical RL, its elements, its elementary solution methods, applications and some of its open issues have been discussed.
Keywords: Reinforcement learning, reward, Q-learning, Sarsa, applications.
Halftone based Secret Sharing Visual Cryptographic Scheme for Color Image using Bit Analysis
-Pavan Kumar Gupta,Naveen Hemrajani,Savita Shiwani,Ruchi Davey
Visual Cryptography is a special type of encryption technique to obscure image-based secret information which can be decrypted by Human Visual System (HVS). It is a kind of secret-sharing scheme that encrypts the secret image into n number of shares. It is imperceptible to reveal the secret information unless a certain number of shares(k) or more are superimposed. As the decryption process is done by human visual system, secret information can be retrieved by anyone if the person gets at least k number of shares. For this, simple visual cryptography is very insecure.
In this current work we have proposed a variable length Symmetric Key based Visual Cryptographic Scheme for color images where a secret key is used to encrypt the image and division of the encrypted image is done using Random Number. Unless the secret key, the original image will not be decrypted. Here secret key ensures the security of the scheme and visual cryptography is used to break the image into number of shares.
Keywords: Visual Cryptography, Secret Sharing, Random Number, Symmetric Key.
Android BACHAOSOS Application
-Mayur Dhande,Amruta Barawkar,Raman Dhoot
Late attention by officers in charge to high volumes of crimes and emergency to an increase of unsolved cases nationwide. In this paper, we proposed the use of smart phones to retrieve the location of the victim to lessen the problems faced by police and fire fighters in retrieving accurate information while patrolling high risk area. The time taken and the accuracy of information are problems normally faced by police and fire fighters in emergency case department. It is crucial for them to get the right information at the right time to their walkie-talkie or other mobile phones. The application is developed by using Eclipse IDE platform and tested using a smart phone with Android OS. The application flow starts by retrieving the location position and sending this information to the family member and then calls to security department.
Keywords – Mobile Phones, Sensors,Voice Recognition System, Android.
Validation of Cluster Based Reusability Model
-Rajender Nath,Munishwar Rai,Jai Bhagwan
Maintenance is the major part of software modules reusability in software engineering. Without maintenance we cannot expect a good SDLC (Software Development Life Cycle). To make the perfect maintenance, we need perfect techniques of cluster analysis. On the basis of perfect clustering, we have proposed a model [1] based upon LOC and similar behaviour elements (relation between functions or modules) or you can say clones. In the proposed model, clusters will be determined by using agglomerative method and then merging of clusters via K-mean method. As we have discussed in literature review, our last approach is not fit for a big sized live project [2]. The buffer problem is fired during the test of a live project. That’s why we will use an additional tool in spite of JB Clone Scanner. The future work can be done in the direction of the implementation of our approach for live projects. A case study should be done on a live project to enhance the reusability of the programs in the comparison of efforts, development time; so that the maintenance can be done easily in the field of software modules reusability.
Keywords- AOP (Aspect Oriented Programming), LOCs (Lines of Code)
An Approach for Finding Attribute Dependencies in an Anonymized Data
-N. Sandeep Varma,V. Valli Kumari
The modern digital world leveraged both public and private organization in collecting personal information of the individuals. Researchers collect non aggregate data for mining or survey purpose from these organizations. However, this data contains individual’s sensitive information like credit card number, salary, disease etc.,. An adversary with hypothetical nature may have access to various external resources like voters/medical list for mapping the individuals so that he/she can identify the individuals potentially. Privacy Preserving models like k-anonymity, l-diversity have been proposed to thwart the privacy attacks. These models use anonymization methods like generalization, suppression and make the data privacy-safe. However, due to the presence of associations between attributes in the anonymized dataset, individual information is being compromised. This paper proposes a novel approach for detecting the associations
Cloud Backup and Disaster recovery for SME’s : Economic advantages & Challenges
-Jobin Babu,Varun Sharma
The world of cloud computing is facing one of the greatest menace i.e. the disaster recovery and back up for data and either if it is available in the market it is in the clutches of the big Guns of industry making it unavailable for SME’s (small and medium enterprises). So throwing some insight over the problem, a simpler solution come into light which gives SME’s the opportunity to backup data online for cloud with disaster recovery. It reduces the cost and helps in the protection of data with seamless transition from one cloud provider to another. A simple hardware backup can is enough to do all the work.
Keywords: Cloud computing, Linux backup, disaster recovery, RPO and RTO, SME
Enhancing Informativeness in Data Publishing while Preserving Privacy using Coalitional Game Theory
-Srinivasa L. Chakravarthy,V. Valli Kumari
k-Anonymity is one of the most popular conventional techniques for protecting the privacy of an individual. The shortcomings in the process of achieving k Anonymity are presented and addressed by using Coalitional Game Theory (CGT) [1] and Concept Hierarchy Tree (CHT). The existing system considers information loss as a control parameter and provides anonymity level (k) as output. This paper proposes techniques to improve informativeness in preserving privacy using Coalitional Game Theory (CGT) Here, each tuple is assigned a Weighted Pay Off (WPO) using CHT. This process is controlled by information loss parameter and provides better anonymization with improved informativeness. Empirical results illustrating the advantages of proposed scheme is discussed.
Keywords—Privacy Preserving Data Publishing, Anonymization, k-Anonymity, Co-Operative Game Theory, Weighted Concept Hierarchy Trees
Analysis of Medical Image Processing and its Applications in Healthcare Industry
-G.Anil Kumar,Prof.NistalaV.E.S.Murthy
Medical image processing needs continuous enhancements in terms of techniques and applications to help improve quality of services in health care industry. The techniques used for interpolation, image registration, compression, medical diagnosis are to be improved to be abreast with growing demands in the industry and emerging technologies pertaining to mobile computing and cloud computing. In this paper we present the present state-of-the-art of medical image processing and its abilities to harness the hardware resources including ever growing GPGPU platforms for improving quality of clinical practices in terms of speed, accuracy, innovation, and globalization and so on. From the analysis of the literature it is understood that the health care domain has got much scope for further research in the areas of diagnosing life threatening diseases, usage of remote health monitoring applications for real time functioning to alert healthcare personnel. The integration of medical equipment and applications with wearable devices is also promising area for further research. This paper provides useful insights into the field of medical image processing and tries to define the future scope of work.
Index Terms – Medical image processing (MIP), medical diagnosis, MIP methods and applications
A Review on Image Processing Technique for Change Detection on SAR Information
-Ajit Saxena,Dileram Bansal,Gajendra Singh
Land use/cover change detection is very important in the application of remote sensing. In the case of Synthetic Aperture Radar (SAR) acquisitions for change detection, the standard detector or change measure is based on the ratio of images. However, this measure is sensitive to the speckle effect. In remote sensing applications, change detection is the process of identifying the differences in the state of land cover or land use by analyzing a pair of images acquired in the same geographical area at different times and . In this paper we have discussed about background details of change detection and SAR with various change detection techniques on SAR information and analysis of these techniques is also presented.
Keywords: SVD (Singular Value Decomposition), Change Detect. PCA (Principle Component Analysis), multispectral SAR (Synthetic Aperture Radar) images.
Baseline of Content-Based Image Retrieval System
-Shubhangi Durgi,Prof. Pravinkumar Badadapure
Content-based image retrieval (CBIR) is used to identify relevant images based on their similarities to query images. This paper presents a novel framework for accurate image retrieval using three image features i.e. color, texture and shape. We use Color Histogram, Color Moment & Color Coherence methods for Color feature extraction. Texture is extracted using Tamura Feature. Corner detection is used for shape feature extraction. In this paper, we formulate two algorithms as Euclidean algorithm for linear structure & Image manifold algorithm for non-linear structure. Under the assumption that the data lie on a submanifold embedded in a high dimensional Euclidean space, we propose a relevance feedback scheme which is conducted only on the image manifold in question rather than the total ambient space. We then develop an algorithmic framework to approximate the optimal mapping function by a Radial Basis Function (RBF) neural network. We name the new algorithm as Image Manifold Learning (IML). Experimental results show that our approach is effective in improving the performance of content-based image retrieval systems.
Survey of Network Traffic Visualization Techniques
-Darshan K. Marode,Prof.R.K.Chavan
Network security in today's days becoming a complex problem. Before some year network administrators works with only text-based tools. These tools often provide no overview that would help users grasp the big-picture. Network traffic visualization tools have successfully enabled security analysts to understand the nature of traffic present in a network. However these tools rely mainly on human expertise to discover anomalies in traffic and attack patterns. The visualization capability provided by Visualization system allows an operator to assess the state of a large and complex network gives an overall view of the entire network and filter/drill-down features with a friendly user interface that allows users to request more detailed information of interest such as specific protocol traffic flows. Visualization tool allows operators to detect and investigate anomalous internal and external network traffic. Visualization tool shows network events graphically. We model the network as a graph with hosts being nodes and traffic being flows on edges. This survey gives a description of Visualization techniques such as parallel coordinate, Bundle View, 3D view etc. and tool which are useful in order to monitor, discover, and investigate security-relevant events
Classified Average Preciseness: CAP Algorithm for Finding Web Search Goals using Session Feedbacks
-M. Sulaiman,K.Ananthajothi,Syed Zubair Ahmed Hussainy,S.Jayakrishnan
The users are commonly using the internet for several information needs. Still, the abstruse word\topic submitted to search engine does not satisfy user information needs, because different users may have different information on dissimilar facets upon the submission of same query to search engine. So discovering different user search goals becomes complicated. The estimation and representation of user search goals can be very useful in improving search engine applicability and user knowledge. This paper proposes an approach for concluding user search goals by analyzing user query logs from several search engines. This proposed method is used to determine dissimilar user search goals for a query by clustering the user feedback sessions. The Feedback sessions are built from click-through logs of various search engines. This method generates virtual-documents to better represent feedback sessions for clustering. Finally, clustering virtual documents to discover different user search goals and describe them with some keywords. Then these user search goals are used to restructure the web search results.
Keywords—User search goals; feedback sessions; pseudo-documents; restructuring search results; classified average precision
Survey on Intrusion Detection Systems in MANET
-Nitin B. Kothwal, Dr. U. V. Kulkarni
Mobile Ad-hoc Network (MANET) is inherently vulnerable to many attacks especially routing attacks. Routing protocols proposed for MANET assumes that all nodes within network are cooperative. This assumption creates a room for attacker to satisfy their malicious intent. Main vulnerability of many routing protocols used for MANET lies in the route discovery phase of these protocols. Intrusion detection system (IDS) keeps watching for suspicious activities within a network and then initiate appropriate action against them. There are many approaches for intrusion detection in wired network but applying them directly into wireless environment is not feasible. MANET has properties like dynamic topology, self-configuration which are main obstacles for audit data collection. IDS have property that it can detect new attack even though it has been not trained for. The cost of false negative is much more than that of false positive rate for any IDS. In this paper we will see different well known attacks found in the MANET and then comparative study of different IDS in MANET.
Index Terms—MANET, IDS, Security vulnerability, wireless network
A Survey on Reversible Data Hiding Techniques
-P. S. Nalwade,Pooja Prabhakar Petkar
Recently, there are so many research is progressing on the field such as internet security, steganography, cryptography. This study describes the concept of reversible data hiding technique which is established on steganography and internet security. When to send the confidential/important/secure data over an insecure and bandwidth constrained channel it is habitual to encrypt as well as compress the cover data and then embed the confidential data into cover media. For attaining this facility there are various encryption/decryption techniques, compression techniques, and data hiding techniques available. It is also important the data hiding should be reversible in nature, should be suitable for encryption/decryption domain. Here we are analyzing the data hiding technique which is reversible in nature by using the encrypted image as a cover data in which the data is embedded. Thus, it is termed as a Reversible data hiding (RDH) technique in encrypted image. In reversible data hiding technique initially a content owner encrypts the original uncompressed image, then a data hider compress the image to create space to provide some additional data. At the receiver side, receivers extract the embedded data and recover the covering image.
Load Balanced Proactive Routing Protocol
-Vishal,Anita Singhrova
In MANET, mobile nodes communicate with each other using wireless channels, without any previously existing infrastructure. Routing plays a very important role in communication in ad hoc networks. Routing is one of the challenging tasks in mobile ad hoc networks. Most of the existing routing algorithms in mobile ad hoc networks are based on the shortest path metric, which uses the same path for routing in several sessions. So, there is a heavy load on the shortest path. Hence, there is need of load balancing in MANETS because the nodes in the network have limited communication resources such as bandwidth, energy. This paper discusses the load balancing in DSDV routing protocol using the parameters like response time, Packet transmission and communication on the nodes for efficient data transmission. Finally, the comparison is drawn between the proposed protocol and the existing protocol using different parameters.
Keywords— DSDV, Load Balancing, Packet Loss Rate, Packet Delivery Fraction, Packet Delay.
Dynamic Inspection of Contract Storages in Cloud using a Third Party Auditor
-Shilpa K S,Dr. K M Ravikumar
Cloud Computing has been envisioned as the next-generation architecture of IT Enterprise. It moves the application software and databases to the centralized large data centres, where the management of the data and services may not be fully trustworthy. This unique paradigm brings about many new security challenges, which have not been well understood. This work studies the problem of ensuring the integrity of data storage in Cloud Computing. In particular, we consider the task of allowing a third party auditor (TPA), on behalf of the cloud client, to verify the integrity of the dynamic data stored in the cloud. The introduction of effective TPA eliminates the involvement of the client through the auditing of whether his data stored in the cloud is indeed intact, which can be important in achieving economies of scale for Cloud Computing.
Develop a Village Information System (VIS) Application Using Visual Basic (VB) Programming
-Dr. Pradip Ashok Saymote
Organizations like Space Application Centre (SAC), Ahmedabad (ISRO) and other several institutes have working a large number of projects related to the Resource Development. GIS awareness and requirements have increased manifold, especially in the Government sector. GIS based Village information system (VIS) will help to improve the governance by decentralizing planning at micro level. In various studies of geoinformatics provides information specifically for analysis and VB programming with particular domain has been integrated in this study on a single platform for effective decision making.Programming languages can be used to write the programs that work as a mode of human communication between system and man. VISUAL BASIC is an ideal Programming Language of Microsoft used on Windows platform for small and medium scale application development.The data like land records, cropping details, soil information, household details, demographic aspects, various types of maps, graphs etc. are stored systematically and one can make use of it as per the given access 24 × 7. This application is dealing with both in English and Marathi language. In this paper an attempt is made to construct village level information system using visual basic programming language.
Keywords: Village Information System (VIS), Visual Basic (VB), Programming Language, GIS.
Comparative Study of SQLIA Detection and Prevention Technique
-Mayur Pradip Kharat,P.S.Nalwade
In today’s era web application increasing day by day very immensely. With these web applications many security attacks are also escalating, form those SQL Injection Attack (SQLIA) is a most precarious vulnerability for web applications. The main factor for SQL Injection is improper validation of user input. Improper input can cause an attacker to retrieve confidential information about the victim. In SQL attack hackers take advantage of weakly developed web application by inserting malicious code to gain more information about the victim. The application doesn’t have proper filters for improper inputs that cause SQLIA a dangerous attack. This paper presents a comparative study of many SQLIA defensive techniques.
Keywords— SQL Injection Attack, Malicious code.
Cloud Computing: Security Threats and Solutions
-Nityendra Nath Shukla,Vijander Singh
Virtualization plays a major role in the handling of cloud technology. Cloud computing uses virtualization to the maximum extent to give cost-effective services to the customer. But, it leads to a major flaw the current cloud industry is facing. The issue related to security in cloud has always been a hot topic for research and debate between the technocrats.This paper identifies the problems in security in cloud computing and tries to magnify it in terms of cloud computing based on the analysis of security threats of a cloud and also the technical components are taken into account.
Keywords: cloud computing, security problems, threats, cloud service user and cloud service provider.
Image File Formats – An Analysis
-Gomathi Kasi Viswanathan,Rayappan Lotus
Images play a major role in every aspect. In today’s modern world, digital images play a major role in many applications like medical analysis, online transactions and biometric security systems. The images thus stored belong to different file formats and are used for different purposes. This paper gives a detailed note on the working of file formats and the characteristics of various file formats with their advantages, disadvantages and their application areas. Thus this paper gives knowledge about selection of correct file formats for each of the images.
IJCTA © Copyrights 2010| All Rights Reserved.

This work is licensed under a Creative Commons Attribution 2.5 India License.