Understanding Captcha: with its types,for security
Sonali S. pawar, Prof. Pravin P. Kalyan
CAPTCHAs are short for Completely Automated Public Turing test to tell Computer and Humans Apart.This test istaken to insure that the user is a human being and not the machine or any program.It contains different types of tests which can only be solved by the humans.this is because to avoid bad interface of machines in an application. Captcha as graphical passwords (CaRP) is one of the new security built on Captcha technology. As its name implies that CaRP is the combination of both CAPTCHA and Graphical password scheme. CaRP addresses a number of security problems altogether, it offers reasonable security and usability with some practical applications for improving online security
Impact of Marker Width to Optimize Fabric Cost of Garments
Md. Rafiqul Islam Manik , Ishrat Jahan
The export of garment products to the world market has become very competitive in recent years. Buyers are demanding to get the products at lower price. Thus, the garment manufacturers need to minimize the cost of the product in order to sustain in the global market. Fabric covers the maximum cost of a garment in terms of percentage. If cost behind fabric can be minimized by utilizing maximum amount of fabric, the cost of the garment will definitely be lower. In this regard marker plays a very important role in usage of fabric. In this paper, we have studied an order where several markers were made in order to observe the influence of marker width to minimize the fabric cost. Finally, we found that marker width has a direct impact on fabric cost. With the change of width, the efficiency of the marker varies and ultimately the cost of fabric varies as well. So, the best width needs to be selected to minimize the fabric consumption and cost for an order.
Network Reconfiguration Of Distribution System Using Particle Swarm Optimization
Priyesh Kumar , Somvir .
This paper present a new simple algorithm for solving the distribution network reconfiguration (DNR) problem. This algorithm is a simple modification to the binary particle swarm optimization (BPSO) called selective particle swarm optimization (SPSO). The search space for proposed algorithm is a set of branches (switches) which are normally closed or normally opened, this search space may be dissimilar for different dimensions. The performance of distribution networks on IEEE -33 bus system has been evaluated using MATLAB programming to test the effectiveness and validity of the proposed algorithm. The obtained results reveal that the proposed methods are promising in distribution system reconfiguration for power loss reduction and voltage profile improvement.
A Round-Robin based Load balancing approach for Scalable demands and maximized Resource availability
Poonam Kumari , Mohit Saxena
In a communication scenario where the capacity of one running service is not enough to serve high demands and it is desired to increase the performance by distributing the workload across multiple resources i.e. services. The solution for such scenarios could be using of load balancer. Load balancer receives hundreds of requests at same instant from client and it distributes the load to the different instances/machines. This Load distribution is independent of the number of instances/machines. To simulate the scenario, this research implements a client application using a service to Sort the n numbers. The calculation is split into many small intervals. Therefore, the service gets overloaded and the performance drops down. In this research, a load balancer is proposed based on the Round-Robin approach. The service processes the message and sends back the response that is routed via the load balancer back to the client. Due to any reason if one of the instance/machine fails during process execution, this does not lead the complete process to failure. The Round-Robin approach is suitable for load balancing because the processing of requests takes approximately same time.
Design and Implementation of Emotional State Recognition via Text Algorithm (E.S.R.T.A)
Sanjib Das ,Subijoy Acharya
Language is used as a mode of communication by human beings. Through language we can directly express our various mental and emotional sates. In this paper, E.S.R.T.A. tries to detect the emotional state of a user through text and respond by displaying web pages and multimedia to improve or support the mood of a user. It also tries to give a brief introduction to a new idea called SMART technology. This can help to improve human-computer interaction.
Blackhole Detection and Prevention Strategies in DTN
Rakhi Sharma and Dr D.V Gupta
Delay Tolerance Network (DTN) is a network which is used for sparse networks where network connectivity is not possible between two nodes so for this number of intermediate nodes is used to transfer messages. These intermediate nodes may cause network so security in DTN is a very difficult task. In this paper blackhole attack and its various detection techniques are presented with literature review of different research papers that covers black hole detection and prevention mechanism. A blackhole node behaves maliciously in network and provides wrong data routing information or may drop the messages receives from other nodes. So it is difficult to find black hole attack and prevent network from them. These techniques are used in the prevention of network from blackhole attack.
The Fault Level Reduction in Distribution System Using an Active Type SFCL
A NageswaraRao , P Rama Krishna
The electricity generation from many small resources is becoming one of the major systems in distribution generation systems to feed electrical loads. The effect of fault current and induced over voltages under abnormal conditions must be taken into account seriously. The effect of fault current can be limited by applying an active type superconducting fault current limiter (SFCL), the active SFCL is composed of an air-core superconducting transformer and a PWM converter. The magnetic field in the air-core can be controlled by adjusting the converters output current, and then the active SFCLs equivalent impedance can be regulated for current limitation and possible overvoltage suppression. During the study process, in view of the changes in the locations of the DG units connected to the system, the DG units injection capacities and the fault positions, the active SFCLs current-limiting and overvoltage suppressing characteristics are both simulated in MATLAB. The simulation results show that the active SFCL can play an important role in restraining the fault current and overvoltage, and it can contribute to avoiding damage on the relevant distribution equipment and improve the systems safety and reliability.
Finite Element Solution of Poisson Equation over Polygonal Domains using an Explicit Integration Scheme and a novel Auto Mesh Generation Technique
H.T. Rathoda* , K. Sugantha Devi
This paper presents an explicit finite element integration scheme to compute the stiffness matrices for linear convex quadrilaterals. Finite element formulationals express stiffness matrices as double integrals of the products of global derivatives. These integrals can be shown to depend on triple products of the geometric properties matrix and the matrix of integrals containing the rational functions with polynomial numerators and linear denominator in bivariates as integrands over a 2-square. These integrals are computed explicitely by using symbolic mathematics capabilities of MATLAB. The proposed explicit finite element integration scheme can be applied solve boundary value problems in continuum mechanics over convex polygonal domains.We have also developed an automatic all quadrilateral mesh generation technique for convex polygonal domain which provides the nodal coordinates and element connectivity. We have used the explicit integration scheme and the novel mesh generation technique to solve the Poisson equation with given Dirichlet boundary conditions over convex polygonal domains.
Prevention of MANET from Co-Operative Black Hole Attacks
M.Dhipa , G. Kiruthika, K. Gayathiri N. Rajkumar
A mobile ad hoc network (MANET) is an infrastructureless wireless network and consists of mobile nodes. Secure communications among the mobile nodes are achieved by consequential challenges. These challenges are overcome by building the multiple security solutions that protect and enhance the network performance. One of the principal routing protocols used in Ad hoc networks is AODV protocol. The security of the AODV protocol is compromised by a particular type of attack called ‘Black Hole’ attack. Black hole attack is one of the severe attacks that come from misbehavior of the node. The misbehaving node acts as selfish or malicious. Malicious node is also called black hole. The black hole intercepts the packet and confidentiality of the message is disclosed. Our approach to combat the Black hole attack is to make use of a ‘Fidelity Table’. Fidelity level that acts as a measure of reliability of the node. And by the use of Fidelity Table blackhole was detected and eliminated. The simulation was carried using NS-2 and the performance of the network is analyzed after removal of black hole attack
Compression of Medical Images by Integer Wavelet Transform
Anushree Srivastava ,Narendra Kumar Chaurasia
In today’s world of information exchange, Image compression has become an important process. It helps in effective utilization of high speed network resources. Medical image compression has an important role in medical field because they are used for future reference of patients. Medical data is compressed in such a way so that no medical information is lost. Medical imaging poses the great challenge of having compression algorithms that reduce the loss of fidelity as much as possible so as not to contribute to diagnostic errors and yet have high compression rates for reduced storage and transmission time. The medical image needs to undergo the process of compression before storing and transmitting it. Firstly, predictive encoding of the pixel values is done then it is transformed using wavelet transform after that obtained variables are encoded by an entropy encoder.
Healthcare Data Clustering with Summary Analysis under Multiple Databases
Dr. C. Kalaiselvi, Ph.D., Ms.Ramya.D
Clustering methods are applied to group the relevant records. Partition based and hierarchy based clustering methods are adapted in the clustering process. Tree based data values and transaction data values are grouped using the clustering process. Transaction similarity is estimated using the distance measures. Data and their geometrical structures are used in the grouping process.
Peer-to-Peer network environment supports multiple database access under the distributed manner. Computational load and communication complexity parameters are considered in the distributed database building process. Distributed data partitioning operations are carried out using the General Decentralized Clustering (GDCluster) mechanism. Data values are formed as summarized views and applied in the clustering tasks. Partition and density based clustering operations are carried out on the summarized views. The GD clustering technique handles the dynamic data values. Weighted K Means clustering algorithm is adapted to perform the distributed data clustering process on healthcare data values.
The General Decentralized (GDCluster) clustering technique is enhanced to support partition and hierarchical data values. Summary analysis model is optimized to handle the hierarchical and grid based data items. The similarity estimation tasks are performed with the priority features. Data update period is also considered in the clustering process. The performance analysis shows that Enhanced GD Clustering scheme reduces the communication delay with high accuracy levels.
Taranath N.L,Dr. Shantakumar b Patil Dr. Premajyothi Patil Dr. C.K. Subbaraya
A Review on Clinical Data Mining
Taranath N.L,Dr. Shantakumar b Patil Dr. Premajyothi Patil Dr. C.K. Subbaraya
v
Clinical data mining is a practice based research strategy by which practitioners and researchers retrieve, analyze and interpret available qualitative and quantitative information from available medical records. It is an active interdisciplinary area of research that is considered the consequent of applying artificial intelligence and data mining concepts to the field of medicine and health care. The aim of this work is to provide a review on the foundation principles of mining clinical dataset, and present the findings and results of past researches on utilizing data mining techniques to mine health care data and patient records. The scope of this article is to present a brief report on preceding investigations made in the sphere of mining clinical data, the techniques applied and the conclusions recounted. The most recent research findings that can further unveil the potential of data mining in the realm of health care and medicine are clearly presented in this review.
Design an Ultra Wideband Low Noise Amplifier at 6 GHz Applications
Jitendra Mishra, P.K.Paul
This paper presents a ultra wideband low noise amplifier for 6GHz Applications. This proposed LNA is the extension of inductively common source amplifier and in this design we used transistor multifingering techniques in order to reduce noise and improves gain. This LNA is simulated by using UMC .18um CMOS mixed signal/RF process in cadence virtuoso. In this design, used current source biasing, with power supply is 1.8v. LNA achieved gain 19dB and noise figure is 1.8dB at operating frequency range, and input & output return losses are -24dB & -15dB respectively, reverse isolation is -36dB and stability is 4, IIP3 is -10dBm, 1-dB compression point -17dBm and total power consumption is 9mw.
K. Sumanth, S Nagakishore Bhavanam., B. Bhaskara Rao
Performance Analysis of Non-uniform Filter Bank with Equi ripple Band pass Filter
K. Sumanth, S Nagakishore Bhavanam., B. Bhaskara Rao
In this paper we present a non-uniform filter bank (NUFB) matched to a given signal. To obtain matched M-channel NUFB, first, we choose the decimation set having M-down sampling/decimation factors for which perfect reconstruction NUFB exist and then using novel approach proposed in this paper, M-channel signal matched analysis bank is estimated. The outputs of all filters at the analysis side of proposed filter bank are mutually as well as across various channels are uncorrelated. By using well established theory of multirate filter bank, M-channel NUFB matched to signal is obtained. The equiripple band pass filter will provide better tradeoff compared to previous non uniform Filter bank obtained in this fashion will be useful to compress code or represent the signal or image in the best possible manner.
Palak Shrivastava Sudheer Kumar Arya , Dr. Priyanka Tripathi
Various Issues & Challenges of Load Balancing Over Cloud: A Survey
Palak Shrivastava Sudheer Kumar Arya , Dr. Priyanka Tripathi
An emerging technological trend of computing over internet is, the Cloud Computing. It has various compensations along with certain crucial issues that need to be determined in instruction to improve reliability, scalability, authenticity etc. of cloud computing situation. These matters are in one way or the other related to the load management, fault tolerance and different security subjects in cloud situation. This paper covers the main unease on Load Balancing in Cloud Computing environment. This load could be CPU load, recollection volume, or system load. Load complementary is the procedure of allocating the load between various nodes of a dispersed organization to avoid a condition where some of the nodes are seriously loaded while other nodes are indolent or responsibility very slight effort in order to recover both supply operation and job answer time. Load balancing safeguards that all the mainframes in the organization or every node in the system does roughly the equal quantity of exertion at any instantaneous of time. There are many approaches to determination the tricky of load balancing in cloud environment, hence by investigation of such procedures with their countless returns, restrictions and issues a new and competent practice for Load Balancing is instigated in future.
— In today’s business world there is excess of available data & a great need to make good use of it. Data mining is art of extracting pattern and knowledge from large amount of data. Frequent itemset plays essential role in many Data Mining tasks that try to find out interesting patterns from database such as association rules. Association rule mining is a finding association among large databases variables. Mining of frequent itemset is most popular problem in data mining. The frequent itemsets recognition is valuable for economic & research purpose. But valuable discovered frequent itemsets should not only assure security but also achieve high data utility & offer time efficiency. The frequent itemsets are patterns or items like itemset, substructures or subsequences that comes out in data set frequently. There are several Frequent Item mining algorithms for frequent item mining such as Apriori, Frequent Pattern growth, Eclat, Utility Pattern growth algorithms.
To provide security or privacy here we use differentially private Utility Item mining algorithm using Utility Pattern- growth algorithm. It consists of Preprocessing & mining phase. In preprocessing phase, to enhance utility & privacy advance smart splitting method is proposed to transform database. For given Database preprocessing phase should be performed only once. In mining phase run time estimation & dynamic reduction performed. To cover the information loss by smart splitting, we contrive run time estimation to calculate actual support of itemsets in original database. For privacy we have added noise in the database, we put forward dynamic reduction method to reduce the noise dynamically which guarantees privacy during mining process. In this paper we proposed new algorithm for mining high utility itemsets called as UP growth which consider not only frequency of itemset but also utility associated with the itemset.
Disease Identification using Concept and Feature Relationship Analysis for Remote Health Services
Dr. C. Kalaiselvi, Ph.D Ms. P. Krishnapriya
Internet provides various resources for Remote health services. Web based communication models are adapted to manage the interaction between the remote people with medical experts. Remote health services are provided in two ways. They are reputable portals and community based health services. Reputable portal provides information related to the health care domains. Community based health services are built to support in a particular way based on health care solutions for the patients.
With the continuing growth of modern communications technology, demand for digital image transmission and storage is increasing rapidly. Digital technology has given a great benefit to the area of image processing. Image compression is an economically viable alternative to these constraints by reducing the bit size required to store and represent the images, while maintaining relevant information content. The improvement of computer hardware including processing power and storage power has made it possible to utilize many-sophisticated signal processing techniques in advanced image compression algorithms.
Frequency Domain Techniques For Blocking Artifact Reduction-A Review
Jagroop Singh .
Block-based coding is used extensively both in image and video coding systems. Image coding systems that divide an image into sub-images have problems in very low bit rate applications. In low bit rate applications, this scheme gives rise to “blocking artifacts” that arise due to image segmentation which severely reduce the visual quality of an image or video. Reducing blocking artifacts is essential to render the compressed visual data acceptable to the viewer. Various deblocking methods have been proposed in the literature to reduce blocking artifacts. Many of these methods are based on the post-processing at the encoding side. In the presentresearch paper various deblocking methods applied in the frequency domain are discussed.
The abstract of this paper discusses the wireless sensor network which is a modernistic addition in the fields of radio networks and also provides new applications with a new prototype for sensing and broadcasting information from various environments with potential to serve many and desired applications at very low cost. In wireless sensor network, a collection of small sensor nodes communicates through radio interface. Due to the requirement of low device complexity with low energy consumption a balanced communication and signal or data processing capabilities must be found.
Coding scheme for defining the behavior of a pedagogical agent
Mohamedade Farouk NANNE .
The overall objective of our work is to define the verbal behavior and nonverbal behavior of a pedagogical agent. Our approach is an empirical approach based on the annotation of corpus videos. This approach we have used in several works. In this paper we focus on the annotation scheme that we put in place to define the verbal component of the future agent behavior
A New Approximated To the Natural Intelligence Decision Tree
Olga Popova , Dmitry Romanov, Marina Evseeva
: The problem of adjustment of modern intelligence enhancement methods and automated data analysis methods to the problems that are still handled manually is fairly topical. For the solution of such problems, this study suggests a new DT representation which uses approximated to the NI knowledge structuring. The structuring is implemented by the authors’ question-answer binary tree. This is a new DT with only most optimal decisions for all known situations excluding non-efficient cases. A set of ‘the most effective’ solutions are leaves of the tree. This new approach can be applied in intelligent decision support systems (IDSS) which enhance the natural intelligence of the scientist in the exploratory research. This tree was tested on the problem of selecting ‘the most suitable’ optimization method out of all known ones. First, detailed material on the main optimization methods was selected. The material was processed by new rules of deriving tree elements. The resulted tree has 127 nodes, 64 leaves are optimization methods (solution options). 63 intermediary nodes form a unique path from root to leaf, showing the progress to the most suitable method. Also, an IDSS was implemented in C#. The paper dwells on all stages of the DT construction with detailed illustrations, including video. The suggested DT allowed: simplify knowledge base designing; reduce system designing time; simplify decision search algorithm in the knowledge base; refer to the expert in case of contributing one’s own developed knowledge to the subject field in the tree; obtain a new way of meta-knowledge representation.
Design And Implementation of Facial Expression Recognition Using Adaptive Neuro Fuzzy Classifier
Swati Mishra , Avinash Dhole
Human facial Expression recognition through computer by means of high recognition rate and less time consumption is still a demanding and motivating task. Various emotional information is conveyed by facial expression alone. Facial expression recognition system have a vital role in numerous areas such as human-computer intelligent interaction system. This paper aimed to present an Automatic Facial Expressions Recognition System that would recognize five foremost expressions, named as Happy, Sad, Neutral, Angry and Disgusted. In this system recognition of five different expressions is done by using some extracted features. A well known Viola Jones face detection method is used for the detection of the frontal face. After face detection ROI (region of interest) that is eyes and mouth is taken for feature extraction in which local binary pattern (LBP) is used as a feature. Then obtained LBP features are clustered by using an efficient method named adaptive Neuro Fuzzy Classifier (ANFIS) to efficiently recognize various expressions. The whole system is implemented on the dataset of 110 images of frontal facial expressions of Happy, Sad, Neutral, Angry and Disgusted from live Indian facial expression images as well as 54 untrained images have been used for testing the developed system to determine the recognition efficiency of new or untrained images by using MATLAB R2012(b). The database is created from live Indian images. After the successful testing with the proposed system the expression recognition efficiency found is 85.45% for five specified expressions for trained images and 38.89% for untrained images.
Green IT is an effective approach to the practice and procedures of using computer resources in an environment friendly way while maintaining overall computing performance. The paper is going to describe the hazards causes by the computer and about the safety measures by which we can save our environment from those. Green IT is a well balanced and sustainable approach towards the achievement of a healthier, greener and safer environment. With Green IT we can build an energy efficient computer system and the other hand we can also reduce energy consumption by using IT. Green IT is comprised of initiatives and strategies that reduce the environmental footprints of technology. Green IT initiative also produces cost savings in energy use, purchase, management and support in addition to environmental benefits. Proper implementations of Green Computing or Green IT an individual and or a organization can reduce almost fifty percent of energy consumption per year, by which a organization not only save the energy but also produce more products with lower cost.
Grid Base Cluster Aproach for Detection Of Sinkhole Attack in WSN
Rupali Prajapati, Nitin Manjhi
Wireless sensor network is most concerning area of research now a days, energy and attacks are most challenging task for sensor network. In this paper we study about prevention and detection of sinkhole attack in sensor network techniques have some drawback too. Overcome all the problems we propose a grid based technique in which we deploy mobile agent in each grid and on the basis of acknowledgement and dely of data we compute the time and then mobile agent send the information to base station and find out the malicious behavior of node. our result shows that by using our methodology network performance enhance.
A Comprehensive Survey of Content Based Image Retrieval Techniques
S.Banuchitra, Dr.K.Kungumaraj
The content based image retrieval (CBIR) is one of the most important research areas of the digital image processing. The content based image retrieval is becoming a new and fast method of information retrieval. The development of the social networking mediums, so many digital images are transitioned and uploaded every day. In order to access the large collection of database, all the oldest searching methods like Google, Bingo, Yahoo are based on the on textual annotation of images. In these tools, all the images are manually annotated with keywords and then retrieved using text-based search methods. Therefore performances of these systems are not satisfactory. So, we need new techniques. These techniques will easy to handle the data and can easily access the data. The CBIR is a technique for retrieving images on the basis of automatically-derived features such as color, texture and shape. It uses digital processing and analysis to automatically generate descriptions directly from the media data. In this paper, we survey some of the technical aspects of content based image retrieval techniques. And also we will discuss the advantages and disadvantages of CBIR methodology.
Effective Ness and Illustration of Distribution Systems and Supply Chain Management.
T.Srinivas .
The distribution professionals verify their operations on a daily basis. The modern logistic leader, use the tips like competitive pressures, mergers, acquisitions, new product lines and greater customer expectations, and so forth. This change is a cost of doing business in the latest “new economy”. This research investigates the auction properties that influence efficiency (ability to maximize price and profit) as the distribution link of the supply chain. Also focuses on different key areas that are the roadmap to an effective, flexible and proactively responsive distribution operation. Also investigates the feasibility of using DEA to measure efficiency and rationalize a distribution network as an alternate approach to the conventional method of optimizing delivery routes and schedules for given supply chain management
Effect Of Combination Of Different Features On Speech Recognition For Abnormal Speech
Ms. Yogita A. More Mrs. S. S. Munot(Bhabad)
Speech is very important for communication. With the help of speech one can express their thoughts, interact with people easily. Feature Extraction is the very first step in speech recognition. This paper presents the effect of combination of different features on speech recognition. Different features of speech such as spectral, temporal, perceptual and energy. Also accuracy for each feature is calculated and it seems that Mel Frequency Cepstral Coefficients (MFCC) gives better accuracy among all the features. And the accuracy of MFCC is further increased by combination of MFCC with bark.
Evaluation of Data Mining Classification Algorithms for Predicting Students Performance in Technical Trades.
Ukwueze Frederick N Okezie Christiana C.
Measuring trainee’s performance in technical/vocational trades involves some peculiar considerations. In this study a survey research method was adopted to generate relevant predictor variables. Our primary data was collected using a simple survey instrument on the regular and sandwich students; the rest was from the Examination Unit of the University Registrars Department and also from various assessment records and instructors’ competency test records in the students department. The secondary data set included three year assessment records 2013 to 2015 in a course, VTE 201: Students Industrial Work Experience of the faculty of Vocational and Technical Education, University of Nigeria Nsukka. The raw data was preprocessed and converted to a required format. A total of 187 student records were obtained. This was used to train four selected classification algorithms whose accuracies were compared. Results showed that Decision Tree Algorithms performed best in predicting student’s terminal performance in four categories of technical trades
Multivariate Web Service Recommendation Using Personalized Collaborative Filtering
Shweta A. Bhalerao , Prof. R.N.Phursule
The increase in the numbers of web services with similar functionalities, leads to the increase in the number of users which are dependent on web service recommendation systems. Currently, the service users pay more importance to non-functional properties also known as ‘Quality of Service(QoS)’ along with finding and going for pertinent web services. The Collaborative filtering method helps in predicting the QoS values of the web services efficiently. The current recommendation systems seldom take into account the personalized effect of the users and pertinent services in determining the synonymy among the users and services. The prospective system is based on ranking oriented hybrid methods assimilating user-based and item-based QoS augury. Quite a few non-functional properties depend on the user and the associated service location. Therefore, the system puts to use the location information of the users and services while choosing synonymous neighbors for the target user and service, consequently making personalized service recommendation for service users. The technique is used persistently for improving the QoS over the internet in the current scenario where quality of the content delivered is of utmost importance for an ideal scope of service improvement and enhancement.
This paper presents an efficient algorithm for iris recognition using support vector machine, and genetic and evolutionary feature extraction techniques. The novelty of this research effort is that we deploy a preprocessing method in an effort to localize the non-ideal iris images accurately. The SVM method incorporates the spatial information into the level set-based curve evolution approach and regularizes the level set propagation locally. The proposed iris localization scheme based on SVM avoids the over-segmentation and performs well against blurred iris/sclera boundary.
Furthermore, we apply a genetic and evolutionary feature extraction (GEFE) technique, which uses genetic and evolutionary computation to evolve modified local binary pattern (MLBP) feature extractor to elicit the distinctive features from the unwrapped iris images. The MLBP algorithm combines the sign and magnitude features for the improvement of iris texture classification performance. The identification and verification performance of the proposed scheme is validated using the CASIA version 3 interval dataset.
Iris Recognition Using Curve let Transformation Based on Gabor Filter& SVM
Bhargavi Singh ,Binay Binod
The work presented in this thesis involved developing an ‘open-source’ iris recognition system in order to verify both the uniqueness of the human iris and also its performance as a biometric. For determining the recognition performance of the system two databases of digitized greyscale eye images were used.
The iris recognition system consists of an automatic segmentation system that is based on Support Vector Machine and is able to localize the circular iris and pupil region, occluding eyelids and eyelashes, and reflections. The extracted iris region was then normalized into a rectangular block with constant dimensions to account for imaging inconsistencies. Finally, the phase data from 1D Log-Gabor filters was extracted and quantized to four levels to encode the unique pattern of the iris into a bit-wise biometric template.
Analysis of Non-Technical Losses in Distributed Transformer System
Pooja ,Devender Kumar
Electrical Energy Audit consists of Studying, Assessing, Measuring and Analyzing electrical utilities. In short, the audit is designed to determine where, when, why and how energy is being used. This information can then be used to identify opportunities to improve efficiency, decrease energy costs and reduce greenhouse gas emissions that contribute to climate change. Just as financial accounting is used for the effective management of an organization, energy accounting is critical to energy management. It can be one of the most cost-effective tools for industries to cut energy costs.India’s power sector is characterized by inadequate and inefficient power supply. In this we have to proposed survey of power losses in Okhala station. We have to survey 24 DT’s of Okhala station. Result is analyzed by Matlab tool. Graph of different DT’s is analyzed according to different months & total power losses.
Reducing the Cold-Start Problem by Explicit Information with Mathematical Set Theory in Recommendation Systems
Haider Khalid , Shengli Wu
The explosive growth of enormous information makes our world as a global village. Recommendation systems are widely used in many different kinds of commercial web sites. A key challenge is how to provide recommendations when historical data for a user is missing and mining relationship between user and recommender system, a problem generally known as cold-start recommendation. This issue is a well-known problem for recommender systems and much research has been done to find the best way to overcome this. The proposed idea is querying user through an initial interview to get explicitly information, this process proposed as new user preferences to make user profile. In this paper, we present mathematical set theory to solve cold-start recommendation problem. Experiment will perform on Movie-lens dataset and user preferences can be formed into mathematical set. The combinations of multiple preferences represent as subsets and the largest subset will be the first choice as input for the recommender system. User Item matrix strategy will be used to get predicted rating for cold users. Experimental results on mathematical set approach for recommendation on the Movie-lens dataset demonstrate that the proposed approach significantly outperforms existing methods for cold-start recommendation.
Performance Enhancement System for the Cloud with Multi Factor Resource Allocation Technique
Dr. D .Ravindran , Mr. S.Lakshmanan
Resource allocation management in a cloud computing environment is the vital problem. Resource allocation models, QoS, time, conditions of the request for access to services are factors to be focused. Therefore this paper proposes the dynamic resource allocation system which allocates to cloud users. The multi factor technique is applied to optimize the allocation of the virtual machine in cloud computing. In Virtual Machine, while job is allocated and executed in the job scheduler, the first process gets to server and allocates resources. The other remains in waiting state. This refer analyses different virtual machines multi factor such as CPU, Time and Memory usage, Space and Speed. It is used to reduce the job makespan of data processing time and job waiting time, turn out time, to allocate resource efficiently. This system that effectively reducesthe system overload and with multi factors load prediction, the number of physical servers. It achieves better performance in terms of server resource utilization with the response time and minimizes the energy consumption.
Implementation Of Encryption And Watermarking Algorithm For Remote Sensing Image.
Faruk Ahmed., Dr. E.N Ganesh
This paper presents the processing of remote sensing image using water marking and encryption algorithm. Earth observation missions have recently attracted rowing interest form the scientific and industrial communities, mainly due to the large number of possible applications capable to exploit remotely sensed data and images. Along with the increase of market potential, the need arises for the protection of the image products from non-authorized use. Such a need is a very crucial one even because the Internet and other public/private networks have become preferred means of data exchange. A crucial issue arising when dealing with digital image distribution is copyright protection. Such a problem has been largely addressed by resorting to watermarking technology. A question that obviously arises is whether the requirements imposed by remote sensing imagery are compatible with existing watermarking techniques. On the basis of these motivations, the contribution of this work is twofold: i) assessment of the requirements imposed by the characteristics of remotely sensed images on watermark-based copyright protection ii) analysis of the state-of-the-art, and performance evaluation of existing algorithms in terms of the requirements at the previous point. so in this method we are going to propose the Double-Density Wavelet Transform for remote sensing image
An Empirical Evaluation of Mutation Testing for Improving The Test Quality of Web Application’s Security
Solanke Vikas*, Prof. Shyam Gupta
Mutation testing could be a methodology for assessing quality of take a look at suites. the method of mutation testing has 2 basic steps. One, generate desired variants (known as mutants) of the original program below take a look at through little grammar transformations. Two, execute the generated mutants against a take a look at suite to check whether or not the take a look at suite will distinguish the behavior of the mutants from the initial program (known as killing the mutants).The additional mutants the take a look at suite will kill, the more practical the take a look at suite is taken into account to be. Mutation take a look ating is commonly viewed because the strongest test criterion in terms of characterizing high-quality take a look at suites . Researchers have used mutation testing in varied studies on code testing; see a recent survey by Jia and Harman.
Analysis of Web base applications testing using mutant
Solanke Vikas* Prof. Shyam Gupta
— Mutation testing was initially proposed in the 1970s as intends to guarantee vigour in test case improvement. By making syntactically right substitutions inside the software under test (SUT) and rehashing the test execution stage against the adjusted code, an evaluation could be made of test quality contingent upon if the definitive test cases could locate the code adjustment. Mutation testing is normally used in small code programs, but for a small portion of large program or for a specific code it is used. This paper test a access control part of web based applications for mutant testing, till date testing of web based application is only up to application level only. Generally test cases are executed and stop the testing, but we can not check capability of test cases.
A Mobile Ad-Hoc Network is a collection of mobile nodes that are dynamically and arbitrarily located in such a manner that the interconnections between nodes are capable of changing on continual basis. Due to security vulnerabilities of the routing protocols, wireless ad-hoc networks are unprotected to attacks of the malicious nodes. One of these attacks is the Black Hole Attack. In this paper, we give an algorithmic approach to focus on analysing and improving the security of AODV, which is one of the popular routing protocols for MANET. Our aim is on ensuring the security against Black hole attack. The proposed solution is capable of detecting & removing Black hole node(s) in the MANET at the beginning. Also the objective of this paper is to provide a simulation study that illustrates the effects of Black hole attack on network performance.
Protection of Inter-Continental Ballistic Missile (ICBM) from Anti-Ballistic Missile (ABM) by using Anti-Anti-Ballistic Missile (AABM)
Manish Debnath .
Ballistic missiles are used to deliver nuclear, chemical, biological or conventional warheads in a ballistic flight trajectory. On the other hand, an anti-ballistic missile (ABM) is generally a surface-to-air missile designed to counter ballistic missile. So, it is clear that to make the operation or mission of an inter-continental ballistic missile (ICBM) successful we have to eliminate the threat of anti-ballistic missile (ABM). This paper will discuss about the arrangement of a small tracking system and some small missiles attached with the main ballistic missile which can destroy any anti-ballistic missile (ABM) coming towards it. So, simply this small air-to-air missiles act as anti-missiles for any incoming anti-ballistic missile (ABM) which is targeting the main ballistic missile and we can simply call them anti-anti-ballistic missiles (AABM).
A Review on Plant Leaf Classification and Segmentation
Lakhvir Kaur , Dr. Vijay Laxmi
A leaf is an organ of vascular plant and is the principal lateral appendage of the stem. Each leaf has a set of features that differentiate it from the other leaves, such as margin and shape. This paper proposes a comparison of supervised plant leaves classification using different approaches, based on different representations of these leaves, and the chosen algorithm. Beginning with the representation of leaves, we presented leaves by a fine-scale margin feature histogram, by a Centroid Contour Distance Curve shape signature, or by an interior texture feature histogram in 64 element vector for each one, after we tried different combination among these features to optimize results. We classified the obtained vectors. Then we evaluate the classification using cross validation. The obtained results are very interesting and show the importance of each feature. the classification of plant leaf images with biometric features. Traditionally, the trained taxonomic perform this process by following various tasks. The taxonomic usually classify the plants based on flowering and associative phenomenon. It was found that this process was time consuming and difficult. The biometric features of plants leaf like venation make this classification easy. Leaf biometric feature are analyzed using computer based method like morphological feature analysis and artificial neural network based classifier. KNN model take input as the leaf venation morphological feature and classify them into four different species.
Chaturvedula Pratyusha, Naveen Kumar, K. Rajasekhar
Automatic Generation of Coverage tests for System Programs
Chaturvedula Pratyusha, Naveen Kumar, K. Rajasekhar
Software testing is one of the critical activity for the organizations who spend lot of time and cost for the improvement of software quality. Programming testing is characterized as the way toward executing a project with the plan of discovering mistakes. Testing would ensure the correctness and produces reliable software. In order to achieve the quality software, sufficient number of test cases should be designed and tested.To calculate the integrity of test cases and identify that there are no unexpected functionalities, the structural code coverage should be measured like, statement or decision coverage.
Since the development of New Austrian Tunneling Method (NATM), shotcrete in tunnels has been widely applied. It’s most important features are durability, speed of application and cost effectiveness. The New Austrian Tunnelling Method (NATM) is characterized by the continuous adaption of driving parameters, such as unsupported length (i.e., the distance between the tunnel face and the shotcrete lining, excavation rate, etc.) to the observed response of the already-excavated part of the tunnel.
In order to devise such tables, two different arch sections, together with three different overburden types, were considered. Some Geotechnical parameters such as apparent cohesion and angle of internal friction of surrounding rocks were chosen, based on the five-category classification of Bieniawski. Two K0 factors (the ratio of horizontal stress to vertical stress) and an average rock density were utilized. Using numerical methods, 60 models were then devised in this way.
Adaptive control for MIMO nonlinear systems based on PID neural networks
Tamer A. Al Zohairy , Khaled S. Salem
In this paper a real time control technique for a nonlinear discrete time Multi-input Multi-output systems is presented. The proposed technique is based on the combination of PID controller properties and neural networks characteristic of self-learning and flexibility of function presentation. The standard back propagation (BP) algorithm is used to find parameters of the PID neural network controller. The suggested technique modifies the architecture used in SISO to fit with MIMO systems. The experimental results are presented toward the end of the paper to show the effectiveness of the proposed technique
Survey and Comparison of Classification Algorithm for Medical Image
Sweety Maniar, Jagdish S. Shah
Medical image classification and retrieval systems have been finding extensive use in the areas of image classification according to imaging modalities, body part and diseases. One of the major challenges in the medical classification is the large size images leading to a large number of extracted features which is a burden for the classification algorithm and the resources. In this paper, a novel approach for automatic classification of fundus images is proposed. The method uses image and data pre-processing techniques to improve the performance of machine learning classifiers.Some predominant image mining algorithms such as Classification, Regression Tree (CART), Neural Network, Naive Bayes (NB), Decision Tree (DT) K-Nearest Neighbor
Performance comparison of Energy Efficient Routing algorithm prolonging network lifetime in wireless Ad Hoc network
Priyanka R. More, Prof. Dr. S.V.Sankpal
As the nodes in Ad Hoc network are battery limited the most important issue that must be considered in designing a data transmission algorithm for wireless Ad Hoc network is how to save energy while meeting needs of users. While satisfying energy requirement it is also necessary to achieve quality of service. Reliable Minimum Energy Routing (RMER) and Reliable Minimum Energy Cost Routing (RMECR) are two proposed routing algorithms which meets the requirements. RMER and RMECR ensure Energy efficiency and Reliability. RMECR considers residual energy of nodes while finding energy efficient path for data transmission thus RMECR along with Energy efficiency and Reliability also prolongs network lifetime. Simulation results mentioned in this paper show the performance comparison of RMER and RMECR based on the performance metrics Average Residual Energy, Reliability, Throughput
Collocation Method for Seventh Order Boundary Value Problems by Using Sextic B-splines
S. M. Reddy .
A finite element method involving collocation method with sextic B-splines as basis functions has been developed to solve seventh order boundary value problems. The seventh and six order derivatives for the dependent variable is approximated by the central differences. The basis functions are redefined into a new set of basis functions which in number match with the number of collocated points selected in the space variable domain. The proposed method is tested on three linear and two non-linear boundary value problems. The solution to a nonlinear problem has been obtained as the limit of a sequence of solutions of linear problems generated by the quasilinearization technique. Numerical results obtained by the present method are in good agreement with the exact solutions available in the literature
Collocation Method for Fifth Order Boundary Value Problems by Using Quintic B-splines
S. M. Redd .
A finite element method involving collocation method with Quintic B-splines as basis functions has been developed to solve fifth order boundary value problems. The fifth order derivative for the dependent variable is approximated by the finite differences. The basis functions are redefined into a new set of basis functions which in number match with the number of collocated points selected in the space variable domain. The proposed method is tested on three linear and two non-linear boundary value problems. The solution to a nonlinear problem has been obtained as the limit of a sequence of solutions of linear problems generated by the quasilinearization technique. Numerical results obtained by the present method are in good agreement with the exact solutions available in the literature.
Yogeesh A C, Dr. Shantakumar B Patil, Dr. Premajyothi Patil
A Survey on Energy Efficient, Secure Routing Protocols for Wireless Sensor Networks
Yogeesh A C, Dr. Shantakumar B Patil, Dr. Premajyothi Patil
The Wireless Sensor Network (WSN) in present generation has gained its popularity due its applicability nature in various areas Such as monitoring system of Oceans, wide life, manufacturing plants, earthquake prediction unit, military units, etc. The cost and structural complexity of a WSN are very low. In general, a WSN consists a sensor node (SN) that gathers the data from the atmosphere/environment. An SN exhibit very low power battery (LPB) and if the battery power gets drained SN will stop its functionality. Once the battery power is drained, it is impossible to recharge it back due to the wide spread network structure. The un-functionality of an SN may lead to failure of the routing protocol. Commonly a routing protocol facilitates an efficient routing path among the SNs. The security of data over the WSN is an always biggest issue which needs to be resolved. Many of the researchers have explained their views for energy efficient, secure routing protocol for a WSN. This survey paper discusses the various energy efficient techniques, secure routing techniques, classifications of routing protocol, attacks on WSN. The surveys towards the recent work on energy efficient & secure routing protocols are discussed with the research gap. Finally, future work is demonstrated followed by a conclusion.
Proposed Novel Hybrid Approach For Improvement in Bug Severity prediction
Kanchan Rawat , Dr. Ajay Goel
In this research study an approach of creating dictionary of critical terms is proposed to assess the bug severity as severe and non severe. It is found that using different approaches of feature selection and classifier the pattern of accuracy and precision is approximately same. However Chi square test and KNN classifier give the maximum performance of precision and accuracy for the all four components. The proposed work will help Triager in classifying bugs based on severity and assigning these bugs to relevant developer.
Selection and Maintenance of Materialized View Using Genetic Algorithm
Ramesh s. Gawali , Prof. Mrunali Vaidya
Data warehouse is a repository of large amount of data collected from multiple heterogeneous and distributed data sources. Quick response time and accuracy are the key points for success of any database. Performance of query can be improved by different approaches like query optimization, use of proper data structure etc. But leaving all these alternatives we are planning to use materialized view approach. Materialized views (MV)are precomputed result of queries. Use of materialized view avoids the visit of data source resulting in the saving the time of query response. In our work we are going to materialize the queries based on their threshold value of accessing the query.
Multi-Dimensional Student's Result Analytical Processing For Tertiary Institutions
Amanze B.C, Amaefue I.A, Etim I.O, Dennis M.C
The objective of this paper work is to develop a web based analytical processing of students’ record in a tertiary institution which will accept student data at all levels, determine students’ performance over a period of time,extract specific information available from the database when there is need and improve the privacy, user-friendliness and enable convenient access to students’ information mounted on the portal. This is done in other to determine the quality of students being graduated over time from the institution. our motivation was bourne out of the need to reduce the stress and discomfort departments encounter during students reconciliation of result. This will help in obtaining accurate information. It will also reduce bribery whereby people with money gets faster attention than others. In other to mine the database of students’ results, the Structured System Analysis and design approach to software engineering was used in the course of this work. This involves identifying the problem which involved looking at the students’ results for area of weaknesses and designing how to go about this identification, acquisition of knowledge and problem solving strategies. The data were collected majorly by interviews and observation. The result generated will help the staff (Lecturers) of the department to remotely input and monitor their results without stress after it has been approved by the senate of the Institution. The department can also have a quick view of student’s record and make a quick decision on it.
- It is not easy to quantify the large amount of data stored electronically. Data is in the unit of zettabytes or exabytes referred as Big Data. Hadoop system is used to process large datasets. Map Reduce program is used to collect data according to the request. To process big data proper scheduling is required to achieve greater performance. Scheduling is a technique of assigning jobs to available resources in a manner to minimize starvation and maximize resource utilization. Performance of scheduling technique can be improved by applying deadline constraints on jobs. The objective is to study Map Reduce and different scheduling algorithms that can be used to achieve better performance.
MM-Wave Planner Antenna For Wireless Communication
Vrishali M. Patil, Shubhangi N. Ghate
The expectation of end users for and data allowance puts pressure on network operators in meeting demand and leads to requests from operators for access to greater amounts of spectrum. Making spectrum available to meet the future requirements of mobile broad band services is complex as prime spectrum for mobile broadband services is also access to services exhibiting increased speed heavily utilised by other services and is a scarce resource. Communications regulators must consider the impact on existing spectrum management arrangements and incumbent users. When making further spectrum available. Some of the issues to be taken into account ,
Shubhangi N. Ghate, Vrishali M. Patil, Monika Rajkumar, Surekha Dudhale , Pallavi Goswami, Kiran Mhaskar
Wireless Communication Based High Speed Spy Bot
Shubhangi N. Ghate, Vrishali M. Patil, Monika Rajkumar, Surekha Dudhale , Pallavi Goswami, Kiran...
The objective behind making this project deals out with satisfying various functional needs such as secretly spying or keeping surveillance over a desired target location. We also aim to achieve a few more additional comprehensive needs such as detection of gas, temperature sensing, camouaging feature and movement of bot. We have made our robot with an advantage of monitoring both audio and video parameters. The most eye catching feature of our bot is that it would be able to change its body colour that it treads along. We have achieved our main goal by aggregating individual robotic functions in a single robotic package. This bot can either be used for keeping an eye or a supervisory control function like a spy bot or with the additional features as that we have added to this robot could serve as an important unmanned vehicle which could actually combat with the
opponents or enemies in the war _elds. Thus making it multifunctional, it could be used to serve more than one application areas. The camouaging feature of bot is solution for reducing human losses in military operations or terrorist attacks. This project is basically a step taken to save the human lives in the area where this bot is used.
SAUDAGAR ANJUMARA SHARPHODDIN SHETKAR SWATI S. ASSISTANT PROFESSOR
SECURED HANDHELD MOBILE DEVICE COMMUNICATION USING BARCODE MODULATION BASED ON OFDM
SAUDAGAR ANJUMARA SHARPHODDIN SHETKAR SWATI S. ASSISTANT PROFESSOR
The inventions and high end technologies has great impact on digital communication domain which takes wireless communication to next level to support advanced applications and to offer high rates. Although tremendous progress has been registered in past few decades but still handheld mobile communication is concerned area in the wireless communications. Large data encryption in small space and data privacy is two drawbacks leads to manipulations in handheld mobile transmissions. In this paper a DWT based barcode modulation approach is proposed which makes use of DPSK-OFDM as primary resource to yield a secure handheld mobile transmission to support wide range of applications in reliable way. Finally the experimental results show the proposed DWT based mechanism yields low complexity and better performance over Fourier transform and that performance is measured in terms of BER and SNR
Simulation Of IOT Based Domestic Devices By Saving Their State Of Remote Database Server
Aarti, Pooja l Mitta
In this research we have developed a simulation environment where we would switch on /off house hold devices remotely using our web based application through our mobile or laptops. IoT(Internet of Things) allows objects should be sensed & controlled remotely across existing network infrastructure, create scope for more integration of physical world into computer-based systems, & resulting in improved effectiveness, accuracy & economic benefit. The current status of device would be saved in database created by us along with time. A Calculator would calculate power consumption by reading status of devices & time they were kept on/off. The power consumption & battery backup would be computed.
Automation in Information Technology: Implication on Job Market In India
V.Hemanth Kumar
The world is growing very fast from recent decades. This growth is strongly assisted by technological advancements. From the past few years the technology has taken various forms to aid the people and the companies. Both companies and the people are getting mammoth benefits out of these technological advancements. The changes in technology have created numerous jobs all over the world. And the companies are expecting to create more millions of jobs in the coming future. The technology has made the life easy and comfortable. The companies are investing huge money on research and development. Result of this research and development is automation, which is a latest trend in Information Technology sector. Slowly this has taken more sophisticated form of technology. The development is paced up with this automation. The automation is fast absorbed by IT Companies. The IT companies are deploying automation technologies all over the world in order to reduce maintenance and labour costs. My study tries to focus on the concept of automation in IT, forms of automation and its implication on job market in Indian Information Technology sector.
Numerical Solution of Fourth Order Boundary Value Problems by Petrov-Galerkin Method with Quintic B-splines as basis functions and Septic B-Splines as weight functions
S. M. Reddy .
This paper deals with a finite element method involving Petrov-Galerkin method with quintic B-splines as basis functions and septic B-splines as weight functions to solve a general fourth order boundary value problem with a particular case of boundary conditions. The basis functions are redefined into a new set of basis functions which vanish on the boundary where the Dirichlet type of boundary conditions are prescribed. The weight functions are also redefined into a new set of weight functions which in number match with the number of redefined basis functions. The proposed method was applied to solve several examples of fourth order linear and nonlinear boundary value problems. The obtained numerical results were found to be in good agreement with the exact solutions available in the literature.
Taxonomy of Cryptography Techniques for Network Security
Kanika Sharma , Dr. Nischay Bahl
Cryptography is the art of secret writing. Data encryption means that only a person having the secret code or key can read scrambled information. The important role of cryptography is to provide the security to the wireless networks. Over the years, many encryption techniques have been provided and used. The conventional methods of encryption can only preserve the data. Developing the new concept in cryptography is a demand of the current time, because the modern cryptography is very much needed to boost the data security. Therefore, it is necessary to relate efficient encryption technique to boost data security. This paper discusses different historical cryptography techniques, modern encryption algorithms (symmetric and asymmetric), and newer areas that are being explored in cryptography. This paper also explores its applications in network security.
Sudha S, Dr Gowrisankar P Rajkumar R, Balaprakash V
Analysis of Implementation of FACTS Devices in Power Factor Improvement
Sudha S, Dr Gowrisankar P Rajkumar R, Balaprakash V
This paper presents an analysis of implementation of Flexible AC Transmission System (FACTS) devices for maintaining Power Factor. The electrical loads include induction motor driven equipments, which consume reactive power, increase the amount of apparent power in the distribution system, which is important because a low power factor can waste energy, and results in inefficient use of electrical power and often result in higher energy bills. The improvement of Power Factor as close as unity is very essential in the industry as well as domestic electric appliances, due to increase in power demand. The Power factor maintenance provides increase in system efficiency. The solution for power factor unity is done with FACTS devices, which has the manageable capacity. The possibility of low power factor increases with inductive load in nature. Hence, the need of unity in power factor is very significant.
Significance of Data Mining Techniques in Classifying Dyscalculia
Mrs. Sampada Margaj Dr. Seema Purohit
Detection of learning difficulties among school children is a topic of research as predicting human behavior is a challenge for entire research community by taking this concern the study aims at predicting and classifying Dyscalculia among primary school children. Basically by following the approach of positive psychology towards learning detecting and designing intervention program for learner is a crucial aspect which actually requires targeted investigation so that right child should get the right help. In the present study we have used three classifiers rule-PART, J48 and SMO to predict the different classes of Dyscalculia
Tamer A. A. Alzohairy , Emad El-Dein H. A. Masameer Mahmoud S. Sayed
Medical Image Registration Based on Feed-forward Neural Networks and Directional Discrete Cosine Transform
Tamer A. A. Alzohairy , Emad El-Dein H. A. Masameer Mahmoud S. Sayed
Registration is used to align two or more pictures taken, for example, at different times, from different sensors, or from different viewpoints. All large systems which evaluate images require the registration of images, which considered as an intermediate step. Examples of systems where image registration is a significant component include change detection using multiple images acquired at different times, fusion of image data from multiple sensor types, environmental monitoring, image mosaicing, weather forecasting, creating super resolution images, integrating information into Geographic Information Systems (GIS) and medical image analysis. In this research, the concentration is on registration of medical images. Analysis of multi-temporal medical images requires proper geometric alignment of the image to compare corresponding regions in each image volume. The proposed image registration technique consists of two steps. In the first step the feature extraction method is performed by using Directional Discrete Cosine Transform (DDCT). Finally the feed forward neural networks based image registration technique is performed .Comparison study in registration process between Directional Discrete Cosine Transform (DDCT) and Traditional Discrete Cosine Transform (DCT) is performed. Experiments have shown that the proposed method provides more accurate results for registration process when using DDCT than traditional DCT.