Optimization of Migration Time affected storage overheads during VM Live Migration using Network Attached Storage device
Preeti P. Thakre Vaishali N. Sahare
Cloud computing has grown in relevant amount from recent years by inheriting a key feature of server virtualization which is the live migration of virtual machines(VMs). This technique mainly used in datacenters in order to provide cloud services without letting servers down by allowing a virtual machine from one system to another with minimum service interruption. Due to limited available network bandwidth, the network traffic get increases due to large amount of storage data which lead to create overheads during migration and hence increases migration time. This paper focuses on such type of duplicated data which consumes only unnecessary shared network bandwidth, increases migration time during live VM Migration and provide optimized solution using proposed scheme with the help of Network Attached Storage Device (NAS).
In this paper we are dealing with the new scheme to provide authentication for files and folders using colours in which the password are generated for every session, that is we have our new password every time you login hence we called it as color scheme authentication for session password. The main purpose for this method is to stricter the authentication, to provide security to our documents in folders and PDF. We have implemented and it proved to be a better technique in providing authentication when compared to textual passwords and other existing techniques.
Learning of RBF network by using Teaching-Learning Based Optimization (TLBO) Algorithm
Mr. Shinju Chacko Mr. Sesham Anand
TLBO (Teaching - learning – based optimization) is a nature inspired optimization algorithm. There are many evolutionary algorithms like genetic algorithm, ant colony optimization, particle swarm optimization etc. All these algorithms depend on algorithmic parameters. A small change in these algorithmic parameters may cause a large change in the effectiveness of the algorithm. In this scenario TLBO is coming to picture. TLBO is independent of algorithmic parameters. TLBO follows the Teacher – Student and Student – Student interaction in the class room. TLBO have two phases, Teacher Phase and Learner Phase. The key feature of TLBO is, in the first stage algorithm attains average learning, in the second stage algorithm pick the best solution. In teacher phase, teacher is one of the learners among the population who has best knowledge level. Teacher tries to improve the mean knowledge level of class up to his level. When learners reached teacher’s knowledge level, algorithm needs a new teacher with more knowledge. In the learner phase, learners interact with each other to improve their knowledge. This technique will be used in the learning of the parameters of the RBF network
Image processing plays a vital role in aspects of all science and technology.In this image processing concepts have great impotance in application oriented research and project.The purpose of the proposed research work is develop a computer system that can recognize a personization by comparing the characteristices of face to those of known individual.Human face recognition is an effective means of authenticating a person.Principal Component Analysis( PCA )is a classical feature extraction and data representation technique widely used in pattern recognition.It is most successful techniques in face recognition. Prototype is designed to work with web cameras for the face detection and recognizing system based on visual 2010 C#, and OpenCV.The proposed method have been evaluated using the Microsoft cognitive service API with Azure API of databases.This system can implement a better security of computational time to detect and recognize the human faces with big database
Abhinav Mohite ,Avadhoot Khadake Preetam Kamat, , Akash Tawade Omkar More , Mr. P.A.Patel
Social Uni-Books Web Service
Abhinav Mohite ,Avadhoot Khadake Preetam Kamat, , Akash Tawade Omkar More , Mr. P.A.Patel
UNI-BOOKS‖ is the web service for the students of particular university where students can sell or buy old books directly to or from other students. The main objective of the project is to create an online book store that allows users to search and purchase old books online based on title, author and subject. The chosen books are displayed in a tabular format and the user can order their books online through cash on delivery payment. Using this Website the user can buy a book online instead of going out to a book store and wasting time.
Diffie-Hellman Key Exchange Protocol with Entities Authentication
Om Pal Bashir Alam
The Diffie-Hellman key exchange protocol provides the opportunity to arrive at a common secret key by exchanging texts over insecure medium without meeting in advance. Diffie-Hellman key exchange protocol is limited to the exchange of key only. Due to lack of authentication of entities, this protocol is vulnerable towards man-in-middle attack and impersonation attack. To eliminate the man-in-middle attack, Nanli[9] presented a research paper on Diffie-Hellma key exchange protocol. It is observed that Nanli‟s protocol, still suffers with impersonation attack. To deal with this vulnerability, an improved key exchange approach based on third party authentication scheme is proposed in this paper.
Recent Trends and Challenges in Development of Smart Systems
Amrita Yadav
The term ―Smart Systems‖ is used to explain the meeting of persistent computing and global data networking. The goal of smart systems is to integrate all intelligent devices with networked systems that are self-sensing, self-controlling, and self-optimizing—automatically, without even human intervention. It would not be far-fetched to call such systems ―self-aware.‖ Smart systems incorporate sensing, actuation and control. They can describe and analyze situations by making analytical, adaptive decisions based on the available data and consequently performing smart actions. The smart system frontier includes machines, devices, people, cyber and physical sub systems and information all connected and interacting in a seamless, adaptive manner. These smart systems have shifted the focus from individual technologies to overall system intelligence, which results in fundamental changes in how the goods and services of tomorrow will be shaped, delivered and monetized.
Transient Stability Analysis of IEEE-9 Bus Electrical Power System
RohitPatrik RupeshShrikhande SurajKamdi
Power system stability is an important aspect which determines the stability of the system. This paper deals with the rotor angle stability of IEEE 9-bus system consists of three generators and nine buses. To demonstrate the performance of the system, a three phase fault is introduced on different locations. The nature of the rotor angle excitation voltage and speed for all three generators are discussed. As the fault is cleared the system takes its own time to settle down. Keywords: Transient stability, three phase fault, multi machine,
Prof.Ashok Kalal, Mr. Piyush Kumar Jha, Mr. Kunal Jondhalekar, Mr. Pavan Pandey Ms. Himanshu Thakur
DeyPoS: Deduplicatable Dynamic Proof of Storage for Multi-User Environments
Prof.Ashok Kalal, Mr. Piyush Kumar Jha, Mr. Kunal Jondhalekar, Mr. Pavan Pandey Ms. Himanshu Thakur
Dynamic Proof of Storage (PoS) is a useful cryptographic primitive that allows a user to check the integrity and efficiently update the files in a cloud server. There has been many solutions proposed for Dynamic Proof of Storage in singleuser environment but for multi user problems is still unsolvable. A multi-user cloud storage system needs the secure client side cross user deduplication technique, which allows a user to stop the uploading process and gain the ownership of the files immediately, when other owners of the same files have uploaded them to the cloud server.As we know, none of the existing dynamic PoSs can support this technique. In this paper, we elaborate the concept of deduplicatable dynamic proof of storage and propose an efficient construction called DeyPoS, to achieve dynamic Proof of Storage and secure cross-user deduplication, simultaneously.To build a novel tool called Homomorphic Authenticated Tree (HAT) to address challenges such as structure diversity and private tag generation.Hence we prove the security of our construction, and the theoretical analysis and experimental results show that our research is practically valid and applicable.
ECIES for Group Key Establishment in WSN for Secure Multicast Communication
Miss.P.Prasanna Laxmi Mrs. M.Anupama
A wireless sensor network (WSN) as the name suggest is a wireless network with spatially distributed autonomous devices making use of sensors for monitoring physical or environmental conditions. WSNs find applications in areas like healthcare, home automation, traffic control etc. WSN with characteristics of self-organization, multi-hop, dynamic topology and limited energy resources, make it extremely difficult to prolong the lifetime of the network. To prolong the life time of WSN with limited energy resources, Multicast can better meet the requirements of network resources. It has an active significance for WSN to increase its performance in the near future. In Wireless sensor networks sensor nodes are grouped together by forming multicast groups. The communication among the nodes is done by broadcasting and multicasting efficient message deliveries among resource-constrained sensor nodes. Two group key protocols are developed for secure multicast communications among the resource-constrained devices. The proposed approach compares the performance of two protocols with ten nodes in each group. We analyze the proposed solution to evaluate the performance using Network Simulator-2 (NS-2) under different network parameters with a number of destination nodes.
This paper deals with analysis of image Enhancement and background detection used in Mathematical Morphological [MM]. In this paper, Low intensity images have been processed through Block Analysis and Morphological Transformation. Basically, Weber‟s Law Operator is used to analyze Low intensity images which are carried out by two methods such as Image background detection by block analysis while second operator utilize opening by reconstruction to define multi background notion. Basic Morphological Transformations are like Erosion, Dilation, Compound operation such as Opening by reconstruction, Closing by Reconstruction and Block Analysis is used to detect the background of images. Analysis of above mention methods illustrated through the processing of images with filtering techniques along with different dark background images.
Literature Survey of Privacy Preserving Data Publishing (PPDP) Techniques
Amita Sharma, N. Badal
Microdata-Information collected by different organizations is published for analysis to the analyst, decision makers, policy makers and researchers. Original data is not published due to some privacy issues. So, techniques are needed to preserve privacy of data. This paper includes the comparative study of various techniques available to preserve the privacy of published data.
Sonal N. Kotangale Pushpa D. Chudhari Prof. Shraddha D. Agnihotri
Enhanced Public Auditing for Code-Based Multi-server Cloud
Sonal N. Kotangale Pushpa D. Chudhari Prof. Shraddha D. Agnihotri
cloud computing is a storing and accessing data and programs over the Internet instead of computer's hardware. Cloud computing is gaining popularity because it provides various on demand services which is location independent. Cloud user can store their data on cloud server remotely. So the data storage is resided with third party cloud service provider. In such situation, maintaining the privacy of user’s data from unauthorized users is not an easy task. Before storing the data on the cloud server, the data can be encrypted. Using privacy preserving public auditing, data hosting service also brings new security threats toward users data, thus making individuals or enterprisers still feel hesitant. Sometimes data owners lose ultimate control over the fate of their outsourced data so there is risk that availability and integrity of the data might be lost. To protect outsourced data in cloud storage against corruptions, adding fault tolerance to cloud storage together with data integrity checking and failure reparation. Due to lower repair bandwidth while providing fault tolerance Regenerating codes have gained popularity
A Clustering Technique for Improving Marketing Strategy in Social Media using Data Mining Approach
Shreyas S, D r. Vidya Raj C
On-line Social Networks (SNSs) are today one of the most popular interactive medium to communicate, share and disseminate a considerable amount of human life information. Daily and continuous communications imply the exchange of several types of content, including free text, image, and audio and video data. The huge and dynamic character of these data creates the premise for the employment of web content mining strategies aimed to automatically discover useful information dormant within the data which helps marketing. This paper aims to focus on four important works i.e. identifying the target users, designing of market strategy/plan, Building the marketing network (groups) & Statistical analysis of categories. Influentially of target user has been discussed with real time instances. Categories have been found based on their influence by using clustering technique. Finally, concluded with statistical analysis that includes graphical representation of highly influenced users. Further this paper helps to extract emotional feelings of the user so that any related articles, posts or videos can be posted to that user
Progressive Localization using Mobile Anchor in Wireless Sensor Network
Suresh Rathod Raj Kumar Paul
Wireless sensor network (WSN) is employed to gather and forward information to the destination. It is very crucial to know the location of the event or collected information. This location information may be obtained using GPS or localization technique in wireless sensor networks. Randomly deployed WSN needs a large amount of GPS-enabled sensor nodes for localization, this necessitates progressive approach. However, nodes with sparse connectivity remain unlocalized. In this paper, a progressive mobile anchor based technique is proposed for node localization. Initially, sensor nodes are localized using anchors in the neighborhood, then these localized nodes progressively localized remaining nodes using multilateration. Mobile anchor node moves randomly in field and broadcast position information. It localized nodes with sparse connectivity. Simulation results show that proposed approach localize all sensor nodes with good accuracy
Sentiment analysis a branch of text analysis that is widely used to increase the reliability of the product and used to analyze the people‟s emotions, opinion towards the products, hot topic, any event and any organization etc. There are various social media as well as e-commerce site which are generating a large amount of data in the form of tweets, blogs, status, reviews etc. In this survey paper we have presented an elaborative hierarchy of sentiment analysis techniques and sub-techniques or mechanisms and algorithms along with their pros and cons. We have also presented here the applications of sentiment analysis in different fields along with various challenges in it to implement. The main target of this survey paper is to give full description of sentiment analysis.
Analysis of Speech Disabled People with Dysarthria using TORGO Database
Usha. M
This paper represents a method for assessment of speech skill of dysarthria disordered patients repeatedly, which is a motor speech disorder comes from neurological injury of the motor element of the motor-speech system. This structure comprises two major features: feature representation and prediction. In the feature representation, the speech sound is changed into a phone series with an regular speech recognition technique and joint with a canonical phone sequence from an intonation dictionary using a biased finite state transducer to obtain the pronunciation mappings such as match, substitution, and deletion. Next, in the prediction process, a structured sparse linear model exists with phonological information that concurrently addresses phonologically structured sparse feature selection and transparency prediction is identified. The TORGO database of dysarthric pronunciation consists of aligned acoustical and measured 3D articulatory features from speakers with either cerebral palsy (CP) or amyotrophic lateral sclerosis (ALS), which are two of the most common causes of speech disability. The major aim of this paper is to supply a flexible and suitable environment for the dysathria speech disordered peoples by recognizing their speech to make others understand them
Sumed Khicha, Prakshali Patil Prerana Roy , Pooja Sinkar J P Rankhambe
A Mobile Based Smart Healthcare System
Sumed Khicha, Prakshali Patil Prerana Roy , Pooja Sinkar J P Rankhambe
In a Homeopathic Consultancy, a patients records are maintained manually, which requires lot of time for searching and updating. Even the communication order to reduce this time requirement & introduce a smooth Doctor-Patient interaction, we need to digitize the whole system. This will result in much more efficient consumption of the resources, viz. time, stationery and man-power. An Android based app will be developed, providing humongous number of features to both, Doctor and Patients. Even the communication process between the Doctor and Medicine Room will be digitized. A confidential database containing the whole CASE-FILES of a respective Patients will be made using MySQL and SQLite. This database could be accessed by the Doctor only. By deploying the database on a Cloud, we will ensure portability, mobility and flexibility in accessing the same for the Doctor. The FrontEnd, i.e. the App will be interfaced by the database using Web Server
A research Paper on Cryptography Encryption and Compression Techniques
Sarita Kumari
Data is any type of stored digital information. Security is about the protection of assets. Data security refers to protective digital privacy measures that are applied to prevent unauthorized access to computers, personal databases and websites. Cryptography is evergreen and developments. Cryptography protects users by providing functionality for the encryption of data and authentication of other users. Compression is the process of reducing the number of bits or bytes needed to represent a given set of data. It allows saving more data. Cryptography is a popular ways of sending vital information in a secret way. There are many cryptographic techniques available and among them AES is one of the most powerful techniques. The scenario of present day of information security system includes confidentiality, authenticity, integrity, nonrepudiation. The security of communication is a crucial issue on World Wide Web. It is about confidentiality, integrity, authentication during access or editing of confidential internal documents.
The amount of multilingual documents generated on internet, is increasing day by day. Multilingual document clustering (MDC) is a technique of classifying documents in different languages. Classification of documents for the languages without labeled training data set is a major challenge. Two major approaches used till date are machine translation of documents for classification and use bilingual dictionaries for effective translation of trained classification models. This paper surveys various MDC challenge and techniques. The major focus is on the problem of translating documents and classifying it semantically.
This paper deals with the design of home automation controlling of home appliances using wireless remote control. This is achieved using a Bluetooth module and an android application. This low-cost system can be accessed remotely using a laptop or smartphone with a software or an application installed in it. Even the elderly or disabled at home can be able to access it, making their work easy and simple. The design is very simple using some low-cost electrical apparatus, with ease of installation and smart home system also provides more safety control over the electrical switches with some power saving methods. Smart home or home automation provides a better standard of living at home with low-cost design and a user friendly interface
Mrs.D.Jennifer Sreenidhi R Vinitha S, Thilakavathy B
Enhancing A Medbox for Health Precautions Using IOT
Mrs.D.Jennifer Sreenidhi R Vinitha S, Thilakavathy B
The ignorant nature and routine non-adherence towards medications have always caused immense imminence in terms of public health, also resulting in a significant amount of finance going run through. In-home healthcare services based on the Internet-of-Things (IoT) have great business potential; however, a comprehensive platform is still missing. This system shows how a Medbox can be used intellectually and effectively.
Inspired by the Virtio module of virtualization, we propose an alternate method to directly communicate with PCI devices such as NIC without the use of any kernel modules. This method uses a specialized module written by us which will avoid the mechanism of bridges like the ones used in Virtio that increase latency. This module will be present in the userspace of the guest OS and we are specifically targeting the e1000 device for this purpose and later plan to make it generic for all PCI devices. Our motivation is to avoid unnecessary communication with the kernel which slows down the system. For the first step. we do resource mapping to map the PCI device memory into userspace. Then, we expose PCI configuration space through a userspace module using ACPI cables. Thus, we create a userspace PCI driver which will decrease the latency in access time and increase speed of execution. The applications in the Guest OS that request communication with the PCI devices will be redirected to our application. This will take some load off the kernel and reduce its overhead. Finally, we boot a VM that actually talks to our PCI device emulator.
Ali zamani , Mohamadreza Moniri Hamada Reza fatemi Mofrad
Error-based Adaptive Update Rate in multi-function Phased-array Radar Using IMM Target-Tracking Algorithm
Ali zamani , Mohamadreza Moniri Hamada Reza fatemi Mofrad
An adaptive-update-rate target-tracking algorithm is indeed a developed version of constant-update-rate tracking algorithms. The update rate is closely related with the level of target maneuvering and the required quality of tracking performance— the shorter the time intervals between two successive updates, the better the radar resources are made use of. Considering the needs of the phased-array radar system and multi-function tracking, we here propose an algorithm which makes a better use of radar resources; therefore, many targets can be tracked with an improved accuracy, and more regions can be detected. The proposed algorithm is based upon the adaptive interactive tracking algorithm (AIMM); the revisit time has been calculated using Van Keuk method, and then the fast AIMM has been amended such that the tracking error is no more than that in Van Keuk method. Our proposed algorithm which has a revisit time different than Van Keuk’s results in 62% saving of the radar resources.
Implementation of Multiqueue Interlacing Peak Scheduling based on Task Classification in Cloud Computing
B.Nandan, A,Nikhil A.Rahul B.Sai Kiran Reddy
The benefit load information, for instance, CPU, I/O, and memory use, is every so often accumulated and redesigned, and the errand information as to CPU, I/O, and memory is accumulated. Second, resources are sorted into three lines as demonstrated by the piles of the CPU, I/O, and memory: CPU heightened, I/O genuine, and memory concentrated, as showed by their solicitations for resources. Finally, once the endeavors have been reserved, they need to interlace the benefit load peak. Some composes of assignments oughtto be facilitatedwiththe benefits whose loads contrast with a lighter sorts of assignments. So to speak, CPU intensive assignments should be facilitated with resources with low CPU use; I/Ogenuine assignments should be facilitated with resources with shorter I/O hold up times; and memory-genuine assignments should be facilitated with resources that have low memory use. The ampleness of this technique is exhibited from the speculative viewpoint. It has also been ended up being less mind boggling regarding time and place. Four examinations were planned to check the execution of this procedure. Tests impact four estimations: 1) typical response time; 2) load modifying; 3) due date encroachment rates; and 4) resource use. The test outcomes exhibit that this procedure can alter stacks and improve the effects of benefit part and utilization sufficiently. This is especially bona fide when resources are compelled. Along these lines, various errands will pursue the same resources. In any case, this system shows advantageover other similar standard computations. In this paper we show the implementation of Multi-queue Interlacing Peak scheduling based on Task Classification in Cloud Computing in Ellipse IDE.
Survey of Intentional Enterprises Threats using Social Engineering Exploits and Prevention Techniques
Swati Chauhan
this is a survey report of social Engineering threats that include various phases of social engineering. As security techniques increase, security break techniques will also increase in the same or more ratios. In this paper, we are trying to cover most areas of social engineering feats with Cause of social engineering in enterprises, various techniques of social engineering, influences and popular social engineering cases with relative study.
Energy Consumption in Wireless Sensor Networks Using Multi Level Clustering Energy Efficient Protocol
Muruganandam. K, Dr.Sibaram Khara
A wireless sensor network (WSN) consists of a huge number of sensor nodes that are inadequate in energy, storage and processing power. One of the major tasks of the sensor nodes is the collection of data and forwarding the gathered data to the Base Station (BS). Hence, the network lifetime becomes the major criteria for effective design of the data gathering schemes in WSN .In this paper , every sensor nodes can converse straight with every other or with the base station. This develops into impracticable when the size of the region of interest enlarge. The anticipated protocol uses a multi-hop communication among the cluster-heads to preserve energy and cover up a huge area of interest. To diminish the quantity of information to be sent to the base station, we incorporated data aggregation. Furthermore, the rotation of cluster-heads and the utilize of the low-power sleep mode by the sensor nodes that do not contribute in routing permit to balance the load and reduce energy utilization considerably. Apply the MAT LAB Simulation software Tool to confirm the proposed design, comprehensive simulation has been approved. The NARRATIVE-LEACH schemes recommend reliable wider experience area and longer life span of WSN. To compare the other modules N-LEACH is the best enhanced in terms of stability period while compromise on lifetime.
An Overview of Theoretical Models of Exchange Bias Mechanism
Taskeya Haider
The research activities on the phenomenon of exchange bias (EB) has recently promulgated due to its versatile use in magnetic sensors and as stabilizers in magnetic reading heads. Since the discovery of EB in 1956, the attention on this matter was limited until such applications related to giant magnetoresistance were developed during late 90’s. This study primarily focuses on the understanding of the phenomenon of EB by reviewing and critically discussing the various theoretical models developed and refined over the years. Relevant characteristics of the bias, coercivity fields, the sensitivity and dependence of the fields to interface structure and quality, long-term stability for the magnitude of the bias field and the orientation of the ferromagnet are discussed in the light of these theoretical models.
V. A. Dhotre, S. J. Mulani ,R. A. Takalikar, P. P. Keskar, S. D. Shinde, K. S. Nagtilak
Implementation of 3D Campus View
V. A. Dhotre, S. J. Mulani ,R. A. Takalikar, P. P. Keskar, S. D. Shinde, K. S. Nagtilak
The proposed system involves creating the 3D model of the SKNSCOE Korti, Pandharpur campus into a virtual model. The model is represented in two ways: A pre-rendered video sequence. The information begins by introducing the project area of virtual urban modeling in general terms. It discusses the modeling process of each building, the problems encountered and what has been done to solve these problems. Lastly, the information discusses the possibilities of future work that can be applied to this project. Appendix A contains the video and real-time application this project has produced. The initial results of reconstructing SKNSCOE Korti, Pandharpur 3D virtual model and future research directions are presented. Unity3D, which is usually treated as game development software, as a virtual reality development platform. The hierarchical approach of geographic information system is adopted in the study area.
pGate: An Introduction to A Novel Universal Gate and Power Drop Calculation of QCA circuits
Soudip Sinha Roy
Quantum Dot Cellular Automata is an emerging nanoscale transistorless computational technology, which permits the logic gate designing schemes to be tinier and extremely faster by dint of high-speed quantum tunneling. The tunneling occurs at a speed of light, which causes the circuit operative speed very faster and operating time in some picoseconds. In this letter one new universal gate designing technique have proposed, which is shaped with five quantum cells. This paper initially covers some basic layouts like two input pNAND and four input pNAND gate. In purpose of physical verification of the proposed pGate one 2 bit multiplexer has proposed which is implemented by 14 cells, which provides 33.70% area optimization compared to previously best reported designs. In this paper, one novel methodology of QCA circuit power drop computation have introduced with brief algorithm. Previous nine 2x1 MUX layouts have undertaken and their power drops have been calculated and provided in a tabulation manner. The commenced designs are compared with other existing techniques significantly in terms of cell uses, AUF, effective area, power dissipation etc. Proposed designs are simulated and approved by QCADesigner 2.0.3. This paper conveys a new information regarding quantum logic gate designing and power computation technique to the nanoelectronic science.
Dr. Geetanjali Amarawat Awanit Kumar, Abdul Hamid Qureshi
Study of machine learning based recommendation techniques used by Ecommerce
Dr. Geetanjali Amarawat Awanit Kumar, Abdul Hamid Qureshi
Customer who viewed this item wills also view that” is an intelligent as well as expert activity that keeps track of customers. Online shopping trends are based on the statistics which execute cross-selling mechanism. This intelligent algorithm will suggest your site visitors with products which were mostly explored by other customers on basis of maximum ratings, purchased or liked and viewed. These suggestions display on product pages that are based on the current product. Various Shopping application and web-sites are using different methods to attract customers. In this paper we are going to study the algorithm and introduction to machine learning approach to find how E-commerce uses recommendation techniques.
Mr. Swapnil Manekar, Prof. Prashant Borkar Mr. Vedprakash Hirwani
Hierarchical Messaging Application for Android Using Salesforce
Mr. Swapnil Manekar, Prof. Prashant Borkar Mr. Vedprakash Hirwani
Messaging applications are a dime a dozen nowadays and can only be differentiated on the basis of some unique features. These applications suffer from various limitations like free posting, joining, and lack of a hierarchy among other things when considered from an organizational or professional point of view. This paper presents the technology behind and structure of an application that limits the users in accordance with an organization specific hierarchy kept separate from the application to keep it universal so that this communication application would be professional and clutter-free. Users would be able to read relevant messages. Post if allowed, get update or news, and hale organizational events scheduled for them. These features would run on Android smartphones while other users would only be able to read the important messages via text SMS thus making the project available to all allowed, though in a limited capacity.
Survey on Various Retrieval Strategies and Utilities for effective Information Retrieval
Mr. Ramesh Babu Pittala M.Nagabhushana Rao
Information Retrieval is mainly used for offering the fair information at the right time and also retrieving the necessary information in the desired form. Information systems which are strongly describes what the user need. The main intension of retrieval strategy states that the level of relevancy between the document and the query increases with increase in the number of items .The retrieval strategy are used for retrieving the information from highest ranked documents based on precision and recall. Different Retrieval Utilities are used to progress the performance of IR strategies. In this paper, specified the various retrieval strategies and utilities which are playing a major role in estimating the performance of IR.
Comparative Analysis of K-Means and Kohonen-SOM data mining algorithms based on student behaviors in sharing information on facebook
Dr. Gurpreet Singh Amandeep Kaur
Clustering can be used for describing and analyzing of data. In this paper, the approach of Kohonen SOM and K-Means and HAC are discussed. After comparing these three methods effectively and reflect data characters and potential rules syllabify. This work will present new and improved results from large-scale datasets. With the development of information technology and computer science, high-capacity data appear in our lives. In order to help people analyzing and digging out useful information, the generation and application of data mining technology seem so significance. Clustering is the mostly used method of data mining.
With 20 million installs a day [1], third-party apps are a major reason for the popularity and addictiveness of Facebook. Unfortunately, hackers have realized the potential of using apps for spreading malware and spam. The problem is already significant, as we find that at least 13% of apps in our dataset are malicious. So far, the research community has focused on detecting malicious posts and campaigns. In this paper, we ask the question: given a Facebook application, can we determine if it is malicious? Our key contribution is in developing FRAppE—Facebook‟s Rigorous Application Evaluator— arguably the first tool focused on detecting malicious apps on Facebook. To develop FRAppE, we use information gathered by observing the posting behavior of 111K Facebook apps seen across 2.2 million users on Facebook. First, we identify a set of features that help us distinguish malicious apps from benign ones. For example, we find that malicious apps often share names with other apps, and they typically request fewer permissions than benign apps. Second, leveraging these distinguishing features, we show that FRAppE can detect malicious apps with 99.5% accuracy, with no false positives and a low false negative rate (4.1%). Finally, we explore the ecosystem of malicious Facebook apps and identify mechanisms that these apps use to propagate. Interestingly, we find that many apps collude and support each other; in our dataset, we find 1,584 apps enabling the viral propagation of 3,723 other apps through their posts. Long-term, we see FRAppE as a step towards creating an independent watchdog for app assessment and ranking, so as to warn Facebook users before installing apps.
Sorting has made their importance in computing field as well as the applications we face in real life. So far many algorithms come into existence in current era. In this research paper we present a new sorting algorithms i.e. Enhanced division Selection sort. We try to enhance the performance of Selection sort by doing some modifications in the pseudo code. A comparison also has done to do analysis between existing Selection Sort and Enhanced division Selection Sort. After comparison we found that the new algorithm has produced better results and good performance during the running time.
G.Dhanalakshmi ,T.Manjulai M.Mirunalini S.Sangeetha Mary
Footstep Power Generation System
G.Dhanalakshmi ,T.Manjulai M.Mirunalini S.Sangeetha Mary
Man has used tremendous amount of energy for his daily needs. Therefore large amount of energy has been exhausted and wasted. Footstep power generation system is designed to be very useful at public places like railway stations where lot of people keep walking through all day. In the footstep power generation system the floor sensors capture the electrical energy produced by the pressure and convert it into electrical charge with the help of the piezo transducers which in turn is used as a power source. Thus the piezoelectric technologies is used in flooring. The power source thus generated has a vast amount of applications in home application, agriculture, street lighting and as a energy source for sensors in remote locations
Shambala S Salunkhe Madhuri D Yadav Vrushali V Kulkarni
IOT Based Waste Monitoring For Smart City
Shambala S Salunkhe Madhuri D Yadav Vrushali V Kulkarni
The IOT is a new trend technology which includes different wireless connectivity like wi-fi, GSM, zigbee, Bluetooth .IOT that is internet of things which basically defines connecting things over wireless connectivity things are any physical quantity in day to day life which will need to be monitor. These quantity may be temperature, level, weight, pressure which impact on human activity these things are monitor control over wireless media. While using such system major focus on capability and system should make user friendly. Conventional wireless media is zigbee to get more capability and physical quantity which monitor is level. To enhance the smart city environment of such IOT based system it is essential to provide smart solution to become smarter. This paper is giving possible solution to make a city clean, hygiene, healthy in smart way.[1][2][6]
Algorithms for Recognition of Geometric and Parametric Features in prismatic parts using IGES
Sunil I. Sangolli S.C. Pilli
Automatic recognition of geometric and topological features from solid models has a great impact on the various levels of integration. The commercial CAD systems contain information of a component which is not suitable for the use in the next level of product life cycle such as process planning. Various solid modeling software’s hold the design data in their individual files. The structures of the files differ from each other based on the modeling software. To have a common structure which can communicate with various CAD systems a recognition algorithm using any of the neutral file formats is necessary. This paper presents geometric algorithms to recognize features from various 3D CAD models of prismatic parts. The features are recognized by three approaches; Hhint based approach, Volumetric decomposition approach and Hybrid approach. A program in Java is developed to recognize geometric entities, with their directrix contained in a solid model.. The algorithm developed to extract the information from the IGES translator uses an inference engine which can handle complex feature libraries. The algorithm works efficiently for complex models built using volumetric decomposition as well as hybrid of hint based and volumetric decomposition approaches. The model is reconstructed for validation using the recognized entities
In the recent years, data mining is the most important domain in the real world aspects. By using data mining Techniques, we can identify the knowledge of different areas and get the best patterns. Educational institutions and universities are facing problems in terms of student employability. It became a big task for the educational institutions. In this regard, we identified the techniques to bring co-relation between the student academics and faculty responsibilities, where co-relation pattern means reading the knowledge from the educational student performance data. Using this data, we are applying different Data mining Techniques to find out the useful patterns and fill the gap between the Student Academics and Employability. This paper includes survey on different prediction algorithms like Classification, decision tree algorithm, C4.5, Feature with Graph structure, Bayesian, RIPPER, SVM, and compares the best performances on different aspects.
As nowadays all the information is available online, a large number of users are accessing it, some of them use this information for gaining knowledge and some use it to know how to use this information to destroy or steal the data of websites or databases without the knowledge of the owner. The purpose of this paper is to tell what is hacking, who are hackers, what is ethical hacking, what is the code of conduct of ethical hackers and the need of them. A small introduction of Linux Operating System is given in this paper. All the techniques are performed on the Linux operating system named Kali Linux. After this some basic hacking attacks covered in the paper are MiTM Attack (Man in The Middle Attack), Phishing Attack, DoS Attack (Denial of Services Attack). Further what is Wi-Fi, what are the techniques used in the Wi-Fi protection and the methods used by the hackers to hacks Wi-Fi passwords is covered in the paper.
Internet banking or E-banking has attracted the attention of banks, securities, insurance companies in developing nations since the late 1990s and the rapid and significant growth in electronic sectors and commerce it’s obvious that electronic (online internet) banking and payments are likely to advance or rapidly increased.
The primary goal of IOT (Internet of Things) is to oversee or manage the current substances empowered for correspondence. Because of improvement in the need of correspondence, an excessive number of gadgets are expanded which prompt greater multifaceted nature in the correspondence. IOT gadgets require an answer of security and protection. To give solid and reliable correspondence between gadgets we can utilize RFID (Radio Frequency Identification) Tags. This paper characterizes the design and convention heaps of IOT, it additionally gives a review of RFID and its different security and protection issues
S.Vairavel, Prof. B.Jose Ravindraraj Prof.Dr.D.Sukumar
Investigations on the Fabrication and Properties of Fibre Reinforced Composites with Natural Fibres of Banana and Coir with Epoxy and Polyester Polymers
S.Vairavel, Prof. B.Jose Ravindraraj Prof.Dr.D.Sukumar
During this investigation coconut coir fibre along with banana fibre being natural fibre components, have been chemically treated with alkaline solution. Here chemically treated are mixed separately with polyester, and epoxy resins, and by using hand lay-up technique these reinforced composite materials are moulded. Several specimens have been fabricated in constant volume percentage of coir and banana fibres and by using two different resins (polyester and epoxy polymers) in order to get more accurate results.
Security Analysis with respect to Wireless Sensor Network – Review
K.Sethu Selvam Dr.S.P.Rajagopalan
Security or Privacy is the most important challenges in network. These challenges and issues are mostly affected in Wireless than Wired network because medium is open and less limited resources. Sensor is a tiny and low cost device. Wireless Sensor Network (WSN) is operated remotely and can be used in various fields like military surveillance, environmental monitoring, traffic monitoring, health monitoring and etc. In this paper, analysis of various security attacks and security techniques of WSN was done.
Privacy Preservation in Dynamic Bigdata for Verification and Correctness
Guthula Anitha Rani Prof P Suresh Varma
Mobile devices makes the mobile crowd sourcing is possible, since the mobile devices are everywhere in a tourism(theme)/network if a requester(travel agency) crowd, sources the data from worker(tourist). However data collection aggregation and data analysis have become challenging problems for requester when the volume of data is huge which is categorized as Bigdata. The data analysis includes set operations like intersection, union, and complementation for filtering redundant data and pre-processing raw data. theme is a necessity of data exchange between the worker, requester for better analysis of the interested worker. But workers may not be willing to participate if the privacy of their sensing data and identity are not well preserved in the untrusted cloud. Hence, the proposed work, establishes the usage of cloud to compute the intersect operation between the requester and the workers data. Also preserves the workers identity and accessible data. This paper says that use of cloud to compute set operation for the requester, at the same time workers data privacy and identity privacy are well preserved. And also, the requester can verify the correctness of set operation results on the dataset sourced by workers and send to the cloud. With this batch verification and data update are comparatively increased and reduce computational costs of the system.
PAPR Reduction in NC-OFDM Based Cognitive Radio System Using Signal Cancelation and Tone Reservation
Revathy G Nair Aswathy Anilkumar Jismi Babu
High data rate wireless access is demanded by many applications. It requires more bandwidth for higher data rate transmission in any of the system. With promising technology and ever-increasing wireless devices, the spectrum is becoming scarcer day by day. In this case, using noncontiguous orthogonal frequency division multiplexing(NC-OFDM) and cognitive radio(CR) for spectrally efficient transmission are an alternative solution. High peak-to-average power ratio (PAPR) and large spectrum sidelobe power are two main drawbacks of this system. In this paper, we propose a novel signal cancelation (SC) method followed by tone reservation for joint PAPR reduction and sidelobe suppression in NC-OFDM-based CR systems. The key idea of the proposed method is to dynamically extend part of the constellation points on the secondary user (SU) subcarriers and add several SC symbols on the primary user (PU) subcarriers to generate the appropriate cancelation signal for joint PAPR reduction and sidelobe suppression. The joint PAPR reduction and sidelobe suppression can be consider as quadratically constrained quadratic program (QCQP) in SC method to obtain its optimal cancelation signal. The main idea of tone reservation method is to keep a small set of tones for PAPR reduction.
With the advent of Information Technology into almost every aspect of our lives, are we all really able to benefit from it? This paper proposes a way to boost the success of government Schemes for Rural Development using kiosks. In the paper, a solution is discussed that addresses the problem of government schemes not reaching their full potential via awareness among each and everyone, and attempts to resolve it by using kiosk machines, to supply information regarding government schemes. The main purpose is to provide information regarding government schemes to even those rural residents who can barely interact with an electronic device. To do so, a very simple and easily understandable interface has been introduced in the paper. This interface may also provide audio/visual aid. Using this, a person may also get a token, using his/her aadhar card number, to meet with the respective office to proceed for a scheme. In the later versions, feature to transfer a particular page onto the persons mobile phone can also be added.
A Frequency Reconfigurable UWB Monopole Antenna with Slotted Ground Structure
Karthika Rajan Sherin P Elias
In this modern world, there has been a significant drive to increase the functional density of consumer devices, especially hand-held electronics. In order to meet this challenge all the components need to be miniaturized. Most commonly used component in modern electronics is an antenna. The size of an antenna is directly related to its operational frequency. Frequency tunable miniaturized antennas are required for next generation electronics. In the existing system a multi-layered metamaterial-inspired antenna with a pixel grid loading structure is explained. In order to produce desired performance appropriate pixel configuration need to be selected. Simulations show that the antenna can be tuned over a wide frequency range by appropriate choice of pixel states. Here we are proposing a novel compact frequency-reconfigurable monopole antenna with various switchable states. Using a switchable slotted structure on the ground plane, the antenna can achieve frequency configuration capability. The proposed antenna has a combined UWB and narrowband functionality, has a good potential for use in cognitive radio. The simulations are done using HFSS (High Frequency Structure Simulator) software.
Spectrum Monitoring In OFDM-Based Cr Networks By Window Based Energy Ratio Algorithm
Aswathy Anilkumar Revathy G Nair, Jismi Babu
This work presents a spectrum monitoring algorithm for OFDM based cognitive radios and in this, monitoring algorithm the primary user reappearance can be detected during the secondary user transmission. The proposed technique reduces the frequency with which spectrum sensing must be performed and greatly decreases the elapsed time between the start of a primary transmission and its detection by the secondary network. The analysis and simulation show that the algorithm can effectively and accurately detect the appearance of the primary user
Sparse Signal Recovery in Compressive Sensing Using sparse Kalman Tress Search Algorithm
Anjaly Krishnan Dhanya Narayan2 Rajalakshmi S
In this modern years compressive sensing (CS) has a very important and valuable attention in the areas of Computer vision problems, Applied mathematics, Signal processing, Optical engineering ,even in Biomedical imaging also CS has a considerable attention. The main concept about these CS is that we can represents most of the signals with only a few number of non-zero coefficients in a advisable dictionary or basis. Once we construct a signal using compressive sensing reconstruction is also needed. There variety of reconstruction algorithms that are used in the area of CS. In our paper we are mainly concentrated on a new sparse signal recovery algorithm known as sparse Kalman Tree Search(sKTS), It provides a powerful reconstruction of sparse vector if the sequence of correlated observation vectors are feasible. Finally we also make a comparison with the sKTS algorithm and other algorithms like, then check its compactability and efficiency towards compressive sensing.
Customer Complaint Analysis Using Hadoop (Consumer Analysis)
Y. Sudha Laxmi, A. Mahendar, Dr. Sheikh gouse
Customer complaint Analysis is Handling Customer Dissatisfaction. It may accompanies Web customer complaint management, This may be a critical Issue for the Customer. In this paper we are going to Investigate the current sources of customer complaints and what are the causes of complaints and want to seek the effective ways of handling customer complaints by examining different type of products and Issues. For achieving customer complaint analysis we are using Big data platform for storing of huge amount of Data. These data are stored in the form of traditional Database. Big data mainly focus on the storage of data. It majorly focuses on three attributes they are Data Volume, Data Velocity and Data Variety.
Video Surveillance Using Adaptive-Rate Compressive Sensing
Rajalakshmi S1 , Dhanya Narayan Anjaly Krishnan
We provide a novel adaptive rate compressive sensing technique for video surveillance with the use of side information .This method exploits the advantages of low resolution information of an image. Unlike the current compressive sensing techniques we consider the upper bound on the number of significant coefficients which contains the image in the video sequence to be unknown. We develop our method based on background subtraction using single pixel camera. For each image in the video sequence the proposed technique assign a set of compressive sensing measurements to adjust from image to image
Survey of Various Face Liveness Detection Techniques for Biometric Antispoofing Applications
Tazeen Anjum , Shrikant V Sonekar
Face recognition is a widely used biometric approach. Face recognition technology has developed rapidly in recent years and it is more direct, user friendly and convenient compared to other methods. But face recognition systems are vulnerable to spoof attacks made by non-real faces. It is an easy way to spoof face recognition systems by facial pictures such as portrait photographs. A secure system needs Liveness detection in order to guard against such spoofing. In this work, face liveness detection approaches are categorized based on the various types techniques used for liveness detection. This categorization helps understanding different spoof attacks scenarios and their relation to the developed solutions. A review of the latest works regarding face liveness detection works is presented. The main aim is to provide a simple path for the future development of novel and more secured face liveness detection approach.
B. Lakshmi, P.V.L.Parimala M. Prasanna Lakshmi B. Srinivas
A Perfect Partner for Event Marketing
B. Lakshmi, P.V.L.Parimala M. Prasanna Lakshmi B. Srinivas
Event marketing is growing at a rate of three times that of traditional advertising. Though relatively small compared to the major components of the marketing communications mix-advertising, sales promotions and point-of-purchase merchandisingexpenditures on event sponsorship are increasing. Event marketing is growing rapidly because it provides companies alternatives to the cluttered mass media, ability to segment on a local or regional basis, and opportunities for reaching narrow lifestyle groups whose consumption behavior or entertainment can be linked with the local event. Event Finder is a website specializing in Event marketing primarily targeting college students, recent graduates, and young professionals. This proposed system allows users to find events. In this system, every event manager has their own login and they can upload the event details. Event details will be sent to external users through SMS based on their area of interests.
Data Integration among Sensor Nodes Using Wireless Toolkit
K. David Raju Shreya Valluri V Harika Naidu
: Network level privacy can be categorized into four sub categories: Identity, route, location and data pivacy.It is so challenging to achieve complete network level privacy due to the constraints like energy, memory and computation power imposed by the sensor nodes and constraints like mobility and topology imposed by the sensor networks and QOS issues like packet reachability and timeliness. In this paper we proposed a new identity routing and location algorithm that provides additional reliability and data privacy.This proposed solution protects the data from various privacy attacks such as eavesdropping and hop-by-hop trace back attacks.
Anticipating Human Activities from Surveillance Videos
Shanmughapriya Murugesan, Ranjith Balakrishnan
Human action recognition from the unconstrained surveillance videos and anticipating human action from onset of video is a challenging task. This work focuses on the study of action recognition, action classification followed by action anticipation. We have used the UT Interaction data set containing interactive videos with six types of activities, the system developed classifies three interactive actions punching, pushing and kicking with accuracy. Anticipating action is a probabilistic process and the all possible outcomes are predicted during anticipation. The framework developed can take any interactive video as input from the web camera or any other camera connected to the laptop and will classify the three interactive actions as said above; similarly when the onset of video is given it produces the probable predictions. Action is modeled as a sequence of changes in Spatio Temporal features and histogram of the gradients helps in identifying the changes. The motion boundary descriptors, histogram of oriented gradients and optical flow features are extracted and SVM algorithm is used for classification. Bag of words approach is used for anticipation. Prediction methodologies are highly needed in surveillance environments for efficient monitoring and management.
In the present scenario, the transfer of data is an important thing between one user to another. Data is mainly sent by the distributors which are generally the owner of data to the user which wants the information mainly the trusted third parties. The information sent by the distributor must be confidential and must be shared by a secure way. Some times during sharing of data, multiple copies of information is generated by different parties which cause a huge amount of loss, this is known as data leakage. To prevent this leakage of data one must put measures in order to detect the leakage in an early stage. The purpose of this paper to discuss data leakage and its prevention by various watermarking techniques.
Image Processing Based Student Attendance System using Raspberry PI
P Prudhvi Kiran Ravi Kumar G2
: Image processing based student attendance System is the easiest way to keep track of attendance for organizations such as Educational Institutions, Business organizations. Among the person identification methods, face recognition is known to be the most natural ones; since the face modality is the modality that uses to identify people in everyday lives. Although other methods, such as fingerprint identification can provide better performance, but they are not appropriate for natural smart interactions due to their intrusive nature. This face detection differentiates faces from non faces and is therefore essential for accurate attendance [6]. Our Proposed strategy involves face recognition for marking the student attendance. Raspberry pi is used for face detection and face recognition. The camera will be connected to the raspberry pi module. The student database is collected. The database includes name of the students with their registered numbers and their face images. Camera will be placed in front of the class in such a way that it can capture the entire class, which is connected to the raspberry pi. Thus with the help of this system time will be saved and it is so convenient to record the attendance at any time throughout the day.
: Recommender systems are found in many ecommerce applications today. Recommender systems usually provide the user with a list of recommendations that they might prefer, or supply predictions on how much the user might prefer each item. Choosing what book to read next has always been a question for many. Even for students, deciding which textbook or reference book to read on a topic unknown to them is a big question. There are two common approaches for providing recommendations, they are collaborative filtering and content based filtering. In this report we try to present a model for a personalized recommendation system for books that uses hybrid recommendation approach which is combination of content based and collaborative filtering. The proposed recommendation system tries to learn the user’s preferences and recommends the books to the user based on their preferences. The system also recommends the books to the user based on the user’s demographic parameters like age and location. The system also tries to understand the user’s favourite author and recommends accordingly.
The purpose of this paper is to study the evolution of website. In the majority of research work the study of different version of same website has been neglected. Website performance is directly linked to user experience. User experience is that what keeps people on your website. The objective of this paper is to analyze the different versions of same website called Tech Team and find the changes in each version with respect to period of time. The Web analytics tools used in the research are GTMetrix, pingdom, Website pulse.
Review on the various Watermarking Techniques Based on Medical Images
Neha Mahajan Chetan Marwaha Sonam
The following document presents in which the creation of multi-media along with IT technology, spreading of pictures will become extremely simple and fast. However Digital camera picture watermarking is the strong usually means to understand the particular illegal usage of copyrighted images. The idea places key information (watermark) in to the coordinator picture that assists in locating the actual usage regarding picture. The idea examines the several strategies similar towards the watermarking which gives higher potential, robustness imperceptibility. The DWT has shown that it applied to the web host picture after which block wise singular elements can be meant for watermark’s principal component part interpolation together with ABC (artificial bee colony) to be able to get a better trade-off among robustness along with imperceptibility that offers an evident enhancement within performance.
Operation and Control of Converter Based Single Phase Distributed Generators in a Utility Connected Grid
K Shalini Karthik K Varthala Divya
The operation and control of converter based single phase distributed generators (DG) in a utility connected grid is proposed in this paper. A common utility practice is to distribute the household single-phase loads evenly between the three phases. The voltage unbalance between the phases remains within a reasonable limit. The single phase sources are operated to deliver available maximum power generated while the rest of the power demands in each of the phases are supplied by the utility (and if available, three phase DG sources). However, the voltage unbalance can be severe if single-phase rooftop mounted PVs are distributed randomly among the households. Moreover, there can also be single-phase nonlinear loads present in the system. The cumulative effect of all these will cause power quality problem on the utility side. The problem can be macabre if three-phase active loads (e.g., induction motors) are connected to the utility feeder
Today, the entire device’s in electronics needs to be realized with low power and optimized Area architectures because of power consumption and Area are of main consideration along with other performance parameters. Low power consumption helps to reduce heat dissipation, increases battery life and also reliability. Arithmetic and Logic Unit (ALU) is one of the frequent and the most fundamental component in low power processor design. An Arithmetic logic unit (ALU) is a major component of the central processing unit of a computer system. It does all process related to arithmetic and logic operations that need to be done on instruction words. As the operations become more complex the ALU also become more complex, more expensive and takes up more space in the CPU hence power consumption is a major issue. In this research work the power flow analysis of ALU circuits is analyzed and optimization of ALU power supply unit.
Secure Authentication using Image Processing through Visual Cryptography
Mary Jolve. J
Authentication is used by a server when the server needs to know exactly who is accessing their information or site. In this process, the user or computer has to prove its identity to the server or client. Usually, authentication by a server entails the use of a user name and password or through cards, retina scans, voice recognition, and fingerprints. An effective method for securely transmitting files, documents and images are found in the field of Visual Cryptography (VC). Visual cryptography method is a cryptographic technique which allows visual information (e.g. printed text, handwritten notes, and images etc.) to be encrypted in such a way that the decryption can be performed by the human visual system (HVS), without the aid of computers. This study focuses on securing a file or document through CAPTCHA images using image processing. The study is to be carried out in two phases where the Phase I would comprise Registration Phase and, Login Phase would be carried out in Phase II.
Signature Verification for Banking Sector Based on SIFT
Mary Jolve. J Jisna Joy
A person can be uniquely identified by evaluating one or more distinguishing biological traits. One such trait is scanned images of hand writing. It is useful biometric modality with application in forensic analysis, banking sector, document verification etc. This study focus on text-independent writer identification method based on scale invariant feature transform (SIFT). It consists of three phase: training, enrolment and identification phase. In all of these three phases an isotropic LoG filter is applied first. It is used to segment the handwriting image into word regions (WRs) and then, the SIFT descriptors (SDs) of word region and the corresponding scales and orientations (SOs) are extracted. In the first phase, an SD codebook is constructed by gathering the SDs training samples. In the second phase, SD signatures (SDS) are generated by looking up the SD codebook and SOs is used to generate a scale and orientation histogram (SOH). And finally in last phase, the SDS and SOH of the input handwriting are extracted and matched with the enrolled ones for identification. Here instead of analysing handwritten document we experiment on signature of an individual. Using SIFT algorithm we demonstrate that he/she is genuine or not.
