Computer Applications

Decision tree classification techniques are currently gaining increasing impact especially in the light of the ongoing growth of data mining services. A central challenge for the decision tree classification is the identification of split rule and correct attributes. In this context, the article aims at presenting the current state of research on different techniques for classification using oblique decision tree. A variation to the traditional approach is the called oblique decision tree or multivariate decision tree, which allows multivariate tests in its non-terminal nodes. Univariate trees can only perform axis-parallel splits, whereas Oblique decision trees can model the decision boundaries that are oblique to attribute axis. The majority of these decision tree induction algorithms performs a top-down growing tree strategy and relay on an impuritybased measure for splitting nodes criteria. In this context, the article aims at presenting the current state of research on different techniques for Oblique Decision Tree classification. For this, the paper analyzes various traditional Multivariate and Oblique Decision Tree algorithms CART, OC1 as well as standard SVM, GDT implementation.

Unsolicited commercial email or "spam" flood mailboxes, causing frustration, wasting bandwidth, and exposing minors to unsuitable content. This paper uses intelligent gatekeepers to interact with spam messages and system referenced in spam. The goal of this paper is to consume spam senders' resources by engaging the spammer in appropriate gatekeepers. There are four gatekeepers have been implemented: Phishing gatekeeper, medicine gatekeeper, bank scam gatekeeper, and web form gatekeeper. This technique provides better results and it cannot deal with the image spam.

In this paper, a resource management technique is proposed to handle the request of Virtual Machines (VM’s) as per the need of users, consisting of resources (mips, vm image size, network bandwidth, number of cpu’s) containing cloudlets which in turn are cloud-based application services (content delivery, social networks) commonly deployed in data centers. There are three priority mechanisms governing the user’s requests namely low, medium and high priority requests. Here, the priority is given to the amount of VM’s requested. To implement the above concept, the Hybrid Cloud model is used by which the benefits of both the private and public clouds can be reaped. This model has its advantages that it proves to be cost-effective as the resources are effectively utilized from private clouds and only when exhausted are taken from public clouds which is cheaper.

An approach for improving quality and performance of collaborative filtering-based recommender systems is proposed in this paper. A slight change on similarity metric is proposed. To obtain more accurate similarity measurement between two users, similarity measurement method needs a well-chosen weight vector. Different weight vectors could be employed based on the recommender system and the taste of users, but only some of them are suitable. To obtain the best results we have to find the most suitable weight vector among all possible ones. A meta-heuristic algorithm has been introduced to find near optimal weight vector. Cuckoo optimization algorithm is used to obtain optimized weight vector. The results are promising and satisfactory. Our results are compared with the results of previous approaches to verify effectiveness of new proposed method.

Graphics Processing Units (GPUs) were developed for graphics processing and it was not highly-parallel. But to overcome this problem developed General Purpose Computing on GPU, this is known as GPGPU.Boyer-Moore exact string matching algorithm are heavily used in the application of antivirus engines, DNA sequencing, text editors, intrusion detection etc. In this environment, the GPU was highly-parallel, multithreaded. In this Paper extend the GPU application into other area such as string matching problem. This paper shows the results on adapting the enhanced Boyer-Moore (EBM) string matching algorithm to run on GPU paradigm and comparison with serial version and multithreaded version on CPU.The experimental results demonstrate that GPU version of enhanced Boyer-Moore (EBM) string matching algorithm 10 times faster than CPU version and 9 times faster than the multithreaded version. It can be also see there that multithreaded version of EBM algorithm about 12 % to 13 % peak performan...

Finding meaningful information among the billions of information resources on the Web is a difficult task due to growing popularity of the Internet. The future of World Wide Web (WWW) is the Semantic Web, where ontologies are used to assign (agreed) meaning to the content of the Web. On the Semantic Web, data will inevitably be linked to many different ontologies, and information processing across ontologies is not possible without knowing the semantic mappings between them. As the resources on the Semantic Web are annotated using these ontologies, new search techniques are required to find specific information. For this, architecture has been proposed for ontology based semantic web crawler. This architecture can exploit the semantic metadata to efficiently discover and extract information from the Semantic Web. In this paper Semantic matching between content of downloaded web page and ontology is used to guide the crawler towards relevant information.

Information security in the banking sector is heavily controlled as banks store and manage their clients' private information. Information security has always been the responsibility of the information technology (IT) department in organizations. Banks have become a component of the internet and daily lives. Libyan banks facade limited cash due to the part up political circumstance since 2014, as a result of limited cash individuals incapable to get their salaries. To solve this problem, most of Libyan banks are set up online electronic installment arrangements to assist individuals in buying their day by day needs. However, Cyber-attacks increasing day by day, and this is the challenge facing by banking where data is critical. These incidents could be prevented by implementing adaptable countermeasures promptly and minimizing risk. In this paper, a framework is proposed to assess the information security issue in Libyan banks. The study aimed at the assessment of security strategy in Libyan banks to identify security gaps. To achieve the aim of this study data collected by interview information security staff to evaluate the current security strategy in Libyan banks.

Artificial intelligence with Human-computer interaction is a discipline concerned with the design, evaluation and implementation of interactive computing systems for human use and with the study of major phenomena surrounding them. Current mobile computing devices such as palmtop computers, personal digital assistants (PDAs) and mobile phones, and future devices such as Blue tooth and GSM enabled cameras, and music players enabled have many implications for the design of the user interface. No longer can designers base computing designs around the traditional model of a single user working with a personal computer at his/her workplace. In addition to mobility and size requirements, mobile devices will also typically be used by a larger population spread than traditional PCs and without any training or support networks, whether formal or informal. Furthermore, unlike early computers which had many users per computer, and PCs with usually one computer per user, a single user is likely to own many mobiles devices which they interact with indifferent ways and for different tasks. Mobile devices present human-computer interaction (HCI).Using Artificial Intelligence Multitasking and support for task interruption is one of the keys to successful Synthesis Based Mobile Architecture.

The most critical and important aspect of disaster recovery is to protect the data from application fail over, natural disasters and infrastructure failures. Taking frequent backups of the huge volumes of data and storing it is also an integral part of the disaster recovery plan. Various scenarios of database replication strategies and techniques are provided in this survey paper addressing the need for replication of data. A wide range of open source and commercial tools have evolved over a period of time to deal with the issues and challenges involved during the process of database replication. This paper describes the general characteristics of replication & disaster recovery. Later the features of open source and commercial replication tools are compared.

Feature detection is the initial step in any image analysis procedure and is essential for the performance of computer vision applications like stereo vision, object recognition, object tracking systems. Research concerning the detection of feature points for different camera motion images in efficient and fast way. In this work, techniques of corner detection, geometric moments and random sampling are presented to simply and accurately locate the important feature points in image. For each extracted feature in image, a descriptor is calculated and based on the homograph transformation the matching is done. The results of experiments conducted on images taken by handheld camera and compared with the most famous SIFT method. The results show that the proposed algorithm is accurate, fast, efficient and robust under noise, transformation and compression circumstances.

Bisthiourea Zinc Acetate (BTZA) a semi organic material has been synthesized by slow evaporation method using water as a solvent. The solubility studies have been carried out in aqueous solution in the temperature range 25 ˚C – 45 ˚C. Crystals have been grown from low temperature solution method by slow evaporation of saturated aqueous solution at room temperature. Single Crystal X-ray diffraction study has been carried out to determine the lattice parameter of the grown crystal. The spectral bands have been compared with similar thiourea complexes using FTIR spectrum in the range 400 – 4000 cm-1. Optical transmittance and absorption percentage of the grown crystal have been measured from UV-Vis studies. The thermal behavior has been investigated by thermogravimetric (TGA) and Differential Thermogram analyses (DTA). The mechanical strength and work hardening coefficient of the grown crystal have been analyzed by Vicker’s microhardness method. Keywords: Growth from solutions; X-ray d...

Vertex coloring is a graph coloring technique which has a wide application area to provide solution for many real world problems. The high computational complexity of graph coloring algorithm led the development of exact heuristic algorithm which can be executed in optimal time. This paper explores some existing graph coloring algorithms to propose taxonomy of exact graph coloring algorithm which is capable to execute large graphs also. This paper presented experimental result on DIMACS graph instances.

introduced in 2003, is a techniques used for hidden communication between two covert parties. It is an art of hidden communication. It also relates to the areas like network protocols and security for practical data hiding in communication networks using Transmission Control Protocol/Internet Protocol (TCP/IP). The typical steganographic method utilizes digitized media files (images, video and audio files) as a cover medium for hiding data, network steganography uses communication protocols such as TCP/IP. Such methods make it harder to detect and eliminate. In a typical steganography using network the modification of a single network protocol occurs. Such modification can be applied to the Protocol Data Unit. Network steganography sheltersa broad spectrum of techniques.

Teenage alcohol addiction poses a major problem to the wellbeing of the individual as well as the society. Prevention of this requires identifying the factors causing this addiction. The existing systems mainly rely on decision trees and are able to isolate the factors causing the addiction. The proposed system will be able to predict whether a student with a set of conditions will get addicted to alcohol or not with high accuracy and thereby verify the extent to which the isolated factors are correct. General Terms Data mining, Student characteristics dataset

Multilayer perceptrons (MLPs) are widely used for pattern classification and regression problems. Backpropagation (BP) algorithm is known technique in the training of multilayer perceptrons. However for its optimum training convergence, the learning and momentum parameters need to be tuned on trial and error method. Further, sometimes the backpropagation algorithm fails to achieve global convergence. To alleviate these problems we suggest a genetic algorithm based training for MLP network. Both binary coded and real coded genetic algorithm are used and a comparative training performance analysis has been studied. It is observed from simulation results that both the schemes outperform backpropagation algorithm and achieve global convergence. Further the real coded GA based training shows a faster convergence than binary coded GA based training. For simulation datasets are taken from UCI based machine learning repository. Hence real-coded genetic algorithm finds an alternative for back propagation based training algorithm.

It is impossible to capture all of the semantics of real world information and to model it in a perfect way. Uncertain information being lacking information, individual interpretation of knowledge is taken into account. Most widely used relational model faced much difficulty to handle complex data requirements. The size of databases and their changing composition such as graphics, video and sound, as well as numbers and text invited a reorganization of existing information systems. Object oriented database draw their strength from graphical user interfaces, advanced data management capabilities and powerful modeling techniques. So in order to deal with inexactness fuzzy techniques have been extensively integrated with more advanced object oriented database system which is capable to represent and manipulate the complex objects as well as complicated and uncertain relationship exiting among them. In this paper uncertainty using Fuzzy Object Oriented Database and Fuzzy Relational Data Base is illustrated.

Agricultural land in Denpasar city from year to year is always decreasing. Based on data from the years 2011-2014, agricultural land decreased significantly with percentage 58.6%. The decline in agricultural land affects agricultural output. The decrease in agricultural land caused by factor, namely the increase in population so that agricultural land is used as a housing or another functions. Seeing this phenomenon due to a lack of information to the public on the impact of agricultural land conversion. The narrow agricultural land in Denpasar will affect the balance of nature, the air will be more crowded and there will be global warming. Based on this analysis then necessary statistical forecasting using method prediction semi trend average which is implemented using the Geographical Information System with ArcView 3.3 as software and digital maps as result. Prediction with this mapping is used to predict the area of agricultural land that would come if the condition is still the same (data used in 2011-2014) so that the government and the general public can know the impact of land conversion and can think of solutions to tackle the agricultural land conversion.

In this paper a new intelligent identification method of uncertainty bound utilizes an adaptive neurofuzzy inference system (ANFIS) in a feedback scheme is proposed. The proposed ANFIS feedback structure performs better in determining the uncertainty bounds with minimum number of iterations and error. In our proposed technique, the intelligent identified uncertainty weighting function is validated utilizing v-gap to ensure the stability of the designed H controlled system. Our proposed intelligent identification of uncertainty bound is demonstrated on a servo motion system. Simulation and experimental results show that the new ANFIS identifier is more reliable and highly efficient in estimating the best uncertainty weighting function for robust controller design.

In this study, an educational tool has been presented to teach fuzzy logic controller (FLC) and classical controllers to undergraduate and graduate level students, so that students could establish a thorough understanding and be able to compare FLC with classical controllers. The tool has flexible structure and user-friendly graphical interface. Direct current (DC) motor speed control has been presented to help students learn and compare the FLC and classical controllers. Students practice on both controller, interpret and draw conclusions related to system parameters by changing parameters of FLC and classical controller with various working conditions. ß

Web usage mining aims to discover interesting user access patterns from web logs. Web usage mining has become very critical for effective web site management, creating adaptive web sites, business and support services, personalization and so on. In this paper, an efficient approach for frequent pattern mining using web logs for web usage mining is proposed and this approach is called as HFPA. In this approach HFPA, the proposed technique is applied to mine association rules from web logs using normal Apriori algorithm, but with few adaptations for improving the interestingness of the rules produced and for applicability for web usage mining. This technique is applied and its performance is compared with that of classical Apriori-mined rules. The results indicate that the proposed approach HFPA not only generates far fewer rules than Apriori-based algorithms (FPA), the generated rules are also of comparable quality with respect to three objective performance measures, Confidence, Lift and Conviction. Association mining often produces large collections of association rules that are difficult to understand and put into action. In this paper effective pruning techniques are proposed that are characterized by the natural web link structures. Experiments showed that interestingness measures can successfully be used to sort the discovered association rules after the pruning method was applied. Most of the rules that ranked highly according to the interestingness measures proved to be truly valuable to a web site administrator.

This project provides better surveillance for our country by using Internet of things. It is a Rover type device which is useful in high risky boundary regions and the lands where human cannot enter. In this project, the motion of the rover and the rotation of the camera can be controlled using internet. Therefore, we can control this device from anywhere in the world. It provides live streaming and more information about that area. Active IR sensor is used for obstacle detection for safe motion of the rover. It also has MQ2 smoke sensor which senses the inflammable gas and the gas presence in the environment. Ultrasonic sensor is used to detect the motion of the objects present in the surroundings. In this project camera can controlled by using pan and tilt servo motors. Land Mines can also be detected by using Land mine detection circuit. IOT is easily supported using Raspberry pi 3 model B. SD card is used for storing the sensed information. This device is used to prevent the hum...

The study of frog is important since the chemical compound in their skin extracts peptides with antimicrobial activity becomes a valuable tool for pharmacology and biochemistry research. Instead of depending on physically observation procedure to identify the particular species, this study proposes an automated frog sound identification system for recognizing frog species. 990 data species that collected from internet database and recorded from Malaysia forest are sampled. Two features i.e. Mel Frequency Cepstrum Coefficient (MFCC) and Linear Predictive Coding (LPC) have been used in the feature extraction techniques. Subsequently Support Vector Machine (SVM) and k Nearest Neighbor (kNN) are obtained to evaluate the performance in the identification system. The experimental results show that kNN gives better performance with accuracy up to 80.33% to 98.4%compare than SVM.

The Binet formula for Pell sequence is viewed as a function of complex variable. In this paper the study of attracting and repelling fixed points of Pell sequence is presented with the complex dynamics resulting in the escape time images. A study of orbits of the Binet type formula is presented in the paper. Besides this, a new class of Mandelbrot sets is also studied for the Mann-iterates.

The healthcare environment is generally perceived as being information rich yet knowledge poor. The healthcare industry collects huge amounts of healthcare data which, unfortunately, are not―mined‖ to discover hidden information. However, there is a lack ...

Phishing is a novel kind of website/network attack which makes a deceitful attempt and influences the amenities or information security instead of stealing personal, financial and transactional data, etc. To preclude users or network from the phishing different techniques has been proposed and implemented.This paper, present the review of literature about the techniques offered by different researchers for exposing and avoiding from the phishing attack also discusses the advantages and limitation of the approaches.

To be able to control devices by voice has always intrigued mankind. Today after intense research, Speech Recognition System, have made a niche for themselves and can be seen in many walks of life. The accuracy of Speech Recognition Systems remains one of the most important research challenges e.g. noise, speaker variability, language variability, vocabulary size and domain. The design of speech recognition system requires careful attentions to the challenges such as various types of Speech Classes and Speech Representation, Speech Preprocessing stages, Feature Extraction techniques, Database and Performance evaluation. This paper presents the advances made as well as highlights the pressing problems for a speech recognition system. The paper also classifies the system into Front End and Back End for better understanding and representation of speech recognition system in each part.

Security of the consumer’s data over internet is the major problem in present time. In this paper we have analyzed blind signature schemes based on RSA and with taking advantage of elliptic curve cryptography to achieve the security goals. Blind signature scheme is one of the security protocol to obtain signature from a signer such that signer sign the message without reading the content of the message and also he could not link the protocol with the resulting message signature pair. Blind signature scheme is used to achieve certain security goals like blindness, untraceability, authenticity, unforgeability. We have analyzed blind signature scheme to achieve the security goals using Elliptic Curve Cryptosystem. Elliptic curve cryptography (ECC) is an approach to public-key cryptography based on the algebraic structure of elliptic curves over finite fields. The use of elliptic curves in cryptography was initially presented by Neal Koblitz and Victor S. Miller. Elliptic curve cryptosy...

In the present paper the authors have introduced a new symmetric key cryptographic method called Bit Level Encryption Standard(BLES) which is based on bit exchanging or bit reshuffling method. The authors have introduced a completely new bit level encryption method. Nath et. al has already developed bit manipulation method called NJJSAA where the authors mainly used bit level right shift, bit level XOR operation. In the present paper the authors have used bit level exchange using random key generator and also byte level exchange using random key generator. The bit exchange was made using different block sizes such as 16 bits, 64 bits, 256 bits and 1024 bits long. To make the system hard the authors have changed the randomization matrix each time when data is extracted from plain text file and whenever the size of the block is changed. After finishing bit level exchange for the entire file the authors used the byte exchange method. The authors have also introduced a special bit manip...

Dimensionality refers to number of terms in a web page. While classifying web pages high dimensionality of web pages causes problem. The main objective of reducing dimensionality of web pages is improving the performance of classifier. Processing time and accuracy are two parameters which influence the performance of a classifier. To reduce the processing time, less informative and redundant terms have to be removed from web pages. This research describes hybrid approach for dimensionality reduction in web page classification using a rough set and naïve Bayesian method. Feature selection and dimensionality reduction methods are used for reducing the dimensionality. Information gain method is used as feature selection method. Rough set based Quick Reduct algorithm is used for dimensionality reduction. Naïve Bayesian method is used for classifying web pages to optimal predefined categories. Assignment of web pages to category is based on maximum posterior probability. Words remaining ...

The rapid spread of 3G wireless network and wireless technologies, are applied in many areas, the education is the interesting approach for using this technique, so the benefit of modern technology can be used in mobile learning. This system is focused on design mobile learning management system which simulates the learning process between teacher and student, by build an educational system that the student can get educational material and procedure MCQ test, open question and analyze student answers and evaluated automatically using modern techniques. Latent semantic analysis (LSA) has been employed in intelligent learning systems for evaluation students' learning by evaluating their answers to questions in the tutoring domain. Latent Semantic Analysis (LSA) is an attempt to solve the problem of Automatically scoring open questions..

Vehicular Ad-hoc Network (VANET) are an emerging technology with vehicle. As a subset of Mobile Ad-hoc Network (MANET) application, VANET is considered to be a new phase of technology to the Intelligent Transportation System (ITS). VANET is a technology Using VANET vehicles can become aware of the dynamic behavior of other vehicles regardless of the driver's ability. In addition, infrastructure can obtain situational awareness at various levels of detail to manage traffic and potentially send emergency services. When traffic jam occurred in pick hour, vehicle in that area should be able to give a way to emergency services such as ambulance. Such traffic happened every day in Jakarta especially on weekdays. This research focused on designing the traffic condition and analyzing the routing protocol for VANET for Jakarta smart cities. Before implementing VANET in Jakarta, simulation using NS2 was conducted with two environment scenes. The first environment scene was the vehicle move one by one on each intersection. The second environment scene was the vehicle move in the opposite direction. The number of mobile nodes used in the environment scene as vehicle and infrastructure were 50, 100, 150, 200, 250, 300, and 350. we set 10 nodes as infrastructures for all number of mobile nodes used in the simulation and the remaining nodes as vehicles. We used more nodes as vehicle because the number of vehicles in the Jakarta was higher than the number of infrastructures. The network area used in this simulation was 2000x2000. We used constant bit rate (CBR), two ray ground propagation and omni antenna to simulate the environment scenes. The routing protocols used in this research were Ad-hoc On-Demand Distance Vector (AODV), Dynamic Source Routing (DSR), and Destination Sequenced Distance Vector (DSDV). The result of this research showed that AODV achieved the highest throughput and the best packet delivery ratio. The lowest end-to-end delay was achieved by DSDV. Accordingly, simulation result showed that AODV has the best performance and preferable routing protocol of VANET for Jakarta environments.

Maintainability of the software is one of the key quality while evaluating software product. Of the overall software development cost, major stake is employed at the maintenance phase. Maintenance time of software is always greater than its development time, so it becomes essential to measure the maintainability of software so that maintenance operational time can be brought down.While going over the prevailing knowledge of literature it is understood that maintenance cost can be regulated by using software metrics at the design phase. There is substantial works in proving that machine learning algorithms is a suitable alternative for many domains of computational sciences including software engineering. This paper is aimed at carrying out a detailed study on the usage of machine learning approaches in the prediction, assessment and evaluation of software maintainability

For many decades researchers in the domain of NLP (Natural Language Processing) and its applications like Machine Translation, Text Mining, Question Answering, Information Extraction and Information retrieval etc. have been posed with a challenging area of research i.e. WSD (Word Sense Disambiguation) WSD can be defined as the ability to correctly ascertain the meaning of a word, with reference to the context in which the word was used. Linguistics, has defined context as the passage, sentence or text in which the word appears that is used for ascertaining its meaning. Thus, context is dependent on the POS (Part Of Speech) where the word is used e.g. Adverb, Adjective, Pronoun, Verb and Noun. In the following study we recommend a unique way of WSD based on Context through WordNet, multimodal algorithm that is knowledge based, map-reduce and soft sense WSD.

The recent advances and the convergence of micro electro-mechanical systems technology, integrated circuit technologies, microprocessor hardware and nano technology, wireless communications, Ad-hoc networking routing protocols, distributed signal processing, and embedded systems have made the concept of Wireless Sensor Networks (WSNs). Sensor network nodes are limited with respect to energy supply, restricted computational capacity and communication bandwidth. Most of the attention, however, has been given to the routing protocols since they might differ depending on the application and network architecture. To prolong the lifetime of the sensor nodes, designing efficient routing protocols is critical. Even though sensor networks are primarily designed for monitoring and reporting events, since they are application dependent, a single routing protocol cannot be efficient for sensor networks across all applications. In this paper, the design issues of sensor networks and a classification and comparison of routing protocols is presented. This paper reveals the important features that need to be taken into consideration while designing and evaluating new routing protocols for sensor networks.

The UMES School of Business and Technology in collaboration with the Center for Student Technology Certification and Training has initiated an innovative three-prong program that uses the IC3 test to evaluate the information and digital literacy of new freshmen in order to examine whether students have the minimal skills necessary for college success, followed by a computer concepts course designed to prepare them for workforce entry, and finally including the availability of advanced course work and professional certifications in order to provide them with the opportunity to develop enhanced skills.

Segmentation is a process of converting inhomogeneous data into homogeneous data. There are many segmentation techniques available inthe literature. Among these techniques, finite Gaussian Mixture Model using EM algorithm is one mostly used. However, Gaussian Mixture Model is suited well when the image under consideration is symmetric. But in reality, medical images are asymmetric. Hence, it is needed to develop new algorithms for segmenting nonsymmetric images. Therefore, skew symmetric mixture model is utilized for this purpose. The segmentation is carried out by using Fuzzy C-Means clustering technique and the updated parameters are obtained through EM algorithm. The model is tested with 8 images and the segmentation evaluation is carried out by using objective evaluation criteria namely Jaccard Coefficient (JC) and Volumetric Similarity (VS), Variation of Information (VOI), Global Consistency Error (GCE) and Probabilistic Rand Index (PRI). The performance evaluation of reconstructed images is carried out by using image quality metrics. The experimentation is carried out using T 1 weighted images and the results are compared with the existing models.

Segmentation of a word into basic characters or strokes is an essential and necessary step for character recognition in many handwritten word recognition systems. The one of the major difficulties in character segmentation is the existence of the skew in the handwritten word. But skew detection in the bangla handwritten word is difficult because of its shape variability of the characters as well as larger number of character classes. If the skew correction is done successfully then the character segmentation of the word will be more perfect and as a consequence the percentage of the correct word recognition will be higher. In this paper, we propose a novel method for skew detection and skew correction of online Bengali handwritten word through holistic approach. This approach works based on center of gravity of left part and right part of a handwritten word. After finding the center of gravity it calculates the angle of the line which connected the two gravity centers in relation to horizontal line. Then Rotates the word clockwise by the angle θ if θ<90º, or anticlockwise by the angle (180º-θ) if θ>90º. All the pixel moves to the particular angle to correct the skew. The algorithm has been verified on a database of 3000 Bengali word data collected from different people of different age group and it gives 92.22% accuracy on word data from the proposed system.

Conversion from paper-based medical records to electronic Health Records provides significant benefits to healthcare. However, there are some challenges perceived by healthcare providers when implementing Electronic Health Records. This paper aims to present some guidelines to overcome barriers associated with implementing Electronic Health Records in developing countries. This paper also presents an overview of Electronic Health Records Barriers discussed in several studies and review some studies performed in developing countries to explore the implementation barriers of the Electronic Health Records.

Information and communication technology is the major tool to improve the quality of education. Indian Government invested huge amount for ICT to improve the education sector. Also, various ICT trainings are given to the school teachers through the government scheme. Though Pune is one of the top educational city, there is a lack of ICT tools in the rural area schools. This article is an extension to our earlier work based on requirement analysis of the computer literacy level of the rural and urban schools. The new scheme to improve the computer literacy level of rural teachers based on analysis of the rural teachers is proposed. The objective of defining this scheme is to enhance the capability of rural teachers to accept the new technology. This scheme mainly focuses on improving usage of computer, teaching skills and culture of rural education. This scheme will bridge the gap between rural and urban school teachers.

Automatic identification of male and female from facial image allows many useful applications in biometrics, surveillance, and human-computer interaction. This paper presents a robust face feature descriptor for gender classification from facial image. The proposed method is based on the compound local binary pattern (CLBP), an extension of the LBP texture operator. The CLBP operator exploits 2P bits to encode the information of a local neighborhood of P neighbors, where P bits are used to express the sign information and the other P bits are used to express the magnitude information of the differences between the center and the neighbor gray values. The performance of the proposed method has been evaluated using a large dataset comprising 1800 facial images collected from the FERET database. Extensive experiments with support vector machine classifier show the superiority of the CLBP feature descriptor against some well-known texture operators.

This paper introduces hybridization of particle swarm optimization (PSO) with genetic algorithm (GA) denoted as PSO+GA provides an efficient approach which is used to solve non linear chaotic datasets. The proposed algorithm employed in probabilistic neural network(PNN) which is a variant of radial basic function artificial neural network (RBFANN) for finding precise value spread factor for accurate classification of chaotic time series. Hybridizing of particle swarm optimization (PSO) and genetic algorithm (GA) in social learning helps collective efficiency, robustness and global effectiveness. The hybrid approached which then is resulted in the integrated framework for complete determination of spread factor with evaluation parameters. The algorithm is tested on two benchmark problems and compared the performance with arbitrary spread factor of PNN. The results showed that the PSO+GA based heuristic optimization algorithm outperform in terms of higher classification and prediction accuracies with short computation time.

The growing complexity of real-world problems has motivated computer scientists to search for efficient problemsolving methods. Divide and conquer techniques are one way to solve large and difficult problems. Division of large work into smaller parts and combining the solution of small problems to get the solution of large one has been a practice in computer research since long time. Swarm also exhibits the behavior of division of work and cooperation to achieve difficult tasks. Evolutionary computation and swarm intelligence meta-heuristics are outstanding examples which show that nature has been an unending source of inspiration. Artificial Swarm/Ant foraging utilizes various forms of indirect communication, involving the implicit transfer of information from agent to agent through modification of the environment. Using this approach, one can design efficient searching methods that can find solution to complex optimization problems. Over times, several algorithms have been designed and used that are inspired by the foraging behavior of real ants colonies to find solutions to difficult problems. In this paper the idea of Ant Colonies is presented with brief introduction to its applications in different areas of problem solving in computer science.

The increased need of content based image retrieval technique can be found in a number of different domains such as Data Mining, Education, Medical Imaging, Crime Prevention, Weather forecasting, Remote Sensing and Management of Earth Resources. This paper presents the content based image retrieval, using features like texture and color, called WBCHIR (Wavelet Based Color Histogram Image Retrieval).The texture and color features are extracted through wavelet transformation and color histogram and the combination of these features is robust to scaling and translation of objects in an image. The proposed system has demonstrated a promising and faster retrieval method on a WANG image database containing 1000 general-purpose color images. The performance has been evaluated by comparing with the existing systems in the literature.

Cloud computing is introducing many huge changes to people's lifestyle and working pattern recently for its multitudinous benefits. However, the security of cloud computing is always the focus of numerous potential cloud customers, and a big barrier for its widespread applications.Companies have increasingly turned to application service providers (ASPs) or Software as a Service (SaaS) vendors to offer specialized web-based services that will cut costs and provide specific and focused applications to users. The complexity of designing, installing, configuring, deploying, and supporting the system with internal resources can be eliminated with this type of methodology, providing great benefit to organizations. However, these models can present an authentication problem for corporations with a large number of external service providers. This paper describes the implementation of Security Assertion Markup Language (SAML) and its capabilities to provide secure single sign-on (SSO) solutions for externally hosted applications, including security measures for federated identity management systems using multifactor authentication ,which also includes Biometric identification.

Nowadays, people deal with a huge amount of data, especially while they are surfing on internet. So, this makes the topic of automatic summarization is very important and in the forefront. In this paper, a review for text summarization methods in Turkish is presented. Brief summary of the methods used for automatic text summarization in the literature, and also brief definitions of summary, abstraction and automatic text summarization are given.