Information Technology

Classification is an important task in data mining and machine learning, in which a model is generated based on training dataset and that model is used to predict class label of unknown dataset. Today most real-world data are stored in relational format. So to classify objects in one relation, other relations provide useful information. Relational data are the popular format for structured data which consist of tables connected via relations (primary key/ foreign key). Relational data are simply too complex to analyze with a propositional (single table learning) algorithm of data mining. So to classify from relational data there is a need of multi relational classification which is used to analyze relational data and predict unknown pattern automatically. This paper contains Multi Relational Classification with weighted voting algorithm for learning from relational data which result in increase accuracy. Also to decrease the running time voting technique is used compared to stacking as a combination method. The experimental study along with results demonstrate the effectiveness of algorithm respect to other existing techniques.

In last two decades continues increase of comput-ational power and recent advance in the web technology cause to provide large amounts of data. That needs large scale data processing mechanism to handle this volume of data. MapReduce is a programming model for large scale distributed data processing in an efficient and transparent way. Due to its excellent fault tolerance features, scalability and the ease of use. Currently, there are several options for using MapReduce in cloud environments, such as using MapReduce as a service, setting up one’s own MapReduce cluster on cloud instances, or using specialized cloud MapReduce runtimes that take advantage of cloud infrastructure services. Cloud computing has recently emerged as a new paradigm that provide computing infrastructure and large scale data processing mechanism in the network. The cloud is on demand, scalable and high availability so implement of MapReduce on the top of cloud services cause faster, scalable and high available MapReduce framework for large scale data processing. In this paper we explain how to implement MapReduce in the cloud and also have a comparison between implementations of MapReduce on AzureCloud, Amazon Cloud and Hadoop at the end.

A person’s learning of a new language starts with learning alphabets of the language. The validation of a learning process is its recognition under any circumstances. The application developed in this paper, is aimed at making the “recognition process of alphabets” after different distortions on the original structure and frame of the alphabet. The system creates the distorted alphabet with graphical transformations and recognition is done by a back propagation neural network. The graphical transformations include scaling, rotation and translation functions written in Open GL. The distorted character is recognized by the neural network coded in C#. The system can be deployed for any distorted image recognition application. The system has shown satisfactory performance for distorted character recognition.

Writer identification is the process of identifying the writer of the document based on their handwriting. The growth of computational engineering, artificial intelligence and pattern recognition fields owes greatly to one of the highly challenged problem of handwriting identification. This paper proposes the computational intelligence technique to develop discriminative model for writer identification based on handwritten documents. Scanned images of handwritten documents are segmented into words and these words are further segmented into characters for word level and character level writer identification. A set of features are extracted from the segmented words and characters. Feature vectors are trained using support vector machine and obtained 94.27% accuracy for word level, 90.10% for character level. An interactive tool has been developed based on the word level writer identification model.

Semantic web technology enables machine to read and process web pages without human intervene. Semantic web information will no longer only be intended for human readers, but also for processing by machines, enabling intelligent information services, personalized web sites, and semantically empowered search-engines. The web has become a major vehicle in performing research and education related activities for researches and students. With increasing student mobility and boom of the international student exchange programmes, a need arises for unifying and presenting information about academic study programmes on the Web. Publishing study programmes using semantic web technologies enables students to easily search and select study topic of their interest. In this paper we present an enterprise semantic framework for e-Learning system which improved the quality of web mining results but also enhanced the functions, services and the interoperability of e-Learning system. The system helps to find suitable semantic data related to students, faculties and courses for the clients. We have implemented semantic web mining in parallel distributed environment in all tiers for decision making, and also increased speed and efficiency of information retrieval.

With the advancement in wireless communication technology, various networks exists simultaneously. The variation in wireless network parameters is imprecise in nature. To handle this imprecise data fuzzy logic can be used as an important tool for wireless network algorithms. Application of fuzzy logic/fuzzy controller in wireless communications is presented in this paper. The objective of this paper is to highlight the importance of use of fuzzy logic based algorithms in heterogeneous wireless environment. This paper will focus on application of fuzzy logic in cognitive radio, wireless sensor networks, decision making in heterogeneous wireless environment, routing in mobile Ad-hoc networks etc.

The applications of audio and video compression are limitless and the ISO has done well to provide standards which are appropriate to the wide range of possible compression products. MPEG coding embraces video pictures from the tiny screen of a videophone to the high-definition images needed for electronic cinema. Audio coding stretches from speech-grade mono to multichannel surround sound. This paper presents an overview of the video compression standards related to the MPEG family. MPEG-7 and MPEG-21 are specially covered including its latest standards. MPEG-7 is mainly used for object descriptions and MPEG-21 is for DRM (Digital Rights Management).

This paper focuses on the bidirectional associative memory its features and the future aspects and the current context of application. BAM is a type of neural network. Artificial neural network (Ann’s) resembled the human nervous system, with algorithms consisting of weighted interconnecting processing units (like neural map of the human brain). To address a particular problem using Ann’s, the interrelated connections are tuned and the value of weights between units is needed. Neural network is a new unexplored topic of interest for the computer scientists. Bam comes under recurrent types of network called Hopfield network. BAM is a resonance model, in the sense that information is passed back and forth between two layers of units until a stable sate is reached. The Hopfield network is said to be auto associative, because it uses a partial and noisy pattern to recall the best match of itself. BAM includes: ASSOCIATIVE NEURAL MEMORIES: Associative neural memories are a class of artificial neural networks (connectionist nets) which have gained substantial attention relative to other neural net paradigms. Associative memories have been the subject of research. NOISE TOLERANCY: This paper analyzes the sensitivity to noise in BAM (Bidirectional Associative Memory), and then proves the noise immunity of BAM relates not only to the minimum absolute value of net inputs (MAV) but also to the variance of weights associated with synapse connections.

Satellite images are used to extract linear features, like roads, etc. The extraction of linear features or boundaries defining the extents of lands, land covers features are important in Cadastral Surveying. Cadastral Surveying is the cornerstone of any Cadastral System. A two dimensional cadastral plan is a model which represents both the cadastral and geometrical information of a two dimensional labeled Image. This paper aims at using a combination of canny and morphological operations for extracting representations of cadastral boundaries from high resolution Satellite imagery hence minimizing the human interventions. The Satellite imagery is initially rectified hence establishing the satellite imagery in the correct orientation and spatial location for further analysis. We, then employ the much available Satellite imagery to segment the relevant cadastral features using the above mentioned methods. We evaluate the potential of using high resolution Satellite imagery to achieve Cadastral goals of boundary detection and extraction of farmlands using image processing algorithms. This method proves effective as it minimizes the human demerits hence providing another perspective of achieving cadastral goals as emphasized by the UN cadastral vision for an improved socio economic development.

Low temperature offers an exciting opportunity to understand physical properties of various material and process. Electrical contact resistance which is fairly understood at room temperature behaves in entirely difference way at temperatures below the room temperature. Estimation of contact resistance and its behavior at low temperatures is not only necessary for its application areas but for understanding the contact mechanism and controlling the contact resistance. Low temperature experiments are highly time-consuming, due to the inherent thermal design of these systems, which takes a lot of time to stabilize. Automation of these experiments not only eases the experimentation but also improve the result accuracy.