2011 Nirma University International Conference on Engineering

The advent of Grid environments made feasible the solution of computational intensive problems in a reliable and cost-effective way. As scheduling carry out more complex and mission-critical applications, Quality of Service (QoS) analysis serves to ensure that each application meets user requirements. In that frame, author presents a novel Ant colony algorithm with a quick convergence of ant to mo... View full abstract»

Content based Image Retrieval systems (CBIR) have become a reliable tool for many image database applications. Today, the need for reliable, automated satellite image classification and browsing systems is more than ever before. Everyday there is a massive amount of remotely sensed data being collected and sent by terrestrial satellites for analysis. The use of automated tools for this analysis ha... View full abstract»

Now day's data integration is the new era of research of combining data residing at different sources and providing the user with a unified view. The problem with designing of data integration system is challenging task in real world applications. Characterization of integrated is interesting from a conceptual point of view. This research presents an overview of data integration of the given mater... View full abstract»

In past three decades, the world of computation has changed from centralized (client-server not web-based) to distributed systems and now we are getting back to the virtual centralization (Cloud Computing). This paper aims to design and implement an optimized infrastructure for secure authentication and authorization in Cloud Environment. SSO (Single Sign-On) is a process of authenticate once and ... View full abstract»

In Recent years, the application of machine learning approaches to conventional IR system evolve a new dimension in the field. The emphasis is now shifted from simply retrieving a set of documents to rank them also for a given query in terms of user's need. The researcher's task is not only to retrieve the documents from the corpus but also to rank them in order of their relevance to the user's re... View full abstract»

Derivation of height information from stereo images is a trivial problem in the field of photogrammetry, remote sensing and computer vision. The algorithms for generation of height information from the stereo imagery in the form of Digital Elevation Model (DEM) primarily involve computationally complex image matching procedures. In this paper, we propose a Graphic Processing Units (GPU) based meth... View full abstract»

The image classifications techniques have been practiced by remote sensing experts following certain methods like unsupervised and supervised. Supervised classification requires precise human intervention to extract features. Enhanced Seeded region growing technique is an image segmentation method; where the image pixel is seeded by latitude and longitude recorded during ground truth data collecti... View full abstract»

The bank notes are the most popular means of the value circulation. The present day financial self-service has made the currency recognition a key activity of the automated banking process. The process of the currency recognition by some extrinsic feature becomes error prone due the pollution and depreciation suffered by the currency during the transactions. Therefore we propose an Indian currency... View full abstract»

Bayesian Theory has been an elegant basis for the design of classifiers. There are several classifiers which do not adhere with the Bayesian principle strictly but motivated from the very theory, termed as naive Bayesian methods. The present work proposes a naive Bayesian Classification approach which limits the classification process to the basic operation of the key comparison. Moreover we are a... View full abstract»

The lack of disk space seems to be a major challenge during transmission and storage of raw images, which in turn pushes the demand for an efficient technique for compression of images. Although, lot of compression techniques are available today, any upcoming technique which is faster, memory efficient and simple surely has the greatest probability to hit the user requirements. In this paper, we h... View full abstract»

This paper improves the human-computer interaction through recognize and respond properly to their user's emotional state. Expression recognition (ER) is the most important task in human-computer-interaction system. In this research work we present the recognition of face expression using brain-computer-interaction techniques EEG(electroencephalogram) and EMG (electromyography). The expression are... View full abstract»

For transferring sensitive data as in military applications it is necessary to achieve integrity, confidentiality and authenticity. In this paper, the scheme to generate encryption key with unimodal biometric fingerprint is discussed. As mobile ad hoc network does not have heavy computational power, multimodal biometric approach is not feasible. From receiver's fingerprint feature sets are generat... View full abstract»

Network coding is a technique in which node is allowed to combine and encode one or more input packets into encoded packets instead of directly forwarding them. It increases throughput and delivery ratio. In this paper, we review basic linear network coding variants with their performance benefits and theoretical results. In practical setting, linear network coding requires central authority to co... View full abstract»

This paper discusses about localization of license plate from vehicle images using different methods. And main focus is on Mean Shift Algorithm which is a non parametric feature space analysis technique. It defines a window around each data points and shifts the center of the window to the mean of the data point though a Mean-Shift Vector till it converges and window shifts to the denser region. T... View full abstract»

Today computing devices generate abundant information which has to be classified and stored to make navigation easier. Semi-supervised learning which is in-between supervised learning and unsupervised learning is explored is explored in the paper, incorporating the fuzziness in the process of textual classification is proposed. Semi-supervised classification is used where training data is not adeq... View full abstract»

Wireless networks are gaining popularity to its peak today, as the user's wants wireless connectivity irrespective of their geographic position. There is an increasing threat of attacks on the Mobile Ad-hoc Networks (MANET). The attacks studied in this paper are against the routing protocols in Mobile ad hoc network. We have used AODV for simulating this attacks using NS3. Black hole attack is one... View full abstract»

Bacterial foraging optimization algorithm (BFOA) has been widely accepted as a global optimization algorithm of current interest for optimization and control. BFOA is inspired by the social foraging behaviour of Escherichia coli. BFOA has already drawn the attention of researchers because of its efficiency in solving real-world optimization problems arising in several application domains. In prese... View full abstract»

This paper represents the technique for converting the text written in Hindi language into speech by using artificial neural network. Text to speech conversion software can have many applications in day to day life. It can be useful for blind people to read the document. It is useful in giving education to the students by listening what is written in books. If someone doesn't have time to read ema... View full abstract»

Grid computing provides a high performance computing platform to solve applications with large number of independent jobs. However, user jobs developed for grid might be small and of varying lengths according to their computational needs and other requirements. In fact, it is a big challenge to design an efficient scheduler, but there exists some grouping based job scheduling strategy that intends... View full abstract»

Content Based Image Retrieval is the method to retrieve stored image from database by supplying query image instead of text. This is achieved using proper feature extraction and matching process. Here we have implemented two methods of content based image retrieval using color and texture. In both of these method feature extraction of color is done using color moment. While feature extraction of t... View full abstract»

Data mining has been an active area of research for the past couple of decades. Classification is an important data mining technique that consists of assigning a data instance to one of the several predefined categories. Various successful methods have been suggested and tested to solve the problem in the binary classification case. However, the multiclass classification has been attempted by only... View full abstract»

We always see our normal mail goes into spam folder of the mail box. Interestingly 90% of the time the mail server classifies it perfectly but sometimes it fails due to spammer are getting highly technical. In this paper, we are using novel approach which uses Vector space model with Naïve Bayes to correctly classify mails as spam mail. Naïve Bayes method is used for spam classification but still ... View full abstract»