Semi-Automatic Noninvasive Tracking of Local Myocardial Motion using Dynamic Programming based Elastic Model

semi-automatic motion-tracking method for local myocardial tissue on M-mode echocardiograms is proposed in this paper. The proposed method is applicable to estimating myocardial performance in clinics. The M-mode echocardiogram is a type of echocardiogram used in clinics to measure diagnostic indexes. Such as the thickening and thinning of myocardial muscle layers. In order to measure such indexes, doctors are required to manually track myocardial motion. However, tracking myocardial motion by hand is a very tedious and time-consuming process. The proposed method for tracking the motion of myocardial tissue is based on Dynamic Programming (DP). A Myocardial Elastic (ME) Model is employed to reduce the accumulation of velocity error. The experiment has 3 parts: visual inspection, statistical estimation and the analysis of systematic error. The results of these three evaluations indicate that the proposed method can provide more accurate motion tracking and can replace the manual tracking method for doctors in clinics.

Application of Adaptive Neuro-Fuzzy Inference System in High Strength Concrete

Intelligent Linear Data Structure with Self Performance Optimization Capacity: Application on Big Data

The access to relevant information from a big data container is gaining immense significance. This depends on storage technics and the organization level. This work proposes an intelligent linear data structure with an integrated cognitive agent reorganizing periodically the data structure content. The reorganization is based on a confidence interval of a random variable estimated by the agent. This random variable represents the demand frequency for each element. The cognitive agent studies the client behavior and puts most popular data in the beginning of the array in order to be found quickly. That increases considerably the search algorithm performance and solves by that one of most problems of the big data field. Models and algorithms in this work are implemented with Java programming language and simulated and that proves the reliability of the approach.

An Improved Expectation Maximization based Semi-Supervised Email Classification using Naïve Bayes and K- Nearest Neighbor

With the development of Internet and the emergence of a large number of text resources, the automatic text classification has become a research hotspot. Emails is one of the fastest and cheapest communication ways that today it has became the part of communication means of millions of people. It has become a part of everyday life for millions of people, changing the way we work and collaborate. The l a r g e percentage of the total traffic over the internet i s the email. Email data is also growing rapidly, creating needs for automated analysis. In many security informatics applications it is important to detect deceptive communication in email. In the iterative process in the standard EM-based semi-supervised learning, there are two steps: firstly, use the current classifier constructed in the previous iteration to predict the labels of all unlabeled samples; then, reconstruct a new classifier based on the new training samples set. In this work, an EM based Semi-Supervised Learning algorithm using Naive Bayesian is proposed in which unlabeled documents are divided into two parts, reliable and misclassified. An Ensemble technique is used to add only reliable unlabeled documents to the training set. Also preprocessing of unlabelled documents is performed before learning process of Naive Bayesian and K-NN classifiers during first step of EM to reduce time of preprocessing, so with this proposed work accuracy of classifier will be increased and execution time will be decreased.

Dijkstra Shortest Path Algorithm using Global Position System

Dijkstra’s Algorithm is used to find the shortest path from one node to another node in a graph.Dijkstra’s algorithm is also known as a single source shortest path algorithm. It is applied only on positive weights. In this paper, Global Positioning System is used for adding a new functionality in Dijkstra’s algorithm. In this paper, using Global Positioning System the position parameter is added in the Dijkstra’s algorithm. From this current position is retrieved at any point. By using this current position, the distance can be determined from one node to another node. The shortest path can also find out using this distance. For this an algorithm is proposed.

An Improved Image Fusion Technique based on Texture Feature Optimization using Wavelet Transform and Particle of Swarm Optimization (POS)

Improved Robust Algorithm for Exemplar based Image Inpainting

Inpainting is technique in which mainly used to filling the region which are damaged and want to recover from unwanted object by collecting the information from the neighbouring pixels. Image inpainting technique has been widely used for reconstructing damaged old photographs and removing unwanted objects from images. In this paper, we present an improved robust algorithm for exemplar based inpainting method by modifying the distance function. The method proved to be effective in removing large objects from an image, ensuring accurate propagation of linear structures, and eliminating the drawback of "garbage growing" which is a common problem in other methods. Experimental results show that our method improves the quality of image inpainting compared with the conventional exemplar-based image completion algorithms. KeywordsTexture Synthesis, Inpainting, PDE, image gradient etc.

A Survey of Quadratic Assignment Problems

Threshold based Approach for Image Blind Deconvolution

attractiveness in digital cameras, the digital image processing is getting more imperative nowadays. One of the most common problems facing with digital photography is noise and blurring that needs restoration. In this paper, we present a new method for image blind deconvolution (2). The Proposed Method employs threshold based image restoration technique in blind image deconvolution. The goal of this work is to restore the image from a noisy and blurred image where the blurring function is not known. The blur process can be formulated as the image takes convolution operation with the Gaussian noise. One of the basic blind deconvolution method is an iterative blind deconvolution method. (5), (31). Although Iterative Blind Deconvolution method can recover the image from blurred image, it is sensitive to initial estimation and computation time required is more. In order to decrease this computation time and better visual results than Iterative blind Deconvolution, we proposed a threshold based Blind image deconvolution algorithm.

Experimental Analysis of the Linux RT-patched for Data Acquisition applied to Power Sector