Abstract

In recent years, interest in visual sensor networks has grown significantly due to the ever increasing amount of commercial, military, and aerospace applications, including video surveillance, target tracking and identification, traffic monitoring, and smart homes. A key issue, however, in visual sensor network design is optimal placement of cameras, due to a number of challenges from environmental complexities to application metrics. Therefore, this paper presents a novel design scheme for optimal sensor placement of omnidirectional cameras operating in a Wireless Sensor Network (WSN). This is achieved by representing the environment using a 2-D grid map with static obstacles identified at different locations. An optimal placement metric is calculated for each grid point based on line-of-site in all possible directions where the known obstacles are taken into consideration. Distance is taken into account using exponential decay. Optimal areas of camera placement are determined based on the areas generating the largest optimal placement metrics. Statistical analysis of this methodology is examined by using Monte Carlo Analysis with various amounts of obstacles and cameras in a defined space.

Abstract

In software project management, there are three major factors to predict and control; size, effort, and quality. Much software engineering work has focused on these. When it comes to software quality, there are various possible quality characteristics of software, but in practice, quality management frequently revolves around defects, and delivered defect density has become the current de facto industry standard. Thus, research related to software quality has been focused on modeling residual defects in software in order to estimate software reliability. Currently, software engineering literature still does not have a complete defect prediction for a software product although much work has been performed to predict software quality.

On the other side, the number of defects alone cannot be sufficient information to provide the basis for planning quality assurance activities and assessing them during execution. That is, for project management to be improved, we need to predict other possible information about software quality such as in-process defects, their types, and so on. In this paper, we propose a new approach for predicting the distribution of defects and their types based on project characteristics in the early phase. This paper explores Orthogonal Defect Classification that combines the statistical approach and semantics of the test data. As a case, we integrated ODC in development and test environment in a web portal and realized improvement in Quality.

Abstract

This paper deals with generating of an optimized route for multiple Travelling Salesman Problem (mTSP). We used a methodology of clustering the given cities depending upon the number of salesman and each cluster is allotted to a salesman. “K- Means clustering” algorithm has been used for easy clustering of the cities. In this way the mTSP has been converted into TSP which is simple in computation compared to mTSP. After clustering, an optimized route is generated for each salesman in his allotted cluster. Once the clustering had been done and after the cities were allocated to the various salesmen, each cluster/tour was taken as an individual Traveling Salesman problem (TSP) and the steps of Genetic Algorithm(GA) were applied to the cluster and iterated to obtain the most optimal value of the distance after convergence takes place. Now every cluster was again solved as a TSP by applying the Ant Colony Optimization (ACO) algorithm to determine the optimal distance value. The algorithms were simulated and executed in “MATLAB” software. After the application of both the heuristic techniques, it was found that the Ant Colony Optimization algorithm gave a better result and a more optimal tour for small size mTSPs in short computational time than Genetic Algorithm due to the extensive search and constructive nature of the algorithm.

Abstract

In the field of pattern recognition, Optical Character Recognition (OCR) has been a cutting edge research area for the last few decades. And for quite some time now, the recognition of Indian language characters has been a subject of attention. A number of approaches have been proposed by researchers for recognizing printed, handwritten and cursive Tamil scripts both off-line and on-line. This article presents a survey of the researches available for optical character recognition of Tamil characters, an Indian language, along with a comparative study of our approaches against the most significant approaches from the literature. In addition, a concise description about the OCR system and the Tamil Script is provided. The aim of this article is to assist the budding researchers in the field of Tamil Optical Character Recognition in understanding the available methods and to aid their research further.

Abstract

In this paper, we propose a hardware-based microstructure inside the architecture of H.264 encoder, called Vector Bank (VB), which can dramatically reduce the bandwidth, memory, and computation time of a multi-camera video surveillance system. VB is a memory-based structure that contains the vector information for every single Macro Block (MB) of the video frame from the Motion Estimation module of the H.264 encoder. After extraction of these vectors from several frames, a dedicated Digital Signal Processor (DSP) can be assigned to analyze and predict the trajectories of the objects in motion. With the application of 2-D edge detectors, such as Sobel or Laplacian of Gaussian (LoG) operators, the objects in motion can be isolated from the background and thus be easily identified. In addition, a middleware-based technique derived from Directional Discrete Cosine Transform (DDCT) is introduced to improve the image quality without sacrificing the system performance. We propose four new modes of operations in DDCT for better image compression ratio. The experimental results show that we can improve the image quality of the targets, isolate them from the background, and track them easily in both linear and exponential trajectories of the motion.

Abstract

In today’s world of rapidly advancing technology, guaranteeing software quality is of paramount importance. The quality of software is intricately connected to the underlying architecture. It is recognized that it is not possible to measure the quality attributes of the final system based on the software architecture design alone, because the software architecture of a system is defined as the “meta-structure“, “which comprise software components, the externally visible properties of those components, and the relationship among them”. This definition focuses only on the internal aspects of the system. In the current work, analysis models such as SAAM (Software Architecture Analysis Method), SAAMCS (Software Architecture Analysis Method Founded on complex Scenario), ESAAMI (Extending SAAM by Integration in the Domain), SAAMER (Software Architecture Analysis Method for Evoluation and Reusability), ATAM (Architecture Trade-Off Analysis Method), SBAR (Scenario-Based Architecture Reengineering), ALPSM (Architecture Level Prediction of Software Maintenance), and SAEM (Software Architecture Evaluation Model) were considered. The Architecture Trade-Off Analysis Method (ATAM) was found the best among them for evaluating the software quality attributes. But, it suffers from inherent drawbacks in terms of cost, quality attributes and business focus. A software architecture analysis model is being presented which will overcome the drawbacks in ATAM by using various innovative patterns like Subtraction pattern, Multiplication pattern, Division pattern, Task Unification pattern and Attribute dependency change pattern. The various innovative patterns were applied to a case study and their results are discussed.

Abstract

With growing integration density and shrinking feature size in the deep sub-micrometer (DSM) technologies, on-chip buses plays an important role in overall performance of the system. Due to a large buses and deep sub-micron effects where coupling capacitance between bus lines are in the same order of magnitude as base capacitance, power consumption of interconnects starts to have a significant impact on a system’s total power consumption. In many digital processors, the power dissipation on the buses is a major part of the total chip power dissipation. For CMOS circuits most power is dissipated as a dynamic power for charging and discharging node capacitances. Coupling transitions contribute to significant energy loss in deep sub-micron data buses. Earlier schemes using the switching activity are not valid in these buses which takes account only substrate capacitance. Hence a new low coupling transition bus encoding scheme is proposed which can reduce the power consumption in   on-chip data buses by reducing the coupling transitions. The proposed technique can able to reduce the coupling transition by 41% to 44% and its efficiency is 1% to 18% more compare with others encoding techniques.

Abstract

Segmentation is an important phase towards designing an optical character recognition system. Most of the segmentation algorithms primarily aim at segmenting text, graphics, page, line and word. It is a critical step as most recognition errors occur due to incorrect segmentation of characters. Character segmentation is the fundamental process in character recognition approaches, which rely on isolated characters. The accuracy of the text recognition system heavily depends on character segmentation.  All the techniques that already exist do not work well when the document contains distorted characters. Special care on “Matra” is needed to segment distorted characters. In this paper, we have empirically implemented algorithms for solving the key problems of distorted characters segmentation. Experimental results show that the proposed technique is accurate, easy for extension, and may be very effective for non-headline based complex Indic scripts.