Design and Evaluation of Parallel Processing Techniques for 3D Liver Segmentation and Volume Rendering
Ensuring Software Quality in Engineering Environments
New 3D Face Matching Technique for an Automatic 3D Model Based Face Recognition System
Algorithmic Cost Modeling: Statistical Software Engineering Approach
Prevention of DDoS and SQL Injection Attack By Prepared Statement and IP Blocking
Nowadays, the analysis of social sites, such as movie reviews’ sites, facebook, news feeds, and online shopping sites has been a broad area of research and customers post a large number of reviews in the form of comments to reveal their feelings as well as opinions as positive, negative, or neutral about a particular movie, product, pictures etc. To predict the reviews of users of such websites is a complex decision making process. These types of sites help the people to take decision about products. This paper proposes a Random Forest classifier with Information Gain based feature selection method for classification of movie review datasets. The results show that Information Gain method with Random Forest classifier has better performance in terms of Accuracy, Precision, and Recall.
The Internet of Things (IoT) is an internetworking of physical devices, vehicles, buildings, and other items- embedded with electronics, software, sensors, and network connectivity that enables these objects to collect and exchange data. Civil habitation in the near future will move to large urban areas thus forming vast cities. These cities will incorporate IoT components in their backbone infrastructure, thus transforming into smart cities. One major component of smart cities is smart environment, a countermeasure for growing pollution. Waste management can be treated as a potential IoT service which exploits robustness and efficiency. IoT provides a novel solution for waste collection service. This paper presents one such solution. Smart bins are designed. These are incorporated with hardware containing microcontroller, sensor and GSM modem. The sensors will sense the level of bin filled and send its status to the server via GSM. At the server application, bin status along with its number and area will be displayed. The server will then notify ward member, driver or officer about bin status through a text message. Also an android application is developed for driver and officer to supervise their respective works and enable remote system handling.
The main objective of this paper is to simulate scientific calculator using NI LabVIEW software, a graphical programming language to automate the calculation procedure making less paper work for problem solving. In this work, the authors build logics by wiring icons in block diagram which is a graphical source code instead of line of text and the front panel acts as a user interface of the VI to create fully featured scientific calculator. It enables execution highlighting on block diagram and makes the flow of data visible at run-time engine and real-time operating system. This software enables the user to correct the errors with an indication of broken arrow (Run button) on the pull down menu.
In this paper, an unsupervised change detection technique of multispectral images based on Non-Subsampled Contourlet Transform (NSCT) has been proposed. The proposed method fuses absolute difference and change vector analysis image using fusion rules. A fuzzy local-information C- means clustering algorithm will be proposed for classifying changed and unchanged regions in the fused difference image. The differencing, changes are measured by subtracting the intensity values pixel by pixel between the considered couple of temporal images. In the case of SAR images, the ratio operator is typically used instead of the subtraction operator since the image differencing technique is not adapted to the statistics of SAR images. The results will be proven that rationing generates better difference image for change detection using spatial fuzzy clustering approach and efficiency of this algorithm will be exhibited by sensitivity and correlation evaluation.
Placing a set of activities or jobs along a timeline is known as scheduling. The interval scheduling problem arises when each job is specified by an interval with starting and finishing times of each job. It will become a weighted interval scheduling problem when a weight or a value is associated with each job. In this paper, the aim is to maximize the total weight of the jobs that could be scheduled without overlapping. A fast algorithm is presented to solve this problem. An upper bound for the total weight is computed and it is shown that the gap between the solutions to the test problems and the upper bound is extremely small.
