http://localhost:80/xmlui/handle/123456789/17409 2026-03-06T04:25:30Z http://localhost:80/xmlui/handle/123456789/19033 Title: AUTOMATED DETECTION OF EARLY TROPICAL CYCLONES FORMATION IN SATELLITE IMAGES Authors: I.S. Bajwa; M.N. Asghar; M.A. Naeem Abstract: The satellite imagery based weather predictions especially identification and classification of pressure zones that leads to formation of tropical cyclones was the objective of this paper. The presented approach was based on Principal Component Analysis (PCA) algorithm and Markov Logic Networks (MLN) for identification of pressure zones where PCA was used to extract features and Markov Logic for classification purposes. The system worked in two phases: Firstly, National Oceanic and Atmospheric Administration (NOAA) satellite images which were used to train the system and in training phase, an image space was generated on the basis of the spatial features of the input images. The results of the experiments showed that Markov Logic improved the accuracy of low level clouds by 8% and for high level clouds 12% classification of pressure zones in NOAA satellite images. 2017-12-14T00:00:00Z http://localhost:80/xmlui/handle/123456789/19032 Title: TOWARDS AN EFFICIENT PARALLEL BINARY SEARCH TREE USING LOCK-FREE INSERTION Authors: A.M. Dogar; M.A. Khan Abstract: Binary Search Tree (BST) was widely used in a large number of applications in order to search data in an efficient manner. On the modern multi-core systems, the implementation of parallel Binary Search Tree (BST) was unable to achieve maximum performance due to a high cost of locking mechanism, which was inevitable since the deployment of multiple parallel threads require locks to be implemented. This paper proposed a parallel lock-free BST which allowed for parallel insertion of data. Our proposed approach used atomic instructions like Compare, Swap, Fetch and Add to implement mutual exclusion and lock avoidance. The proposed implementation outperformed the sequential and the existing lock-based parallel binary search tree implementation. The proposed mplementation of the parallel BST was evaluated on different platforms like Intel Xeon and Intel Core i5 processor based systems. The proposed approach achieved up to 12% performance improvement over the parallel lock-based implementation. 2017-12-13T00:00:00Z http://localhost:80/xmlui/handle/123456789/19031 Title: HYBRID JAVA PARALLELIZER: A FRAMEWORK FOR PARALLELIZATION OF JAVA CODE Authors: A. Iqbal; M.A. Khan Abstract: An enormous effort had been placed for converting sequential code to parallel in an automated way. In this regard, the frameworks like JOMP and JaMP, were proposed to facilitate Java programmers for parallelization of code. However, the programmer was still bound to provide directives to the compiler about possibly parallel portion of code and architectural specification in some predefined format. Moreover, these frameworks required source code as input, thereby constraining performance improvement subject to the availability of the source code. This paper proposed a framework called Hybrid Java Parallelizer (HJP) which was aimed at performance improvement through parallelization of Java code. It did not require source code for parallelization and was able to create threads according to the available cores. Experimentation was performed on the well-known matrix multiplication benchmark. Results showed that HJP achieved average speed-ups of 6.99, 3.54, and 6.98 times on machines having Intel Corei7, Core i5, and Xeon based processors, respectively. 2017-12-12T00:00:00Z http://localhost:80/xmlui/handle/123456789/19030 Title: AN ENHANCED ALGORITHM FOR OPTIMAL CATHETERSELECTION DURING CORONARY ANGIOGRAPHY Authors: A. Khalil; S.U. Rahman; F. Alam; H. Khalil; K. Gulati Abstract: Image processing based catheter selection is an advanced technique in which three dimensional (3D) curve of the coronary arteries and aorta were projected on a two dimensional (2D) plane and the parameters were estimeted. During the projection of 3D curve to 2D plane there was information loss which affected the final results. In present study, an algorithm for selecting an optimal plane which reduced the information loss during the projection phase was suggested. The proposed method was evaluated on the ground truth and the obtained intraclass correlation coefficients and their 95% confidence intervals had the confidence limit between 0.996 –1.00. The results showed that the proposed method minimized information loss during projection. It minimized mean error in angle calculation to 2% as compared to the existing algorithm that had 6% error rate. The proposed method was time efficient and it estimated the parameters from the patient image data on optimal plane 2017-12-11T00:00:00Z