Tarik Elamsy - Academia.edu (original) (raw)

Papers by Tarik Elamsy

2022 International Arab Conference on Information Technology (ACIT)

2021 Eighth International Conference on Social Network Analysis, Management and Security (SNAMS), 2021

Entity resolution (ER) aims at identifying and merging records in one or more datasets that refer... more Entity resolution (ER) aims at identifying and merging records in one or more datasets that refer to the same real-world entity. The ER problem is becoming more challenging in the context of Big Data. We study the ER problem by transforming it into a Social Network where data records can be treated as real-world entities capturing the existing relationships (e.g. friendship, householder). A framework to handle the transformation of the data model is presented and evaluated on several datasets. The framework is tested using four state-of-the-art ER, including (1) k-mean, (2) Levenshtein, (3) Jaro Winkler, and (4) Soundex on SNA in terms of time and accuracy performance metrics.

2021 8th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2021

This study describes the effectiveness of applying a Fuzzy controller into the renewable energy s... more This study describes the effectiveness of applying a Fuzzy controller into the renewable energy storage system for better efficiency. Different small-size power generators need to be initially started up in order to fulfil the demand for power at the rush hours.V2G (Vehicle to Grid) technology is an interface of the bi-directional electrical grid which allows electric vehicles for taking energy from the mesh. The calculation for the power requirement of the battery is initiated for identifying the charging load. Power management for the EVs, information technology plays a vital role in the V2G framework. The delivery of power requests to the aggregate of EVs through the aggregator is done with the help of sending a signal from the RTO/ISO. Load is generated with the help of huge as well as continuously running units of power generation and gradable EVs. In V2Goptimization, lowering the overall operational cost for supply of power by the wind power as well as by the grid are the major areas of focusing.

2021 8th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2021

Car driving in off-road areas and the deserts, in particular, is a challenging task. In such a ha... more Car driving in off-road areas and the deserts, in particular, is a challenging task. In such a harsh environment, drivers need to move while avoiding getting stuck in the sand or rolled upside down. In UAE, with its vast desert, this is a daily challenge for oil companies who operate in inland oil exploring, organizers of safari tours, and the border guards. This paper introduces an intelligent route finder for UAE desert driver based on A* Algorithm (IRF) framework as a route guidance tool for off-road driving. The goal is to find the shortest and safest path to the destination. The IRF combines Artificial Intelligence (AI) pathfinding algorithms and Geographic Information Systems (GIS), such as the Digital Terrain Model (DTM) and Surface Type, to enhance pathfinding decisions. We model and combine this information to improve cost estimation in the A* artificial intelligence searching algorithm. Drivers can use the developed software to predict the safest optimal route to help navigate more safely in the sandy desert and save time.

Innovative Computing Information and Control Express Letters, Part B: Applications, 2019

Advances in Intelligent Systems and Computing, 2018

In UAE, environmental issues are considered as very crucial at all levels. This study attempts to... more In UAE, environmental issues are considered as very crucial at all levels. This study attempts to analyze the current data available on the Ozone Layer in UAE via different data mining techniques. The study aims at giving a general idea about the Ozone Layer in UAE and generates some general rules that will help maintaining the future of Ground Ozone (O 3) Level. Such understanding can support decision makers take action at the right time. The results produced from some well-known classification algorithm show that Sharjah has a sign of 'Low Pollution' in general. Also, the high temperature in summer may cause some problems in the reading which can be addressed in the near future.

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015

Automatic license plate recognition (ALPR) is the process of locating and extracting vehicles pla... more Automatic license plate recognition (ALPR) is the process of locating and extracting vehicles plate information from images or videos. The extracted information is essential for several everyday applications, ranging from automated payment services (e.g. parking and toll roads payment collection) to more critical applications, like border crossing security and traffic surveillance systems. Various solutions have been proposed for the ALPR problem, with many available commercial packages. However, amid plate variations from place to place, ALPR systems tend to be region-specific. There is no general solution that works effectively everywhere for every province/state or country. In this paper, we have reviewed a set of state-of-the-art ALPR methods and, compared their respective performances by testing them on a rich database of vehicles from Ontario (Canada).

Communications in Computer and Information Science, 2019

We propose in this work a practical method to compute the Euclidean (metric) 3D reconstruction of... more We propose in this work a practical method to compute the Euclidean (metric) 3D reconstruction of a scene, observed by a stereo pair of static, off-the-shelf, zooming cameras. The proposed method does not assume any form of explicit, pattern-based, calibration. The stereo system acquires a set of pairs of images, at different zooming levels, making it possible to obtain an affine calibration. The latter is obtained by taking advantage of the translation motion of the principal plane of each zooming camera. In particular, each pair of zoom images provides a pair of parallel planes that intersect at infinity. This makes it possible to estimate the principal point of each camera. Finally, a 3D metric reconstruction is calculated. Extensive experiments on both indoor and outdoor images have demonstrated the viability and accuracy of the proposed method.

2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA), 2019

Detecting DeepFake videos are one of the challenges in digital media forensics. This paper propos... more Detecting DeepFake videos are one of the challenges in digital media forensics. This paper proposes a method to detect deepfake videos using Support Vector Machine (SVM) regression. The SVM classifier can be trained with feature points extracted using one of the different feature-point detectors such as HOG, ORB, BRISK, KAZE, SURF, and FAST algorithms. A comprehensive test of the proposed method is conducted using a dataset of original and fake videos from the literature. Different feature point detectors are tested. The result shows that the proposed method of using feature-detector-descriptors for training the SVM can be effectively used to detect false videos.

Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2020

The novel coronavirus (COVID-19) pandemic is spreading across the globe at an alarming rate causi... more The novel coronavirus (COVID-19) pandemic is spreading across the globe at an alarming rate causing more infections and deaths in comparison to SARS or MERS. In the absence of specific vaccines for theCOVID-19, the early diagnosis of COVID-19 disease is crucial for disease treatment and control. Recent researches have shown that Medical Radiology imaging may be a more reliable, practical, and rapid method to diagnose and assess COVID-19 in comparison to the official laboratory RT-PCR tests, especially with the lack of medical professionals. In this article, we investigate the aid of Artificial Intelligence and Data Mining techniques to automate the task of diagnosing COVID-19 from Chest X-Rays medical images. The results obtained are promising and are better than previous results published earlier.

This dissertation proposes new algorithms to recover the calibration parameters and 3D structure ... more This dissertation proposes new algorithms to recover the calibration parameters and 3D structure of a scene, using 2D images taken by uncalibrated stationary zooming cameras. This is a common configuration, usually encountered in surveillance camera networks, stereo camera systems, and event monitoring vision systems. This problem is known as camera auto-calibration (also called self-calibration) and the motivation behind this work is to obtain the Euclidean three-dimensional reconstruction and metric measurements of the scene, using only the captured images. Under this configuration, the problem of auto-calibrating zooming cameras differs from the classical auto-calibration problem of a moving camera in two major aspects. First, the camera intrinsic parameters are changing due to zooming. Second, because cameras are stationary in our case, using classical motion constraints, such as a pure translation for example, is not possible. In order to simplify the non-linear complexity of this problem, i.e., auto-calibration of zooming cameras, we have followed a geometric stratification approach. In particular, we have taken advantage of the movement of the camera center, that results from the zooming process, to locate the plane at infinity and, consequently to obtain an affine reconstruction. Then, using the assumption that typical cameras have rectangular or square pixels, the calculation of the camera intrinsic parameters have become possible, leading to the recovery of the Euclidean 3D structure. Being linear, the proposed algorithms were easily extended to the case of an arbitrary number of images and cameras. Furthermore, we have devised a sufficient constraint for detecting scene parallel planes, a useful information for solving other computer vision problems. v Dedication To my beloved wife Rana and sons.... vi Acknowledgement Though only my name is printed on the title page of this dissertation, this work would not have been possible without the help of many individuals who in one way or another contributed in the completion of this work. First and foremost, I would like to express my heartfelt gratitude to my family. For my parents who planted the love of science in my heart and supported me in all my pursuits. And most of all for my loving, supportive, encouraging, and patient wife Rana to whom this dissertation is dedicated to. Her faithful support during the years of this Ph.D. is so appreciated. My deepest and utmost gratitude is to my advisor Dr. Boubakeur whom it has been an honor for me to be his Ph.D. student. He did not save any effort in guiding and helping me throughout the years of my studies. He gave me the freedom to explore on my own, but at the same time never saved his guidance when my steps faltered. I appreciate all his contributions of time, advices, ideas, and funding to make my years of Ph.D. study productive and stimulating. The discussions that I had with Dr. Boufama helped me developing many ideas in this dissertation. However, what I learned from him is way more beyond just scientific. That is why I cannot thank you enough. I also would like to gratefully thank and acknowledge Dr. Adlan for his valuable advices and support. I am deeply obliged to him for the many hours of discussions and for helping me to sort out many technical details of my work.

2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2009

The Flooding Zone Initialization Protocol (FZIP) was proposed as a mechanism to provide power eff... more The Flooding Zone Initialization Protocol (FZIP) was proposed as a mechanism to provide power efficient flooding for real-time multimedia data over Wireless Sensor Networks (WSNs). FZIP can initialize different FZ sizes with different performance levels (i.e. loss rate, latency, and overhead). Increasing the FZ size increases redundancy which in turn reduces packet loss but consumes extra power overhead. However, how to choose a suitable FZ size poses a tradeoff between packet loss rate and power efficiency under different network sizes, densities, and radio channel conditions. The static FZ size estimation under dynamic WSNs' conditions leads to unnecessary power overhead or fail to deliver good quality resulting in high packet loss rate. In this paper, we propose the Flooding Zone Control Protocol (FZCP) to overcome this problem. FZCP monitors the incoming multimedia packets to detect performance deterioration and change the FZ size (increase/decrease) accordingly. Simulation results show that FZCP enhances the flooding performance and delivers and maintains good quality of real-time multimedia sessions with low energy overhead.

2008 IEEE Symposium on Computers and Communications, 2008

ABSTRACT Flooding protocols have shown to be failure resilient and robust in transporting data ov... more ABSTRACT Flooding protocols have shown to be failure resilient and robust in transporting data over multi-hop wireless networks, e.g. wireless sensor networks and ad hoc networks. However, flooding protocols are considered to be less efficient in power consumption compared to unicast based protocols. In this paper, we present our Flooding Zone Initialization Protocol (FZIP) which constrains the flooding storm in a carefully selected set of intermediate nodes between the session endpoints. The use of flooding protocols in the constructed zone reduces power expenditure as well as packet loss compared to unrestricted flooding zone. We validate FZIP for diffusing multimedia flows using the NS2 simulator in comparison with flooding without FZIP and using end-to-end UDP. FZIP shows better results in terms of packet delivery and power consumption, especially in large scale multi-hop scenarios with high error rates.

2013 International Conference on Computer and Robot Vision, 2013

ABSTRACT This paper proposes a new method for the automatic identification of parallel planes for... more ABSTRACT This paper proposes a new method for the automatic identification of parallel planes form uncalibrated images of a scene. First, we demonstrate that, given a priori knowledge about a single pair of parallel planes, it is possible to identify all other parallel planes from uncalibrated images of a scene. Then, we show that a pair of parallel virtual planes can be made available when the scene is imaged by stationary non-rotating zooming cameras leading to a fully automatic identification method.Experiments with indoor and outdoor real images have validated our method.

2012 19th IEEE International Conference on Image Processing, 2012

ABSTRACT This paper presents a simple, yet effective, method to recover the affine structure of a... more ABSTRACT This paper presents a simple, yet effective, method to recover the affine structure of a scene from a (stereo) pair of stationary zooming cameras. The proposed method solely relies on point correspondences across images and no knowledge about the scene whatsoever is required. Our method exploits implicit properties of the projective camera matrices of zooming cameras and allows to estimate the affine structure of a scene by solving a linear system of equations. The 3D reconstruction results obtained by using our method, on both real and simulated data, have remarkably validated its feasibility.

Lecture Notes in Computer Science, 2011

In this paper, we propose a method that combines plane parallelism and the Mendonça/Cipolla self-... more In this paper, we propose a method that combines plane parallelism and the Mendonça/Cipolla self-calibration constraints. In our method each pair of images is treated independently and can therefore use a different pair of parallel planes not necessarily visible in the other views. While, for each pair of images, constraints on the singular values of the essential matrix provide two algebraic constraints on the intrinsic parameters, those we derive from plane parallelism have the advantage of providing two additional ones making the calibration of a no-skew camera possible from two images only.

21st International Symposium on High Performance Computing Systems and Applications (HPCS'07), 2007

Page 1. Construction of a Webportal and User Management Framework for Grid LichunZhu, Robert D. K... more Page 1. Construction of a Webportal and User Management Framework for Grid LichunZhu, Robert D. Kent, Akshai Aggarwal, Peiris Viranthi, Quazi Rahman, Tarik Elamsy, Ositadimma Ejelike School of Computer Science, University of Windsor ...

Image and Vision Computing, 2014

This paper proposes a new method for self-calibrating a set of stationary non-rotating zooming ca... more This paper proposes a new method for self-calibrating a set of stationary non-rotating zooming cameras. This is a realistic configuration, usually encountered in surveillance systems, in which each zooming camera is physically attached to a static structure (wall, ceiling, robot, or tripod). In particular, a linear, yet effective method to recover the affine structure of the observed scene from two or more such stationary zooming cameras is presented. The proposed method solely relies on point correspondences across images and no knowledge about the scene is required. Our method exploits the mostly translational displacement of the so-called principal plane of each zooming camera to estimate the location of the plane at infinity. The principal plane of a camera, at any given setting of its zoom, is encoded in its corresponding perspective projection matrix from which it can be easily extracted. As a displacement of the principal plane of a camera under the effect of zooming allows the identification of a pair of parallel planes, each zooming camera can be used to locate a line on the plane at infinity. Hence, two or more such zooming cameras in general positions allow the obtainment of an estimate of the plane at infinity making it possible, under the assumption of zero-skew and/or known aspect ratio, to linearly calculate the camera's parameters. Finally, the parameters of the camera and the coordinates of the plane at infinity are refined through a nonlinear least-squares optimization procedure. The results of our extensive experiments using both simulated and real data are also reported in this paper.

2022 International Arab Conference on Information Technology (ACIT)

2021 Eighth International Conference on Social Network Analysis, Management and Security (SNAMS), 2021

2021 8th International Conference on Internet of Things: Systems, Management and Security (IOTSMS), 2021

Innovative Computing Information and Control Express Letters, Part B: Applications, 2019

Advances in Intelligent Systems and Computing, 2018

2015 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2015

Communications in Computer and Information Science, 2019

2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA), 2019

Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics, 2020

2009 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), 2009

2008 IEEE Symposium on Computers and Communications, 2008

2013 International Conference on Computer and Robot Vision, 2013

2012 19th IEEE International Conference on Image Processing, 2012

Lecture Notes in Computer Science, 2011

21st International Symposium on High Performance Computing Systems and Applications (HPCS'07), 2007

Image and Vision Computing, 2014

2022 International Arab Conference on Information Technology (ACIT)