Marwa Khamis Elteir

Dr. Marwa Khamis Elteir


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 December 2007
Verified
Conference Paper
Closed access
SLShaimaa Lazem
Shaimaa Lazem
MEMarwa Khamis Elteir
Marwa Khamis Elteir
AAAyman A. Abdel-Hamid
Ayman A. Abdel-Hamid
Denis GracaninDenis Gracanin
Denis Gracanin
Remote Image-based rendering (IBR) is an effective solution for rendering complex 3D scenes on mobile devices. A server renders the 3D scene and streams the rendered images to the client. However, sending a large number of images is inefficient due to the possible bandwidth limitations of wireless connections. In this paper, we propose a server-side prefetching scheme that predicts client movements and hence prefetches the corresponding images. In addition, an event driven simulator was designed and implemented to evaluate the performance of the proposed scheme. The simulator was used to compare between prediction-based prefetching and prefetching images based on spatial locality. Several experiments were conducted to study the performance using different movement patterns and different virtual environments (VEs). The results have shown that the hit ratio of the prediction-based scheme is greater than the localization scheme in the case of random and circular walk movement patterns by approximately 35% and 17%, respectively. For a VE with high level of details, the proposed scheme outperforms the localization scheme by approximately 13%. However, for a VE with low level of details, the localization based scheme outperforms the proposed scheme by only 5%.

8 January 2025 in Discover Applied Sciences
Verified
Journal Article
Open access
PDF file
MEMarwa Khamis Elteir
Marwa Khamis Elteir
An effective Twitter-based surveillance system should provide insights at national and subnational levels. The literature identifies two methodologies for geolocating tweets: using only geotagged tweets or retrieving and geolocating all relevant tweets, then filtering out those not belonging to the target geographical region. The first methodology is accurate, cost-effective, and time-efficient but has limited coverage. The second offers better coverage but is less accurate, particularly for informal Arabic text, and is neither cost-effective nor time-efficient due to Twitter’s new policies. There is a gap in the literature for an accurate, cost-effective, and time-efficient solution with reasonable coverage at national and subnational levels. To fill this gap, we propose a methodology that uses an underutilized feature in the Twitter backend to geolocate tweets during data collection. This retrieves both geotagged and geolocated tweets, ensuring accuracy and better coverage. It is also cost-effective and time-efficient as only the target tweets are retrieved. Applying this to Saudi Arabia for COVID-19, we generated a dataset, KSAGeoCOV, with 4.25 times more tweets than a geotagged-only dataset. It successfully predicted two COVID-19 outbreaks in June 2021 and January 2022. The Pearson correlation coefficient between WHO weekly reported cases and weekly returned tweets, with a 1-week lag, is \(r = 0.733;\,p < 0.001\) for Arabic tweets and \(r = 0.814;\,p < 0.001\) when including English tweets, indicating a very strong correlation at the national level. At the subnational level, top-populated provinces show strong correlations (\(r = 0.64\) to \(0.74;\,p < 0.003\)).

18 January 2025 in Information
Verified
Journal Article
Open access
PDF file
MEMarwa Khamis Elteir
Marwa Khamis Elteir
Leveraging Twitter data for crisis management necessitates the accurate, fine-grained geolocation of tweets, which unfortunately is often lacking, with only 1–3% of tweets being geolocated. This work addresses the understudied problem of fine-grained geolocation prediction for Arabic tweets, focusing on the Kingdom of Saudi Arabia. The goal is to accurately assign tweets to one of thirteen provinces. Existing approaches for Arabic geolocation are limited in accuracy and often rely on basic machine learning techniques. Additionally, advancements in tweet geolocation for other languages often rely on distinct datasets, hindering direct comparisons and assessments of their relative performance on Arabic datasets. To bridge this gap, we investigate eight advanced deep learning techniques, including two Arabic pretrained language models (PLMs) on one constructed dataset. Through a comprehensive analysis, we assess the strengths and weaknesses of each technique for fine-grained Arabic tweet geolocation. Despite the success of PLMs in various tasks, our results demonstrate that a combination of Convolution Neural Network (CNN) and Long Short-Term Memory (LSTM) layers yields the best performance, achieving a test accuracy of 93.85%.

26 March 2018 in Current Bioinformatics
Verified
Journal Article
Closed access
MEMarwa Khamis Elteir
Marwa Khamis Elteir
SRShaheera A. Rashwan
Shaheera A. Rashwan
AKAshraf A. Khalil
Ashraf A. Khalil
Proteomics was built around two-dimensional (2D) gel electrophoresis. Accurately analyzing the images generated from 2D gel electrophoresis for spot detection is a timeconsuming process especially for high-resolution and large images. In this paper, we present an accurate GPU-accelerated software tool for the detection and quantification of protein spots in 2D gel electrophoresis images. We adopt pixel-based approach that employs wavelet relational fuzzy C-means clustering and distance transform to detect and quantify the protein spots. This approach is proved to exhibit better spot detection in quantitative comparisons with the commercial software tools. Specifically, it achieves a degree of improvement in F-measure of 21.237% and 11.716% on the average compared to Delta2D and Melanie respectively. This pixel-based spot detection approach is more accurate than the contour-based approaches; however it is compute-intensive. So, along with algorithmic optimizations, we present the mapping and optimization of the pixel-based spot detection algorithm onto graphics processing units (GPUs); including NVIDIA and AMD GPUs. We carry out experiments on images of large size and high resolution for healthy and diseased samples. Our implementation has accomplished up to five orders of magnitude speedup compared to the single-threaded MATLAB implementation.