Search

Your search keyword '"Toma, Anas"' showing total 24 results
Start Over Author "Toma, Anas"
24 results on '"Toma, Anas"'

1. A Cloud-based Deep Learning Framework for Early Detection of Pushing at Crowded Event Entrances

Author

Alia, Ahmed, Maree, Mohammed, Chraibi, Mohcine, Toma, Anas, and Seyfried, Armin

Subjects
Computer Science - Machine Learning, Computer Science - Computer Vision and Pattern Recognition
Abstract

Crowding at the entrances of large events may lead to critical and life-threatening situations, particularly when people start pushing each other to reach the event faster. Automatic and timely identification of pushing behavior would help organizers and security forces to intervene early and mitigate dangerous situations. In this paper, we propose a cloud-based deep learning framework for automatic early detection of pushing in crowded event entrances. The proposed framework initially modifies and trains the EfficientNetV2B0 Convolutional Neural Network model. Subsequently, it integrates the adapted model with an accurate and fast pre-trained deep optical flow model with the color wheel method to analyze video streams and identify pushing patches in real-time. Moreover, the framework uses live capturing technology and a cloud-based environment to collect video streams of crowds in real-time and provide early-stage results. A novel dataset is generated based on five real-world experiments and their associated ground truth data to train the adapted EfficientNetV2B0 model. The experimental setups simulated a crowded event entrance, while the ground truths for each video experiment was generated manually by social psychologists. Several experiments on the videos and the generated dataset are carried out to evaluate the accuracy and annotation delay time of the proposed framework. The experimental results show that the proposed framework identified pushing behaviors with an accuracy rate of 87% within a reasonable delay time.

Published
2023
Full Text
View/download PDF

2. Computation Offloading for Frame-Based Real-Time Tasks under Given Server Response Time Guarantees

Author

Toma, Anas S. M. and Chen, Jian-Jia

Subjects
computation offloading, task scheduling, real-time systems, Technology, Electrical engineering. Electronics. Nuclear engineering, TK1-9971, Electronics, TK7800-8360
Abstract

Computation offloading has been adopted to improve the performance of embedded systems by offloading the computation of some tasks, especially computation-intensive tasks, to servers or clouds. This paper explores computation offloading for real-time tasks in embedded systems, provided given response time guarantees from the servers, to decide which tasks should be offloaded to get the results in time. We consider frame-based real-time tasks with the same period and relative deadline. When the execution order of the tasks is given, the problem can be solved in linear time. However, when the execution order is not specified, we prove that the problem is NP-complete. We develop a pseudo-polynomial-time algorithm for deriving feasible schedules, if they exist. An approximation scheme is also developed to trade the error made from the algorithm and the complexity. Our algorithms are extended to minimize the period/relative deadline of the tasks for performance maximization. The algorithms are evaluated with a case study for a surveillance system and synthesized benchmarks.

Published
2014
Full Text
View/download PDF

7. A cloud-based deep learning system for improving crowd safety at event entrances

Author

Alia, Ahmed, Maree, Mohammed, Chraibi, Mohcine, Toma, Anas, and Seyfried, Armin

Subjects
Computer and information sciences [FOS], Computer Vision and Pattern Recognition (cs.CV), Machine Learning (cs.LG)
Abstract

Crowding at the entrances of large events may lead to critical and life-threatening situations, particularly when people start pushing each other to reach the event faster. A system for automatic and timely identification of pushing behavior would help organizers and security forces to intervene early and mitigate dangerous situations. In this paper, we propose a cloud-based deep learning system for early detection of pushing automatically in the live video stream of crowded event entrances. The proposed system relies mainly on two models: a pre-trained deep optical flow and an adapted version of the EfficientNetV2B0 classifier. The optical flow model extracts the characteristics of the crowd motion in the live video stream, while the classifier analyses the crowd motion and annotates pushing patches in the live stream. A novel dataset is generated based on five real-world experiments and their associated ground truth data to train the adapted EfficientNetV2B0 model. The experimental situations simulated a crowded event entrance, and social psychologists manually created the ground truths for each video experiment. Several experiments on the videos and the generated dataset are carried out to evaluate the accuracy and annotation delay time of the proposed system. Furthermore, the experts manually revised the annotation results of the system. Findings indicate that the system identified pushing behaviors with an accuracy rate of 89% within an acceptable delay time.

Published
2023

10. Covid-19 severity and urban factors: investigation and recommendations based on machine learning techniques.

Author

Qanazi, Saleh, Hijazi, Ihab, Toma, Anas, Abujayyab, Sohaib, Dehbi, Youness, Zabadae, Shaker, and Xin Lif

Subjects
COVID-19 pandemic, MACHINE learning, SPATIAL analysis (Statistics), GEOGRAPHIC information systems, REGRESSION analysis
Abstract

Since March 5, 2020, the West Bank has faced a real crisis due to the Coronavirus disease 2019 (COVID-19) pandemic. It has infected 581,678 people and caused 5,382 deaths so far, which has resulted in negative impacts on public health and other aspects of daily life. Based on the data provided by the Palestinian Ministry of Health, we inferred the spatial distribution patterns of the pandemic condition in different communities using Geographic Information System (GIS) analysis for pattern and clustering by studying the impact of urban factors on the number of confirmed COVID-19 cases. Ten urban factors were selected (i.e., population, population density, aging ratio, the hierarchy of services, health services, land use, commercial services, road density, green areas, and open spaces) to check their relation to pandemic severity using a linear model, where five factors showed a globally-significant relation. Then, the Geographically Weighted Regression' model (GWR) was adopted to define their unevenly distributed effects in the urban areas on the northwest bank. Among the five factors, the population factor has the most significant impact on the epidemic situation with a positive correlation. However, a negative correlation has been stated between the area of commercial services per person, population density, hierarchy of services, and health services. Finally, we provide recommendations that coordinate various urban factors to mitigate the pandemic spread. This paper will help decision-makers plan and develop different areas in Palestine and worldwide by better understanding the transmission, occurrence, and diffusion of the COVID-19 pandemic in urban areas. [ABSTRACT FROM AUTHOR]

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results