Epidemics control is a continues struggle. In this paper is an attempt to model and then simulate an epidemiological disease known as Cutaneous Leishmaniasis (CL), which is currently affecting large communities in Libya. The model is developed to facilitate the Agent Based Models (ABM) as one of the many tools applied for epidemiological management. Validation of the model is considered by comparing the model's behavior with a trend of field data used by Libyan authorities. The methodology used for describing and designing CL model is derived from nature of the disease mechanisms. The ABM model involves three types of agents: Human, Rodent and Sand-fly. Each agent has its own properties. Additionally, global model parameters are used for following the human infection processes. Several experiments are given for illustrating the model performance, and monitor the number of people infected. Simulation results show that active human agents are more vulnerable to sand-fly bites, and infection rate is increasing or decreasing dependent on number of sand-fly vectors, number of host rodents, and human population awareness level. arabic 9 English 68
Rudwan A. Husain, Hala Shaari, Marwa Solla, Hassan A. H. Ebrahem(3-2019)

Agent-Based Models (ABM) have become popular as tools for epidemiological simulations due to their ability to model real life phenomena at individual entity levels. ABM is a relatively new area for modelling as compared to the classical modelling methods. Many different fields use agentbased models including ecology, demography, geography, political science and epidemiology. Recently, an abundance of literature has presented applications of agent-based modeling in the biological systems. In this paper, the authors present an agent-based model attempts to simulate an epidemiological disease known as Cutaneous Leishmaniasis (CL). The model is developed to investigate the ability of ABM in modelling a disease that keeps speeding in Libya. The methodology used for describing and designing CL model is derived from nature of the disease mechanism. The ABM model involves three types of agents: Human, Rodent and Sand-fly. Each agent has its own properties, in addition to other global parameters which affect the human infection processes. The main parameter used for monitoring the model's performance is the number of people infected. The model experiments are designed to investigate ABM’s performance in modeling CL disease. Simulation results show that human infection rate is increasing or decreasing dependent on number of sand-fly vectors, number of host rodents, and human population awareness level arabic 7 English 62
Rudwan A. Husain, Hala Shaar, Marwa Solla, Hassan A. H. Ebrahem(3-2019)

Antipersonnel landmines represent a very serious hazard endangering the lives of many people living in armed conflict counties. The huge number of human lives lost due to this phenomenon has been a strong motivation for this research. Deep Learning (DL) is considered a very useful tool in object detection, image classification, face recognition and other computer vision activities. This paper focuses on DL for the problem of landmines recognition in order to identify its type based on shape features. This research work consists of several stages: gathering a new dataset of Anti-Personnel Mines (APMs) images for training and testing purposes, employing several augmentation strategies to boost the diversity of training data, applying four different Convolutional Neural Network (CNN) models namely VGG, ResNet, MiniGoogleNet and MobileNet, and evaluating their performances on APMs recognition. In conclusion, results indicate that MiniGoogleNet exceed all of other three models in recognizing APMs with the highest accuracy rate of 97%. arabic 9 English 69
Hassan Ali Hassan Ebrahem, Abdelhamid Elwaer, Marwa Solla, Fatima Ben Lashihar, Hala Shaari, Rudwan A. Husain(7-2021)

Antipersonnel landmines represent a very serious hazard endangering the lives of many people living in armed conflict counties. The huge number of human lives lost due to this phenomenon has been a strong motivation for this research. Deep Learning (DL) is considered a very useful tool in object detection, image classification, face recognition and other computer vision activities. This paper focuses on DL for the problem of landmines recognition in order to identify its type based on shape features. This research work consists of several stages: gathering a new dataset of Anti-Personnel Mines (APMs) images for training and testing purposes, employing several augmentation strategies to boost the diversity of training data, applying four different Convolutional Neural Network (CNN) models namely VGG, ResNet, MiniGoogleNet and MobileNet, and evaluating their performances on APMs recognition. In conclusion, results indicate that MiniGoogleNet exceed all of other three models in recognizing APMs with the highest accuracy rate of 97%.
Hassan Ali Hassan Ebrahem, Abdelhamid Elwaer, Marwa Solla, Fatima Ben Lashihar, Hala Shaari, Rudwan A. Husain(7-2021)