Free space optical (FSO) communication is a promising solution to deliver the last mile communication and to guarantee a high data rate. However, the performance of FSO links can be significantly degraded by adverse weather conditions. Recently, machine learning algorithms (MLAs) have emerged for robust prediction to optimize the network performance. In this work, the Quality factor (Q) of FSO systems is estimated by means of four MLA models, namely, multi-linear regression, support vector regression, decision tree regression, and random forest regression. The synthetic data is used for training and testing these MLAs models, and several atmosphere conditions are considered with multiple transceivers FSO link system. The results of decision tree and random forest models demonstrated high coefficient of determination (R 2 ) and low mean square error (MSE) as compared to the other models.
Amal A. Algedir, Taissir Y. Elganimi(10-2020)

يمر العالم بمرحلة انتقالية تموج بتحولات جذرية عميقة وشاملة في كافة المجالات، مرحلة تنكسر فيھا القيود وتلغى الحدود وتنفتح الأسواق ، وتشتعل المنافسة، ويتعاظم دور التكنولوجيا الحديثة التي تلعب دوراً رئيسا ً في إحداث ھذه التحولات وأھمھا التحول من الأساليب التقليدية في الإدارة إلى الأساليب الإلكترونية، وبات مصطلح الحكومة الإلكترونية ھو عنصر تميز المؤسسات والهيئات والدول. يسعى هذا البحت إلى إتاحة المحتوى العلمي للإدارة الإلكترونية وذلك من خلال سرد لمحة تاريخية عنها ومميزاتها وسبيل الإستفادة منها بجميع المجالات وخاصة بمجال التعليم والتطرق الي جامعة طرابلس كحالة دراسية.
وائل صالح محمد أبوغريس, عطية محمود البحباح, محمد أحمد مغيدر(6-2022)

The introduction of new services with different bandwidth requirements, e.g., data and multimedia, to cellular mobile radio networks makes many of the traditional mechanisms unusable or less efficient. The call admission control and the handover handling are the most sensitive issues to this extension. The performance of all services including the traditional voice and the new services can be dramatically effected if no appropriate schemes are used. In this research work, a new call admission and handover handling schemes for a cellular mobile network that offers two service types: voice and data is proposed. The data connections are assumed to be transmitted at different data rates, which are an integer multiple to that of one traffic channels, which are full speed(Cd1) & reduced peed(Cd2). In order to reduce the handover failure probability of data connections, the data mobile terminals (MT) are assumed to have the capability of transmitting at two different data rates. If the handover request can not be satisfied by the base station of the destination cell due to unavailable free traffic channels, the data mobile terminals tries with a lower data rate. The handover fails if the network is incapable on providing the minimum data rate at which the mobile terminal can transmit. The reduced data connection or data rate can be speeded up to full data rate or full speed as soon as enough bandwidth is available. The effect of different traffic and configuration parameters on the performance of the different models for two cell model with equal input traffic intensity, two cell model with different input traffic intensity, and two cell model with equal input traffic intensity considering the congestion rate for the highway model are studied as the models of this research. These models are built using MOSEL language (Modeling Specification and Evaluation Language). The results of investigating the mentioned models showed the effect of the handover, and speed of data on these different models.
W. ABUGHRES(1-2000)