Abstract. One innovative initiative that shows how technology and creativity can save lives in dire circumstances is the creation of a smart autonomous drone system for Search and Rescue Operations in Libya. The Search and Rescue Drone is a ray of hope that is intended to transform rescue operations by offering a quick and effective way to find persons who are in trouble or who may have been lost in Libya's desert or Mediterranean Sea. A Raspberry Pi, a Pixhawk flying controller, the Internet of Things, and a specially created mobile application are the main parts of the study. With the help of the YOLOv4-tiny module and object detection algorithms, the system enables users to operate the drone and quickly and accurately identify those who go missing in challenging environments. By fusing technological innovation with a humanitarian goal, this paper paves the way for future search and rescue operations in Libya and other nations to be safer and more responsive. The work shows how technology can save lives in dire circumstances and serves as an example of how it can benefit humanity at its most vulnerable times.

Alzheimer's disease (AD) is a complex neurological illness that has several deep reasons. According to recent research, the use of machine learning techniques (ML) on MRI images can assist in identify the brain regions and the connections between them that are implicated in dementia. The study aims to review literature from 2017 to 2023 on the use of machine learning algorithms to identifying and categorize AD. The precision of each machine learning model is assessed, and mind map models are employed to illustrate the study and compare the outcomes.

Abstract—Fault detection and classification is critical to the reliability of modern control systems in different industries, where detecting and classifying faults in operational processes are very important things while failure to detect and classify them, may cause irreparable damage. In this paper, fault detection and classification approach is presented. The first step, multi stage recursive least squares parameter estimation approach for controlled autoregressive autoregressive moving average systems (CARARMA) is developed with a view to estimate the parameters of the system, additionally, improve the effectiveness of the computation. By means of multi stage approach, the (CARARMA) system is decomposed into three simple identification models, and the parameters of each simple model is identified one by one. These parameters estimated by this approach are referred to as features, and not all of them have the same useful data about the system. In order to select the valuable features and improve a classification accuracy, the Linear Discriminant Analysis (LDA) approach based on scattering matrices is applied for dimension reduction. The classification between these reduced classes is done based on the Naive Bayes classifier. Finally, the obtained results explain the performance of this proposed approach.

Abstract: Network operators are confronted with the demanding requirements resulting from the evolution of IP networks. As a result, it has become necessary to provide rigorous Service Level Agreements (SLAs) that are in line with these requirements. However, traditional IP networks lack the necessary flexibility, scalability, and manageability to meet these demands. In order to address these limitations, the segment routing (SR) architecture has been developed. SR is based on source-routing and tunneling paradigms, which enable IP/MPLS and IPV6 networks to operate in a simplified and more scalable manner. The focus of this paper is on network protection (resiliency) using Topology Independent Loop-Free Alternatives Fast Re-Route (TI-LFA FRR) using MPLS as the underlying technology. SR overcomes the limitations of previous network protection mechanisms in terms of coverage and optimal path selection. To show the effectiveness of SR TI-LFA in comparison to its predecessor, Remote Loop-Free Alternate (rLFA), we have implemented various scenarios. These scenarios are designed to highlight the superior capabilities of TI-LFA. 

Net Zero Energy (NZE) buildings play a crucial role in meeting the Sustainable Development Goals (SDG) and creating environmentally friendly residential areas. These buildings are designed to generate as much energy as they consume, resulting in a net balance of zero energy consumption from the grid. By integrating innovative technologies and sustainable design principles, NZE buildings minimize their carbon footprint and contribute to a more sustainable future. The acquired result has been presented and discussed. The concept of Net Zero Energy Buildings (NZEBs) has gained significant attention in recent years as a crucial strategy for achieving sustainability in the built environment. NZEBs are designed to produce as much energy as they consume, resulting in a net energy balance of zero over a specified period.

The classical Model Predictive Control (MPC) is still considered in many industrial applications, although advanced control methods have seen  significant development over the last few years. However, a lot of MPC strategies still suffer from  robustness to cope with a variety of process dynamics. For the MPC controller to work effectively,  it must be properly tuned. However, MPC is challenging and there is no ideal analytic method to  obtain exact solutions that result in the best desired responses. Based on that, this paper  investigate the robustness performance for a MPC tuning strategy. Three formulae were derived  (Proposed , Proposed  and Proposed ). These formulae are used for calculating the suppression coefficient. The three  formulae were derived by fitting the optimal empirical suppression coefficients for varies process  dynamics commonly found in industry. Simulation results show that the use of the proposed strategy results in good performance compared to other strategies previously proposed. The proposed   strategy also demonstrated a robust performance with respect to modelling errors of process  parameters. The results demonstrate the effectiveness and validity of proposed strategy when  compared with conventional strategies.

  Reservoir performance prediction is important aspect of the oil & gas field development planning and reserves estimation which depicts the behavior of the reservoir in the future. This project is conducted in order to integrated production modelling with MBAL software to define the water influx model and its properties of an aquifer for Libyan oil reservoir. The objectives of this project are to determination the PVT of oil, gas, and water. Determination drive mechanism, identification of suitable water influx model and unknown parameter calculations. Define water influx using influx model. Define properties of an aquifer. Material balance software is used as principal method in order to achieve the objectives of those objectives. Based on the Material balance software results, the main source of energy in reservoir was from Water influx, pore volume, and fluid expansion drive mechanism. At the begging, the fluid expansion is from 0 to 40 % and pore volume compressibility is from 40 % to 64 % and the water influx is from 64 % to 100%, after that we has water injection. The model for this reservoir is the Hurst-van Everding-Odeh with the system is radial aquifer. Finally, central objective of this paper with the help of reservoir simulation fulfilled to know the water influx model and its properties and to produce future prediction that will lead to optimize reservoir performance which meant reservoir developed in the manner that brings utmost benefit to the commercial business.

This paper investigates the effects of applying fuzzy techniques to artificial neural networks (ANN) for

the classification of biological data. A fuzzy neural networks (FNNs) model was proposed and evaluated

as a system for image classification. This system involved the process of collecting dataset, image

processing and image classification. Patch-based technique is used to present images to the neural

network. Feed-Forward Backpropagation neural networks are used to build the system. Fuzzy Min-Max

Neural Networks (FMNN) approach was used to synthesize Fuzzification and neural networks to generate

fuzzy neural networks that can handle imprecision and uncertainty. The approach is evaluated using

images from the data portal (Papers with Code) website. Experimental results have shown an improvement

in the performance of fuzzy neural networks compared with neural networks.

Abstract:

This paper explores the utilization of ANSYS software to replace traditional stainless steel in

Liquid Natural Gas (LNG) cylinders with a lightweight composite material called E Glass Epoxy.

The goal is to reduce the cylinder's weight through finite element analysis using ANSYS, adhering

to Libyan market standards. Stresses under internal pressure are analyzed and compared with

analytical solutions for steel cylinders. The study highlights weight reductions for steel and

composite LNG cylinders, emphasizing the practicality, utility, and safety considerations in

addressing the challenges faced by the Indian Gas supply system, especially for housewives

dealing with heavy stainless steel cylinders.

This project aims to provide a user-friendly alternative, maintaining gas storage efficiency while

significantly reducing cylinder weight

In this study, two software MBAL - Petroleum Experts and Eclipse are used to do comprehensive reservoir study for LCSF plane of development, this study covered analyses and evaluation. Gas injection essentially increases the rate of oil field development and in many cases permits increased oil recovery. This paper demonstrates a successful simulation case study based on a field data of a project. The objective of this study is to improve recovery from Libyan Carbonate Sedimentary Field by three wells of gas injection. To do that, first, the simulation 3-D model was built by using advanced reservoir simulation software (Schlumberger Eclipse). Second, select the best zone for gas injection. Third, select the best location for injector well. Fourth, determine the injector well depth. The results of the paper can be seen to match the real data of the reservoir with the results of the program using a MBAL software. The simulator results show the reservoir pressure history curve is matching to the stimulation curve, this gives a good allusion of the input data that has been entered to the model. The driving mechanism of this reservoirs it comes from three natural forces, which are fluid expansion, PV compressibility, and water influx. Gas injection scenario has a good plateau bpd lasts approximately 3 years and after that started to decrease. The Cumulative oil production is 108442340 STB barrels of oil with the recovery factor approximately 0.52805 and final reservoir pressure is maintained 328.76 pisa