Al-Iraqia Journal for Scientific Engineering Research

In the last few years, Artificial Intelligence (AI) has greatly increased. One specific area has seen significant progress: the use of AI in producing key generation algorithms for cryptography. These algorithms are a critical part of the encryption process. By using AI in this way, the cryptographic community hopes to make the process more secure and efficient. This push has led to several research papers and a wide range of different approaches. Here, we survey the scientific literature in this area and discuss the various strategies that have been taken.

The Vehicular Ad Hoc Network (VANET) is a novel and auspicious performance within the Intelligent Transportation Systems (ITS) field. Numerous scholars endeavoured to enhance the VANETs' Quality of Service (QoS) by creating routing procedures that were reliable, scalable, and efficient. One of the most significant issues of vehicular networks is building a routing protocol that guarantees a specific level of quality of service (QoS), as VANETs are distinguished by special properties, including constrained mobility, a very dynamic topology, and high node speed. For drivers to be able to make the right decisions, communication between vehicular nodes must be highly reliable. Link breakdown issues typically lower the quality of service (QoS) of a vehicular ad hoc network (VANET). This, in turn, lowers the following parameters that influence the QoS. This method depends on a for parameter Packet parameter of Delivery Ratio (PDR ), Packet Loss, Delay of End to End, and Throughput. The simulation results show that the proposal protocol has increased the longevity effectiveness of the network by around (PDR) 93%, Loss of packet 6%, (E2ED) 45.6 seconds, and Throughput 1500/ bps.

The increasing demand for non-invasive, rapid, and cost-effective disease diagnostics has driven advancements in integrating Iridology with computer vision and Artificial Intelligence (AI). This review examines research conducted from 2009 to 2024 on iris-based disease detection. The key findings showed the significant role of Machine Learning (ML) and Deep Learning (DL) in enhancing diagnostic accuracy and efficiency. Iridology-based intelligent systems show great promise for early detection of hidden diseases and organ dysfunctions, offering transformative potential for healthcare.

One of Iraq's primary water sources, the Euphrates River, was the subject of this water quality assessment. This study set out to evaluate the quality of the water flowing down the Euphrates River in Iraq. Water samples were collected seasonally at seven stations: S1 (Al-Ramadi), S2 (Al-Hilla), S3 (Karbala), S4 (Al-Najaf), S5 (Al-Diwaniya), S6 (Al-Samawa), and S7 (Al-Nasiriyah) from January 2023 to December 2023. Five parameters were analyzed, Hydrogen Ions (pH), and total dissolved solid (TDS). Dissolved oxygen (DO), Nitrate (NO3), and Phosphate (PO4). In the research region of the Euphrates River, seasonal fluctuations in the tested parameters of water varied from one season to the next. The values of these parameters are high in all stations in Summer, and they decrease in Spring. The parameters (pH, DO, NO3, and PO4) in all stations were within the allowable limit of water quality according to the (Iraqi Standards of River Water), while in station (5), the value of TDS exceeded the allowable value in Summer (2750) and Autumn (2600), in stations (6) the values of TDS were exceed the allowable value in all Seasons which reach (2291ppm, 2750 ppm, 1870 ppm, 3120 ppm and 2990 ppm). In stations (7), TDS exceeded the allowable value in all Seasons which reach (2709 ppm, 2305 ppm, 3900 ppm, and 3670 ppm).

Scientists tested reinforced concrete slabs for their behavior and strength under punching shear stress. An electric oven was used to experimentally heat reinforced concrete slabs to high temperatures (up to 400 °C), and the punching shear behavior of these slabs is the primary focus of this research. A steel reinforcing mesh with a diameter of (Î6mm) and slab dimensions of (400x400x60) mm was used to construct each of the six models. The concrete used in their construction combined regular and high strength. Using an entirely high-strength concrete mixture results in a 56.65% reduction in deflection, an 80% rise in First Crack Loading (FCL), and a 118.9% increase in Ultimate Load (UL), according to laboratory tests. As a result of layering, the (HSC) mixture was comparable to that of a slab composed completely of (HSC). This provides extra cost advantages compared to utilising a slab with complete high strength. Deflection dropped by 18.19%, whereas FCL and UL increased by 30.0%, 60.0%, and 43.24%, respectively, for a 73% increase. A partial region of a high-strength mixture performed better when the findings were enhanced by expanding the dimensions of the HSC area. Deflection values from the reference slab decreased by 0.91 percent, 10%, and 27.73 percent, respectively, whereas FCL and UL increased by 0% and %, respectively, according to the data. These findings promote cost-effective, fire-resistant construction by optimising material use, enhancing punching shear resistance, and improving structural durability under high temperatures.

Telemedicine is revolutionising health care by enabling remote patient monitoring and diagnosis, which is critical for the management of such chronic diseases as those affecting the heart. Although improved, existing frameworks often focus narrowly on triage or diagnosis, not incorporating multisource data to offer a comprehensive assessment. The proposed AI-powered IoMT-based framework solves these limitations in real-time triaging and diagnosing patients with chronic heart disease. The system integrates sensory and non-sensory information through rule-based algorithms for assigning patients to five emergency categories and offers preliminary diagnosis with practical treatment recommendations. The evaluated system was tested on a dataset of 250 patients in a virtual application scenario, achieving an overall triage classification and diagnostic accuracy of 98.4%. The approach strengthens the capacity of Telemedicine to provide timely, accurate, and resource-effective healthcare, especially in under-resourced or remote settings. Future work will focus on incorporating more advanced AI methods, extending the framework to other chronic diseases, and more considerable real-life scenario validation.

The increasing usage of Unmanned Aerial Vehicles (UAVs) in diverse applications necessitates the development of effective flight control systems. A major difficulty, nevertheless, is maintaining robust flight control under complex and dynamic environmental conditions, such as obstacle and non-flying zones, wind disturbances, and sensor noise. Traditional control techniques fail to achieve required flight control in these environments. To address this point, an adaptive control strategy is proposed based on a Deep Reinforcement Learning (DRL) model to enhance the flight performance of quadcopters. The learning and adaptation of the DRL-based control strategy are implemented in real-time through continuous interaction with the environment. This is to improve flight control and achieve consistent UAV performance under varying conditions. Proximal policy optimization with a reward function is used to minimize positional errors, ensure collision-free flight paths, and reduce energy consumption. The developed DRL model for quadcopters is trained in a simulated environment and then tested in three complex environmental scenarios, including urban, forest and mountain terrains. Experimental results demonstrate remarkable improvements in UAV flight performance. In the training phase, the reported training reward increased from 10 to 110 and the train loss is dropped from 0.85 to 0.05, which indicated successful model learning. Also, during system verification, rewards increased from 12 to 115 and UAV flight path deviations were decreased from 0.5 to 0.08m. The proposed controller outperforms conventional approaches in urban environments by lowering average trajectory deviations to 0.2m from 0.35m for MPC and 0.6m for PID. Also, the developed DRL-based controller outperformed the PID and MPC controllers, with path deviations of 0.18m in mountains and 0.12m in forests. In addition, fewer collision rates with obstacles are achieved with the model, 3% in forest, 1.8% in urban areas, and 4.5% in mountains. Furthermore, the consumed energy is reduced to 950J as compared to 1200J for PID and 1050J for MPC. The results show the strength of deploying the proposed controller in following the intended UAV flight path with high precision, effectively avoiding detected conflicts and minimizing consumed energy by the UAV.