With COVID-19, formal education was interrupted in all countries and the importance of distance learning has increased. It is possible to teach any lesson with various communication tools but it is difficult to know how far this lesson reaches to the students. In this study, it is aimed to monitor the students in a classroom or in front of the computer with a camera in real time, recognizing their faces, their head poses, and scoring their distraction to detect student engagement based on their head poses and Eye Aspect Ratios. Distraction was determined by associating the students’ attention with looking at the teacher or the camera in the right direction. The success of the face recognition and head pose estimation was tested by using the UPNA Head Pose Database and, as a result of the conducted tests, the most successful result in face recognition was obtained with the Local Binary Patterns method with a 98.95% recognition rate. In the classification of student engagement as Engaged and Not Engaged, support vector machine gave results with 72.4% accuracy. The developed system will be used to recognize and monitor students in the classroom or in front of the computer, and to determine the course flow autonomously.

<!-- *** Custom HTML *** --> A C-shaped split ring resonator-based metamaterial (MTM) structure placed on a patch antenna is proposed. An artificial neural network (ANN) is applied to design and determine dimensions of an MTM structure that is similar to those used in wireless communication systems, such as Wi-Fi and WiMax, as well as in military vehicles and space stations. The proposed microstrip antenna interacts with the MTM-based structures to improve the reflection coefficient (S₁₁) and quality factor. The design of the proposed structure is optimized for this purpose in accordance with the ANN studies in the related literature. Both simulation and experimental studies show that ANN calculated MTM antennas improved the quality factor, which is calculated as 230 at 5.18 GHz. The simulated S₁₁ is verified by experiment to show the integrity of the proposed work.

In this manuscript, a resonator layer is presented for the purpose of reducing the mutual coupling effect between each antenna element of a cross dipole antenna. In design processes, an artificial neural network approach was used for various resonator designs. In the operating frequency band of 2.2–2.7 GHz, 48 different 6 × 6 resonator layers were created and integrated into the cross dipole antenna to reduce transmission and improve isolation between each antenna elements. Moreover, when training an artificial neural network in the Matlab program, 48 different resonator layers were used with the return losses and transmission values of cross dipole antenna elements. After training process, eight unknown resonator designs were tested and accurate results were obtained. Finally, one of the resonator planes, which was obtained from the artificial neural network, was fabricated and experimentally tested, then an accurate result was obtained. This study provides a good solution, especially for improving isolation in multiport antenna systems, using an artificial neural network approach.

The authors present the development of a technique which uses a ‘multi objective’ genetic algorithm for the structural synthesis of combinational VLSI circuits by employing one or more cell-based design libraries. Throughout, the genetic evaluation circuits which are optimal with regard to different criteria at various levels within the design hierarchy are sought. The genetic algorithm succeeds in manipulating a highly complex solution space of circuit structures and provides solutions in a relatively small number of generations. The structural cell based GA implemented, the circuit synthesised, and the results obtained, have not been reported in the literature so far.

Chiral metamaterials have been a research area for many researchers due to their polarization rotation properties on electromagnetic waves. However, most of the proposed chiral metamaterials are designed depending on experience or time-consuming inefficient simulations. A method is investigated for designing a chiral metamaterial with a strong and natural chirality admittance by optimizing a grid of metallic pixels through both sides of a dielectric sheet placed perpendicular to the incident wave by using a genetic algorithm (GA) technique based on finite element method solver. The effective medium parameters are obtained by using constitutive equations and $S$ parameters. The proposed methodology is very efficient for designing a chiral metamaterial with the desired effective medium parameters. By using GA-based topology, it is proven that a chiral metamaterial can be designed and manufactured more easily and with a low cost.

Today, control systems have become an important branch of science in parallel with the increase of production and quality needs. There are purpose-specific automatic control systems and algorithms controlling them for production in industrial facilities. In this study, modeling electric arc furnace scrap melting plant, which has an essential place in the iron-steel industry has been made using artificial neural networks. The facility where the study is carried out is in active production and controlled by classical algorithms. Artificial neural networks were trained using the data taken over the current control system and pressure sensors attached to the electrodes and the modeling and control of the arc furnace with the trained network was carried out. The software developed with an artificial neural network to control the electrodes used in electric arc furnaces provided 98% success in monitoring the system including the operator’s intervention out of the algorithm. All input and output data of an active production facility were copied to the network with the developed software. Since this software does not require various calculations, calibrations and parameter changes, it responds faster than the classical control algorithm used in the factory.