A mobile ad hoc network (MANET) poses significant challenges such as route failure and end-to-end delay due to the decentralized nature of mobile ad hoc wireless networks, mobility of devices, and resource constraints. Motivated by this, in this work, a new routing protocol by implementing intelligent reflecting surfaces (IRSs) in MANET, called MRIRS, is proposed. The developed MRIRS investigates the role of IRS as an intermediate node which helps not only for multi-flow multi-path routing even in non-line-of-sight (NLoS) scenarios but also supports delay minimization in the route discovery phase and helps with interference-avoiding channel assignment to the primary users (PUs). Comparison in terms of packet delivery ratio (PDR) and end-to-end delay (PD) averaged on 40 topologies based on the same source and destination pair with 3 flows shows that MRIRS has an 8% improvement in PDR and 800 msec improvement in PD. In environments with 8 m/s average node speed, MRIRS shows 114.88 kbps improvement in terms of throughput where 15.97% link failure is recorded on average. In environments with 16 m/s, link failure is around 24% where it is almost 98% for other routing protocols.

Derin Öğrenme modelleri kompleks deneyimlerden bilgi çıkarımına imkân sağlayan spesifik Makine Öğrenmesi yöntemleridir. Kapalı bir mekândaki bazı veri değerlerindeki değişiminin öğrenilmesi ile odada herhangi bir kişinin bulunup bulunmamasının tespit edilmesi bu deneyimlerden biridir. Bu çalışmanın amacı zaman serileri olarak oluşturulmuş ve zaman içinde ışık, sıcaklık, nem ve CO2 değerlerindeki değişimler ile kapalı bir mekânda doluluk tespiti probleminin Bir Boyutlu Evrişimli Sinir Ağı (1D-CNN) ile gerçekleştirilmesidir. Bir adet eğitim ve iki adet test veri seti kullanılarak model eğitilmiş ve daha önce tecrübe edilmeyen test veri setleri ile modelin başarısı gözlenmiştir. Keras uygulama programlama arayüzünde 1D-CNN modeli ile gerçekleştirilen testlerde doluluk tespiti sınıflandırmasının RF (Random Forest), GBM (Gradient Boosting Machines), CART (Classification and Regression Trees), LDA (Linear Discriminant Analysis) yöntemlerinden daha başarılı sonuçlar verdiği gözlenmiştir.

Looking into the concept of next-generation (5G) cellular systems, it is necessary to do a revision of existing radio spectrum management techniques and come up with more flexible solutions. A new wave of spectrum policy reforms can be envisaged with a direction shift from static to dynamic optimization. According to the peak hours, the number of served users in mobile networks is increasing. Since the radio spectrum is limited, cognitive radio (CR) technology provides an opportunity to recognize under-utilized cellular spectrum (licensed band) resources. To this end, efficient spectrum management techniques based on CR technology should be implemented to share the spectrum between different types of users in order to maximize spectrum utilization and spectral efficiency. In this work, we present dynamic decision-based spectrum sharing model among multiple classes of users in CR network (CRN) in order to increase network utilization and the quality of experience (QoE) by increasing the users' satisfaction. Obtained simulation results from created toolkit in Matlab tool (calibrated by data set from real 3GGP LTE-Advanced system) show the performance of the developed model and appropriate user selection among multiple users' types.

Hazelnut (Corylus avellana L.) is a significant global agricultural product due to its high economic and nutritional worth. The traditional methods used to measure the hazelnut kernel percentage for quality assessment are often time-consuming, expensive, and prone to human errors. Inaccurate measurements can adversely impact the market value, shelf life, and industrial applications of hazelnuts. This research introduces a novel system for calculating hazelnut kernel percentage utilizing a non-destructive X-ray imaging technique along with deep learning methods to assess hazelnut quality more efficiently and reliably. An image dataset of hazelnut kernels has been developed using X-ray technology, and defective areas are identified employing YOLOv7 architecture. Additionally, a novel bounding box regression technique called DCIoU and an algorithm for Neighborhood Relationship have been introduced to enhance object detection capabilities and to improve the selection of the target box with greater precision, respectively. The performance of these proposed methods has been evaluated using both the created hazelnut dataset and the COCO-128 dataset. The results indicate that the system can serve as a valuable tool for measuring hazelnut kernel percentages by accurately identifying defects in hazelnuts.