Hamit Armağan

With the occurrence of global climate change and the depletion of agricultural water resources, there is a growing need to develop rapid, non-destructive, and autonomous plant health monitoring systems. As an economically valuable crop, Ocimum basilicum L. (basil) is sensitive to changes in water availability and may exhibit stress-related morphological variations under drought and over-irrigation conditions. However, due to the visual similarity of leaf symptoms under drought stress, waterlogging stress, and optimal irrigation conditions, accurately distinguishing these conditions remains challenging in practical applications. To address this challenge, this paper presents an attention-based dual-branch deep learning framework designed to extract both subtle leaf details and channel-related features from high-resolution plant images. By combining the Convolutional Block Attention Module (CBAM) and Squeeze-and-Excitation (SE) mechanism in a parallel structure, the proposed network improves the analysis of high-resolution images with an input size of 720 × 720 pixels. Under controlled environmental conditions, with ground-truth labels obtained using soil moisture sensor measurements, the proposed model was compared with eight deep learning architectures, including DenseNet121, InceptionV3, and VGG16. The proposed model achieved a hold-out evaluation accuracy of 99.54%, outperforming the second-best model, DenseNet121, which achieved 96.43%. In addition, the proposed model reached a class-specific precision value of 100% for the Drought Stress category and achieved an area under the receiver operating characteristic curve of 1.00 under the controlled experimental setting. Taylor Diagram analysis also indicated that the model closely preserved the variability pattern of the reference data. These results suggest that the proposed application-specific framework may support non-destructive basil water-stress detection under controlled conditions. After further validation with larger datasets, different cultivars, variable environmental conditions, and real-world agricultural scenarios, the proposed approach may contribute to precision irrigation management and sustainable agricultural production. The contribution of this study should be interpreted as an application-specific implementation and evaluation of complementary attention mechanisms for controlled-environment basil water-stress classification, rather than as the introduction of a fundamentally new deep learning methodology.

The integration of immersive technologies has transformed nursing education, yet existing solutions often lack holistic ICU workflow experiences. This chapter presents VRicuLAB, a Virtual Reality-Based Intensive Care Unit designed to provide nursing students with a realistic, risk-free, and process-oriented learning environment. VRicuLAB enables users to perform procedures, operate virtual devices, and monitor patients through high-fidelity simulations. Beyond technical architecture, the system integrates data-driven tracking and educator dashboards for objective assessment and personalized feedback. By combining engineering precision with instructional design, VRicuLAB aims to enhance accessibility, inclusivity, and engagement. The chapter discusses theoretical foundations, educational rationales for design decisions, and sustainable immersive learning approaches, bridging the gap between engineering and healthcare disciplines.

This study investigates the prediction of Escherichia coli growth in environments where experimental data are limited, by integrating mathematical curve fitting with machine learning regression models. Two hybrid frameworks are developed: Fourier Series Curve Fitting combined with Gaussian Process Regression (FSCF-GPR), and Gaussian Curve Fitting integrated with Support Vector Machine Regression (GCF-SVMR). The raw dataset, initially composed of only 10 experimental measurements, was expanded to 114 data points through mathematical smoothing, providing a richer basis for model training. Model performance was assessed using Root Mean Square Error (RMSE), Mean Squared Error (MSE), Coefficient of Determination (R²), and Mean Absolute Error (MAE). Results demonstrate that the FSCF-GPR framework achieved outstanding predictive accuracy with an R² of 0.9999, while GCF-SVMR also showed strong performance with an R² of 0.9934. These findings highlight that data augmentation via curve fitting can substantially enhance the accuracy and robustness of machine learning approaches in microbiological growth prediction under data-scarce conditions.

Forest fires are destructive natural disasters that not only destroy vast forested areas but also threaten biodiversity, degrade air quality, damage agricultural land, and accelerate climate change. Due to rising global temperatures, prolonged droughts, and human-induced factors, the frequency and intensity of forest fires are increasing year by year. Consequently, the early detection and rapid classification of forest fires are critical for preventing loss of life and property and ensuring the effective management of disaster response processes. This study aims to present a deep learning-based approach for the early detection and classification of forest fires. In this context, four advanced convolutional neural network (CNN) architectures (Xception, InceptionV3, DenseNet121, and EfficientNetV2), which have shown outstanding success in image classification tasks in recent years, were comparatively evaluated for the classification of forest fire images. Training and testing procedures were performed using the Forest Fire Images dataset, consisting of fire and non-fire classes. The experimental results revealed that all models performed well in forest fire classification; however, the Xception model demonstrated superior performance, exhibiting higher accuracy than the others. These results emphasize that deep learning architectures are effective tools for the rapid and accurate classification of forest fires, thereby making significant contributions to forest fire monitoring and management strategies.

Accurate prediction of microbial growth is of great importance in critical areas such as food safety and environmental sciences. In this study, a hybrid of mathematical methods and machine learning-based approaches are used to model the growth dynamics of foodborne pathogen Bacillus cereus. Since the use of mathematical models alone does not sufficiently cover the non-linear data structure of bacterial systems, better results are obtained when hybrids are used together with machine learning methods. We examine the results of five different tree-based models for predicting the growth of Bacillus cereus, namely Fine Tree, Medium Tree, Coarse Tree, Ensemble Boosted Trees and Ensemble Bagged Trees. We evaluate each model with performance metrics such as Root Mean Square Error (RMSE), Mean Square Error (MSE), R² and Mean Absolute Error (MAE). The results show that the Ensemble Bagged Trees model performs the best, with a validation RMSE of 0.0094 and an R² value of 0.9995. Also, the Fine Tree model has an R² value of 0.9990. In general, ensemble methods offer significant advantages in prediction accuracy.

Bu çalışmanın amacı, pandemi süreçlerinde hastalık şüphesi taşıyan sağlıklı bireyler (S- susceptable), hastalığa yakalanan bireyler (I- infected) ve iyileşen ya da vefat eden bireylerden (R- recovered) oluşan S-I-R gruplarının sayısını tahmin etmek için farklı regresyon modellerinin performansını değerlendirmektir. Türkiye'deki COVID-19 verileri Türkiye Cumhuriyeti Sağlık Bakanlığı'nın resmi internet sitesinden alınmıştır. Çalışmada kullanılan veri seti, pandeminin başlangıcından itibaren seçilen zaman dilimini kapsamakta ve günlük S-I-R grup sayılarını içermektedir. Polinom regresyonu, Fourier regresyonu, Gauss regresyonu ve sin toplamı regresyonu gibi farklı regresyon modelleri incelenmiş ve tahmin performansları analiz edilmiştir. Ayrıca, Chebyshev polinomlarına dayalı doğrusal olmayan bir denklem sistemi olan SIR modelinin diferansiyel çözümleri ile karşılaştırılmıştır. Performans ölçütleri olarak R2 (RSquare- Determination Coefficient) ve Ortalama Hatanın Karekökü (RMSE- Root Mean Squared Error) kullanılmıştır. Sonuçlar, farklı regresyon modellerinin S-I-R gruplarının sayısını tahmin etmedeki performansını değerlendirerek pandemi süreçlerinin analizi için en uygun modelin belirlenmesine katkı sağlamaktadır.

In this study, a virtual laboratory has been developed to enable the effective running of applied courses in formal and distance education. Embedded systems, field programmable gate arrays (FPGA), application programming interfaces (API), and web‐based software infrastructure are used together in the virtual laboratory. Experiments belonging to digital electronics and digital communication courses can be performed by the students in the developed experiment set. Process steps performed by the student in the experiments can be followed by the designed log circuit. Every transaction performed on the experiment set was recorded and a web environment was provided to the educators where they could evaluate the experiment process. Two groups of students were formed to evaluate the success of the virtual laboratory. The first group performed the circuit setup using the traditional method and the second group on the developed virtual laboratory. According to the survey questions directed to the students, it was revealed that the use of the virtual laboratory informal and distance education would bring positive results and provide equal opportunities for disadvantaged individuals. At the same time, it was revealed that a virtual laboratory has been developed that will provide cost benefits in educational institutions.