Yazar "Sahin, Hasan" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Integrating AI detection and language models for real-time pest management in Tomato cultivation
    (Frontiers Media Sa, 2025) Sahin, Yavuz Selim; Gencer, Nimet Sema; Sahin, Hasan
    Tomato (Solanum lycopersicum L.) cultivation is crucial globally due to its nutritional and economic value. However, the crop faces significant threats from various pests, including Tuta absoluta, Helicoverpa armigera, and Leptinotarsa decemlineata, among others. These pests not only reduce yield but also increase production costs due to the heavy reliance on pesticides. Traditional pest detection methods are labor-intensive and prone to errors, necessitating the exploration of advanced techniques. This study aims to enhance pest detection in tomato cultivation using AI-based detection and language models. Specifically, it integrates YOLOv8 for detection and segmentation tasks and ChatGPT-4 for generating detailed, actionable insights on the detected pests. YOLOv8 was chosen for its superior performance in agricultural pest detection, capable of processing large volumes of data in real-time with high accuracy. The methodology involved training the YOLOv8 model with images of various pests and plant damage. The model achieved a precision of 98.91%, recall of 98.98%, mAP50 of 98.75%, and mAP50-95 of 97.72% for detection tasks. For segmentation tasks, precision was 97.47%, recall 98.81%, mAP50 99.38%, and mAP50-95 95.99%. These metrics demonstrate significant improvements over traditional methods, indicating the model's effectiveness. The integration of ChatGPT-4 further enhances the system by providing detailed explanations and recommendations based on detected pests. This approach facilitates real-time expert consultation, making pest management accessible to untrained producers, especially in remote areas. The study's results underscore the potential of combining AI-based detection and language models to revolutionize agricultural practices. Future research should focus on training these models with domain-specific data to improve accuracy and reliability. Additionally, addressing the computational limitations of personal devices will be crucial for broader adoption. This integration promises to democratize information access, promoting a more resilient, informed, and environmentally conscious approach to farming.
  • Küçük Resim Yok
    Öğe
    Integration of Machine Learning Algorithms and Discrete-Event Simulation for the Cost of Healthcare Resources
    (Mdpi, 2022) Atalan, Abdulkadir; Sahin, Hasan; Atalan, Yasemin Ayaz
    A healthcare resource allocation generally plays a vital role in the number of patients treated (p(nt)) and the patient waiting time (w(t)) in healthcare institutions. This study aimed to estimate p(nt) and w(t) as output variables by considering the number of healthcare resources employed and analyze the cost of health resources to the hospital depending on the cost coefficient (delta(i)) in an emergency department (ED). The integration of the discrete-event simulation (DES) model and machine learning (ML) algorithms, namely random forest (RF), gradient boosting (GB), and AdaBoost (AB), was used to calculate the estimation of the output variables depending on the delta(i) of resources cost. The AB algorithm performed best in almost all scenarios based on the results of the analysis. According to the AB algorithm based on the delta(0.0), delta(0.1), delta(0.2), and delta(0.3), the accuracy data were calculated as 0.9838, 0.9843, 0.9838, and 0.9846 for p(nt); 0.9514, 0.9517, 0.9514, and 0.9514 for w(t), respectively in the training stage. The GB algorithm had the best performance value, except for the results of the delta(0.2) (AB had a better accuracy at 0.8709 based on the value of delta(0.2) for p(nt)) in the test stage. According to the AB algorithm based on the delta(0.0), delta(0.1), delta(0.2), and delta(0.3), the accuracy data were calculated as 0.7956, 0.9298, 0.8288, and 0.7394 for p(nt); 0.8820, 0.8821, 0.8819, and 0.8818 for w(t) in the training phase, respectively. All scenarios created by the delta(i) coefficient should be preferred for ED since the income provided by the p(nt) value to the hospital was more than the cost of healthcare resources. On the contrary, the w(t) estimation results of ML algorithms based on the delta(i) coefficient differed. Although w(t) values in all ML algorithms with delta(0.0) and delta(0.1) coefficients reduced the cost of the hospital, w(t) values based on delta(0.2) and delta(0.3) increased the cost of the hospital.
  • Küçük Resim Yok
    Öğe
    Statistical Optimization and Analysis of Factors Maximizing Milk Productivity
    (Mdpi, 2025) Kurtulus, Yuecel; Sahin, Hasan; Atalan, Abdulkadir
    This study was conducted to determine the biological and environmental factors affecting milk yield and dry matter consumption and to analyze the effects of these factors on animal production. The study determined the variables affecting milk yield as input factors, such as lactation period, number of days of gestation, age, TMR dry matter ratio, and environmental factors. As a result of regression analyses, it was determined that each 1% increase in the TMR dry matter ratio decreased the milk yield by 0.9148 L, and each increase in the number of lactations increased the daily milk yield by 3.753 L. However, it was observed that the increase in the number of lactation days caused a decrease in milk production, and milk yield decreased as the gestation period extended. The most appropriate independent variable values were determined using statistical optimization analyses to maximize milk yield and optimize dry matter consumption. As a result of the analyses, the optimum value for the TMR dry matter ratio was calculated as 46.77%, 5 for lactation number, 6 for lactation day number, 230 days for gestation period, 55.8 months for cow age, and 20 degrees C for air temperature. The optimum values of the dependent variables were determined to be 61.145 L for daily milk yield and 19.033 units for dry matter consumption. The prediction intervals provided by the model served as reference points for future observations and showed that milk production was strongly affected by certain environmental and biological factors.