Person: ERDOĞAN, HİLAL
Loading...
Email Address
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
ERDOĞAN
First Name
HİLAL
Name
3 results
Search Results
Now showing 1 - 3 of 3
Publication Machine learning-based detection and severity assessment of sunflower powdery mildew: A precision agriculture approach(Bursa Uludağ Üniversitesi, 2023-09-18) Erdinç, Atilla; BÜTÜNER, ALPEREN KAAN; ŞAHİN, YAVUZ SELİM; ERDOĞAN, HİLALSunflower powdery mildew (Golovinomyces cichoracearum (DC.) V.P. Heluta) is a substantial threat to sunflower crops, causing significant yield loss. Traditional identification methods, based on human observation, fall short in providing early disease detection and quick control. This study presents a novel approach to this problem, utilizing machine learning for the early detection of powdery mildew in sunflowers. The disease severity levels were determined by training a Decision Trees model using matrix of soil, powdery mildew, stems, and leaf images obtained from original field images. It was detected disease severity levels of 18.14% and 5.56% in test images labeled as A and C, respectively. The model's demonstrated accuracy of 85% suggests high proficiency, indicating that machine learning, specifically the DTs model, holds promising prospects for revolutionizing disease control and diseases prevention in agriculture.Publication Entomopathogenic nematode dispensing robot: Nemabot(Elsevier, 2021-02-14) Erdoğan, Hilal; Ünal, Halil; Lewis, Edwin E.; ERDOĞAN, HİLAL; ÜNAL, HALİL; Bursa Uludağ Üniversitesi/Ziraat Fakültesi/Biyosistem Mühendisliği Bölümü; 0000-0002-0387-2600; AAP-5834-2020; IHS-3745-2023Entomopathogenic nematodes (EPN) are obligate endoparasites of many insect species and they are important biocontrol agents. Application strategies that improve precision and reduce labor would increase their potential in many cropping systems. We developed a unique robotic system to apply EPNs to a surface area precisely. The robotic system picks up EPNs from a suspension in a reservoir with a peristaltic pump and transfers them to an exact point with an exact amount. Four suspensions were prepared with four concentrations of EPNs; 0.1, 0.2, 0.4 and 0.8 g of commercial EPN product per 2 L of water. All suspensions were applied in three different amounts of water (25, 50 and 100 mL per application). In total, 12 different applications were conducted with the robot. Conical falcon centrifuge tubes were used to collect applied EPNs. Five samples (10 ?l) were taken from collected 25, 50 and 100 mL EPN suspensions and the average nematode number in the samples were scaled to the whole suspension. Results of the experiments showed that all robot applications, except 25 mL?0.1 g dose, were not significantly different from those of the control treatment, application with a pipette.. Thus, the robotic system has been found to make consistent applications.Publication Potential for early detection of powdery mildew in okra under field conditions using thermal imaging(Univ Agronomic Sciences & Veterinary Medicine Bucharest - Usamv, 2023-01-01) ŞAHİN, YAVUZ SELİM; BÜTÜNER, ALPEREN KAAN; Bütüner, Alperen Kaan; Erdoğan, Hilal; ERDOĞAN, HİLAL; Bursa Uludağ Üniversitesi/Ziraat Fakültesi/Bitki Koruma Bölümü.; Bursa Uludağ Üniversitesi/Ziraat Fakültesi/Biyosistem Mühendisliği Bölümü.; 0000-0002-0387-2600; AAP-5834-2020; AAH-2823-2021In recent years, apprehensions surrounding the pervasive employment of chemical control methods in global agricultural production have intensified, primarily due to their detrimental effects on non-target organisms. This situation accentuates the importance of technology-driven alternatives for managing plant diseases in agriculture. One such technological innovation, thermal imaging technology, has emerged as a promising tool for the early detection of plant diseases. Infections often induce stress in plants, leading to either elevated or reduced temperatures at the point of infection. It is postulated that thermal imaging may effectively identify such temperature deviations in plant tissues afflicted by disease during the initial stages. The study investigated temperature differences in leaves infected by Erysiphe cichoracearum, with disparities up to 1.6 degrees C. Over three weeks, the surface temperatures of numerous leaves were analysed at 30-minute intervals. In three weeks period, it was shown that infected leaf surfaces had significantly lower average daily temperatures than ambient and healthy leaf temperatures. Furthermore, healthy leaf temperatures remained consistently lower than ambient temperatures throughout the study.