Yazar "Önler, Eray" seçeneğine göre listele
Listeleniyor 1 - 12 / 12
Sayfa Başına Sonuç
Sıralama seçenekleri
Öğe A study regarding the fertility discrimination of eggs by using ultrasound(Agricultural Research Communication Centre, 2017) Önler, Eray; Çelen, İlker Hüseyin; Gülhan, Timur; Boynukara, BanurThe aim of this research was to track the growth of chicken eggs, and make a decision as to whether the egg was fertilized or not. A digital imaging system has been developed in order to take an image from six different points without damaging the egg shell. All the images were transferred to a PC and turned into binary images. All the images were reduced to 1024 pixels and fed directly into the classification algorithm. The logistic regression method was used to discriminate the fertility of the eggs. Python programming language and the scikit-learn machine learning library was used to carry out the classifications. True positive, true negative, wrong positive, and wrong negative detection numbers in the trials were 350, 344, 56, and 50, respectively. Negative indicates the egg was infertile, and positive indicated that the egg was fertilized. The model accuracy was measured as 0.8675.Öğe Automation of liquid fertilizer application aystem in a direct drill machine(2022) Aktepe, Behice Boran; Bayhan, Yılmaz; Önler, ErayAn automation system was designed to measure and monitor the amount of liquid fertilizer sprayed on a direct drill machine with the ability to apply liquid fertilizer. The clogging of spray nozzles is a common problem in liquid fertilizer machines. The objective is to detect clogged spray nozzles during the application of liquid fertilizer and to allow the tractor driver to monitor the amount of liquid fertilizer discharged with this designed automation system. It gives a visual warning to the driver when the flow is zero. Flow sensors are mounted on the spray nozzles of the machine. The machine was operated at 540 rpm PTO speed. A total of 30 measurements were taken from each flow sensor with 3 replications. The actual volume was found from the amount of liquid collected in the scaled vessels that are placed under the spraying nozzles and the measured volume obtained from the flow sensors. The calibration curve of the liquid fertilizer system was created by performing a regression analysis with measurements taken from the sensors and scaled vessels. At the same time, the real volume and the volume measured by the sensor were compared with the t-test and analyzed whether there was a statistically p< 0.05 difference between the measurements. As a result of the measurements, the volume measured by the sensor was slightly higher than the actual volume. The mean difference was calculated as 0.17 liters and the standard deviation as 0.08 liters. The regression curve between the actual and the measured volume shows that there is a high linear relationship and the regression coefficient was calculated as R2= 0.947. At the same time, since p=0.012 (p<0.05) was found as a result of the independent two-way t-test, it was determined that there was no statistical difference between the actual volume and the measured volume.Öğe Comparative Analysis of Genetic and Greedy Algorithm for Optimal Drone Flight Route Planning in Agriculture(2024) Önler, ErayIn this study, the performance of the Genetic Algorithm (GA) in optimizing the agricultural drone flight route was compared with the Greedy Algorithm, revealing that GA produce routes that are, on average, 17.44 % more efficient. This efficiency, measured over 500 generations in a static field model, suggests substantial potential for saving resources and time in agricultural operations. Despite the effectiveness of the GA, its computational intensity limits real-time field applications, but offers advantages in offline route planning for pre-mapped areas. A t-test between flight lengths created by the algorithms highlighted a significant difference, with a p-value of approximately 7.18×10?9, indicating the GA's superior performance. Future research should aim to bridge the gap between the simplified binary field model used in simulations and the complexities of real-world agricultural landscapes to improve the practical deployment of GAs in drone route optimization.Öğe Determination of energy balance of apple (Malus domestica) production in Turkey: A case study for Tekirdag province(2017) Çelen, İlker Hüseyin; Baran, Mehmet Fırat; Önler, Eray; Bayhan, Yılmazbelirlenmesi amaçlanmıştır. Enerji kullanım etkinliği çalışması, Tekirdağ ili Merkez ilçesi Nusratlı köyündeki bir işletmede 2015 üretim sezonunda 12 da alana sahip elma bahçesinde yapılan gözlem ve ölçüm yoluyla gerçekleştirilmiştir. Girdiler içerisinde mekanizasyon enerjisinin rolü ortaya konulmaya çalışılmıştır. Hesaplanan verilere göre, elma yetiştiriciliğinde toplam enerji girdisi, toplam ürün verimi, toplam enerji çıktısı, enerji çıktı/girdi oranı, özgül enerji, enerji verimliliği ve net enerji verimi sırasıyla 58839.65 MJ ha-1, 38370 kg ha-1, 92088.00 MJ ha-1, 1.56, 1.53 MJ kg-1, 0.64 kg MJ-1 ve 33248.35 MJ ha-1 olarak belirlenmiştir. Sonuç olarak, elma yetiştiriciliğinde genel enerji girdileri içerisinde en fazla enerji tüketim sırasıyla gübre enerjisi, yakıt-yağ enerjisi, kimyasallar, makine, insan işgücü ve sulama enerjisi olarak belirlenmiştir.Öğe Determining the Energy Usage Efficiency of Different Soil Tillage Methods and No-Till Method in Aftercrop Beans Production(Parlar Scientific Publications (P S P), 2017) Bayhan, Yılmaz; Çelen, İlker Hüseyin; Önler, ErayThis study presented the energy usage efficiency of 3 different soil tillage method and no-till method in aftercrop beans production. As a result, the value of specific energy was found as 1.63 MJ/kg in No-till, 1.80 MJ/kg in Rotary tiller + drilling (ROT), 2.01 MJ/kg in Disc harrow + rotary tiller + roller + drilling (HD+ROT), and 3.36 MJ/kg in Disc harrow + drilling (DT). The energy output/input ratio was obtained as 9.01 in no-till, 8.16 in ROT, 7.32 in HD+ROT and 4.38 in DT. It was found that the highest share in the total input energy in all methods was held by fertilizer energy, while fuel-oil had the second place.Öğe Estimation of Monthly, Seasonal and Annual Total Solar Radiation on the Tilted Surface at Optimum Tilt Angles in Two Provinces, Turkiye(2023) Önler, Eray; Kayişoğlu, BirolIn solar energy systems that use solar panels, it's important to know the best tilt angle to optimize solar energy production. Monthly, seasonal, and annual optimum tilt angles were determined in this study using meteorological insolation data from many years in the provinces of Tekirdag and Konya, which are located in different regions of Turkey. At optimum tilt angles, monthly, seasonal, and annual total radiation on the tilted surface were 1516.7 kWh m-2 year-1, 1504.1 kWh m-2 year-1 and 1448.1 kWh m-2 year-1 in Tekirdag, respectively. In Konya, these values were 1851.4 kWh m-2 year-1, 1833.51 kWh m-2 year-1 and kWh m-2 year-1, respectively. In the seasonal and annual optimum tilt angles, there was an approximately 1% and 5% loss in the total radiation values on the tilted surface, respectively, according to the monthly optimum tilt angle. In addition, the coefficients of the relationship between the monthly mean daily radiation on the tilted surface and the tilt angles were determined for each month using the cubic regression model in both provinces. The Cubic regression model coefficients are computed for each month in the provinces of Tekirdag and Konya. All months in both provinces had R2 (Coefficient of determination) values of 0.999 for the Cubic model. To determine whether there is a difference between the total amounts of radiation reaching the tilted surface for each month at the best tilt angles obtained by the two methods, the t-test was used. The monthly average daily radiation values on the tilted surface obtained by the two methods at the best tilt angles in both provinces have not been found to differ statistically (p>0.05; t=0.001).Öğe Evaluation of Residue Distribution of Spraying Nozzles Produced for the Prevention of Spray Drift(2020) Önler, Eray; Çelen, İlker Hüseyin; Avcı, Gürkan GüvençThe widespread use of pesticides has negative impacts on human health and the environment. This situation increases the severityday by day. Especially spray drift is one of the factors that should be controlled. In addition, pesticide costs have led to newsolutions. Conventional spraying nozzles and anti-drift spraying nozzles are discussed in this study. The study carried out inviticulture areas. Pesticide residual amounts were determined by sampling surfaces placed in different parts of the plant. Thesampling surfaces were placed on the top and bottom surfaces of the leaves. Pesticide residue rates were determined in differentregions of the plant. The average pesticide residual amounts on the leaves with the anti-drift spray nozzles AITX 8002 VK and ITR8002 were found to 63.5% and 49.9% higher than the conventional TX VK12 spray nozzle, respectively, also 44.2% and 32.2%higher than the other conventional spray nozzle TR 8002, respectively. The lowest value of top to bottom pesticide residue ratiofor leaves was 2.22 at anti-drift ITR 8002 spray nozzle and the highest value of top to bottom pesticide residue ratio for leaveswas 2.95 with the conventional spray nozzle TR 8002. All the type of spray nozzles except anti-drift AITX 8002, produced lessresidue in the inner parts compared to outer parts. The highest penetration rate was 90% with the AITX 8002 VK spray nozzle andthe lowest penetration was 55% with the conventional TX VK12 spray nozzle type.Öğe Feature fusion based artificial neural network model for disease detection of bean leaves(Amer Inst Mathematical Sciences-Aims, 2023) Önler, ErayPlant diseases reduce yield and quality in agricultural production by 20-40%. Leaf diseases cause 42% of agricultural production losses. Image processing techniques based on artificial neural networks are used for the non-destructive detection of leaf diseases on the plant. Since leaf diseases have a complex structure, it is necessary to increase the accuracy and generalizability of the developed machine learning models. In this study, an artificial neural network model for bean leaf disease detection was developed by fusing descriptive vectors obtained from bean leaves with HOG (Histogram Oriented Gradient) feature extraction and transfer learning feature extraction methods. The model using feature fusion has higher accuracy than only HOG feature extraction and only transfer learning feature extraction models. Also, the feature fusion model converged to the solution faster. Feature fusion model had 98.33, 98.40 and 99.24% accuracy in training, validation, and test datasets, respectively. The study shows that the proposed method can effectively capture interclass distinguishing features faster and more accurately.Öğe Meyve bahçelerinde değişken düzeyli ilaçlama için otonom tarım aracı tasarımı(Namık Kemal Üniversitesi, 2018) Önler, EraySon yıllarda tarımsal üreticiler; tarımsal işçi erişiminin belirsizliği, güvenli, erişilebilir ve yüksek kaliteli tarımsal ürünler konusunda artarak devam eden müşteri talebi, uluslarası üreticilerle olan rekabet ve karbon ayak izinin azaltılması ihtiyacı nedeniyle önemli zorluklarla karşı karşıyadır. Üreticilerin rekabetçi ve karlı üretimi devam ettirebilmeleri teknolojiye yatırım yaparak işçi maliyetlerini düşürüp, verimi arttırmalarından geçmektedir. Otonom tarımsal araçlar meyve bahçelerinde proseslerin otonom hale getirilmesi, verimliliğin arttırılması, bahçe yönetimi konusunda alınan kararlar için gerekli verilerin toplanması, işletme giderlerinin ve karbon ayak izinin azaltılması konularında önemlidir. Bu çalışmada meyve bahçelerinde değişken düzeyli ilaçlama sistemini taşımak için otonom araç tasarımı ve simülasyonu yapılmıştır. Meyve bahçelerinde odometri ve LIDAR sensörlerinden gelen verileri kullanarak meyve bahçesinin engel haritasını çıkarabilen, adaptif monte karlo lokalizasyon yöntemi ile LIDAR ve odometri sensörlerinden gelen verileri harita ile karşılaştırarak otonom aracın harita üzerindeki konumunu doğru olarak belirleyebilen, aracın harita üzerinde istenilen noktalara otonom olarak gitmesini sağlayan ve bulunduğu noktadan hedef noktaya giderken karşısına çıkan engellerden dinamik pencere yaklaşımı algoritmasını kullanarak sakınabilen bir yazılım geliştirilmiştir. Tasarlanan otonom araç değişken düzeyli ilaçlama sisteminin sadece istenilen lokasyon içerisinde ilaçlama yapmasını sağlamak için ilaçlama makinasını çalıştırma ve durdurma komutlarını verebilmektedir. Çalışmada tasarlanan otonom araç, GPS’ in doğru şekilde çalışamayacağı üstü örtülü meyve bahçelerinde, çalışacak olması nedeniyle özgün bir çalışmadır. Ayrıca dışarıdan GPS verisi gibi herhangi bir veriye ihtiyaç duymayacağı için tam otonom bir araçtır. Elde edilen tasarımdan uygulamada daha az çevre kirliliği, daha az işletme gideri ve daha az iş gücü kullanılmasını sağlayarak daha yüksek verim elde edilmesi beklenmektedir. Haritalama uygulamasının başarısı, haritanın ne kadar yer değiştirme yapıldıktan sonra güncelleneceğine ve haritalamada kullanılan parçacık sayısına bağlıdır. Robotun 50 cm yer değiştirmesi ile haritanın güncellenmesi ve 30 parçacık kullanılması durumunda gerekli işlem gücü ve performans bakımından en uygun olan 3,03 entropi değeri elde edilmiştir. Lokalizasyon, robottaki sensörlerden alınan verilerin ve harita bilgisinin adaptif monte karlo lokalizasyon algoritması kullanılarak karşılaştırılması ile sağlanmıştır. Lokalizasyon başarısı, robota ait pozisyonun ne kadarlık yer değiştirme sonucu güncelleneceğine ve lokalizasyonda kullanılan parçacık sayısına bağlıdır. Konum güncellemesinin robotun 2 cm yer değiştirmesi ile yapıldığında ve minimum 500, maksimum 2000 parçacık kullanımında gerekli işlem gücü ve performans bakımından en uygun olan 3,50 cm ortalama hata elde edilmiştir. Rota planlama uygulaması, harita üzerinde lokalizasyonu sağlanmış robotun bulunduğu noktadan istenilen noktaya gidebilmesi için geliştirilmiştir. Rota planlama için Dijkstra algoritması kullanılmış, planlama global ve lokal planlama olarak iki aşamada yapılmıştır. Lokal planlamada kullanılan dinamik pencere yaklaşımı ile robotun önüne çıkan engellerden kaçabilmesi sağlanmıştırÖğe Öğe Spray Characterization of an Unmanned Aerial Vehicle for Agricultural Spraying(College of Agriculture and Food Science, University of the Philippines Los Banos, 2023) Önler, Eray; Özyurt, Hasan Berk; Şener, Mehmet; Arat, Sezen; Eker, Bülent; Çelen, İlker HüseyinSustainability and higher efficiency in crop production are possible with the use of new technologies. The use of unmanned aerial vehicles brings many advantages both in terms of monitoring agricultural areas and pesticide applications. This technology allows us to detect diseases and damages in an early manner and apply them in areas that are not accessible by conventional sprayers. However, a lack of knowledge on how to use UAVs and what parameters need to be considered prevent the widespread use of drone technology in agriculture. This study established parameters for spraying with clean water using a DJI Agras 14 MG-1P (RTK) Unmanned Aerial Vehicle. Droplet distribution and droplet analyses were examined in the studies carried out at different heights (1.5, 2.0, and 2.5 m) and flow rates (10, 15, 20, 25, and 30 L/ha). Droplets were analysed using DepositScan. Coefficients of variation of droplet distribution tend to decrease with the increasing spray rate. The trials with the closest values to uniformity are spraying applications made with a flight height of 2 m. When we evaluate pesticide efficacy according to the number of droplets per unit area, insecticides and all herbicides can be effective at applications with flight heights of 1.5 and 2 m and spray rate of 20 L/ha. While all spraying is done with flight heights of 1.5 and 2 m and spray rates of 25 L/ha, fungicides are ineffective when applied from 2.5 m height. As a result, this study found the measurements made at 2 m altitude and 20 L/ha spray rate have the highest coverage rate and lowest drift potential. © 2023, College of Agriculture and Food Science, University of the Philippines Los Banos. All rights reserved.Öğe Ultrasonik sensör yardımıyla belirlenen yaprak yoğunluğuna göre püskürtme miktarını ayarlayan sistemin tasarımı (akıllı ilaçlama makinası)(Namık Kemal Üniversitesi, 2012) Önler, ErayElma bahçesinde ağaçların büyüme sezonu boyunca yaprak yoğunluğunda meydana gelen değişimlere göre atılacak ilaçlı sıvı miktarını sürekli olarak ayarlayarak, ilaçlama uygulamasının optimize edilmesini sağlayacak bir ilaçlama makinası geliştirilmiştir. Bu amaçla ultrasonik sensörler kullanılarak hedef bitkinin yaprak yoğunluğunun tespiti yapılmış ve uygulanan dozun adapte edilmesi sağlanmıştır. Çalışmada hava destekli piyasada Ahtapot diye isimlendirilen bağ ve bahçelerde kullanılan hava destekli bir ilaçlama makinesinden faydalanılmıştır. Her kola bir adet ultrasonik sensor, üç adet solenoid valf ve sensör çıkışlarını yorumlayıp solenoid valfleri kontrol edecek elektronik kontrol kartı eklenmiştir. Her bir solenoid valf farklı debide çıkış veren bir ilaçlama memesini kontrol ettiği için bitki üzerine atılacak ilaçlı sıvı miktarı üç farklı debiye ayarlanabilmiştir. Atılan ilaçlı sıvı miktarı gerçek zamanlı olarak ultrasonik sensörler ile algılanan yaprak yoğunluğuna gore; tasarlanan sistem tarafından otomatik olarak değiştirilmektedir.
