Search

Sunflower constitutes an important source of protein, mineral, vitamin, fatty acid, and offer a balanced source of amino acids. Machine learning is mostly performed for the prediction of descriptive attributes in the quality evaluation of foods. In this study physical attributes of two different sunflower varieties (Metinbey and İnegöl Alası) were determined and algorithms were applied for size and shape prediction of these varieties. In addition, five different machine learning predictors were used as Multilayer Perceptron (MLP), Gaussian Processes (GP), Random Forest (RF), k-Nearest Neighbors (kNN), and Support Vector Regression (SVR). The prediction of surface area, volume, geometric mean diameter, aspect ratio, elongation, and shape index were based on the main physical attributes. İnegöl Alası variety had the greatest physical attributes. The seed length, width and thickness were obtained from İnegöl Alası variety as 23.89, 8.80 and 4.15 mm and from Metinbey as 17.88, 6.20 and 4.01 mm. All varieties were determined as significant in terms of the selected attributes as reported by Pillai Trace and Wilks’ Lambda (p

Due to the short harvest season and their sensitivity to storage, the preservation of fresh mulberry fruits is a very important process. Drying is a method used to preserve mulberry fruits in the long term. In this study, response surface methodology (RSM) was applied for the optimization of hybrid drying conditions of two different sour black mulberries. The linear and interaction effects of independent parameters such as temperature (50, 60 and 70°C) and microwave power (100, 200 and 300 W) variables were determined on mulberries. Bioactive properties and energy aspects were monitored as influenced by drying conditions. According to the results increase in microwave power provided a significant decrement in the specific energy consumption (SEC) and the total anthocyanin content (TAC), while increase in the energy efficiency (ηen) and total phenolic content (TPC) for both genotypes. In all cases, statistical values showed that all drying curves of black mulberry were best described by the Logistic model. Multiple response optimization was carried out for studied parameters and it was concluded that maximum antiradical activity (ARA), TPC, TAC, ηen and minimum drying time (DT) and SEC values would be at 300 W-50 ºC (desirability=0.842) and 300 W-66.5 ºC (desirability=0.744), for Morus nigra 1 (MN1) and Morus nigra 2 (MN2), respectively. According to the finding, the greatest TPC, ARA, TAC, DT, SEC and ηen were determined as 20.10 mg GAE/g, 86.00%, 456 mg/kg, 330 min, 18.59 kWh/kg and 9.04% for MN1, and 18.08 mg GAE/g, 83.92%, 835.81 mg/kg, 330 min, 16.16 kWh/kg and 10.40 % for MN2, respectively.

Beans usually have similar physical attributes; thus, it is difficult to distinguish them manually. Size, shape, and mass attributes of seeds help in breeding, selection, classification, separation, and machine design. This study was conducted to determine physical attributes of 20 bean genotypes with the use of image processing techniques. Color characteristics of the present genotypes were also determined. Then, four different machine learning algorithms (MLP, RF, SVR, andk-NN) were employed to predict seed mass. Among the present genotypes, Güzelöz and Özdemir genotypes had the highest size, shape, and color characteristics. Highly significant positive correlations were encountered between projected area-equivalent diameter (r = 1.00), between geometric mean diameter—surface area and volume (r = 1.00). On the other hand, highly significant negative correlations were seen between sphericity—elongation in vertical orientation (r = − 0.98). In hierarchical cluster analysis for physical attributes, Alberto–Aslan and Aras98–Şahin genotypes were identified as the closest genotypes. According to PCA analysis, the first two principal components (PC1 and PC2) were able to explain 73% of total variation among the genotypes. While PC1 axis included projected area (vertical), equivalent diameter (vertical), and length, PC2 axis includedL*,a*,b*, sphericity, roundness (vertical), and elongation (vertical). Among the present machine learning algorithms, RF yielded the best performances in mass estimation of bean seeds. It was concluded that machine learning techniques increased the efficiency of related machinery and helped to save time and labor.

Yenilenebilir enerji kaynakları içerisinde yer alan biyokütle, yakıt elde etmek için birçok avantaja sahiptir.Biyokütle kaynaklarından çeşitli işlemler sonucu katı, sıvı ve gaz halinde yakıtlar vb. ürünler eldeedilmekte ve bu yakıtların yakılması ile de ısı ve elektrik üretilmesi mümkün olmaktadır. Bununla birliktebiyokütle kaynakları sadece enerji elde etmek için değil aynı zamanda gıda, kâğıt, kereste ve bazıyüksek değerli kimyasalları elde etmek için de kullanılabilmektedir. Ayrıca, biyokütle içerisinde fosilyakıtlarda bulunan çevreye zararlı maddeler ve kükürt olmadığı için de çevre dostudur. Bununla birliktebitkisel üretimin ana kaynağı olan güneş enerjisi var olduğu sürece biyokütle tükenmez bir enerji kaynağıolarak değerlendirilecektir.Tarımsal atıkların, özellikleri iyileştirilmiş katı enerji kaynağı olarak kullanılmasında en etkin yollardanbirisi de pelet haline getirilmesidir. Son yıllarda tarımsal atıkların hem dünyada hem de ülkemizde enerjikaynağı olarak katı yakıt formunda değerlendirilmesi büyük önem kazanmıştır.Önerilen bu projede bölgemizde yaygın olarak yetiştiriciliği yapılan çerezlik kabak bitkisinden elde edilentarımsal atıklara peletleme işlemi uygulanacaktır. Elde edilen peletlerin parça yoğunluğu, mekanikdayanıklılık direnci, basınç direnci, darbe dayanım direnci ve nem alma özellikleri belirlenecektir. Ayrıcaboyut, hacim, alan ve şekil özellikleri görüntü işleme yöntemi ile belirlenecektir.

Sunflower constitutesan important source of protein, mineral, vitamin, fatty acid, and offer abalanced source of amino acids. Machine learning is mostly performed for theprediction of descriptive attributes in the quality evaluation of foods. In thisstudy physical attributes of two different sunflower varieties (Metinbey andİnegöl Alası) were determined and algorithms were applied for size and shapeprediction of these varieties. In addition, five different machine learningpredictors were used as Multilayer Perceptron (MLP), Gaussian Processes (GP),Random Forest (RF), k-Nearest Neighbors (kNN), and Support Vector Regression (SVR).The prediction of surface area, volume, geometric mean diameter, aspect ratio,elongation, and shape index were based on the main physical attributes. İnegölAlası variety had the greatest physical attributes. The seed length, width andthickness were obtained from İnegöl Alası variety as 23.89, 8.80 and 4.15 mmand from Metinbey as 17.88, 6.20 and 4.01 mm. All varieties were determined assignificant in terms of the selected attributes as reported by Pillai Trace andWilks’ Lambda (p

Agricultural products tend to rot and deteriorate shortly after harvest due to the intense moisture content. The aroma, color, appearance and nutritional properties of these products, which begin the decay regime, are lost. In order to prevent these quality losses and to increase the shelf life of the products, various preservation methods have been applied from past to present. The most economical and widely used of these methods is the preservation method by drying. It has advantages over other preservation methods such as convenience in transportation and storage, more concentrated nutrient content, long-term preservation, and less packaging costs. In addition, products with commercial value such as dried figs, dried apricots, drying grapes and raisins are obtained by drying. The aim of this study is to examine the sun, shade, convective, vacuum, microwave, freeze, spray, foam, puff, infrared, osmotic, electrohydrodynamic and hybrid drying methods used for drying agricultural products in accordance with the literature., Tarımsal ürünler bünyesinde bulunan yoğun nem sebebiyle hasattan kısa bir süre sonra çürüme ve bozulma eğilimine girmektedir. Çürüme rejimine giren bu ürünlerin aroma, renk, görünüş ve besinsel özelliklerinde kayıplar meydana gelmektedir. Bu kalite kayıplarını önlemek ve ürünlerin raf ömrünü artırmak amacıyla geçmişten günümüze kadar uygulanan çeşitli muhafaza yöntemleri uygulanmıştır. Bu yöntemlerden en ekonomik ve yaygın olarak kullanılanı kurutarak muhafaza yöntemidir. Kurutulmuş ürünün; taşıma ve depolamada kolaylık sağlaması, besin içeriği açısından daha konsantre bir özellik göstermesi, çok uzun süre boyunca muhafaza edilebilmesi, paketleme masrafının daha az olması gibi diğer muhafaza yöntemlerine göre üstünlükleri vardır. Ayrıca kurutma işlemi ile kuru incir, kuru kayısı, kuru üzüm gibi ticari değeri olan ürünler elde edilmektedir. Bu çalışmanın amacı literatür bilgileri doğrultusunda tarımsal ürünlerin kurutulmasında yararlanılan güneşte, gölgede, konvektif, vakumlu, mikrodalga, dondurarak, sprey, köpük, puf, kızılötesi, ozmotik, elektrohidrodinamik ve hibrit kurutma yöntemlerinin incelenmesidir.

Bu çalışmada, konvektif kurutma yönteminin iki farklı elma çeşidinin (Granny Smith ve Red Delicious) kurutulmasında, kurutma sıcaklığı (50, 55 ve 60°C), numune kalınlığı (5, 7 ve 9 mm) ve kuruma süresi (8, 9 ve 10 saat) gibi bağımsız değişkenlerin özgül enerji tüketimi, özgül nem çekme oranı, enerji verimliliği, termal etkinlik ve efektif nem difüzyonu özelliklerine etkisi incelenmiştir. Bulgulara göre, ikinci derece polinom denklemlerinin yanıt değişkenlerini temsil etmede başarılı olduğu tespit edilmiştir. Ayrıca ANOVA sonuçlarına göre bağımsız değişkenlerin yanıt değişkenleri üzerinde istatistiksel olarak önemli seviyede etkili olduğu belirlenmiştir (p, In this study, the effects of independent variables in convective drying methods two different apple varieties (Granny Smith and Red Delicious) such as drying temperature (50, 55 and 60°C), sample thickness (5, 7 and 9 mm) and drying time (8, 9 and 10 hours) on specific energy consumption, specific moisture extraction rate, energy efficiency, thermal efficiency, and effective moisture diffusivity were investigated. According to the findings, it was determined that the quadratic polynomial equations were successful in representing the response variables. In addition, according to the ANOVA results, it was determined that the independent variables had a statistically significant effect on the response variables (p