No abstract

Hazelnut is one of the most popular nuts consumed by people; it has different cultivars in Turkey. The aim of the current study was to characterize some physicomechanical characteristics, shape features, color, and biochemical properties of 6 standard and 3 local hazelnut cultivars grown in Turkey. The shape and size properties of the samples were determined using image processing techniques as an alternative to conventional measurement methods. Additionally, principal component analysis (PCA) was used to classify the hazelnut samples in terms of the biochemical parameters of the hazelnut cultivars. According to the findings, the highest crude oil (63.25%) and lowest protein contents (13.63%) were observed in the Kalınkara cultivar. Oleic and linoleic acids were the major fatty acids for all hazelnut samples. While local Devedişi and standard Çakıldak cultivars had the highest oleic acid levels, the highest linoleic acid level was observed for the Dağ fındığı cultivar. The cultivars of Foşa had the highest Zn and Mn, while the highest Cu was found in the Tombul cultivar. The greatest surface and projected areas were calculated for the Kara fındık and Dağ fındığı samples, while the greatest hardness value was measured for the Devedişi cultivar. PCA revealed some positive and negative correlations between the physicomechanical and biochemical parameters. The present analyses revealed significant correlations between hardness and internal shell b* values and between Cu content and internal L*. Such correlations should be taken into consideration in food processing applications and machine design for these hazelnut cultivars.

No abstract

In this study, three different apple cultivars were dried using five different drying methods and moisture ratio (MR), moisture content (MC) and drying rate values were determined. Then, different machine learning algorithms (artificial neural network, k‐nearest neighbors, random forest, gaussian processes, and support vector regression) were used to estimate MR, MC and drying rate. For MR estimation of Golden Delicious, Oregon Spur and Granny Smith cultivars, Random Forest was most successful algorithm with correlation coefficients (R) of 0.9800, 0.9873, and 0.9841, respectively. This was followed by SVR with R: 0.9323 for Golden Delicious, ANN with R: 0.9766 for Oregon Spur and 5‐NN with R: 0.9827 for Granny Smith. MC and drying rate estimation results showed that RF, SVR, and k‐NN achieved higher R for all cultivars. It was concluded that machine learning algorithms are an effective approach for the accurate estimation of the drying characteristics of apple slices. Practical applications Machine learning‐like precise modeling techniques are used to estimate the drying characteristics of agricultural commodities. Models should be assessed and compared for optimization of drying conditions and operational costs. Machine learning models predictions agreed well with testing data sets and they could be useful for understanding and controlling the factors affecting drying behaviors.

No abstract