Tuğba Karaköse has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Development of a Ridge Sowing Machine for Clay Soil Conditions and Determination of Its Field Performance

    by Tuğba Karaköse, Ali Tekgüler, Mehmet Arif Beyhan

    Preparing seedbed operations in clay soils is quite difficult. As moisture content increases in these soils, the soil attains a plastic consistency, adheres to tillage implements, and, when it dries out, large clods form during tillage. Furthermore, problems with seed germination occur in clay soils with poor drainage. This study aimed to design and manufacture a sowing machine that prepares seedbeds on ridges in clay soils. This machine consists of a lister, a rotary cultivator, and a pneumatic sowing unit. A ridge was created using the lister to eliminate seed germination problems. Due to the clayey nature of the soil, only the ridge was tilled with a rotary cultivator to a width of 20 cm and a depth of 10 cm to facilitate soil fragmentation. Soybean (Glycine max.) cultivation was carried out. Field trials were conducted on plowed plots (plowed in autumn) and on unplowed plots, and the system was compared with the conventional sowing method (plowing + disc harrowing + sowing machine). The field emergence rate was 73.04% in the plots tilled in autumn with the prototype machine and 76.05% in the plots without tillage when tilled with the prototype machine. This value remained at 31.43% under conventional tillage. Fuel consumption in conventional sowing was 2.51 times higher than sowing with the prototype machine. In addition, the prototype machine saved 69.56% of compared to conventional tillage.

  • Blueberry Harvest Mechanisms

    by Ali Tekgüler, Tugba Karaköse

    Blueberry (Vacciniumcorymbosum L.) is a perennial plant that shed leaves in winter. It is from Ericaceae family and it is in the form of bushes. It grows in temperate climates and its motherland is America. It spread from American culture 110 years ago. It can grow in lightly textured and acidic soil. For this reason, the areas where agriculture can be done are limited. Because the production quantities are not enough, the selling prices are also high (Çelik H., 2008). Grape berries can be harvested by hand and machine. For the Blueberry harvest, harvesters with three different types of harvesting mechanisms were produced. The first blueberry harvester was manufactured in 1956, adapted from a mechanical cranberry picker. This machine had a mechanism consisting of a six-row scraper stick (Farooque A., 2014). These machines with high collection capacity reduce the need for labor and the cost of harvest. Blueberry manual harvesting hectare requires 1300 h of labor, while single row harvesting machine requires 25 h of labor/hectare. Thus, the cost of harvest falls from $ 2.8 per kg to $ 0.26 per kg (Takeda F. et.al., 2017). These machines are not economical for medium and small sized farms. In machine harvest, there are some problems for this plant. These problems are fruit falling on the ground during fruit harvest, the harvest of fruit that has not reached sufficient maturity, fruit and plant damage during picking. A lot of work has been done and continues to be done. However, sufficient harvesting efficiency has not yet been achieved. Blueberry should be harvested with a high quality and long shelf life that will appeal to the consumer.


  • Open Access

    Development of Baler Machine for Humid Areas

    by Tugba Karaköse, Kemal Çağatay Selvi̇

    Baler machines collect the swath straw when it reaches a sufficient level of moisture and bale it. However, the drying time of the material is prolonged in humid regions. This causes the land not to be used for the second crop and to get wet again in case of rainfall. Clogging is observed in commonly used baling machines when baling these products because they are more humid. The study aims to collect and bale the material even if the straw is not sufficiently dried in humid areas. For this purpose, dimensional improvements were made in the stubble chopper unit of a baler and compared with two widely used machines in the country. While clogging was observed in the other machine, no clogging was observed in the improved machine. In terms of direct usability, feed with particle size distribution smaller than 15 cm was 93.20% for the developed machine (DM) and 89.43% for the baler machine (BM-1). DM clogging problems have not been observed.

  • Open Access

    Multiclass Apple Varieties Classification Using Machine Learning with Histogram of Oriented Gradient and Color Moments

    by Alper Taner, Mahtem Teweldemedhin Mengstu, Kemal Çağatay Selvi, Hüseyin Duran, Önder Kabaş, İbrahim Gür, Tuğba Karaköse, Neluș-Evelin Gheorghiță

    It is critically necessary to maximize the efficiency of agricultural methods while concurrently reducing the cost of production. Varieties, types, and fruit classification grades are crucial to fruit production. High expenditure, inconsistent subjectivity, and tedious labor characterize traditional and manual varieties classification. This study developed machine learning (ML) models to classify ten apple varieties, extracting the histogram of oriented gradient (HOG) and color moments from RGB apple images. Support vector machine (SVM), random forest classifier (RFC), multilayer perceptron (MLP), and K-nearest neighbor (KNN) classification models were trained with 10-fold stratified cross-validation (Skfold) by using the textural and color features, and a GridSearch was implemented to fine-tune the hyperparameters. The trained models, SVM, RFC, MLP, and KNN were tested with separate test data and performed well, having an accuracy of 98.17%, 96.67%, 98.62%, and 91.28%, respectively. Having the top results, the MLP and SVM models demonstrated the potential of applying HOG and color moments to train ML models for classifying apple varieties. This study suggests conducting further research to thoroughly examine additional image features and determine the impact of combining features and utilizing different classifiers.


  • Open Access

    Prediction of design parameters of pneumatic cleaners with MARS method

    by Ali Tekgüler, Emre Dünder, Tuğba Karaköse

    One of the cleaning methods for agricultural materials is based on aerodynamic properties. Pneumatic cleaners are developed on this method. The purpose of this study is to predict the parameters such as fan angle, air velocity, and tunnel length, which are used in the design of pneumatic cleaners, through the multivariate adaptive regression splines (MARS) method. Some parameters have been estimated using the MARS method in order to use pneumatic cleaners under optimum conditions and adapt them to automation systems. The cleaners have a collection box which was installed at the outlet of the storage. Two different product collection boxes of 400 mm (defined as the first box) and 800 mm (defined as the second box) from the storage outlet section were used. From the results obtained, it was observed that the first box R2 was higher. When looking at the cross validation, it was observed that the results of the first box were more acceptable. With this study, MARS equations were used to obtain dependent variables at desired values. Using these equations, independent variables have been demonstrated to be identifiable. In the application results obtained, cleaning efficiency values were obtained in a wide range. While cleaning efficiency values reached up to 100%, the loss rate was found to be very high. Independent variables have been made identifiable to reduce the loss rate. The highest and feasible of these values were determined by MARS as 41° fan angle and 15 m/s air velocity in order to be able to apply at 97% CE and 1% LR determined for the first box. The MARS method allows for the use of more dependent and independent variables. Usable equations were obtained as a result of statistical analysis. More precise values can be obtained with these equations. It will contribute to the design of the parameters of the machine manufactured, such as speed, angle, and feeding amount. Keywords: MARS, pneumatic cleaner, cleaning efficiency, loss ratio DOI: 10.25165/j.ijabe.20211402.5715 Citation: Tekgüler A, Dünder E, Karaköse T. Prediction of design parameters of pneumatic cleaners with MARS method. Int J Agric & Biol Eng, 2021; 14(2): 106–111.