Akar, Özlem; Akar, Alper; Bayata, Halim Ferit

This study investigates the use of vegetation indices for accurately identifying crops with similar spectral characteristics as grapes, apricots, tomatoes, wheat, and clover for enhancing crop monitoring and management. A 59-hectare area in Karakaya Village, located in the Üzümlü district of Erzincan Province, Türkiye, was selected as the study area. This area contains crops with varying textures, object height, and spectral characteristics. In the study, multispectral (MS) images were acquired using the SenseFly eBee SQ unmanned aerial vehicle (UAV), and subsequently processed to generate an orthophoto, digital terrain model (DTM), and digital surface model (DSM). Fifteen vegetation indices, Gabor texture features, and object heights were integrated into MS bands. Crop classification was performed using two high-accuracy machine learning algorithms: Random Forest (RF) and Support Vector Machine (SVM). According to the overall classification accuracy results, the use of vegetation indices improved classification accuracy by 9% for RF and 5% for SVM. Incorporating Gabor texture features with the top-performing indices (MACARI1, OSAVI, ADVI, and DVI) further increased accuracy to 20% for RF and 12% for SVM. Additionally, including object height alongside the indices and Gabor features resulted in further accuracy gains of 10% and 11% for RF and SVM, respectively. F1-score, specificity, and accuracy analyses, along with various kappa statistics, also the significant improvements in classification performance. According to the McNemar test, the χ^2 values comparing orthophoto images with those incorporating indices, texture, and object height ranged from 6.353 to 35.556 for RF, and from 7.220 to 11.021 for SVM. Since all χ^2 values exceeded 3.84, the results indicate statistically significant improvements in the classification accuracy at the 95% confidence interval.

Tastimur, Canan; Kaya, Volkan

Insect pests pose a significant threat to agricultural productivity, making early and accurate identification essential for effective pest management. This study proposes a novel deep learning-based classification framework for multi-class pest recognition from field images. The proposed approach enhances discriminative region representation by integrating a patch embedding module, a Vision Transformer backbone, and a learnable spatial attention mask. This hybrid design enables the model to focus on critical visual cues without requiring segmentation-based preprocessing. The attention mask, learned via convolutional layers, is pooled and directly applied to Transformer-encoded patch tokens to refine spatial feature emphasis. Positional embeddings are further employed to preserve spatial context within the tokenized image representation. Experimental evaluations conducted on publicly available pest datasets with 5, 9, and 12 classes demonstrate the effectiveness and robustness of the proposed framework. The model achieves accuracies of 99.67%, 99.52%, and 97.00% on the Pest5, Pest9, and Pest12 datasets, respectively, indicating strong generalization across varying classification complexities. To enhance model transparency and reliability, visual interpretability is provided through Grad-CAM and attention heatmap visualizations that reveal the model’s focus regions. Additionally, t-SNE-based feature visualization illustrates clear separability in the learned embedding space. The proposed framework shows strong potential for practical deployment in smart agriculture and precision pest monitoring systems.

Yangılar, Filiz; Gerek, Merve Dilara

The study aimed to evaluate the potential of creating a functional beverage by enriching Anthriscus sylvestris (L.) kombucha production with guava peel and pulp, showcasing the variety and richness of the product formulations. This was done due to kombucha being a fermented beverage rich in various bioactive compounds that have significant effects on health and the possibility of enhancing product diversity through different formulations. Thus, the kombucha tea was physicochemical, phytochemical, antioxidant activity, and sensory evaluation during the 15-day fermentation period. The increased acetic acid bacteria and yeast count indicates that Anthriscus sylvestris is a viable substrate for the proliferation of Kombucha symbiotic microbes. Adding guava peel and rosemary oil to kombucha significantly increased its total phenolic, flavonoid, and vitamin C content (P<0.05). Anthriscus sylvestris-guava kombucha has antibacterial properties (zones of inhibition of 18.32 and 17.31 mm against Staphylococcus aureus ATCC 25923 and Escherichia coli ATCC 25922, respectively). Moreover, it also provided an inhibitory effect on α-glucosidase and α-amylase, enzymes associated with diabetes. The DPPH, ABTS*+, FRAP, CUPRAC, and ORAC capacities were found to be 66.89-78.90%, 70.83-97.25%, 367-723.15 µmol Trolox/mL, 381.40-460.45 µmol Trolox/mL, and 486.50-737.50 µmol Trolox/mL, respectively. Anthriscus sylvestris kombucha has well-balanced and pleasant sensory properties. These findings indicate that preparing Anthriscus sylvestris kombucha tea with guava may have health effects and that further research is needed to determine potential health benefits.

Kaya, Volkan; Akgül, İsmail; Zencir Tanir, Özge

In the classification of fish, both knowledge and great effort are required to determine the characteristics of fish. Traditionally, however, manual classification of extrinsic characteristics of different fish species has been a difficult and time-consuming process due to their close resemblance to each other. Re-cently, deep learning methods used in the light of developments in the field of computer vision have facilitated the training of fish image classification models and the recognition of various fish species. In this study, a new convolutional neural network model classifying 8 different belonging to 6 families (Mulli-dae, Sparidae, Carangidae, Serranidae, Clupeidae, Salmonidae) fish species using deep learning methods was proposed. The species include Clupeonella cultriventris N., Sparus aurata L., Trachurus trachurus L., Mullus barbatus L., Pagrus major T & S., Dicentrarchus labrax L., Mullus surmuletus L. and Oncorhynchus mykiss W. The proposed model (IsVoNet8) is compared with the ResNet50, ResNet101 and VGG16 models. The success accuracies obtained as a result of the comparison are respectively; 98.62% in the IsVoNet8, 91.37% in the ResNet50 model, 86.12% in the ResNet101 model and 97.75% in the VGG16 model. However, it was obtained that the loss rates of ResNet50 0.3646, ResNet101 0.5811, VGG16 0.0696 and with the IsVoNet 0.0568. As a result, it has been observed that the IsVoNet classifies marine fish, which is widely consumed in Türkiye.

Yangilar, Filiz; Çakmakçi, Songul

It was aimed in the present study to determine the mineral content, probiotic, sensory, physical and chemical characteristics of probiotic yogurt-PC (only probiotic Lactobacillus acidophilus DSMZ 20079 strains with direct vat set starter culture) obtained with the addition of corn flour (CF) at different concentrations during a 21-day storage period. It was found in the study that all probiotic yogurt formulations with CF gave high L. acidophilus viabilities between 6.89 and 7.87 log cfu g(-1) during the storage and CF addition did not affect the viability of the probiotic bacteria. The viscosity and dry matter content increased in CF added samples with increasing CF concentrations. Syneresis in PC yogurt sample was found to be significantly higher than that in other samples. The greater the CF supplementation (5%) has the lower the syneresis on the 21st day of storage. The CF+PC ( 5%) sample was determined to be a better source of Ca, Mg, P and Fe than the Control and PC yogurts. The general acceptability of yogurt involving 5% PC decreased significantly than the others. Considering all the properties in general, 2.5% CF + PC sample it is recommended to be found as probiotic yohurt.

Yangilar, Filiz; Çakmakçi, Songül

It was aimed in the present study to determine the mineral content, probiotic, sensory, physical and chemical characteristics of probiotic yogurt-PC (only probiotic Lactobacillus acidophilus DSMZ 20079 strains with direct vat set starter culture) obtained with the addition of corn flour (CF) at different concentrations during a 21-day storage period. It was found in the study that all probiotic yogurt formulations with CF gave high L. acidophilus viabilities between 6.89 and 7.87 log cfu g-1 during the storage and CF addition did not affect the viability of the probiotic bacteria. The viscosity and dry matter content increased in CF added samples with increasing CF concentrations. Syneresis in PC yogurt sample was found to be significantly higher than that in other samples. The greater the CF supplementation (5%) has the lower the syneresis on the 21st day of storage. The CF+PC (5%) sample was determined to be a better source of Ca, Mg, P and Fe than the Control and PC yogurts. The general acceptability of yogurt involving 5% PC decreased significantly than the others. Considering all the properties in general, 2.5% CF + PC sample it is recommended to be found as probiotic yohurt.

Tanır, Özge Zencir; Korkmaz, A. Şeref

In this study, Zippin's triple-catch removal method was used to estimate density and biomass of fish species in Kirmir Stream of Sakarya River, Central Anatolia Turkey. A total area of 1.5256 ha was sampled and 4167 fishes were caught using electrofishing between February 2007 and November 2007. A total of 9 fish species representing 2 families Cyprinidae and Cobitidae were recorded. Fish species identified are as follows: Chub (Leuciscus cephalus Linnaeus, 1758), barbel (Barbus plebelejus escherichi Heckel, 1843), Capoeta tinca Heckel, 1843, spirlin (Alburnoides bipunctatus Bloch, 1782), Capoeta capoeta sieboldi Steindachner, 1864, tirgis-nase (Chondrostoma regium Heckel, 1843), bleak (Alburnus orontis Sauvage, 1882), spined-loach (Cobitis taenia Linnaeus, 1758) and angora-loach (Noemacheilus angorae Steindachner, 1897). A. orontis was the most dominant species, constituting 1199 fish and 28.77% of the total fishes, followed by C. tinca (1173 fish and 28.15%), B. p. escherichi (584 fish and 14.01%), L. cephalus (454 fish and 10.90%), A. bipunctatus (322 fish and 7.73%), C. regium (245 fish and 5.88 %), N. angorae (107 fish and 2.57%) C. c. sieboldi (65 fish and 1.56%) and C. taenia (18 fish and 0.43%). The density and biomass values were estimated as 11456 fish ha-1 and 346.78 kg ha-1 in February 2007, 8982 fish ha-1 and279.82 kg ha-1 in May 2007, 6320 fish ha-1 and 251.52 kg ha-1 in August 2007 and 2887 fish ha-1 and 168.87 kg ha-1 in November 2007, respectively. The lowest density and biomass values were observed in November 2007.

Zencir Tanir, Özge; Korkmaz, A. Şeref

In this study, Zippin’s triple-catch removal method was used to estimate density and biomass of fish species in Kirmir Stream of Sakarya River, Central Anatolia Turkey. A total area of 1.5256 ha was sampled and 4167 fishes were caught using electrofishing between February 2007 and November 2007. A total of 9 fish species representing 2 families Cyprinidae and Cobitidae were recorded. Fish species identified are as follows: Chub (Leuciscus cephalus Linnaeus, 1758), barbel (Barbus plebelejus escherichi Heckel, 1843), Capoeta tinca Heckel, 1843, spirlin (Alburnoides bipunctatus Bloch, 1782), Capoeta capoeta sieboldi Steindachner, 1864, tirgis-nase (Chondrostoma regium Heckel, 1843), bleak (Alburnus orontis Sauvage, 1882), spined-loach (Cobitis taenia Linnaeus, 1758) and angora-loach (Noemacheilus angorae Steindachner, 1897). A. orontis was the most dominant species, constituting 1199 fish and 28.77% of the total fishes, followed by C. tinca (1173 fish and 28.15%), B. p. escherichi (584 fish and 14.01%), L. cephalus (454 fish and 10.90%), A. bipunctatus (322 fish and 7.73%), C. regium (245 fish and 5.88 %), N. angorae (107 fish and 2.57%) C. c. sieboldi (65 fish and 1.56%) and C. taenia (18 fish and 0.43%). The density and biomass values were estimated as 11456 fish ha-1 and 346.78 kg ha-1 in February 2007, 8982 fish ha-1 and 279.82 kg ha-1 in May 2007, 6320 fish ha-1 and 251.52 kg ha-1 in August 2007 and 2887 fish ha-1 and 168.87 kg ha-1 in November 2007, respectively. The lowest density and biomass values were observed in November 2007.

Koçyiğit, Rıdvan; Aydin, Recep; Yanar, Mete; Güler, Olcay; Diler, Abdülkerim; Avci, Mehmet; Özyürek, Selçuk; Kabakci, Dilek; Hirik, Elif Nur

The purpose of this research was to investigate the possibility of the reducing weaning age of Brown Swiss x Eastern Anatolian Red F1 crossbred calves reared in North East Region of Anatolia. A total of 26 calves were housed in individual hutches and weaned at 2 (early weaning) or 3 (late weaning) months of age. While weaning weight of the calves in different weaning age treatment groups was significantly (P<0.01) different in favor of calves weaned lately, 6 months weight was not significantly affected by ages of weaning. Average 6 months weight of the male calves was significantly (P<0.05) higher than that of female calves. The effects of weaning ages on the weight gain in both post-weaning and overall periods of the trial were not significant. Total milk dry matter intake (DMI) of the late weaned calves were significantly (P<0.01) greater than that of early weaned calves. However, starter DMI of the calves weaned 2 months of age was higher (P<0.05) than that of late weaned calves, but dry hay and total feed DMI were not affected by the weaning ages. Sex of the calves also did not result in significant effects on the milk, dry hay, starters and total feed DMI. Feed conversion efficiency in a period between birth and 6 months of age were not significantly affected by weaning ages. The weaning age and sex of calves did not significantly affect the gains in body measurements. Percentage of time spent for lying, standing, eating and drinking water behaviors were not also significantly affected by both weaning ages and sex of calves. The results of this study suggested that the crossbred calves could be weaned successfully at 2 months of age without having adverse effect on their growth, feed conversion efficiency and behavioral traits.

Yildirim, Mustafa; Çakmak, Mustafa

Grain yield estimate from early segregating populations is an interesting feature of today s wheat breeding programs,and F 1 populations are generally recommended as the most suitable population by researchers. In the present study,we evaluated the population vigor of diallel F 4 offsprings of six bread wheat genotypes (Sultan, Bezostaya, Süzen,Harmankaya, Altay and Gerek) under irrigated (IR) and rain-fed conditions (RF). The experiment as two sets under IRand RF were established in the feld of Anatolian Agricultural Research Institute, Eskişehir. The mean of grain yield(5468 kg ha -1 ) of F 4 populations in RF and IR had been lower than the mean of genotypes (5654 kg ha -1 ). The mean ofgrain yield of genotypes (7062 kg ha -1) under IR was higher than F 4 populations (6703 kg ha -1 ), while genotypes and F 4populations were nearly similar under RF (4246 kg ha -1 and 4234 kg ha -1, respectively). The mid-variety population vigorfor grain yield varied from -6.70% (Hrm/Grk) to 8.77% (Bez/Grk) under RF, and from -22.58% (Sltn/Alty) to 10.87%(Bez/Süzen) under IR. There was not positive signifcance population vigor in F 4s. According to results under RF andIR, F 4 populations are observed as the most suitable populations for realistically estimation of grain yield performanceof populations.