Browsing by Author "Altintas, V"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    UPGMA and artificial neural networks applications on wild type olives
    Sesli, M; Yegenoglu, ED; Altintas, V; Gevrekçi, Y
    Aim: Plant genetic sources are important to study genetic variability and richness of hereditary knowledge of plant species in gene pool. Local varieties, rural populations, wild types and old varieties are the primary ones. In this respect, wild type olives (Olea europaea oleaster) are valuable in terms of olive breeding, cultivation and ecosystem. The aim of the study was to determine genetic distances between olive varieties. Methodology: Artificial Neural Networks intuitive algorithm application was performed on seven wild type olives grown in different regions of Turkey by using data obtained from twenty-two ISSR primers. Results: UPGMA dendrograms were developed through Jaccard, simple matching coefficients, and similarity matrices; and genetic similarities and dissimilarities were exhibited. Interpretation: It was concluded that Artificial Neural Networks would be beneficial for estimating olive types accurately based on the results obtained from earlier studies performed with genetic markers.
  • No Thumbnail Available
    Item
    THE EFFECT OF BLOWING DIRECTION ON HEAT SINK PERFORMANCE BY THERMAL IMAGING
    Abuska, M; Sevik, S; Altintas, V
    Heat sinks (HSs) are designed for the mechanical, electrical and electronic components that generate heat in considerable amount. For this purpose, an aluminum conical pin fin heat sink is designed. Aluminum conical pin-fins geometry has been experimentally investigated for the blowing direction (pushing or pulling) which is the energy efficient option for the heat sink. The heat sink was tested at the same fan power for pushing and pulling conditions for 25, 50, 75 and 100 W resistance heater power. Designed aluminum conical pin fin heat sink can be easily used in heat sweeping processes. It has found that pushing configuration of the fan is more efficient for this design.
  • No Thumbnail Available
    Item
    ARTIFICIAL NEURAL NETWORKS AND FUZZY LOGIC APPLICATIONS THROUGH ISSR MARKERS ON CULTIVATED TYPE OLIVES
    Sesli, M; Yegenoglu, ED; Altintas, V
    Olive producing countries grow olives belonging to the subtype of Olea europaea L. sativa (cultivated type olive) in Olea variety and a vast diversity of varieties are available. Olive agriculture is present in the Black Sea, Marmara, Aegean, Mediterranean and Southeastern Anatolia regions, starting from the north in Turkey. The values obtained by using 7 ISSR primers on 13 cultivated type olives, Edremit, Gemlik, Do mat, Uslu, Cilli, Esek, Kaba, Cekiste Nazilli, Memecik, Taysan Ytiregi, Halhali, Manzanilla, Cekiste Bozdogan, which are included in this diversity of varieties spread to a wide ecology, were modeled using Artificial Neural Networks and Fuzzy Logic, being the branches of artificial intelligence, and the applicability of results were studied. In this study, ISSR primers were used on different cultivated type olives with economic importance and the applicability of results in estimation were studied through artificial neural networks and fuzzy logic artificial intelligence techniques.
  • No Thumbnail Available
    Item
    Evaluation of prediction and modeling performance using machine learning methods for thermal parameters of heat sinks under forced convection: The case of external validation
    Çorumlu, V; Altintas, V; Abuska, M
    The capability of ML models in thermal systems is generally determined by internal validation, while this study investigates the prediction performance of ML models with external validation. ANN, XGBoost, and RF models were created with the training-test data set obtained from the results of flat, conical, and cross-cut pin fin heat sinks. Data of 33, 66, and 99 W for the training-test data set were used for training and internal validation, while data of 49.5 W for conic Model-I and 82.5 W for conic Model-II were used for external validation. The RF showed the highest performance on the test data-internal validation and the ANN on the external validation. According to the test data not used in training, the lowest MSE is 0.0270-(RF), 1.7437-(ANN), and 14.7140-(XGBoost). In RF and XGBoost, the external validation performance decreased significantly compared to the internal validation. The MSE of the models are 8.0683-ANN, 214.4047-XGBoost, and 300.6012-RF for external validation. The thermal resistance provides more realistic results than the Nusselt number for the thermal performance evaluation of heat sinks with ML methods. The ANN based on external validation may be used to predict heat sinks' thermal performance and save money, labor, and time compared to CFD simulations.
  • No Thumbnail Available
    Item
    The Fuzzy Logic Modeling of Solar Air Heater Having Conical Springs Attached on the Absorber Plate
    Abuska, M; Akgül, MB; Altintas, V
    Solar air collectors (SAC) are usually used for space heating and drying of agricultural products. In SACs, thermal efficiency is low due to the low heat transfer between the absorber plate and fluid. In this study, a novel absorber plate geometry is designed and manufactured for enhancing the thermal efficiency. A comparative test system consisting of a flat absorber plate with staggered conical springs and a collector with flat absorber plate was established. It is aimed to increase the thermal efficiency by increasing the turbulence effect of the surface area, the interaction between the fluid and the absorber plate with the staggered conical springs. The performance of the systems was tested experimentally. In the experiments, inlet and outlet temperature of the collectors, global radiation, the exit velocity of air from the collectors, the absorber plate temperatures, backside surface temperature and transparent cover temperatures were measured. The thermal efficiency was calculated based on the measurements. Consisting of the fuzzy logic model of the system with the experimental data obtained, the outlet air temperature of the collector and thermal efficiency is modeled based on the input parameters according to three different membership functions (Triangle-Gaussian-Trapeze). As a result, it is concluded that the model based on the triangular membership function with fuzzy logic is 96% for the outlet temperature and 94-95% for the thermal efficiency.