Yazar "Baykara, Muhammet" seçeneğine göre listele

Listeleniyor 1 - 3 / 3
  • Küçük Resim Yok
    Öğe
    Investigation and prediction of ethylene Glycol based ZnO nanofluidic heat transfer versus magnetic effect by deep learning
    (Elsevier, 2021) Demirpolat, Ahmet Beyzade; Baykara, Muhammet
    In this study, ZnO (zinc oxide) nanoparticle production was performed. Heat transfer coefficients (h) were measured for Ethylene Glycol Based ZnO nanofluids that were produced using pure water, ethanol, and ethylene glycol materials. In the literature, this is the first study in which Nanofluid was produced and experimental results were estimated by using LSTM and CNN-LSTM deep learning models. The study graphs' show the relationship between heat transfer coefficients. Besides, Reynolds numbers were drawn and predictive models were created by using the LSTM and CNN-LSTM deep learning models for h values of nanofluids. In addition, the deep learning architecture that predicts the effects of the magnetic effect on the heat transfer coefficient has been introduced to the literature as an innovation. The results showed that the heat transfer coefficients can be estimated with the LSTM and CNN-LSTM deep learning model with an average error of 0.7342% and 0.2001% respectively. In addition, the relative error of the heat transfer coefficients as a result of the magnetic effect was determined as 0.02944 and 0.01701, respectively, with the same methods and model. Applying the magnetic effect to the system, an irregularity was observed in the flow and as a result of increased heat transfer, the friction on the pipe wall increased. The importance of the study is modeling the heat transfer coefficient values depending on the different pH values that were used during the synthesis of ZnO nanomaterial and observing the effects of the magnetic effect on the system.
  • Küçük Resim Yok
    Öğe
    OptiMap: Heuristic Clustering Algorithm for Minimum Cost Paths
    (Institute of Electrical and Electronics Engineers Inc., 2024) Okutan, Huseyin Enes; Baykara, Muhammet
    Grouping algorithms refer to a procedure where certain entities within a community can form new sub-communities according to their characteristic features without disrupting the general order of the community. These sub-communities generally show division in a way that contributes to the order of the parent communities from which they are separated. The main purpose of grouping algorithms is to divide the elements in the data set into groups within a purpose according to their similarities or certain features. This purpose is often based on grouping similar entities within a group into a certain cluster according to their features. Unlike grouping certain entities within a group according to their similarities, in cases where certain problems cannot be solved holistically, there are also approaches that focus on solving the problem specifically for these sub-groups by creating sub-groups according to the scope of the problem. Such approaches enable large and complex problems to be solved by dividing them into more manageable parts. Each sub-group addresses a specific aspect of the problem, and in this way, a holistic solution is obtained by combining the sub-groups. Within the scope of the study, the problem of multiple resources navigating randomly distributed multiple targets in a way that follows minimum-cost paths is addressed. In this context, a new heuristic grouping algorithm is proposed that can group entities within a region where certain targets are located in a way to obtain minimum transit paths. This proposed algorithm is based on the fact that each target to be grouped knows its closest neighbor and uses this information to divide the group in a way to reveal minimum transit paths. Within the scope of the study, first of all, a matrix called the heuristic matrix, which contains the neighborhood information and costs of the targets, is created. This heuristic matrix is scanned with a specially designed search algorithm and the target that can create potential minimum transit paths is grouped in the same group. After the implementation of the originally created OptiMap grouping algorithm, the testing phase was started. In order to evaluate the ability of the OptiMap algorithm to group in a way to reveal minimum cost paths, test scenarios were created for regions with uniform and complex distributions. As a result of testing the OptiMap algorithm under different scenarios with different target distributions, it was seen that it can group in a way to create minimum transit paths. © 2024 IEEE.
  • Küçük Resim Yok
    Öğe
    OptiRoute: Operational Routing Algorithm for Swarm Robots
    (Institute of Electrical and Electronics Engineers Inc., 2024) Okutan, Hüseyin Enes; Baykara, Muhammet
    Swarm Robotics is a dynamic system consisting of robots inspired by nature and working together. Studies in this field focus on understanding how decision-making processes and communication can be carried out effectively by examining collective behaviors and coordination. In this study, an important study topic in the field of swarm robotics, which involves assigning each robot to specific targets and navigating on these targets in a way that will determine the minimum cost paths, and which has NP-Hard Combinatorics characteristics, is addressed. In order to solve this problem addressed in the study, a heuristic routing algorithm is proposed in which swarm robots can navigate by following minimum cost paths in a coordinated and collective manner. The OptiRoute algorithm, which is based on the neighborhoods of targets in a certain region and the idea that each target has information about its closest neighbor, has been tested in simulation environments based on various levels of complexity. In this context, it is observed that the proposed OptiRoute algorithm performs routing in a way that will select the minimum cost paths when the algorithm is configured to work with an appropriate number of robots according to the number of targets and characteristics of the environment. © 2024 IEEE.