Publication: Performance of Hyperparameters in Prediction with Deep Neural Networks of Electrical Properties of Nano-Coated Glasses Nano-Kaplamali Camlarin Elektriksel zelliklerinin Derin Sinir Aglari Ile Tahmininde Hiper Parametrelerin Performansi
Abstract
Nano-coated glasses are widely used in different fields such as industry, transportation and architectural structures. After these glasses are obtained by various thin film coating applications, they are subjected to the heat treatment process (tempering, bending, etc.), which is considered as a secondary process. Both of these two-stage processes lead to changes in the electrical and mechanical properties of the final product. While electrical properties such as transmittance, coated surface reflection and uncoated surface reflection values obtained as a result of the first stage can be calculated by analytical methods; the chaotic nature of the second stage does not allow these parameters to be calculated with similar methods. Therefore, in this study, a multi-input-multi-output deep neural network structure was designed for the estimation of the electrical properties of the nano-coated glass type produced for commercial use in architectural fields. Moreover, The dataset with 64 different coating types was augmented by adding noise technique and the performances of the hyperparameters in prediction success were compared. The performance of the network structure was measured by the mean absolute error, mean squared error, and coefficient of determination metrics. The designed network structure was tested on 16 samples and according to the results obtained, it was observed that the best performance was achieved with the Adadelta learning algorithm and ReLU activation function on the augmented data set.
Description
Keywords
Tıp, Sosyal ve Beşeri Bilimler, Sosyoloji, Kütüphanecilik, Tarımsal Bilimler, Ziraat, Tarım Makineleri, Tarımda Enerji, Biyoyakıt Teknolojisi, Bilgisayar Bilimleri, Algoritmalar, Sağlık Bilimleri, Temel Tıp Bilimleri, Biyoistatistik ve Tıp Bilişimi, Mühendislik ve Teknoloji, Medicine, Social Sciences and Humanities, Sociology, Library Sciences, Agricultural Sciences, Agriculture, Farm Machinery, Energy in Agriculture, Biofuels Technology, Computer Sciences, algorithms, Health Sciences, Fundamental Medical Sciences, Biostatistics and Medical Informatics, Engineering and Technology, Klinik Tıp (MED), Mühendislik, Bilişim ve Teknoloji (ENG), Sosyal Bilimler (SOC), Klinik Tıp, Bilgisayar Bilimi, Mühendislik, Sosyal Bilimler Genel, TIBBİ BİLİŞİM, BİLGİSAYAR BİLİMİ, YAPAY ZEKA, ENERJİ VE YAKITLAR, BİLGİ BİLİMİ VE KÜTÜPHANE BİLİMİ, Clinical Medicine (MED), Engineering, Computing & Technology (ENG), Social Sciences (SOC), CLINICAL MEDICINE, COMPUTER SCIENCE, ENGINEERING, SOCIAL SCIENCES, GENERAL, MEDICAL INFORMATICS, COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE, ENERGY & FUELS, INFORMATION SCIENCE & LIBRARY SCIENCE, Yapay Zeka, Fizik Bilimleri, Bilgisayar Bilimi Uygulamaları, Bilgisayarla Görme ve Örüntü Tanıma, Bilgi Sistemleri ve Yönetimi, Sosyal Bilimler ve Beşeri Bilimler, Enerji Mühendisliği ve Güç Teknolojisi, Tıbbi Bilişim, Artificial Intelligence, Physical Sciences, Computer Science Applications, Computer Vision and Pattern Recognition, Information Systems and Management, Social Sciences & Humanities, Energy Engineering and Power Technology, Health Informatics, deep neural networks, machine learning, thin film coating
Citation
Yenginer H., Eraslan S., Gundogdu B., KORKMAZ H., \"Performance of Hyperparameters in Prediction with Deep Neural Networks of Electrical Properties of Nano-Coated Glasses Nano-Kaplamali Camlarin Elektriksel zelliklerinin Derin Sinir Aglari Ile Tahmininde Hiper Parametrelerin Performansi\", 2023 Innovations in Intelligent Systems and Applications Conference, ASYU 2023, Sivas, Türkiye, 11 - 13 Ekim 2023