| Yazarlar (1) |
Dr. Öğr. Üyesi Fatih UYSAL
Kafkas Üniversitesi, Türkiye |
| Özet |
| Electronic components of different sizes and types can be used in microelectronics, nanoelectronics, medical electronics, and optoelectronics. For this reason, accurate detection of all electronic components such as transistors, capacitors, resistors, light-emitting diodes and electronic chips is of great importance. For this purpose, in this study, an open source dataset was used for the detection of five different types of electronic components. In order to increase the amount of the dataset, firstly, data augmentation processes were performed by rotating the electronic component images at certain angles in the right and left directions. After these processes, multi-class classifications were performed using five different deep learning based neural network models, namely Vision Transformer, MobileNetV2, EfficientNet, Swin Transformer and Data-efficient Image Transformer. As a result of the electronic component detection processes performed with these various deep learning based models, all necessary evaluation metrics such as precision, recall, f1-score and accuracy were obtained for each model, and the highest accuracy value result was obtained as 0.992 in the Data-efficient Image Transformer model. |
| Anahtar Kelimeler |
| Artificial Intelligence | Deep Learning | Electronic Chip | Electronic Components | Transistor |
| Makale Türü | Özgün Makale |
| Makale Alt Türü | SCOPUS dergilerinde yayımlanan tam makale |
| Dergi Adı | International Journal of Computational and Experimental Science and Engineering |
| Dergi ISSN | 2149-9144 |
| Dergi Tarandığı Indeksler | TR DİZİN |
| Makale Dili | Türkçe |
| Basım Tarihi | 01-2025 |
| Cilt No | 11 |
| Sayı | 1 |
| Sayfalar | 542 / 549 |
| Doi Numarası | 10.22399/ijcesen.855 |
| Makale Linki | https://doi.org/10.22399/ijcesen.855 |
| Atıf Sayıları | |
| SCOPUS | 3 |
