Araştırma Makalesi
BibTex RIS Kaynak Göster

AlexNet Mimarisi ile Muz Olgunlaşma Evrelerinin Sınıflandırılması

Yıl 2023, , 135 - 141, 31.08.2023
https://doi.org/10.31590/ejosat.1252946

Öz

Muz lezzetli meyvelerin en başında yer almaktadır. Muzun besleyici değeri yüksektir. Aynı zamanda muz besin değerleri bakımından yüksektir. Muzun içeriğinde yoğun miktarda potasyum bulunmaktadır. Muz dalından yeşil olarak toplanmaktadır. Muz kopartıldıktan sonra çok hızlı olgunlaşmaktadır. Muz yeşilden sarıya döndükçe olgunlaşmaktadır. Sarı muz olgunlaşmış aynı zamanda tatlanmıştır. Yapılan çalışma ile muz meyvesinin yedi farklı olgunlaşma evresinin yapay zekâ ile tespiti sağlanmıştır. Bunun için muz meyvesinin dalından koparıldıktan sonra olgunlaşıncaya kadar resimleri çekilmiştir. Muz meyvesinin yedi farklı olgunlaşma evresinden 700 fotoğraf çekilmiştir. Bu fotoğraflarla bir veri seti oluşturulmuştur. Bu veri seti ile derin öğrenme ile sınıflandırması gerçekleştirilmiştir. Derin öğrenmede AlexNet mimarisi kullanılmıştır. AlexNet mimarisi ile %96,63 oranında bir doğruluk elde edilmiştir.

Kaynakça

  • Ağdaş, M, T., & Gülseçen, S. (2022). Automatic Weapon and Knife Detection System on Security Cameras: Comparative YOLO Models. European Journal of Science and Tecnology. 41, 16-22.
  • Bu, F., & Wang, X. (2019). A Smart Agriculture IoT system Basic on Deep Learning Reinforcement Learning. Future Generation Computer System. 99, 500- 507.
  • Chen, H., Chen, A., Xu, L., Xie, H., Qioa, H., Lin, Q., & Cai, K. (2020). A Deep Learning CNN Achitecture Applied in Smart Near-Inferad Analysis of Water Population for Agriculturel Irrigation Resources. Agriculturel Water Managemant. 240, 1-8,
  • Coulibaly, S., Kamsu B., & Kamissoko, D. (2022). Deep Learning for Precision Agriculture: A Bibliomtric Analysis. Intelligent System with Aplication. 16,1-18.
  • Gayani C, Kokul T, & Amalka P, A (2020). Comprehensive Study on Deep Image Classification with Small Datasets
  • Junxi F, Xiohai H, Qizhi T, Chao R, Honggang C, Yang L, (2019). Reconstruction of porous media from extremely limited information using conditional generative adversarial networks. Physical Review E 100, 033308
  • Isha G, Priyadarshini P, Kaushik R, (2019). A Low Effort Approach to Structured CNN Design Using PCA. IEEE Access, 1-12.
  • Natarajan S, (2019). Artificial Intelligence (AI) vs. Machine Learning vs. Deep Learning
  • Meshram, V., Patil, K., Meshram, V., Hanchate, D., & Ramkteke, S, D. (2020). Machine Learning in Agricultere Domain: A State of Art Survey. Artifical Intelligance in Thre Life Science. 1, 1-11.
  • Uzun, Y., Akkuzu, B., & Kayırıcı, M. (2021). The Relationship of Articaial Intelligence to Culture Art. European Journal of Science and Tecnology. 28, 753-757.
  • Sevi, M., Aydın, İ., & Karaköse, M. (2022). Classification of Railway Fasteners by Deep Learning Methods. European Journal of Science and Tecnology. 35, 268-274.
  • Tan, F, G., Yüksel, A, S., Aydemir, E., & Ersoy, M. (2021). A Rview On Object Detection and Tracking with Deep Learning Technique. European Journal of Science and Tecnology. 25, 157-171.
  • Tetilia, E, C., Machoda, B, B., Astolfi, G., Belete, N, A, S., Amorin, W, P., Roel, A, R., & Pistori, H. (2020). Dedection and Classification of Soybean Pets using Deep Learning with UAV Images. Computer and Electronics in Agriculture. 179, 1-11.

Classification of Banana Ripening Stages with AlexNet Architecture

Yıl 2023, , 135 - 141, 31.08.2023
https://doi.org/10.31590/ejosat.1252946

Öz

Banana is one of the most delicious fruits. Banana has high nutritional value. At the same time, bananas are high in nutritional values. Bananas contain a large amount of potassium. It is collected from the banana branch as green. Banana ripens very quickly after being picked. Banana ripens as it turns from green to yellow. Yellow bananas are ripe and sweetened at the same time. With the study, seven different ripening stages of banana fruit were determined by artificial intelligence. For this, pictures were taken of the banana fruit until it ripened after it was plucked from the branch. 700 photos were taken from five different ripening stages of the banana fruit. A data set was created with these photographs. With this data set, classification was carried out with deep learning. AlexNet architecture is used in deep learning. With the AlexNet architecture, an accuracy of 96.63% has been achieved.

Kaynakça

  • Ağdaş, M, T., & Gülseçen, S. (2022). Automatic Weapon and Knife Detection System on Security Cameras: Comparative YOLO Models. European Journal of Science and Tecnology. 41, 16-22.
  • Bu, F., & Wang, X. (2019). A Smart Agriculture IoT system Basic on Deep Learning Reinforcement Learning. Future Generation Computer System. 99, 500- 507.
  • Chen, H., Chen, A., Xu, L., Xie, H., Qioa, H., Lin, Q., & Cai, K. (2020). A Deep Learning CNN Achitecture Applied in Smart Near-Inferad Analysis of Water Population for Agriculturel Irrigation Resources. Agriculturel Water Managemant. 240, 1-8,
  • Coulibaly, S., Kamsu B., & Kamissoko, D. (2022). Deep Learning for Precision Agriculture: A Bibliomtric Analysis. Intelligent System with Aplication. 16,1-18.
  • Gayani C, Kokul T, & Amalka P, A (2020). Comprehensive Study on Deep Image Classification with Small Datasets
  • Junxi F, Xiohai H, Qizhi T, Chao R, Honggang C, Yang L, (2019). Reconstruction of porous media from extremely limited information using conditional generative adversarial networks. Physical Review E 100, 033308
  • Isha G, Priyadarshini P, Kaushik R, (2019). A Low Effort Approach to Structured CNN Design Using PCA. IEEE Access, 1-12.
  • Natarajan S, (2019). Artificial Intelligence (AI) vs. Machine Learning vs. Deep Learning
  • Meshram, V., Patil, K., Meshram, V., Hanchate, D., & Ramkteke, S, D. (2020). Machine Learning in Agricultere Domain: A State of Art Survey. Artifical Intelligance in Thre Life Science. 1, 1-11.
  • Uzun, Y., Akkuzu, B., & Kayırıcı, M. (2021). The Relationship of Articaial Intelligence to Culture Art. European Journal of Science and Tecnology. 28, 753-757.
  • Sevi, M., Aydın, İ., & Karaköse, M. (2022). Classification of Railway Fasteners by Deep Learning Methods. European Journal of Science and Tecnology. 35, 268-274.
  • Tan, F, G., Yüksel, A, S., Aydemir, E., & Ersoy, M. (2021). A Rview On Object Detection and Tracking with Deep Learning Technique. European Journal of Science and Tecnology. 25, 157-171.
  • Tetilia, E, C., Machoda, B, B., Astolfi, G., Belete, N, A, S., Amorin, W, P., Roel, A, R., & Pistori, H. (2020). Dedection and Classification of Soybean Pets using Deep Learning with UAV Images. Computer and Electronics in Agriculture. 179, 1-11.
Toplam 13 adet kaynakça vardır.

Ayrıntılar

Birincil Dil Türkçe
Konular Mühendislik
Bölüm Makaleler
Yazarlar

Selami Kesler 0000-0002-7027-1426

Abdil Karakan 0000-0003-1651-7568

Yüksel Oğuz 0000-0002-5233-151X

Erken Görünüm Tarihi 10 Eylül 2023
Yayımlanma Tarihi 31 Ağustos 2023
Yayımlandığı Sayı Yıl 2023

Kaynak Göster

APA Kesler, S., Karakan, A., & Oğuz, Y. (2023). AlexNet Mimarisi ile Muz Olgunlaşma Evrelerinin Sınıflandırılması. Avrupa Bilim Ve Teknoloji Dergisi(51), 135-141. https://doi.org/10.31590/ejosat.1252946