Yoğun Evrişimli Sinir Ağı ile Gökyüzü Görüntülerinden Hava Durumu Tespiti

Öz

Hava durumu koşulları değiştirilemez bir yapı olarak karşımıza çıkmaktadır. Ancak hava koşullarının tespit edilip belirlenmesi bireylerin fiziksel aktivitelerini planlamasında yardımcı olabilmektedir. Yapılan çalışmada farklı gökyüzü görüntüleri ile hava durumu tespiti işlemlerini son yıllarda bilgisayar alanında popüler çalışma konularından biri olan görüntü sınıflandırma yöntemleriyle gerçekleştirilmeye çalışılmıştır. Çalışmada farklı hava koşullarına ve çözünürlüklere sahip görüntüden oluşan veri seti kullanılmış. Görüntüler üzerinde görüntü işleme teknikleri uygulanarak görüntülerin özellik haritaları çıkarılmıştır. %96.4 doğruluk oranı ile sınıflandırma işlemi gerçekleştirilmiştir. Gerçekleştirilen sınıflandırma sayesinde doğruluk oranı yüksek, kısa zamanlı ve maliyeti düşük hava durumu tespiti gerçekleştirilebilir.

Anahtar Kelimeler

• Görüntü sınıflandırma
• Görüntü İşleme
• Veri Arttırma
• DenseNet

Weather Detection from Sky Images with Dense Convolutional Neural Network

Öz

Weather conditions appear as an unchangeable structure. However, determining and determining weather conditions can help individuals plan their physical activities. In the study, it has been tried to perform different sky images and weather detection processes with image classification methods, which is one of the popular work subjects in the computer field in recent years. In the study, a data set consisting of images with different weather conditions and resolutions was used. The number of images in the data set has been increased by using various data augmentation methods. The feature maps of the images were obtained by applying image processing techniques to the images. In the next part of the study, the classification process was carried out on the images with an accuracy rate of 96.4% using the DenseNet image classification model.

Anahtar Kelimeler

• Image classification
• Image Processing
• Data Augmentation
• DenseNet

Kaynakça

1. Ajayi GO, Wang Z (2019) Multi-class weather classification from still ımage using said ensemble method. In: Proceedings of 2019 South African Univ Power Eng Conf Mechatronics/Pattern.
2. Akgül, İ., & Funda, Akar. (2022). Derin Öğrenme Modeli ile Yüz İfadelerinden Duygu Tanıma. Journal of the Institute of Science and Technology, 12(1), 69-79.
3. Aydoğan, M., & Karci, A. (2020). Improving the accuracy using pre-trained word embeddings on deep neural networks for Turkish text classification. Physica A: Statistical Mechanics and its Applications, 541, 123288.
4. Bengio, Yoshua; LeCun, Yann; Hinton, Geoffrey, (2015). "Deep Learning". Nature, doi:10.1038/nature14539.
5. Bengio, Yoshua; Lee, Dong-Hyun; Bornschein, Jorg; Mesnard, Thomas; Lin, Zhouhan, (2015). Towards Biologically Plausible Deep Learning. arXiv:1502.04156v3.
6. Campbell, J.B, (1996). Introduction to Remote Sensing. Guilford Press, , New York, 621 s.
7. Dhananjaya, M. M., Kumar, V. R., & Yogamani, S. (2021). Weather and light level classification for autonomous driving: Dataset, baseline and active learning. In 2021 IEEE International Intelligent Transportation Systems Conference (ITSC) (pp. 2816-2821). IEEE.
8. Gao J., (2009). Digital analysis of remotely sensed imagery. The Mc Graw-Hill Companies, USA.

9. Gu J, Wang Z, Kuen J, Ma L, Shahroudy A, Shuai B, Chen T, et al., (2018). Recent advances in convolutional neural networks. arXiv:1512.07108.
10. Hanbay K., (2020). Hyperspectral image classification using convolutional neural network and two-dimensional complex Gabor transform. Journal of the faculty of engıneerıng and archıtecture of gazı unıversıty, 35(1):443-456.
11. Huang G, Liu Z, Van Der Maaten L, Weinberger KQ., (2017). Densely connected convolutional networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu:IEEE p. 4700-4708.
12. Huntingford, C., Jeffers, E.S., Bonsall, M.B., Christensen, H.M., Lees, T., Yang, H., (2019). Machine learning and artificial intelligence to aid climate change research and preparedness. Environ. Res. Lett. 14 (12), 124007. https://doi.org/10.1088/1748-9326/ab4e55.
13. Jehong An, Yunfan Chen, Hyunchul Shin, (2018). Weather Classification using Convolutional Neural Networks. 2018 International SoC Design Conference (ISOCC), https://doi.org/10.1109/ISOCC.2018.8649921.
14. Jose Carlos Villarreal Guerra, Zeba Khanam, Shoaib Ehsan, Rustam Stolkin, Klaus McDonald-Maier, (2018). Weather Classification: A new multi-class dataset, data augmentation approach and comprehensive evaluations of Convolutional Neural Networks. 2018 NASA/ESA Conference on Adaptive Hardware and Systems(AHS).,https://doi.org/10.1109/AHS.2018.8541482.
15. Kumar R., (2019). Adding binary search connections to ımprove densenet performance. 5th International Conference on Next Generation Computing Technologies, Dehradun: NGCT- 2019;2019. SSRN: https://ssrn.com/abstract=3545071.
16. Kurt F., (2018). Sinir Ağlarında Hiper Parametrelerin Etkisinin İncelenmesi. Ankara:Hacettepe Üniversitesi.
17. L. Deng and D. Yu, , (2014). “Deep Learning: Methods and Applications,” Found. Trends® Signal Process., vol. 7, no. 3–4, pp. 197–387.
18. Li X, Shen X, Zhou Y, Wang X, Li TQ., (2020). Classification of breast cancer histopathological images using interleaved DenseNet with SENet (IDSNet). PloS One. 2020;15(5):e0232127.
19. Li-Wei Kang, Ke-Lin Chou, Ru-Hong Fu, (2018). Deep Learning-Based Weather Image Recognition. 2018 International Symposium on Computer, Consumer and Control(IS3C).https://doi.org/10.1109/IS3C.2018.00103.
20. Manzo, M., & Pellino, S. (2021). Voting in transfer learning system for ground-based cloud classification. Machine Learning and Knowledge Extraction, 3(3), 542-553.
21. Marblestone, A. H., Wayne, G., & Kording, K. P. (2016). Toward an integration of deep learning and neuroscience. Frontiers in computational neuroscience, 94.
22. Milletari F. Navab N. Ahmadi SA., (2016). V-net: Fully convolutional neural networks for volumetric medical image segmentation. Fourth International Conference on 3D Vision, 3DV 2016. ABD: IEEE; 2016. p. 565- 571.
23. Min S, Lee B, Yoon S., (2017). Deep learning in bioinformatics. Briefings in bioinformatics, 2017;18(5):851-869.
24. Mirbabaie, M., Stieglitz, S., Frick, N.R.J., (2021). Artificial intelligence in disease diagnostics: A critical review and classification on the current state of research guiding future direction. Health Technol. (Berl) 11 (4), 693–731. https://doi.org/10.1007/s12553-021-00555-5.
25. Niepert M. Ahmed M. Kutzkov K., (2014). Learning convolutional neural networks for graphs. In International conference on machine learning, . Germany:2016. p. 2014-2023.
26. Olshausen, B. A., (1996). Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature, 381 (6583): 607–609. Bibcode:1996Natur.381..607O.doi:10.1038/381607a0. PMID 8637596. S2CID 4358477.
27. Pacal, I., & Karaboga, D. (2021). A robust real-time deep learning based automatic polyp detection system. Computers in Biology and Medicine, 134, 104519.
28. Pacal, I., Karaboga, D., Basturk, A., Akay, B., & Nalbantoglu, U. (2020). A comprehensive review of deep learning in colon cancer. Computers in Biology and Medicine, 126, 104003.
29. Schultz, M., Reitmann, S., & Alam, S. (2021). Predictive classification and understanding of weather impact on airport performance through machine learning. Transportation Research Part C: Emerging Technologies, 131, 103119.
30. Şahin, F., Işik, G., Şahin, G., & Kara, M. K. (2020). Estimation of PM10 levels using feed forward neural networks in Igdir, Turkey. Urban Climate, 34, 100721.
31. Toğaçar, M., & Ergen, B. (2019). Biyomedikal Görüntülerde Derin Öğrenme ile Mevcut Yöntemlerin Kıyaslanması. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 31(1), 109-121.
32. Toğaçar, M., & Ergen, B. (2022). Classification of cloud images by using super resolution, semantic segmentation approaches and binary sailfish optimization method with deep learning model. Computers and Electronics in Agriculture, 193, 106724.
33. Toğaçar, Mesut; Ergen, Burhan; Cömert, Zafer. (2021) Detection of weather images by using spiking neural networks of deep learning models. Neural Computing and Applications, 33.11: 6147-6159.
34. Triva, J., Grbić, R., Vranješ, M., & Teslić, N. (2022). Weather Condition Classification in Vehicle Environment Based on Front-View Camera Images. In 2022 21st International Symposium INFOTEH-JAHORINA (INFOTEH) (pp. 1-4). IEEE.
35. Veri Seti: https://www.kaggle.com/vijaygiitk/multiclass-weather-dataset (15.11.2021).
36. Wilkie, D. S., (1996). Remote sensing imagery for natural resources monitoring: a guide for first-time users. Columbia Univ. Press.
37. X. Liu, Z. Deng, Y. Yang,, (2019). Recent progress in semantic image segmentation. Artif. Intell. Rev. 52 (2019), 1089–1106, https://doi.org/10.1007/s10462-018-9641-3.
38. Y. Lecun, Y. Bengio, G. (2015) .Hinton, Deep learning, Nature 521 436–444, https://doi.org/10.1038/nature14539.