Kurum Üzüm Tanelerinin Sınıflandırılması İçin Hibrit Bir Yaklaşım

Yıl 2022, , 62 - 71, 29.04.2022

Serhat Kılıçarslan

https://doi.org/10.46387/bjesr.1084590

Cited By: 2

Öz

Kuru üzüm içeriğinde barındırdığı mineraller ve vitaminlerden kaynaklı çok iyi bir enerji ve besin kaynağı olarak karşımıza çıkmaktadır. Dünya genelindeki kuru üzümün %23’ü Türkiye’deki topraklardan elde edilmektedir. Geleneksel olarak, kuru üzümün cinsine ve kalitesine karar vermek uzun ve maliyetli bir süreçtir. Ayrıca, kuru üzümün cinsinin belirlenmesinde tecrübe ve bilgi birikimler önem arz etmektedir. Bu nedenle, kuru üzümün doğru sınıflandırılabilmesi açısından veri madenciliği yöntemleri ile karar destek siteminin geliştirilmesi önemlidir. Bu çalışmada, kuru üzüm tanelerinin türünün tahmini için rotasyon ormanı (RO) ve yığınlanmış otokodlayıcı (YOK) derin öğrenme algoritmalarını kullanan bir hibrit model öneriyoruz. Deneysel değerlendirme sonucunda, hibrit YOKRO yöntemi çalışmada kullanılan klasik veri madenciliği yöntemleri ile derin öğrenme yöntemlerinden performans açısından %91,50 ile yüksek başarı elde edilmiştir.

Anahtar Kelimeler

Kuru Üzüm Taneleri, Derin Öğrenme, Klasik Veri Madenciliği, Hibrit, Sınıflandırma

A Hybrid Approach for Raisin Grains Classification

Öz

Raisin grains are a very good source of energy and nutrients due to the minerals and vitamins they contain. Since raisins constitute 23% of the world in Turkey, it is important to determine the variety and quality. Traditionally, deciding on the type and quality of raisin grains is a long and costly process. In addition, experience and knowledge are important in determining the type of raisin grains. In addition, since each of the experts has different experience, knowledge and expertise, there is a difference in terms of classification of raisins. Therefore, it is important to develop a decision support system with data mining methods for the correct classification of raisin grains. In this study, we propose one hybrid model using rotation forest (RO) and deep learning algorithms of Stacked Autoencoder (SAE) for the prediction of the type of raisin grains. As a result of the experimental evaluation, the hybrid SAE-ROF method has achieved a high success rate of 91.50% in terms of performance from the classical data mining methods and deep learning methods used in the study.

Anahtar Kelimeler

Raisin Grains, Deep Learning, Classical Data Mining, Hybrid, Classification, Hybrid, Classification

Kaynakça

• Uzun, T. , Hallaç, B. , Altın, A. & Kaya, G., “Midyat/Mardin ve Beşiri/Batman İlçelerinde Satışa Sunulan Bazı Kuru Üzüm Çeşitlerinin Fizikokimyasal Özelliklerinin Karşılaştırılması”, Turkish Journal of Agricultural Engineering Research, vol.1, no. 2, pp. 404-414, 2020.
• Karimi, N., Kondrood, R. R., & Alizadeh, T., “An intelligent system for quality measurement of Golden Bleached raisins using two comparative machine learning algorithms”, Measurement, vol. 107, pp. 68-76, 2017.
• Çınar, İ. , Koklu, M. & Taşdemir, P. D. Ş., “Classification of Raisin Grains Using Machine Vision and Artificial Intelligence Methods”, Gazi Mühendislik Bilimleri Dergisi (GMBD), vol. 6, no. 3, pp. 200-209, 2020.
• Mollazade, K., Omid, M., & Arefi, A., “Comparing data mining classifiers for grading raisins based on visual features”, Computers and electronics in agriculture, vol. 84, pp. 124-131, 2012.
• Wang, S., Liu, K., Yu, X., Wu, D., & He, Y., “Application of hybrid image features for fast and non-invasive classification of raisin”, Journal of food engineering, vol. 109, no. 3, pp. 531-537, 2012.
• Yu, X., Liu, K., Wu, D., & He, Y., “Raisin quality classification using least squares support vector machine (LSSVM) based on combined color and texture features”, Food and Bioprocess Technology, vol. 5, no. 5, pp. 1552-1563, 2012.
• Adem, K., Kiliçarslan, S., & Cömert, O., “Classification and diagnosis of cervical cancer with stacked autoencoder and softmax classification”, Expert Systems with Applications, vol. 115, pp. 557-564, 2019.
• Kilicarslan, S., Adem, K., & Celik, M., “Diagnosis and classification of cancer using hybrid model based on ReliefF and convolutional neural network”, Medical hypotheses, vol. 137, no. 109577, 2020.
• Kilicarslan, S., Celik, M., & SAHIN, Ş., “Hybrid models based on genetic algorithm and deep learning algorithms for nutritional Anemia disease classification”, Biomedical Signal Processing and Control, vol. 63, no. 102231, 2021.
• Cui, M., Wang, Y., Lin, X., & Zhong, M., “Fault diagnosis of rolling bearings based on an improved stack autoencoder and support vector machine”, IEEE Sensors Journal, vol. 21, no. 4, pp. 4927-4937, 2020.
• Kaynar, O., Aydın, Z., & Görmez, Y., “Sentiment Analizinde Öznitelik Düşürme Yöntemlerinin Oto Kodlayıcılı Derin Öğrenme Makinaları ile Karşılaştırılması”, Bilişim Teknolojileri Dergisi, vol. 10, no. 3, pp.319-326, 2017.
• Bengio, Y., “Learning deep architectures for AI”, Foundations and Trends in Machine Learning, vol. 2, no. 1, pp. 1-127, 2009.
• Chen, W., Gou, S., Wang, X., Li, X., & Jiao, L., “Classification of PolSAR Images Using Multilayer Autoencoders and a Self-Paced Learning Approach”, Remote Sensing, vol. 10, no. 1,pp. 1-17, 2018.
• Erkan, U., “A precise and stable machine learning algorithm: eigenvalue classification (EigenClass)”, Neural Computing and Applications, vol. 33, no. 10, pp. 5381-5392, 2021.
• Pacal, I., & Karaboga, D., “A Robust Real-Time Deep Learning Based Automatic Polyp Detection System”, Computers in Biology and Medicine, no. 104519, 2021.
• Pacal, I., Karaboga, D., Basturk, A., Akay, B., & Nalbantoglu, U., “A comprehensive review of deep learning in colon cancer”, Computers in Biology and Medicine, no. 104003, 2020.
• Ozkok, F. O., & Celik, M., “A hybrid CNN-LSTM model for high resolution melting curve classification”, Biomedical Signal Processing and Control, vol. 71, no. 103168, 2022.
• Adem, K., & Kılıçarslan, S., “COVID-19 Diagnosis Prediction in Emergency Care Patients using Convolutional Neural Network”, Afyon Kocatepe Üniversitesi Fen Ve Mühendislik Bilimleri Dergisi, vol 2. No. 2, pp. 300-309, 2021.
• Adem, K., “Diagnosis of breast cancer with Stacked autoencoder and Subspace kNN”, Physica A: Statistical Mechanics and its Applications, vol. 551, no. 124591, 2020.
• Bülbül, M. A., & Öztürk, C., “Optimization, Modeling and Implementation of Plant Water Consumption Control Using Genetic Algorithm and Artificial Neural Network in a Hybrid Structure”, Arabian Journal for Science and Engineering, vol. 47, no. 2, pp. 1-15, 2021.
• Memiş, S., Enginoğlu, S., & Erkan, U., “Numerical data classification via distance-based similarity measures of fuzzy parameterized fuzzy soft matrices”, IEEE Access, vol. 9, pp. 88583-88601, 2021.
• Kılıçarslan, S., & Çelik, M., “Rotasyon orman sınıflandırma algoritması kullanarak kronik böbrek rahatsızlığının tahmini”, Journal of Science and Technology of Dumlupınar University, no. 43, pp. 21-34, 2019.
• Rodríguez, J. J., Kuncheva, L. I., & Alonso, C. J., “Rotation forest: A New classifier ensemble method”, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 2810, pp. 1619–1630, 2006.
• Akçetin, E., & Çelik, U., “İstenmeyen Elektronik Posta (Spam) Tespitinde Karar Ağacı Algoritmalarının Performans Kıyaslaması”, Journal of Internet Applications & Management/İnternet Uygulamaları ve Yönetimi Dergisi, vol. 5, no. 2, pp. 1-20, 2014.
• Namlı, Ö. H., & Özcan, T., “Makine Öğrenmesi Algoritmaları Kullanarak Gişe Hasılatının Tahmini”, Yönetim Bilişim Sistemleri Dergisi, vol. 3, no. 2, pp. 130-143, 2017.
• Çıtak, D., & Sabancı, D., “ Response surface methodology and hydrophobic deep eutectic solvent based liquid phase microextraction combination for determination of cadmium in food and water samples”, Journal of Food Measurement and Characterization, vol. 15, no. 2, pp. 1843-1850, 2021.
• Kiliçarslan, S., & Celik, M., “RSigELU: A nonlinear activation function for deep neural networks”, Expert Systems with Applications, vol. 174, no. 114805, 2021.
• Okamura, N. K., Delwiche, M. J., & Thompson, J. F., “Raisin grading by machine vision”, Transactions of the ASAE (USA), vol. 2, no. 36, pp. 485-492, 1993.
• Abuzir, Saleh, and Yousef Abuzir. "Data Mining For CO2 Emissions Prediction In Italy." Mühendislik Bilimleri ve Araştırmaları Dergisi , vol. 3, no. 1, pp. 59-68, 2020.