Kalite Değerlendirmesi için Portakal Özelliklerinin Makine Öğrenimi ile Sınıflandırılması

Öz

Portakallar narenciye ailesinin bir üyesidir ve yüksek C vitamini içeriği, tatlı ve ekşi tadı ve yararlı lif ve antioksidan nitelikleri nedeniyle büyük miktarlarda yenir. Portakalda kalite güvencesi, pazarda rekabet gücü ve müşteri memnuniyeti için çok önemlidir. Kaliteyi değerlendirmeye yönelik geleneksel yaklaşımlar maliyetlidir ve insanlar tarafından yapılan hatalara açıktır. Bu araştırma, farklı makine öğrenimi algoritmalarının portakal kalitesi değerlendirme prosedürünü ne kadar iyi otomatikleştirdiğini ve geliştirdiğini araştırmayı amaçlamaktadır. Rastgele Orman (RF), XGBoost ve k-En Yakın Komşular (k-NN) algoritmalarının etkinliğini değerlendirmek için 241 örnek ve 11 özellik (boyut, ağırlık, tatlılık (Brix), asitlik (pH) ve renk) içeren bir veri kümesi kullanılmıştır. Bulgulara göre, k-NN %69,38 ile en yüksek doğruluğu elde ederken, RF %67,34 ile ikinci ve XGBoost %63,26 ile üçüncü sırada yer aldı. Bu sonuçlar, makine öğrenimi modellerinin daha güvenilir ve etkili bir yaklaşım sunarak portakal endüstrisinde kalite kontrolünü iyileştirmek için nasıl kullanılabileceğini göstermektedir. Bu çalışmaya göre, makine öğrenimi portakallar için kalite kontrol prosedürlerini büyük ölçüde geliştirebilir, bu da müşteriler için daha yüksek kaliteli ürünler ve tedarikçiler için daha fazla üretkenlikle sonuçlanabilir. Portakal sektörü bu teknolojileri kullanarak ürün kalitesini artırabilir ve işlemleri hızlandırabilir; bu da sonuçta hem üreticilere hem de tüketicilere fayda sağlayacaktır.

Anahtar Kelimeler

• Yapay Zeka
• Kalite Sınıflandırma
• Portakal Kalitesi
• Makine Öğrenmesi Algoritmaları

Classification of Orange Features for Quality Assessment Using Machine Learning Methods

Öz

Oranges are a member of the citrus family and are eaten in large quantities due to their high vitamin C content, sweet and tart taste, and useful fiber and antioxidant qualities. Orange quality assurance is essential to market competitiveness and customer satisfaction. Conventional approaches to evaluating quality are costly and susceptible to mistakes made by people. This research aims to investigate how well different machine learning algorithms automate and improve the orange quality assessment procedure. A dataset containing 241 samples and 11 features (size, weight, sweetness (Brix), acidity (pH), and color) was used to evaluate the effectiveness of the Random Forest (RF), XGBoost, and k-Nearest Neighbors (k-NN) algorithms. According to the findings, k-NN acquired the maximum accuracy of 69.38%, with RF coming in second at 67.34% and XGBoost third at 63.26%. These results demonstrate how machine learning models may be used to improve quality control in the orange industry by offering a more dependable and effective approach. According to this study, machine learning can greatly improve the quality control procedures for oranges, resulting in higher-quality goods for customers and more productivity for providers. The orange sector can enhance product quality and expedite operations by utilizing these technologies, which will eventually benefit both producers and consumers.

Anahtar Kelimeler

• Artificial Inteeligence
• Quality Classification
• Orange Quality
• Machine Learning Algorithms

Kaynakça

1. Asriny DM, Rani S, Hidayatullah AF (2020). Orange fruit images classification using convolutional neural networks. IOP Conference Series: Materials Science and Engineering.
2. Cayuela JA, Weiland C (2010). Intact orange quality prediction with two portable NIR spectrometers. Postharvest Biology and Technology 58(2): 113-120. https://doi.org/10.1016/j.postharvbio.2010.06.001
3. Chen T, Guestrin C (2016). Xgboost: A scalable tree boosting system. Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining.
4. Cinar I, Taspinar YS, Koklu M. (2023). Development of early stage diabetes prediction model based on stacking approach. Tehnički Glasnik 17(2): 153-159. https://doi.org/10.31803/tg-20211119133806
5. Denata I, Rismawan T, Ruslianto I (2021). Implementation of deep learning for classification type of orange using the method convolutional neural network. Telematika: Jurnal Informatika dan Teknologi Informasi 18(3): 297-307. https://doi.org/10.31315/telematika.v18i3.5541
6. Ganesh P, Volle K, Burks T, Mehta S (2019). Deep orange: Mask R-CNN based orange detection and segmentation. Ifac-papersonline 52(30): 70-75. https://doi.org/10.1016/j.ifacol.2019.12.499
7. Gencturk B, Arsoy S, Taspinar YS, Cinar I, Kursun R, Yasin ET, Koklu M (2024). Detection of hazelnut varieties and development of mobile application with CNN data fusion feature reduction-based models. European Food Research and Technology 250(1): 97-110. https://doi.org/10.1007/s00217-023-04369-9
8. Guo G, Wang H, Bell D, Bi Y, Greer K (2003). KNN model-based approach in classification. On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE: OTM Confederated International Conferences, CoopIS, DOA, and ODBASE, November 3-7, 2003. Catania, Sicily, Italy.

9. Heydarian M, Doyle TE, Samavi R (2022). MLCM: Multi-label confusion matrix. IEEE Access 10: 19083-19095. https://doi.org/10.1109/ACCESS.2022.3151048
10. Koklu M, Cinar I, Taspinar YS, Kursun R (2022). Identification of sheep breeds by CNN-based pre-trained InceptionV3 model. 11th Mediterranean Conference on Embedded Computing (MECO),
11. Koklu M, Kahramanli H, Allahverdi N (2012). A new approach to classification rule extraction problem by the real value coding. International Journal of Innovative Computing, Information and Control 8(9): 6303-6315.
12. Koklu M, Kahramanli H, Allahverdi N (2014). A new accurate and efficient approach to extract classification rules. Journal of the Faculty of Engineering and Architecture of Gazi University 29(3). https://hdl.handle.net/20.500.12395/30550
13. Kumar S, Pandey AK, Raghav D, Gupta G, Srivastava V (2024). A deep learning approach for multiclass orange disease classification. 2nd International Conference on Disruptive Technologies (ICDT).
14. Kursun R, Bastas KK, Koklu M (2023). Segmentation of dry bean (Phaseolus vulgaris L.) leaf disease images with U-Net and classification using deep learning algorithms. European Food Research and Technology 249(10): 2543-2558. https://doi.org/10.1007/s00217-023-04319-5
15. Lorenzo-Seva U, Ferrando PJ (2021). Not positive definite correlation matrices in exploratory item factor analysis: Causes, consequences and a proposed solution. Structural Equation Modeling: A Multidisciplinary Journal 28(1): 138-147. https://doi.org/10.1080/10705511.2020.1735393
16. Santiago WE, Lopes GD, Faceto AD, Lobo Júnior A, Caldeira R (2019). Classification of oranges by digital image processing.
17. Sarica A, Cerasa A, Quattrone A (2017). Random forest algorithm for the classification of neuroimaging data in Alzheimer's disease: a systematic review. Frontiers in Aging Neuroscience 9: 329. https://doi.org/10.3389/fnagi.2017.00329
18. Shruthi (2024). Orange Quality Analysis Dataset. https://www.kaggle.com/datasets/shruthiiiee/orange-quality
19. Steiger JH (1980). Tests for comparing elements of a correlation matrix. Psychological Bulletin 87(2): 245. https://doi.org/10.1037/0033-2909.87.2.245
20. Tutuncu K, Cinar I, Kursun R, Koklu M (2022). Edible and poisonous mushrooms classification by machine learning algorithms. 11th Mediterranean Conference on Embedded Computing (MECO),
21. Yasin E, Koklu M (2023). Utilizing Random forests for the classification of pudina leaves through feature extraction with inceptionV3 and VGG19. Proceedings of the International Conference on New Trends in Applied Sciences.
22. Yildiz MB, Hafif MF, Koksoy EK, Kursun R (2024a). Classification of diseases in tomato leaves using deep learning methods. Intelligent Methods In Engineering Sciences 3(1): 22-36. https://doi.org/10.58190/imiens.2024.84
23. Yildiz MB, Yasin ET, Koklu M (2024b). Fisheye freshness detection using common deep learning algorithms and machine learning methods with a developed mobile application. European Food Research and Technology 1-14. https://doi.org/10.1007/s00217-024-04493-0
24. Yong CC (2019). Random forest for image classification. https://hdl.handle.net/10356/78792