Yağ Gülü (Rosa damascena Mill.) Bitkisinin Hasat Durumunun Makine Öğrenmesi ve Derin Öğrenme Yöntemleri ile Tespiti

Abstract

Bitkiler uzun yıllardır çoğu sektörde insan hayatında önemli bir yer tutmaktadır. Pembe Yağ Gülü olarak adlandırılan Rosa damascena Mill. bitkisi, gül çeşitleri arasında kendine özgü keskin ve yoğun kokusu ile kozmetik, parfüm, ilaç ve gıda endüstrisi gibi sektörler için ekonomik değeri olan bir türdür. Türkiye’de Mayıs aylarında hasadına başlanan yağ gülü, tomurcuklarının çiçek açması durumunda hasadı yapılmaktadır. Tomurcuk halindeki güller ise açması durumuna kadar hasat edilmeden bırakılmaktadır. Bu çalışmada makine öğrenmesi ve derin öğrenme yöntemleri kullanarak her bir yağ gülünün “hasat edilebilir/hasat edilemez” durumuna göre ikili sınıflandırılması gerçekleştirilmiştir. Gül bahçelarinden elde edilen görüntüler ile oluşturulan veri seti, yapay zekâ modellerinin eğitim ve testinde kullanılmıştır. Makine öğrenmesi modeli olarak DVM sınıflandırıcısı, derin öğrenme modelleri olarak da VGG16, VGG19 ve InceptionV3 kullanılmıştır. Sınıflandırma başarımı; DVM modelinde %71.06, VGG16 modelinde %96.44, VGG19 modelinde %97.96 ve InceptionV3 modelinde %72.08 olarak elde edilmiştir.

Keywords

• Makine öğrenmesi
• Derin öğrenme
• Rosa damascena Mill.
• DVM
• VGG16
• VGG19
• InceptionV3

Detection of Harvest Status of Oil Rose (Rosa damascena Mill.) with Machine Learning and Deep Learning Methods

Abstract

Plants have an important place in human life in many sectors for many years. Rosa damascena Mill plant, which is called Pink Oil Rose, is a species that has economic value for sectors such as cosmetics, perfume, medicine and food industry with its distinctive sharp and intense scent among rose varieties. Oil rose is harvested in May in Turkey when its buds bloom. Roses in bud form are left unharvested until they bloom. In this study, binary classification of each oil rose according to "harvestable/non-harvestable" status was carried out using machine learning and deep learning methods. The data set created with the images obtained from the rose gardens was used in the training and testing of artificial intelligence models. DVM classifier was used as machine learning model, and VGG16, VGG19 and InceptionV3 were used as deep learning models. Classification performance is 71.06% in the DVM model, 96.44% in the VGG16 model, 97.96% in the VGG19 model and 72.08% in the InceptionV3 model.

Keywords

• Machine learning
• Deep learning
• Rosa damascena Mill.
• InceptionV3
• VGG16
• VGG19

References

1. [1]. Gökdoğan, O., Isparta yöresinde yağ gülü yetiştiriciliğinin Türkiye ekonomisindeki yeri. Süleyman Demirel Üniversitesi Sos Bilim Enstitüsü Derg., Published online 2013,51-58.
2. [2]. Dilmen, R., Baydar, NG., Yağ Gülü (Rosa damascena Mill.)’nün mikroçoğaltımında en uygun sürgün ve köklenme ortamlarının belirlenmesi. Süleyman Demirel Üniversitesi Fen Bilim Enstitüsü Derg., 2020;24(1),209-216.
3. [3]. Baydar, H., Erbaş, S., Kıneci, S., Kazaz, S., Yağ gülü (Rosa damascena Mill.) damıtma suyuna katılan tween-20’nin taze ve fermente olmuş çiçeklerin gül yağı verimi ve kalitesi üzerine etkisi. Ziraat Fakültesi Derg., 2007;2(1),15-20.
4. [4]. Mileva, M., Krumova, E., Miteva-Staleva, J., Kostadinova, N., Dobreva, A., Galabov, AS., Chemical compounds, in vitr o antioxidant and antifungal activities of some plant essentia l oils belonging to Rosaceae family. Compt Rend Acad Bulg Sci., 2014;67(10),1363-1368.
5. [5]. Özkan, G., Sagdiç, O., Baydar, NG., Baydar, H., Note, Antioxidant and antibacterial activities of Rosa damascena flower extracts. Food Sci Technol Int., 2004;10(4),277-281.
6. [6]. Khosh-Khui, M., Biotechnology of scented roses: a review. Int J Hortic Sci Technol., 2014;1(1),1-20.
7. [7]. Niazi, M., Hashempur, MH., Taghizadeh, M., Heydari, M., Shariat, A., Efficacy of topical Rose (Rosa damascena Mill.) oil for migraine headache: A randomized double-blinded placebo-controlled cross-over trial. Complement Ther Med., 2017;34,35-41.
8. [8]. Heydari, N., Abootalebi, M., Jamalimoghadam, N., Kasraeian, M., Emamghoreishi, M., Akbarzaded, M., Evaluation of aromatherapy with essential oils of Rosa damascena for the management of premenstrual syndrome. Int J Gynecol Obstet., 2018;142(2),156-161.

9. [9]. Dagli, R., Avcu, M., Metin, M., Kiymaz, S., Ciftci, H., The effects of aromatherapy using rose oil (Rosa damascena Mill.) on preoperative anxiety: A prospective randomized clinical trial. Eur J Integr Med., 2019;26,37-42.
10. [10]. Anonim. Tarım Ürünleri Piyasaları Gül. Tarım Ürünleri Piyasaları. Published 2021.
11. https://arastirma.tarimorman.gov.tr/tepge/Belgeler/PDF Tarım Ürünleri Piyasaları/2021-Haziran Tarım Ürünleri Raporu/Gül, Haziran-2021, Tarım Ürünleri Piyasa Raporu, TEPGE.pdf
12. [11]. Gorji-Chakespari, A., Nikbakht, AM., Sefidkon, F., Ghasemi-Varnamkhasti, M., Brezmes, J., Llobet, E., Performance comparison of fuzzy ARTMAP and LDA in qualitative classification of iranian rosa damascena essential oils by an electronic nose. Sensors, 2016;16(5),636.
13. [12]. Gorji Chakespari, A., Mohammad Nilbakht, A., Sefidkon, F., Ghasemi Varnamkhasti, M., Investigation of electronic nose system in classification of Rosa damascena Mill. essential oil by artificial neural network. Iran J Med Aromat Plants Res., 2017;33(3),339-349.
14. [13]. Rodrigues D de, A., Ivo, RF., Satapathy, SC., Wang, S., Hemanth, J., Reboucas Filho, PP., A new approach for classification skin lesion based on transfer learning, deep learning, and IoT system. Pattern Recognit Lett., 2020;136,8-15.
15. [14]. Patra, S., Middya, AI., Roy, S., PotSpot: Participatory sensing based monitoring system for pothole detection using deep learning. Multimed Tools Appl., 2021;80(16),25171-25195.
16. [15]. Pancholi, N., Goel, S., Nijhawan, R., Gupta, S., Classification and Detection of Acne on the Skin using Deep Learning Algorithms. In: 2021 19th OITS International Conference on Information Technology (OCIT). IEEE, 2021,110-114.
17. [16]. Ünal, Y., Öztürk, Ş., Dudak, MN., Ekici, M., Comparison of Current Convolutional Neural Network Architectures for Classification of Damaged and Undamaged Cars. In: Advances in Deep Learning, Artificial Intelligence and Robotics. Springer, 2022:141-149.
18. [17]. Vivek, P., Goel, S., Nijhawan, R., Gupta, S., CNN Models and Machine Learning Classifiers for Analysis of Goiter Disease. In: 2022 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS). IEEE, 2022,1-6.
19. [18]. Malik, M., Ikram A., Batool S. N., and Aslam W., “A performance assessment of rose plant classification using machine learning,” in International Conference on Intelligent Technologies and Applications, 2018, pp. 745–756.
20. [19]. Köse, U., Zeki optimizasyon tabanlı destek vektör makineleri ile diyabet teşhisi. Politek Derg., 2019;22(3),557-566.
21. [20]. Metlek, S., Kayaalp, K., Derin Öğrenme ve Destek Vektör Makineleri İle Görüntüden Cinsiyet Tahmini. Düzce Üniversitesi Bilim ve Teknol Derg., 2020,8(3),2208-2228.
22. [21]. Vapnik, VN., Lerner, AY., Recognition of patterns with help of generalized portraits. Avtomat i Telemekh. 1963,24(6),774-780.
23. [22]. Boser, BE., Guyon, IM., Vapnik, VN., A training algorithm for optimal margin classifiers. In: Proceedings of the 5th Annual ACM Workshop on Computational Learning Theory, 1992,144-152.
24. [23]. Battineni, G., Chintalapudi, N., Amenta, F., Machine learning in medicine: Performance calculation of dementia prediction by support vector machines (SVM). Informatics Med Unlocked, 2019,16,100200.
25. [24]. Sui, X., Wan, K., Zhang, Y., Pattern recognition of SEMG based on wavelet packet transform and improved SVM. Optik (Stuttg), 2019,176,228-235.
26. [25]. Cervantes, J., Garcia-Lamont, F., Rodríguez-Mazahua, L., Lopez, A., A comprehensive survey on support vector machine classification: Applications, challenges and trends, Neurocomputing, 2020,408,189-215.
27. [26]. Metlek, S., Kayaalp, K., Makine Öğrenmesinde, Teoriden Örnek MATLAB Uygulamalarına Kadar Destek Vektör Makineleri, İksad Yayınevi, Published online 2020.
28. [27]. Chang, Y-W., Hsieh, C-J., Chang, K-W., Ringgaard, M., Lin, C-J., Training and testing low-degree polynomial data mappings via linear SVM. J Mach Learn Res., 2010,11(4).
29. [28]. Chaudhuri, A., De, K., Fuzzy support vector machine for bankruptcy prediction. Appl Soft Comput., 2011,11(2),2472-2486.
30. [29]. Sanjaa, B., Chuluun, E., Malware detection using linear SVM. Ifost., Vol 2. IEEE, 2013,136-138.
31. [30]. Simonyan, K., Zisserman, A., Very deep convolutional networks for large-scale image recognition. arXiv Prepr arXiv14091556. Published online 2014.
32. [31]. Neurohive, VGG16 – Convolutional Network for Classification and Detection. Published 2018. https://neurohive.io/en/popular-networks/vgg16/
33. [32]. Krishnaswamy Rangarajan, A., Purushothaman, R., Disease classification in eggplant using pre-trained VGG16 and MSVM, Sci Rep., 2020,10(1),1-11.
34. [33]. Swasono, DI., Tjandrasa, H., Fathicah, C., Classification of tobacco leaf pests using VGG16 transfer learning. 2019 12th International Conference on Information & Communication Technology and System (ICTS), IEEE, 2019,176-181.
35. [34]. Pravitasari, AA., Iriawan, N., Almuhayar, M., et al. UNet-VGG16 with transfer learning for MRI-based brain tumor segmentation, Telkomnika, 2020,18(3),1310-1318.
36. [35]. Chhabra, M., Kumar, R., An Advanced VGG16 Architecture-Based Deep Learning Model to Detect Pneumonia from Medical Images, Emergent Converging Technologies and Biomedical Systems, Springer, 2022,457-471.
37. [36]. Patilkulkarni, S., Visual speech recognition for small scale dataset using VGG16 convolution neural network, Multimed Tools Appl, 2021,80(19),28941-28952.
38. [37]. Hridayami, P., Putra, IKGD., Wibawa, KS., Fish species recognition using VGG16 deep convolutional neural network. J Comput Sci Eng. 2019,13(3),124-130.
39. [38]. Dubey, AK., Jain, V., Automatic facial recognition using VGG16 based transfer learning model, J Inf Optim Sci., 2020,41(7),1589-1596.
40. [39]. Mateen, M., Wen, J., Song, S., Huang, Z., Fundus image classification using VGG-19 architecture with PCA and SVD, Symmetry (Basel), 2018,11(1),1.
41. [40]. Mahdianpari, M., Salehi, B., Rezaee, M., Mohammadimanesh, F., Zhang, Y., Very deep convolutional neural networks for complex land cover mapping using multispectral remote sensing imagery, Remote Sens., 2018,10(7),1119.
42. [41]. Rajinikanth, V., Joseph Raj, AN., Thanaraj, KP., Naik, GR., A customized VGG19 network with concatenation of deep and handcrafted features for brain tumor detection, Appl Sci., 2020,10(10),3429.
43. [42]. Zhou, J., Yang, X., Zhang, L., Shao, S., Bian, G., Multisignal VGG19 network with transposed convolution for rotating machinery fault diagnosis based on deep transfer learning, Shock Vib., 2020,2020.
44. [43]. Awan, MJ., Masood, OA., Mohammed, MA., et al. Image-Based Malware Classification Using VGG19 Network and Spatial Convolutional Attention, Electronics, 2021,10(19),2444.
45. [44]. Cheng, S., Zhou, G., Facial expression recognition method based on improved VGG convolutional neural network, Int J Pattern Recognit Artif Intell., 2020,34(07),2056003.
46. [45]. Subetha, T., Khilar, R., Christo, MS., A comparative analysis on plant pathology classification using deep learning architecture–Resnet and VGG19, Mater Today Proc., Published online 2021.
47. [46]. Setiawan, W., Damayanti, F., Layers modification of convolutional neural network for pneumonia detection, Journal of Physics: Conference Series, Vol 1477. IOP Publishing, 2020,52055.
48. [47]. Szegedy, C., Liu, W., Jia, Y., et al. Going deeper with convolutions, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015,1-9.
49. [48]. Li, Y., Liu, L., Image quality classification algorithm based on InceptionV3 and SVM. MATEC Web of Conferences, Vol 277, EDP Sciences, 2019,2036.
50. [49]. Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z., Rethinking the inception architecture for computer vision, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016,2818-2826.
51. [50]. Ali, L., Alnajjar, F., Jassmi, H., Gochoo, M., Khan, W., Serhani, MA., Performance evaluation of deep CNN-based crack detection and localization techniques for concrete structures. Sensors, 2021,21(5),1688.
52. [51]. Al Husaini, MAS., Habaebi, MH., Gunawan, TS., Islam, MR., Elsheikh, EAA., Suliman, FM., Thermal-based early breast cancer detection using inception V3, inception V4 and modified inception MV4, Neural Comput Appl., 2022,34(1),333-348.
53. [52]. Tallapragada, VV., Alivelu Manga, N., Nagabhushanam, MV., Venkatanaresh, M., Greek Handwritten Character Recognition Using Inception V3, Smart Systems, Innovations in Computing, Springer, 2022,247-257.
54. [53]. Jaithavil, D., Triamlumlerd, S., Pracha, M., Paddy seed variety classification using transfer learning based on deep learning, 2022 International Electrical Engineering Congress (IEECON), IEEE, 2022,1-4.
55. [54]. Duman, B., Özsoy, K., Toz yatak füzyon birleştirme eklemeli imalatta kusur tespiti için öğrenme aktarımı kullanan derin öğrenme tabanlı bir yaklaşım, Gazi Üniversitesi Mühendislik Mimar Fakültesi Derg., 2022,37(1),361-376.
56. [55]. Awais, M., Long, X., Yin, B., et al. Can pre-trained convolutional neural networks be directly used as a feature extractor for video-based neonatal sleep and wake classification?, BMC Res Notes, 2020,13(1),1-6.
57. [56]. Noor, FNM., Mohd Isa, WH., Khairuddin, IM., et al. The Diagnosis of Diabetic Retinopathy, A Transfer Learning with Support Vector Machine Approach, International Conference on Innovative Technology, Engineering and Science, Springer, 2020,391-398.
58. [57]. Gour, M., Jain, S., Sunil Kumar, T., Residual learning based CNN for breast cancer histopathological image classification. Int J Imaging Syst Technol, 2020,30(3),621-635.
59. [58]. Abhishek, A., Jha, RK., Sinha, R., Jha, K., Automated classification of acute leukemia on a heterogeneous dataset using machine learning and deep learning techniques, Biomed Signal Process Control, 2022,72,103341.
60. [59]. Srivastava, S., Kumar, P., Mohd, N., Singh, A., Gill FS. A Novel Deep Learning Framework Approach for Sugarcane Disease Detection, SN Comput Sci., 2020;1(2),1-7.