Hiperspektral Verilerde J48 Sınıflandırma Ağacı Algoritmaları ile Bazı Biyokimyasal Özelliklerin Sınıflandırılması

Abstract

Hiperspektral algılama yöntemleri tarımda uzun yıllar bitkilerin abiyotik ve biyotik stres faktörlerine karşı fizyolojik olayların belirlenmesinde kullanılmaktadır. Sürdürülebilir tarımsal üretim modelleri altındaki bitkilerin görünür ve yakın kızılötesi bölgedeki hiperspektral verileri kullanılarak biyokimyasal özellikler ile ilişkili dalga boylarının belirlenmesi üzerine araştırmalar sınırlı sayıdadır. Bu araştırmada, sürdürülebilir üretim modellerinden organik tarım yapılan tıbbı ve aromatik bitkilerden coğrafi işaretli Isparta Yağ gülü abiyotik ve biyotik stres faktörlerinden kültürel uygulamalardan kaynaklı etkinin en az olması göz önüne alınarak kullanılmıştır. Organik tarım yapılan Isparta Yağ gülü yapraklarında hiperspektral ölçümler ve klorofil a (mg g-1), klorofil b (mg g-1), klorofil a+b (mg g-1), toplam flavonoid madde içeriği (mg catechin g-1), toplam fenolik madde içeriği (mg GAE g-1) ve toplam antioksidan kapasitesi (mg TEAC g-1) biyokimyasal özelliklerin J48 sınıflandırma ağacı algoritması kullanılarak öznitelik seçimi yapılmıştır. Sınıflandırma algoritmasında her bir biyokimyasal özellik için bağımsız değişken olarak farklı hiperspektral veriler (bantlar) kullanırken, bağımlı değişken her bir biyokimyasal özelliklerinin miktarlarının ortalamaya göre düşük ve yüksek olması ikili yanıt değişkeni (binary) şeklinde modele alınmıştır. Bağımsız değişken seçiminde ise çoklu doğrusal bağlantıya (multicollinearity) neden olmayan korelasyon tabanlı CfsSubsetEval algoritması kullanılmıştır. Klorofil a, klorofil b, klorofil a+b, toplam flavonoid madde içeriği, toplam fenolik madde içeriği ve toplam antioksidan kapasitesi özelliklerinin sınıflandırma performansları olan sınıflama doğrulukları, duyarlılık, özgüllük, alıcı işletim karakteristiği (ROC) eğrileri altında kalan alanlar sırasıyla, “%72.1, %73.3, %76.25, %69.6, %71.7, %67.5”, “0.353, 0.440, 0.553, 0.714, 0.771, 0.657”, “0.782, 0.811, 0.802, 0.653, 0.621, 0.682” ve “0.558, 0.643, 0.631, 0.638, 0.723, 0.625” olduğu belirlenmiştir. Çalışma sonucunda organik tarım yapılan Isparta Yağ gülü yapraklarının biyokimyasal içeriklerinin görünür ve yakın kızılötesi hiperspektral veriler ile sınıflamasında klorofil a+b (mg g-1) içeriğinin J48 sınıflandırma ağacı algoritması ile en yüksek doğrulukta belirlendiği sonucuna varılmıştır.

Keywords

• Hiperspektral algılama
• biyokimyasal özellik
• organik tarım
• CfsSubsetEval
• J48 karar ağacı algoritması
• sınıflama

Classification of Some Biochemical Properties with J48 Classification Tree Algorithms in Hyperspectral Data

Abstract

Hyperspectral sensing methods have been used in agriculture for many years to determine physiological events against abiotic and biotic stress factors of plants. Studies on the determination of wavelengths associated with biochemical properties using hyperspectral data of plants in the visible and near-infrared region under sustainable agricultural production models are limited. In this research, Isparta Oil rose with the geographical indication product from organic farming medicine and aromatic plants from sustainable production models were used considering that the effect of cultural practices from abiotic and biotic stress factors is minimal. Hyperspectral measurements and feature selection of chlorophyll a (mg g-1), chlorophyll b (mg g-1), chlorophyll a+b (mg g-1), total flavonoid content (mg catechin g-1), total phenolic content (mg GAE g-1), and total antioxidant capacity (mg TEAC g-1) biochemical properties are made using the J48 classification tree algorithm in organically grown Isparta Oil Rose leaves. In the classification algorithm, different hyperspectral data (bands) are used as independent variables for each biochemical feature, while the amounts of each biochemical feature of the dependent variable are lower and higher than the mean, and the binary response variable (binary) is taken into the model. In the selection of independent variables, the correlation-based CfsSubsetEval algorithm, which does not cause multicollinearity, was used. The areas under the classification accuracies, sensitivity, specificity, and receiver operating characteristic (ROC) curves, which are the classification performances of chlorophyll a, chlorophyll b, chlorophyll a+b, total flavonoid content, total phenolic substance content, and total antioxidant capacity, are given as “72.1%, 73.3%, 76.25%, 69.6%, 71.7%, 67.5%”, “0.353, 0.440, 0.553, 0.714, 0.771, 0.657”, “0.782, 0.811, 0.802, 0.653, 0.621, 0.682” and “0.558, 0.643, 0.631, 0.638, 0.723, 0.625” were determined respectively. As a result of the study, it was concluded that the chlorophyll a+b (mg g-1) content was determined with the J48 classification tree algorithm with the highest accuracy in the classification of the biochemical contents of made the organic farming Isparta Oil rose leaves with visible and near-infrared hyperspectral data.

Keywords

• Hyperspectral Sensing
• Biochemical Feature
• Organic Farming
• Cfssubseteval
• J48 Decision Tree Algorithm
• Classification

References

1. Mahlein, A. K., Oerke, E. C., Steiner, U., & Dehne, H. W., “Recent advances in sensing plant diseases for precision crop protection”. European Journal of Plant Pathology, 133(1), 197-209, 2012.
2. Chlingaryan, A., Sukkarieh, S., & Whelan, B., “Machine learning approaches for crop yield prediction and nitrogen status estimation in precision agriculture: A review”. Computers and electronics in agriculture, 151, 61-69, 2018.
3. Demir, S., Başayiğit, L., “The effect of restricted irrigation applications on vegetation index based on UAV multispectral sensing”. Yuzuncu Yıl University Journal of Agricultural Sciences, 31(3), 629-643, 2021.
4. Teke, M., Deveci, H. S., Haliloğlu, O., Gürbüz, S. Z., Sakarya, U., “A short survey of hyperspectral remote sensing applications in agriculture”. In 2013 6th international conference on recent advances in space technologies (RAST) (pp. 171-176). IEEE, 2013.
5. Sahoo, R. N., Ray, S. S., & Manjunath, K. R., “Hyperspectral remote sensing of agriculture”. Current science, 848-859, 2015.
6. Ang, K. L. M., Seng, J. K. P., “Big data and machine learning with hyperspectral information in agriculture”. IEEE Access, 9, 36699-36718, 2021.
7. Singh, P.; Pandey, P.C.; Petropoulos, G.P.; Pavlides, A.; Srivastava, P.K.; Koutsias, N.; Deng, K.A.K.; Bao, Y., “Hyperspectral remote sensing in precision agriculture: Present status, challenges, and future trends”. In Hyperspectral Remote Sensing; Elsevier: Amsterdam, The Netherlands, pp. 121–146, 2020.
8. Khan, A., Vibhute, A. D., Mali, S., Patil, C. H., “A systematic review on hyperspectral imaging technology with a machine and deep learning methodology for agricultural applications”. Ecological Informatics, 101678, 2022.

9. Cheng, T., Zhu, Y., Li, D., Yao, X., Zhou, K., “Hyperspectral Remote Sensing of Leaf Nitrogen Concentration in Cereal Crops”. In Hyperspectral Indices and Image Classifications for Agriculture and Vegetation (pp. 163-182). CRC Press, 2018.
10. Candiani, G., Tagliabue, G., Panigada, C., Verrelst, J., Picchi, V., Rivera Caicedo, J. P., Boschetti, M., “Evaluation of Hybrid Models to Estimate Chlorophyll and Nitrogen Content of Maize Crops in the Framework of the Future CHIME Mission”. Remote Sensing, 14(8), 1792, 2022.
11. Krishna, G., Sahoo, R. N., Singh, P., Bajpai, V., Patra, H., Kumar, S., ... Sahoo, P. M., “Comparison of various modelling approaches for water deficit stress monitoring in rice crop through hyperspectral remote sensing”. Agricultural water management, 213, 231-244, 2019.
12. Jan, R., Asaf, S., Numan, M., Kim, K. M., “Plant secondary metabolite biosynthesis and transcriptional regulation in response to biotic and abiotic stress conditions”. Agronomy, 11(5), 968, 2021.
13. Yilmaz, R., Yildirim, A., Çelik, C., Karakurt, Y., “Determination of nut characteristics and biochemical components of some pecan nut cultivars”. Yuzuncu Yıl University Journal of Agricultural Sciences, 31(4), 906-914, 2021.
14. Yıldırım, F., Esen, M., Binici, S., Çelik, C., Yıldırım, A., Karakurt, Y., “Antioxidant Enzymes activities of walnut nursery trees to drought stress progression”. International Journal of Agriculture Forestry and Life Sciences, 5(2), 217-225, 2021.
15. Medini, F., Fellah, H., Ksouri, R., Abdelly, C., “Total phenolic, flavonoid and tannin contents and antioxidant and antimicrobial activities of organic extracts of shoots of the plant Limonium delicatulum”. Journal of Taibah University for science, 8(3), 216-224, 2014.
16. Mazid, M., Khan, T. A., Mohammad, F., “Role of secondary metabolites in defense mechanisms of plants”. Biology and medicine, 3(2), 232-249,2011.
17. Khanam, U. K. S., Oba, S., Yanase, E., Murakami, Y., “Phenolic acids, flavonoids and total antioxidant capacity of selected leafy vegetables”. Journal of Functional Foods, 4(4), 979-987, 2012.
18. Baydar, N. G., Baydar, H., “Phenolic compounds, antiradical activity and antioxidant capacity of oil-bearing rose (Rosa damascena Mill.) extracts”. Industrial Crops and Products, 41, 375-380, 2013.
19. Hassan, F., Al-Yasi, H., Ali, E., Alamer, K., Hessini, K., Attia, H., El-Shazly, S., “Mitigation of salt-stress effects by moringa leaf extract or salicylic acid through motivating antioxidant machinery in damask rose”. Canadian Journal of Plant Science, 101(2), 157-165, 2020.
20. Janse, P. V., Kayte, J. N., Agrawal, R. V., Deshmukh, R. R., “Standard spectral reflectance measurements for ASD FieldSpec Spectroradiometer”. In 2018 Fifth International Conference on Parallel, Distributed and Grid Computing (PDGC) (pp. 729-733). IEEE, 2018.
21. Zhang, Z., Huang, R., “Analysis of malondialdehyde, chlorophyll proline, soluble sugar, and glutathione content in Arabidopsis seedling”. Bio-protocol, 3(14), e817-e817, 2013.
22. Singleton, V. L., Rossi, J. A., “Colorimetry of total phenolics with phosphomolybdic-phosphotungstic acid reagents”. American journal of Enology and Viticulture, 16(3), 144-158, 1965.
23. Zhishen, J., Mengcheng, T., Jianming, W., “The determination of flavonoid contents in mulberry and their scavenging effects on superoxide radicals”. Food chemistry, 64(4), 555-559, 1999.
24. Kumaran, A., & Karunakaran, R. J., “Activity-guided isolation and identification of free radical-scavenging components from an aqueous extract of Coleus aromaticus”. Food Chemistry, 100(1), 356-361, 2007.
25. Taghizadeh-Mehrjardi, R., Ayoubi, S., Namazi, Z., Malone, B. P., Zolfaghari, A. A., Sadrabadi, F. R., “Prediction of soil surface salinity in the arid region of central Iran using auxiliary variables and genetic programming”. Arid Land Research and Management, 30(1), 49-64, 2016.
26. Mandrekar, J. N., “Receiver operating characteristic curve in diagnostic test assessment. Journal of Thoracic Oncology”, 5(9), 1315-1316, 2010.
27. R Core Team, R., “R: A language and environment for statistical computing”. 2018.