Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir

Köksal Karadaş; Osman Doğan Bulut

doi:10.18016/ksutarimdoga.vi.1215856

EN TR

Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir

Öz

Among the vegetable species in the world, the plant with the most cultivation area is tomato. Increasing tomato yield is important in terms of contributing more to the world economy, producer’s income and human health. With the advancement in software technologies, the importance of data mining algorithms is increasing due to the fact that these algorithms can produce more sophisticated solutions for regression and classification problems. Determining the factors affecting tomato yield and comparing different data mining algorithms on prediction of tomato yield are the purpose of this study. For this purpose, survey study was conducted with the 105 farmers, selected by Simple Random Sampling Method in Igdir province in 2016. Different data mining algorithms including Classification and Regression Tree, Exhaustive CHAID, Chi-Square Automatic Interaction Detector, Artificial Neural Network Algorithm, Multivariate Adaptive Regression Splines and General Linear Model were developed and compared their predictive performance. MARS decision tree has been able to build a model with greatest predictive accuracy, and the others are respectively ANN, GLM, CART, CHAID and Exhaustive CHAID. In the MARS model, number of irrigation , amount of chemical fertilizer , age of farmer , number of seedlings , education level , soil analysis status , sowing region were found statistically significant (P˂0.05). Preferring the MARS model could give an opportunity to detect factors affecting tomato yield and their interactions with higher accuracy. Moreover, results can be easily interpreted and the rules are understandable.

Anahtar Kelimeler

Farklı Veri Madenciliği Algoritmalarının Domates Verimindeki Tahmin Performanslarının Karşılaştırılması: Iğdır İli Örneği

Öz

Domates sebze türleri arasında en fazla ekim alanına sahip bitkidir. Domates veriminin artırılması dünya ekonomisi ve çiftçi gelirine daha fazla katkı sağlaması açısından önemlidir. Yazılım teknolojilerinin ilerlemesi ile regresyon ve sınıflandırma problemlerine daha gelişmiş çözümlerin sunulması veri madenciliğinin önemi artırmaktadır. Bu çalışmada domates verimini etkileyen faktörlerin belirlenmesi ve domates veriminin tahmininde farklı veri madenciliği algoritmalarının karşılaştırılması amaçlanmıştır. Bu amaç ile Iğdır ilinde 105 çiftçi ile anket çalışması yapılmıştır. Sınıflandırma ve Regresyon Ağacı (CART), Ki-Kare Otomatik Etkileşim Dedektörü (CHAID), Exhaustive CHAID, Yapay Sinir Ağı Algoritması (ANN), Çok Değişkenli Uyarlamalı Regresyon Analizi (MARS) ve Genel Doğrusal Model (GLM) gibi farklı veri madenciliği algoritmaları kullanılarak tahmin performansları karşılaştırılmıştır. MARS karar ağacı, en yüksek tahmin doğruluğuna sahip modeli oluşturmuştur. Tahmin performanslarına göre diğer algoritmalar ANN> GLM> CART> CHAID> Exhaustive CHAID’dır. MARS modelinde, sulama sayısı, kimyasal gübre miktarı, çiftçi yaşı, fide sayısı, eğitim düzeyi, toprak analiz durumu ve ekim bölgesi değişkenleri istatistiksel olarak anlamlı bulunmuştur (P˂0.05). MARS modelinin tercih edilmesi, domates verimini etkileyen faktörleri ve bunların etkileşimlerini daha yüksek doğrulukla tespit edilmesini sağlayacaktır. Verim artışı için dekara en az 1450 fide dikilmeli ve en az 5 defa sulama yapılmalıdır.

Anahtar Kelimeler

Kaynakça

Anonymous, (2018). Food and Agricultural Commodities Production Database. http://faostat.fao.org/site/339/default.aspx (Date accessed: 12.05.2021).
Anonymous, (2019). Crop Production Statistics. https://www.tuik.gov.tr/Home/Index (Date accessed: 12.02.2021).
Anonymous, (2020). Temperature Data for the Province of Igdir. https://tr.climate-data.org/asya/tuerkiye/igd%C4%B1r-693/ (Date accessed: 12.03.2021).
Aytekin, İ., Eyduran, E., Karadaş, K., Akşahan, R., & Keskin, İ. (2018). Prediction of fattening final live weight from some body measurements and fattening period in young bulls of crossbred and exotic breeds using MARS data mining algorithm. Revista Brasileira de Zootecnia 50(1), 189-195. http://doi.org/10.17582/journal.pjz/2018.50.1.189.195
Bostancı, B. & Eren-Atay, C. (2018). Decision support tools for barley yield: the case of Menemen – Turkey. Dokuz Eylul University Faculty of Engineering Journal of Science and Engineering 20(60), 1057-1067. https://doi.org/10.21205/deufmd.2018206085
Camdeviren, H.A., Yazici, A.C., Akkus, Z., Bugdayci, R., & Sungur, M.A. (2007). Comparison of logistic regression model and classification tree: an application to postpartum depression data. Expert Systems with Applications 32(4), 987–994. https://doi.org/10.1016/j.eswa.2006.02.022
Celik, S., Eyduran, E., Tatliyer, A., Karadas, K., Kara, M.K., & Waheed, A. (2018). comparing predictive performances of some nonlinear functions and multivariate adaptive regression splines (MARS) for describing the growth of daera dın panah (DDP) goat in Pakistan. Pakistan Journal of Zoology 50(3): 1-4. http://doi.org/10.17582/journal.pjz/2018.50.3.sc2
Cho, W., Na, M. & Park, Y. (2018). Extraction of optimum condition of cultivation factors to improve tomato production using statistical regression analysis and response surface methodology. Advanced Science Letters 24(3), 2084-2087.

Comlekcioglu, N. & Şimşek, M. (2014). The effect of gibberellic acid (GA3) on fruit set in industrial tomato at high temperature conditions and different water level. Yuzuncu Yil University Journal of Agricultural Science 24(3), 270- 279.
Debela, K. B., Belew, D., & Nego, J. (2016). Evaluation of tomato (Lycopersicon Esculentum Mill.) varieties for growth and seed quality under jimma condition, South Western Ethiopia. International Journal of Crop Science and Technology 2(2), 69-77.
Degefa, G., Benti, G., Jafar, M., Tadesse, F., & Berhanu, H. (2019). Effects of intra-row spacing and n fertilizer rates on yield and yield components of tomato (Lycopersicon Esculentum L.) at Harawe, Eastern Ethiopia, Journal of Plant Sciences 7(1), 8-12. https://doi.org/10.11648/j.jps.20190701.12
Duru, M., Duru, A., Karadas, K., Eyduran, E., Cinli, H., & Tariq, M.M. (2017). Effect of carrot (Daucus carota) leaf powder on external and internal egg characteristics of hy-line white laying hens. Pakistan Journal of Zoology 49(1), 125-132. https://doi.org/10.17582/journal.pjz/2017.49.1.125
Estrada-Ortiz, E., Trejo-Tellez, L.I., Gomez-Merino, F.C., Nunez-Escobar, R., & Sandoval-Villa, M. (2013). The effects of phosphite on tomato yield and fruit quality. The Journal of Soil Science and Plant Nutrition 13(3), 612–620. https://doi.org/10.4067/S0718-95162013005000049
Eyduran, E., Zaborski, D., Waheed, A., Celik, S., Karadas, K. & Grzesiak, W. (2017). Comparison of the predictive capabilities of several data mining algorithms and multiple linear regression in the prediction of body weight by means of body measurements in the indigenous beetal goat of Pakistan. Pakistan Journal of Zoology 49(1), 257-265. https://doi.org/10.17582/journal.pjz/2017.49.1.257.265
Friedman, J.H. (1991). Multivariate adaptive regression splines. The Annals of Statistics 19(1), 1-67. https://doi.org/10.1214/aos/1176347963
Hahn, F. (2013). Sensing, control and instrumentation during tomato growth. tomatoes: cultivation, varieties and nutrition. Food science and technology. Nova Science Publishers, 339pp.
Haworth, F. (1961). The effects of organic and inorganic nitrogen fertilisers on the yield of early potatoes, spring cabbage, leeks and summer cabbage. Journal of Horticultural Science 36, 202-205
Helyes, L., Lugasi, A., & Pek, Z. (2012). Effect of irrigation on processing tomato yield and antioxidant components. The Turkish Journal of Agriculture and Forestry 36(6), 702-709. https://doi.org/10.3906/tar-1107-9
Irmak, S., & Ercan, U. (2017). Determining of the affecting factors edible oil consumption using data mining method. Kafkas University Economics and Administrative Sciences Faculty the Journal 8(15), 57-79.
Karadas, K. & Birinci, A. (2019). Determination of factors affecting dairy cattle: a case study of ardahan province using data mining algorithms. Revista Brasileira de Zootecnia 48: 1-11. https://doi.org/10.1590/rbz4820170263
Karadas, K. & Kadirhanogullari, I.H. (2017). Predicting honey production using data mining and artificial neural network algorithms in apiculture. Pakistan Journal of Zoology 49(5), 1611-1619. https://doi.org/10.0.68.174/journal.pjz/2017.49.5.1611.1619
Kibria, G., Islam, M., & Alamgir, M. (2016). Yield and nutritional quality of tomato as affected by chemical fertilizer and biogas plant residues. International Journal of Plant & Soil Science 13(2), 1-10. https://doi.org/10.9734/IJPSS/2016/29434
Kiracı, S. & Karataş, A. (2015). Organic tomato growing plant activator applications effects on yield and quality. Journal of Adnan Menderes University Agricultural Faculty 12(1), 17–22.
Küçükönder, H., Vursavuş, K.K., & Üçkardeş, F. (2015). Determining the effect of some mechanical properties on color maturity of tomato with K-Star, Random Forest and Decision Tree (C4.5) Classification Algorithms. Turkish Journal of Agriculture - Food Science and Technology 3(5), 300-306. https://doi.org/10.7161/omuanajas.952786
Letourneau, G., Caron, J., Anderson, L., & Cormier, J. (2015). Matric potential-based irrigation management of field-grown tomato: effects on yield and water use efficiency. Agricultural Water Management 161, 102–113. https://doi.org/10.1016/j.agwat.2015.07.005
Liu, J., Hu, T., Feng, P., Wang, L., & Yang, S. (2019). Tomato yield and water use efficiency change with various soil moisture and potassium levels during different growth stages. Plos One 14(3), 1-14. https://doi.org/10.1371/journal. pone.0213643.
Manan, A., Ayyub, C.M., Aslam, Pervez, M., & Ahmad, R. (2016). Methyl jasmonate brings about resistance against salinity stressed tomato plants by altering biochemical and physiological processes. The Pakistan Journal of Agricultural Sciences 53(1), 35-41. https://doi.org/10.21162/PAKJAS/16.4441
Na, M., Park, Y., & Cho, W. (2017). A study on optimal environmental factors of tomato using smart farm data. Journal of the Korean Data & Information Science Society 28(6), 1427–1435. https://doi.org/10.7465/jkdi.2017.28.6.1427
Navarro-Gonzále, I., García-Alonso, J., & Periago, M. J. (2018). Bioactive compounds of tomato: Cancer chemopreventive effects and influence on the transcriptome in hepatocytes. Journal of Functional Foods 42, 271-280. https://doi.org/10.1016/j.jff.2018.01.003
Neta, M.N.A., Mota, W.F., Pegoraro, R.F., Pacheco, M.C., Batista, C.M., & Sorases, M.C. (2019). Agronomic yield and quality of industrial tomatoes under NPK doses. Revista Brasileira de Engenharia Agrícola e Ambiental 24(1), 59-64. https://doi.org/10.1590/1807-1929/agriambi.v24n1p59-64
Özer, H. (2016). Organic tomato production. international journal of agricultural and wildlife sciences, Abant Izzet Baysal University Faculty of Agriculture and Natural Sciences 2(1), 43–53.
Özkan, Z., Ünlü, L., & Ögür, E. (2017). Comparison of the efficiency of pheromone and pherolite traps used against tomato moth (tuta absoluta meyrick) in greenhouse tomato growing. Harran Journal of Agricultural and Food Sciences 21(4), 394-403. https://doi.org/10.29050/harranziraat.290747
Sajjad, M., Ashfaq, M., Suhail, A., & Akhtar, S. (2011). Screening of tomato genotypes for resistance to tomato fruit borer (helicoverpa armiger hubner) in Pakistan. The Pakistan Journal of Agricultural Sciences 48(1), 59-62.
Söylemez, S., & Pakyürek, A. Y. (2017). Effect of different rootstocks and nutrient induced ec levels on element content of the tomato fruits. Turkish Journal of Agricultural and Natural Sciences 4(2), 155–161.
Sun, J. & Hui, L. (2008). Data mining method for listed companies, financial distress prediction. Knowledge-Based Systems 21(1), 1-5. https://10.1016/j.knosys.2006.11.003
Svec, L. V., Thoroughgood, C. A., & Mok, H. C. S. (1976). Chemical evaluation of vegetables grown with conventional or organic soil ammendments. Communications in Soil Science and Plant Analysis 7(2), 213-228. https://doi.org/10.1080/00103627 609366634
Tapiero, H., Townsend, D. M., & Tew, K. D. (2004). The role of carotenoids in the prevention of human pathologies. Biomedicine and Pharmacotherapy 58(2): 100-110. https://doi.org/10.1016/j.biopha.2003.12.006
Tatar, M., & Pirinç, V. (2017). Potential of industrial tomato production of Southeast Anatolian Region in Turkey. Iğdır University Journal of the Institute of Science and Technology 7(2), 11-20. https://doi.org/10.21597/jist.2017.121
Tesafay, T., Gebremariam, M., Gebredsadik, K., Hagazi, M., & Girmay, S. (2018). Tomato yield and economic performance under vermicompost and mineral fertilizer applications. The Open Agriculture Journal 12(1), 262-269. https://doi.org/10.2174/1874331501812010262
Toor, R.K., Geoffrey, P.S., & Anuschka, H. (2006). Influence of different types of fertilisers on the major antioxidant components of tomatoes. Journal of Food Composition and Analysis 19(1), 20–27. https://doi.org/10.1016/j.jfca.2005.03.003
Wang, X., & Xing, Y. (2017). Evaluation of the effects of irrigation and fertilization on tomato fruit yield and quality: a principal component analysis. Scientific reports 7(1), 350. https://doi.org/10.1038/s41598-017-00373-8
Yamane, T. (2001). Turkish Translation of the Basic Sampling Methods. Translators: Esin, A., Aydın, C., Bakır, M.A., Gürbüzsel, E., Literatür Yayınları, Tukey. pp.509.
Yaraş, G., & Daşgan, H. Y. (2012). Effects of soil-applied micronized-sulphur with bentonite and organic matter on soil ph, tomato plant growth, yield and fruit quality under greenhouse conditions. Reserach Journal of Agricultural Sciences 5(1): 175-180

Ayrıntılar

Birincil Dil

İngilizce

Konular

Ziraat, Veterinerlik ve Gıda Bilimleri

Bölüm

Araştırma Makalesi

Yazarlar

Köksal Karadaş ^*
0000-0003-1176-3313
Türkiye

Osman Doğan Bulut
0000-0003-2682-6356
Türkiye

Erken Görünüm Tarihi

21 Ocak 2024

Yayımlanma Tarihi

1 Nisan 2024

Gönderilme Tarihi

7 Aralık 2022

Kabul Tarihi

7 Eylül 2023

Yayımlandığı Sayı

Yıl 2024 Cilt: 27 Sayı: 2

DOI

https://doi.org/10.18016/ksutarimdoga.vi.1215856

IZ

https://izlik.org/JA87YJ76YS

Kaynak Göster

RIS / Bibtex

APA

Karadaş, K., & Bulut, O. D. (2024). Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, 27(2), 443-452. https://doi.org/10.18016/ksutarimdoga.vi.1215856

AMA

1.Karadaş K, Bulut OD. Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi. 2024;27(2):443-452. doi:10.18016/ksutarimdoga.vi.1215856

Chicago

Karadaş, Köksal, ve Osman Doğan Bulut. 2024. “Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir”. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi 27 (2): 443-52. https://doi.org/10.18016/ksutarimdoga.vi.1215856.

EndNote

Karadaş K, Bulut OD (01 Nisan 2024) Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi 27 2 443–452.

IEEE

[1]K. Karadaş ve O. D. Bulut, “Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir”, Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, c. 27, sy 2, ss. 443–452, Nis. 2024, doi: 10.18016/ksutarimdoga.vi.1215856.

ISNAD

Karadaş, Köksal - Bulut, Osman Doğan. “Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir”. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi 27/2 (01 Nisan 2024): 443-452. https://doi.org/10.18016/ksutarimdoga.vi.1215856.

JAMA

1.Karadaş K, Bulut OD. Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi. 2024;27:443–452.

MLA

Karadaş, Köksal, ve Osman Doğan Bulut. “Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir”. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi, c. 27, sy 2, Nisan 2024, ss. 443-52, doi:10.18016/ksutarimdoga.vi.1215856.

Vancouver

1.Köksal Karadaş, Osman Doğan Bulut. Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir. Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi. 01 Nisan 2024;27(2):443-52. doi:10.18016/ksutarimdoga.vi.1215856

Cited By

Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model

Kahramanmaraş Sütçü İmam Üniversitesi Tarım ve Doğa Dergisi

https://doi.org/10.18016/ksutarimdoga.vi.1486797

Comparison of Predictive Performance of Data Mining Algorithms in Predicting Tomato Yield with the A Case Study in Igdir

Öz

Anahtar Kelimeler

Farklı Veri Madenciliği Algoritmalarının Domates Verimindeki Tahmin Performanslarının Karşılaştırılması: Iğdır İli Örneği

Öz

Anahtar Kelimeler

Kaynakça

Ayrıntılar

Birincil Dil

Konular

Bölüm

Yazarlar

Erken Görünüm Tarihi

Yayımlanma Tarihi

Gönderilme Tarihi

Kabul Tarihi

Yayımlandığı Sayı

DOI

IZ

Kaynak Göster

Cited By

Comparative Analysis of CNN Algorithms for Mushroom Classification with Proposed Lightweight CNN Model

e-ISSN: 2619-9149