Evaluation of Decision Tree Algorithms in Precision Agriculture

Abstract
Authors
Keywords
Conclusion
References

Precision Agriculture (PA) is a farm management approach which ensures that plants and animals' needs are adequately met. One of the advances in PA is Autonomous Irrigation System (AIS). Various AISs have been proposed to ensure effective management of water resources, soil water content optimization and increasing crop yield. However, these systems require some level of decision-making algorithm in order to make the appropriate irrigation decisions that are critical. Decision tree algorithms were evaluated and results are presented in this study. The results of evaluation showed that CART recorded an increase of 0.06% and 0.26% compared to C5.0 and ID3 respectively in terms of accuracy. CART also records an increase of 0.38% and 1.76% against the C5.0 and ID3 respectively with regard to precision. Evaluating the recall, CART records an increase of 0.12% and 0.33% in comparison to C5.0 and ID3 respectively. The F-measure of CART also records an increase of 0.24% and 1.05% against the C5.0 and ID3 respectively.

Published In : IJCAT Journal Volume 7, Issue 3

Date of Publication : March 2020

Pages : 25-33

Figures :08

Tables :06

Kalesanwo Olamide : Babcock University, Ilishan Remo Ogun State, Nigeria.

Awodele Oludele : Babcock University, Ilishan Remo Ogun State, Nigeria.

Eze Monday : Babcock University, Ilishan Remo Ogun State, Nigeria.

Kuyoro 'Shade : Babcock University, Ilishan Remo Ogun State, Nigeria.

Ajaegbu Chigozirim : Babcock University, Ilishan Remo Ogun State, Nigeria.

Autonomous Irrigation Systems, Data validation, Decision making, Irrigation, Precision Agriculture

From the outcome of the study, it was discovered that temperature state of the soil (hot, cold or warm), air temperature and humidity level are key determinant in making irrigation decisions. Also, the CART algorithm outperforms the remaining decision tree algorithm evaluated and this algorithm can be utilized in developing the decision module of AISs.

[1] R. Leclerc, "How to Invest In Agritech," Forbes. 2016. [2] J. Lakshmi and G. Naresh, "A review on developing tech-agriculture using deep learning methods by applying UAVs," Int. J. Sci. Res. Comput. Sci. Eng. Inf. Technol., vol. 3, no. 1, pp. 1858-1863, 2018. [3] S. Campbell and A. Tully, "Artificial intelligence helps supply chains minimize waste in food and medicine," SAP news center, 2018. [Online]. Available: https://news.sap.com/2018/05/artificial-intelligence-helps-supply-chains-minimize-waste-food-medicine/. [4] M. Irimia, "Five ways agriculture could benefit from artificial intelligence," IBM Watson, 2016. [Online]. Available: https://www.ibm.com/blogs/watson/2016/12/five-ways-agriculture-benefit-artificial-intelligence/. [5] P. Taechatanasat and L. Armstrong, "Decision Support System Data for Farmer Decision Making," in Proceedings of Asian Federation for Information Technology in Agriculture, 2014, pp. 472-486. [6] C. Lokhorst, R. De-Mol, and C. Kamphuis, "Invited review: Big Data in precision dairy farming," Anim. Consort., vol. 14, pp. 1-10, 2019. [7] N. Karayiannis and A. Venetsanopoulos, "Decision making using neural networks," Neurocomputing, vol. 6, no. 3, pp. 363-374. [8] N. Zhifang, L. Phillips, and G. Hanna, "The use of bayesian networks in decision making," Key Top. Surg. Res. Methodol., vol. 1, no. 9, pp. 1-10, 2010. [9] O. Awodele, O. Kalesanwo, F. Osisanwo, and S. Kuyoro, "Performance Evaluation of Some Mobile Adhoc Network Routing Protocols," Int. J. Sci. Eng. Res., vol. 8, no. 4, pp. 766-770, 2017. [10] Y. Duan, J. Edwards, and Y. Dwivedi, "Artificial intelligence for decision making in the era of Big Data - evolution, challenges and research agenda," Int. J. Inf. Manage., vol. 48, pp. 63-71, 2019. [11] B. Keswani et al., "Adapting weather conditions based IoT enabled smart irrigation technique in precision agriculture mechanisms," Neural Comput. Appl., vol. 31, pp. 277-292, 2019. [12] A. Mohapatra and S. Lenka, "Hybrid decision support system using PLSR-fuzzy model for GSM-based site-specific irrigation notification and control in precision agriculture," Int. J. Intell. Syst. Technol. Appl., vol. 15, no. 1, pp. 4-18, 2016. [13] A. Mohapatra, S. Lenka, and B. Keswani, "Neural network and fuzzy logic based smart DSS model for irrigation notification and control in precision agriculture," in Proceedings of the National Academy of Sciences India, 2019, vol. 89, no. 1, pp. 67-76. [14] M. Maharajan, T. Abirami, and S. Anitha, "Energy efficient wireless sensor network for precision agriculture," Adv. Eng. Res., vol. 142, no. 18, pp. 131-136, 2018. [15] P. Ippolito, "Feature extraction techniques," Towards Data Science, 2019. [Online]. Available: towardsdatascience.com/feature-extraction-techniques-d619b56e31be. [16] R. O'Donnell, "Information Theory," Carnegie Mellon University, 2013. [17] A. Sarah, "Basic evaluation measures from the confusion matrix," class eval, 2016. [Online]. Available: https://classeval.wordpress.com/introduction/basic-evaluation-measures/. [18] K. Shung, "Accuracy, Precision, Recall or F1?," Towards Data Science, 2018. [Online]. Available: https://towardsdatascience.com/accuracy-precision-recall-or-f1-331fb37c5cb9. [19] J. Brownlee, "Feature selection with the Caret R package," Machine Learning Mastery, 2014. [Online]. Available: https://machinelearningmastery.com/feature-selection-with-the-caret-r-package/.