keywords: Artificial neural network, decision support system, Fertigation
One of the sectors that contribute to the country’s economy is agriculture which needs the improvement of science and technology from time to time such as in its fertigation system. The manual applications of fertilizer that are commonly used are very stressful and consume enormous time especially when cultivating a large area of land and also do not ensure efficient management of fertilizer. This paper presents a Decision Support System (DSS) for automatic application of fertilizer and water to tomato plants using artificial neural network. The system is capable of dispensing required fertilizer to tomato plants; at the developmental stages based on nitrogen, phosphorous, and potassium contents of the soil. The tomato plant images at every stages of its growth were acquired using digital camera, in addition to NPK sensor used to measures the available fertilizer at every stages of the tomato plants. The acquired images were preprocessed using Contrast enhancement, RGB to Grayscale conversion and Median filter. The feature extraction techniques such as number, perimeter, area, minor axis and major axis length of the connected regions were used for the purposed of differentiating the stages of tomato. The combination of information from the images and data obtained using NPK sensor was used to determine whether fertilizer should be applied or not. For twelve experiments that were taken, an accuracy of 91.67% was achieved. The experimental results promise that the system will fulfil the needs for efficient management of fertilizer.
Adegboye MA, Ajao LA, Folorunso TA, Mamudu AY & Isah AS 2017. Automatic fertilized-irrigation control and management system. FUW Trends in Sci. & Techn. J., 2(2): 801-805. Aliyu A, Kolo JG, Aibinu AM, Agajo J, Orire AM, Folorunso TA & Adegboye MA 2017. A proposed fish counting algorithm using digital image processing technique. ATBU, J. Sci., Techn. & Edu. (JOSTE), 5(1): 2277-2281. Ghorban S & Yaser M 2016. Application of artificial neural network model in predicting price of milk in Iran. Modern Applied Science, 10(4): 173. Haifa LA 2005. Nutritional recommendations for tomato in open-field, tunnels and greenhouse. Pioneering the Future, pp. 1-40. Kriesel D 2005. A Brief Introduction to Neural Networks. Bonn: University of Bonn, Germany. Matt R & Bussan AJ 2007. Fertility Management of tomatoes and Pepper. India. Retrieved from www.soils.wisc.edu/extension. Mohd Salih JE, Adom AH & Md Shaakaf AY 2012. Solar powered automated fertigation control system for Cucumis melo L. cultivation in Green House. Asia-Pacific Chem., Bio. & Envtal. Engr. Soc. Procedia, 4: 79 – 87. Odílio C, Da-roch N, Adunias DS, Teixeira AP, De SB & Clemilson CD 2016. Application of artificial neural networks as an alternative to volumetric water balance in drip irrigation management. Watermelon Crop., pp. 7-12. ShankaraVD, Barbara G, Marja De VJ & Joep N 2005. Cultivation of tomato: Production, processing and marketing. Agromisa/CTA, 17.