Open AccessA Fuzzy Inference System for Maize Plant Yield Prediction
Author(s) -
Olajide Blessing Olajide,
Odeniyi Olufemi Ayodeji,
Olabiyi Olatunji Coker,
Adewale Joseph Adekunle,
Yakubani Yakubu
Publication year - 2021
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.k9493.09101121
Subject(s) - identification (biology) , preprocessor , crop , yield (engineering) , set (abstract data type) , fuzzy logic , mathematics , agricultural engineering , microbiology and biotechnology , machine learning , agronomy , data mining , statistics , computer science , artificial intelligence , biology , engineering , botany , materials science , metallurgy , programming language
Ascertaining infections in maize plants is through observation of the crop plant for visual indications which a farmer is able to relate to specific diseases. The perception of the farmer is prone to human error which may sometimes link some symptoms to the wrong disease and could impact the application of suitable preventive and curable routines to combat the identified diseases. Hence, accurate identification of crop plant disease is of high importance to a farmer to aid response to diseases. The objective of this article is to apply fuzzy set and interpolation technique to develop an expert system to carry out field-based identification and yield forecast for the maize plant. For this study, some associated factors were recognized for maize plant diseases and confirmed by a professional Botanists. For this study, a number of associated factors were identified for maize plant diseases and validated by experienced Botanists. Further to this, triangular membership functions was used to develop the fuzzy inference system model following the preprocessing of identified factors and related output. 32 inferred rules were formulated using IF-THEN statements which adopted the values of the factors as antecedent and the yield of maize plant as the consequent part of each rule for classification of the yield of maize plant. The Fuzzy model was simulated for each of the identified five factors. The simulation results showed that the risk factors identified; black moldy growth on kernels and ears, blights on leaves, rotten cobs, infected husks and black kernels and seed decay have noticeable influence on the maize plant yield if timely remedy is not administered. The study established that the utilisation of fuzzy technique is helpful to appraise the yield of maize such that the lesser the manifestation of identified associated features then the higher the yield of the maize plant.