Litcius/Paper detail

Enhancing Accuracy in Crop Yield Estimation Through the Integration of Naive Bayes and Convolutional Neural Networks

Samanth Reddy P, R Surendran, M. Venkatraman

202310 citationsDOI

Abstract

This article improves the accuracy of crop yield forecast by using convolutional neural network and Naive Bayes algorithm. Supplies and Procedures. The study comprised 42 samples, which were grouped into two sets of 21 samples each. While the second group utilised the Convolutional Neural Network technique, the first group used the Naive Bayes technique. The statistical power of the study was established at 80% with an alpha level of 0.05 and a beta level of 0.20, using G power. Results: The Naive Bayes algorithm tends to have a higher accuracy rate, which in this case is around 88%. On the other hand, the Convolutional Neural Network algorithm has a slightly lower accuracy rate of approximately 82%. Independent sample t-test using this paper. It has a significant value of p is .046 (p<0.05), this is statistically significant. Conclusion: The Naive Bayes algorithm was discovered to exhibit a higher level of accuracy in comparison to the Convolutional Neural Network Algorithm.

Topics & Concepts

Convolutional neural networkComputer scienceNaive Bayes classifierBayes' theoremArtificial intelligenceYield (engineering)Machine learningEstimationPattern recognition (psychology)Bayesian probabilitySupport vector machineEngineeringMetallurgySystems engineeringMaterials scienceSpectroscopy and Chemometric AnalysesSmart Agriculture and AI
Enhancing Accuracy in Crop Yield Estimation Through the Integration of Naive Bayes and Convolutional Neural Networks | Litcius