Determination of Sample Size for Plant Leaves in Deep Learning Models for Predicting Late Blight in Irish Potatoes: An experimentation methodology in Kigezi –Uganda

Abstract Background Determining the sample size of Deep learning models still remains a challenges in the Artificial Intelligence world. This is because most of the developers of deep learning models utilize available data collected from public datasets sites such PlantVillage or Kaggle. This study proposes using the acreage method putting into consideration of the machine learning dataset condition. Objective The main objective of this research is to experiment the methods that can be used to determine the appropriate sample size for a Deep learning model. Methods This study used the experimental and statistical methodologies and incorporated the boundaries of the Machine learning condition. Results The average sample estimation of the measurements in the piece of land (plot) was (1x4X10) cm. The measurement of the leaves was 3.5-5cm in length and 1.5-3 cm in width. The experiments were done between (2:00-4:00) am to have a good lighting condition. The optimal leaning rate of the deep learning architectures involved in the study used a learning rate of 0.0001. The study covered an acreage of 28000.25 acres and the Dataset 2145 Irish potato leaves was obtained and got 9,660 images after augmentation. This was purposively collected from ten sub-counties due to time and financial constraints in this study. Conclusion This study proposed a methodology for obtaining the sample size using the acreage methodology and purposive sampling and there use the Machine learning condition for sample sizes for creation of deep learning models from potato leaf images targeted at preventing late blight based on leaf images. Future research may extend this study to further more validate the acreage methodology putting into account the Machine learning condition and also developing the Deep learning condition.