Implementation of ML Algorithm for Mung Bean Classification using Smart Phone

This work is an extension of my work presented a robust and economically efficient method for the discrimination of four Mung-Beans varieties based on quantitative parameters, Due to the advancement of technology day by day users try to find the solutions to their daily life problems using smartphones but still there is limited resources are available in smartphone concerning computing power and memory so there is need to find the best classifier which can classify the Mung-Beans using already suggested features in previous work with minimum memory requirements and computational power. For achieving the goal of this study, we take the experiments on various supervised classifiers which have simple architecture and calculations and give the robust performance on the most relevant 10 suggested features are selected by Fisher Co-efficient, Probability of Error, Mutual Information, and wavelet features. After the analysis, we replace the Artificial Neural Network and Deep learning with such a classifier which gives approximately the same classification results as the above classifier but is efficient in terms of resources and time complexity. This classifier is easily implemented in the smartphone environment.

I. Introduction

The Mung bean plays an important role in a balanced and healthy diet due to its protein-rich edible grains and nutritional contents. It is a warm-season leguminous plant that is mostly grown as crop rotation with cereals like rice and wheat. It contains 59% carbohydrate, almost 20-24 percent protein, 4 percent fiber, vitamin (A, B, C, and E), and a good source of folate and dietary fiber. They also supply a significant amount of iron, potassium, calcium, and magnesium [1], [2]. From this, it may be concluded that it is considered a good source of protein for vegetarians and it has evolved for different food products such as snacks, sweets, dhals, and savory foods.