Development of a mobile application to predict amount of rice husk generated after rice milling.
Abstract
As the global demand for rice continues to rise, so does the generation of rice husk waste, posing significant environmental challenges. This report presents the development of a smartphone application aimed at predicting the amount of rice husk generated based on independent variables such as the amount of rice, moisture content, and rice variety. By leveraging the computational power of smartphones, this application offers a convenient and cost-effective solution for estimating rice husk waste, aiding in waste management and resource optimization.
The study utilized a dataset comprising various rice varieties, corresponding moisture contents, and known quantities of rice processed. Leveraging machine learning techniques, a predictive model was developed to establish relationships between the independent variables and the amount of rice husk generated. The model underwent rigorous training and validation processes to ensure accuracy and reliability.
To create a user-friendly experience, the smartphone application was designed with an intuitive interface that allows users to input the desired variables, such as the quantity of rice, moisture content, and rice variety. Upon submission, the application employs the trained model to generate an estimate of the resulting rice husk waste.
The report discusses the technical aspects of developing the application, including data pre-processing, feature engineering, and the implementation of the predictive model. Furthermore, the evaluation of the model's performance is presented, with emphasis on accuracy and precision metrics.
The results demonstrate promising accuracy and usefulness in predicting the amount of rice husk generated. The smartphone application provides a valuable tool for rice farmers, rice mill operators, and waste management authorities to anticipate and manage rice husk waste more effectively. This predictive technology can aid in optimizing resource allocation, waste recycling, and the development of sustainable practices in the rice industry