Demeter: A Rice Panicle Grain Loss Detection Software

Context: Rice is one of the world's most consumed food and requires high production. Over rice production, farmers may face several scenarios that can compromise the production, reducing the harvest productivity. Problem: Climatic events, diseases, soil problems, and pests are factors that may cause the loss of rice grain. Grain loss estimation is commonly made through a manual sampling process. Manual sampling tends to be slow and expensive. Solution: We present in this work Demeter, a rice panicle grain loss detection software. IS Theory: Demeter is proposed based on the information processing theory. Method: We use machine learning algorithms, specifically Support Vector Machine (SVM), Decision Tree, and Forest Random, to identify the grain missing in a rice panicle. Summary of Results: The best result was obtained with the SVM algorithm, with an accuracy of 70%. Contributions and Impact in the IS area: We advocate that our work contributes to the IS area by developing a system to help in the agriculture field, promoting an interdisciplinary study, use of AI technology and information systems.