Paper Title
A DEEP LEARNING-BASED MOBILE APPLICATION FRAMEWORK FOR CLASSIFYING RICE CROP DISEASES IN LABO, CAMARINES NORTE

Abstract
Abstract - This study was conducted in response to current issues in the Department of Agriculture's rice crops in Camarines Norte. The goal of this study was to create an architectural framework for classifying and identification of rice crop diseases. The researcher used a qualitative approach in this study, employing focus group discussions. Literature review, flowcharting, and block diagram were the system methodologies used in developing the architectural framework. Respondents were selected using purposive sampling. The selected participants participated in the focus group discussion via an online meeting. An in-depth informal interview with the respondents was also facilitated in order to gather additional information for the development of an architectural framework. Based on the result of this study, it was discovered that there are several issues concerning the identification and classification of rice crop diseases, such as insufficient information about the specific disease, time consuming in waiting for the results of tested rice crop leaf sample, and difficulty in early disease prevention, which leads to poor performance in early identification and classification, which also affects rice crop production. Keywords - Architectural Framework, Identifying, Classifying, Neural Network, Mobile Application.