A Prototype to Prevent Fruits from Spoilage: An Approach Using Sensors with Machine Learning †

Abstract

One of the significant issues facing the world right now is food deterioration. If the freshness or deterioration of a fruit can be determined before it is lost, the fruit waste problem may be mitigated. The goal of this work is to develop a simple model for tracking fruit quality using sensors with a machine learning (ML) approach. This model uses from the gases emitted by fruits to determine the ones that will ripen and require use earlier. Two gas sensors (MQ3 and MQ7) and an Arduino Uno serve as the main processing components of the suggested system. Principal component study (PCA) is a widely employed discriminating approach that has been utilised to differentiate between fresh and rotten apples based on sensed data. The study yielded a cumulative variance of 99.1% over a span of one week. The data were also evaluated using a linear Support vector machine (SVM) classifier, which achieved an accuracy of 99.96%. The distinctive feature of the system is that it evaluates the levels of spoilage based on real-time data and deploys a low-cost, straightforward model that can be used anywhere to preserve any type of fruit.