Key points are not available for this paper at this time.
This study discusses a project introducing an in-tegrated food quality checking system, merging the Internet of Things (IoT) and machine learning technologies. The primary objective is to combat the common issue of non-preservative food spoilage due to various factors. Leveraging machine learning and IoT, the project aims to provide effective solutions to this problem in the form of a low-cost, portable electronic nose (Smart electronic nose) that can predict the expiry of fruits so that they can be consumed accordingly. The sensors, featuring metal oxide semiconductors - the MQ2 sensor and DHT11 sensor are interfaced with Arduino Uno and Node MCU for creating, storing, and analyzing the dataset containing the levels of gas emissions, humidity, and temperature of fruits with the help of a machine learning algorithms and IoT. After utilizing various regression algorithms such as Linear Regression, Random Forest Regression, K-Nearest Neighbors (KNN), and Support Vector Regression (SVR), the Smart electronic nose was finally able to predict the expiry of bananas with a Mean Squared Error (MSE) of 0.1207. This underscores its potential for assessing fruit freshness and predicting expiry dates, contributing significantly in reducing food wastage.
Rana et al. (Fri,) studied this question.