Intelligent Fruit Quality Monitoring System using Sensor Networks and Deep Learning

This paper presents a novel approach for fruit quality detection using a multi-modal system that combines sensor data and image processing techniques with deep learning. In the first stage of our experiment, we employed various sensors to measure temperature, gas levels, and moisture content using DHT 11 and MQ-135 sensors. These sensors provide valuable insights into the environmental conditions surrounding the fruits, which are crucial indicators of their freshness. In the second stage, we utilized image processing algorithms to pre-process fruit images and train a SqueezeNet convolutional neural network (CNN) to classify fruits into two classes: fresh and rotten. By integrating sensor data with image-based classification, our proposed method offers a comprehensive solution for real-time fruit quality assessment. Experimental results demonstrate the effectiveness of our approach in accurately detecting fruit quality, paving the way for advanced applications in food safety and quality control.