The main objectives of this project are to develop a portable real-time electronic nose system for evaluating seafood freshness using machine learning algorithms. It analyzes gas emissions from seafood samples through sensor arrays to detect spoilage levels. This solution ensures food safety, reduces waste, and enables rapid freshness assessment in markets and supply chains.
This project presents a portable real-time electronic nose system for seafood freshness evaluation using Arduino UNO, MQ2 sensor, MQ6 sensor, DHT11 sensor, pH sensor, LCD display, buzzer, and the Random Forest machine learning algorithm. The sensors continuously monitor gas concentration, temperature, humidity, and pH levels associated with seafood quality. The collected data is analyzed by the Random Forest model to classify the freshness status accurately. The results are displayed on the LCD screen, while sensor data and classification results are uploaded to the ThingSpeak cloud platform for remote monitoring. When spoilage conditions are detected, the buzzer alert is activated. The proposed system provides a low-cost, portable, and efficient solution for real-time seafood quality monitoring and food safety management.
Keywords: Arduino UNO, Electronic Nose, Seafood Freshness Evaluation, Random Forest, Thing Speak.NOTE: Without the concern of our team, please don't submit to the college. This Abstract varies based on student requirements.
