Proposal for a Gas Sensor Device to Classify Hydrobiological Species and Estimate Non-Refrigeration Time

The quality of hydrobiological species for human consumption, such as fish and shellfish, is crucial to ensure their safety. This article highlights the use of Metal Oxide Semiconductor Resistive (MOSR)-based MQ sensor modules, along with temperature and humidity, to analyze these species. The prototype is based on the use of an Arduino Mega 2560 Rev3 to connect the sensors with data stored on a Raspberry Pi 4, which can be accessed via Wi-Fi for downloading. Machine learning (ML) models were applied to classify and estimate non-refrigeration time with different quantities of variables, using species such as Illex argentinus, Sardina pilchardus, Scomber colias, and Sepia pharaonis. In total, 33 classification models and 28 regression models were employed. The best results were obtained with Boosted Trees model, achieving an accuracy of 99.93% in the validation phase and 99.74% in the testing phase. In the regression models to estimate non-refrigeration time, with 38 variables, the best model was Bagged Trees, with an R-squared of 0.995 for the validation phase and 0.997 for the testing phase.