Constrained Tiny Machine Learning for predicting gas concentration with I4.0 low-cost sensors

Résultats de recherche: Contribution à un journal/une revueArticleRevue par des pairs


Low-cost gas sensors (LCS) often produce inaccurate measurements due to varying environmental conditions that are not consistent with laboratory settings, leading to inadequate productivity levels compared to high-quality sensors. To address this issue, we propose the use of Machine Learning (ML) to predict accurate concentrations of pollutant gases acquired by LCS integrated into an embedded Internet of Things platform. However, a key challenge is to optimize an accurate ML design under low memory and computation power constraints of microcontrollers (MCUs) while maintaining accurate ML scores. After data analysis and pre-processing, we assess and analyze the performance of five ML algorithms to predict the concentration of pollutants gases from multiple specifications (weather, presence of other gases etc.). To support the experiments, datasets from three sources are used: 1- VOCSens, 2- Belgian Interregional Environment Agency cell (IRCELINE), and 3- Visual-Crossing. Once the best model was optimized and validated, multiple hard constraints were added to the selected ML structure to satisfy material and expert requirements. Trained models were ported in order to be implemented locally in a microcontroller (MCU) after comparing several porting libraries. The assembled code obtained is evaluated based on two metrics: storage memory consumption and inference time, relative to the highest attainable capacities. The improved Random Forest (RF) is the best ML model for the used data set with an R2 score meeting of 0.72 and Root Means Square Error (RMSE) of 0.0028 ppm. The best generated Tiny ML model needs 3% of RAM and 98% of Flash storage. The empirical results prove that the developed ML algorithm applied to LCS provides high accuracy to predict pollutant gases. This algorithm can also be used to adjust the LCS systems to provide calibrated data in real-time, even if the platform being used is not particularly advanced or powerful.
langue originaleAnglais
journalACM Transactions on Embedded Computing Systems
Les DOIs
Etat de la publicationPublié - 2023

Empreinte digitale

Examiner les sujets de recherche de « Constrained Tiny Machine Learning for predicting gas concentration with I4.0 low-cost sensors ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation