Chemical detection system with at least one electronic nose

A system comprising:

• an electronic nose (e-nose) comprising:
• a plurality of thin film gas sensors;
• a first processor configured to supply power to the plurality of thin film gas sensors to bias the sensors and receive output from each of the plurality of thin film gas sensors;
• and
• a second processor configured to:
• receive the output from each of the plurality of thin film gas sensors, the output from each of the plurality of thin film gas sensors being in response to different analytes separately positioned near the plurality of thin film gas sensors, respectively, one at a time, and different combinations of analytes positioned near the plurality of thin film gas sensors, respectively, one at a time;
• generate randomly a first dataset for training and a second dataset for testing a plurality of models using the received output;
• train and test the plurality of models using one or more combinations of outputs from the plurality of thin film gas sensors, the plurality of models are generated using a plurality of different machine learning techniques, the training based on the first dataset and the testing based on the second dataset;
• evaluate a prediction accuracy of each of the plurality of models using an evaluation parameter and select a model from among the plurality of models to deploy for detecting analytes based on a comparison of the evaluation parameter for each of the plurality of models;
• receive, an output of each of the plurality of thin film gas sensors caused by unknown one or more analytes;
• and
• predict, using the deployed model, the one or more analytes that causes the output.