Z-ENG: Machine Learning Algorithms for an Electronic Nose

Félév: 2024-2025 ősz

Kategória: Nincs megadva

Téma leírása

The topic is available also in Hungarian

The electronic nose technology mimics the biological nose. Our device (already done) is basically a MOx based sensor fusion device. The electric conducting capability (resistance / impedance) of a MOx sensor changes depending on the actual molecule that reacts with the surface of the sensor. Furthermore, such sensors are coated with a membrane, which restricts the set of molecules that can reach the surface of the sensor. The sensors available on the market differ on their physical characteristics, thus the conducting capability of each sensor changes differently based on the actual molecule to be detected. We work with a sensor fusion solution meaning that multiple different sensors are combined, which leads to a kind of fingerprinting approach.

There are various application domains, e.g., as MedTech (detecting health issues based on biomarkers), Industry 4 (detecting gases of carcinogen nature), FoodTech (freshness of meat, microbiological contamination, spoiled food), air pollution analysis.

The actual problems students can work on are as follows.

• Separating compounds - At the moment, only single materials are measured by the device. A straightforward step is to conduct the measurement of multiple materials and work on the algorithms to separate the signals.

• Algorithms to calibrate the sensors - A well known problem of MOx sensors is degradation / ageing. Furthermore, some sensors are low quality and have different bias and variance parameters. The goal of calibration is to standardise the measurements. 

• Biomarker based person identification - Anonymous breath sample collection, exploratory data analysis (EDA), classification based person identification.

• Algorithms to compensate the background air effect - Different locations provide different air compositions. It means that samples measured in the lab cannot be used directly in other locations. In order to apply the devices, the air bias needs to be solved.

• Students can also propose a topic.

Maximális létszám: 6 fő