MedTech: Deep learning based breathalyzer to detect Covid-19
This topic can be conducted both in English and Hungarian ! / A téma magyarul és angolul is felvehető !
The breathalyzer is based on the detection of biomarkers emitted from the human body by breath. By biomarkers we mean the molecules that can be detected with metal-oxide (MOx) sensors. It means that we do not detect the virus itself but we detect the reaction of the human organism to the infection.
MOx sensors can be involved in various application domains, e.g., pharma, food, cosmetics, petrochemistry, medtech. The electric conducting capability (resistance / impedance) of a MOx sensor is changed 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.
The role of deep learning is to match the sensor signals to the diagnosis. Its task is to find the interdependencies in the sensor data measured. The techniques to be applied are, e.g., sensor data preprocessing, deep feed forward network, recurrent neural network.
The task of the student is to work on deep learning algorithms that processes the raw sensor data in order to provide high accuracy classification, e.g., the diagnosis (Covid+/Covid-).
The task of the student is to work on the software of the measuring instrument (ESP32 based) that manages the realtime measurements and estimates the actual diagnosis (Covid+/Covid-) by running the machine learning model.