Hybrid model with optimal features for non-invasive blood glucose monitoring from breath biomarkers

Anita Gade, V. Vijaya Baskar, John Panneerselvam

Abstract: Highlights•At first, a new NICBGM based model from exhaled breathe is introduced in this study.•The median filtering is used for pre-processing. At the next stage the features are extracted.•Further, optimal features are chosen, which are then put through a hybrid scheme that combines “Deep Max out (DMO) and Long Short-Term Memory (LSTM)”.•Then, mean is taken DMO and LSTM to attain the fine output. Here, LSTM weights are optimized via Wild Beest Updated HGSO (WBU-HGSO) model.