Evolutionary Optimization of 1D-CNN for Non-contact Respiration Pattern Classification

arXiv:2312.13035v2 Announce Type: replace-cross
Abstract: In this study, we present a deep learning-based approach for time-series respiration data classification. The dataset contains regular breathing patterns as well as various forms of abnormal breathing, obtained through non-contact incoherent light-wave sensing (LWS) technology. Given the one-dimensional (1D) nature of the data, we employed a 1D convolutional neural network (1D-CNN) for classification purposes. Genetic algorithm was employed to optimize the 1D-CNN architecture to maximize classification accuracy. Addressing the computational complexity associated with training …

abstract arxiv classification cnn cs.lg data data classification dataset deep learning eess.sp forms light nature optimization patterns sensing series study technology through type