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

TL;DR

This paper introduces an optimized 1D-CNN model, enhanced with genetic algorithms and transfer learning, for accurate and efficient classification of normal and abnormal respiration patterns using non-contact light-wave sensing data.

Contribution

It presents a novel combination of genetic algorithm optimization and transfer learning to improve 1D-CNN performance for respiration pattern classification.

Findings

Optimized 1D-CNN achieved high classification accuracy.

Transfer learning reduced training time significantly.

Effective detection of abnormal breathing patterns.

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 the 1D-CNN across multiple generations, we implemented transfer learning from a pre-trained model. This approach significantly reduced the computational time required for training, thereby enhancing the efficiency of the optimization process. This study contributes valuable insights into the potential applications of deep learning methodologies for enhancing respiratory anomaly detection through precise and efficient respiration classification.