English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

In this study, we present a deep learning-based approach for time-seriesrespiration data classification. The dataset contains regular breathingpatterns as well as various forms of abnormal breathing, obtained throughnon-contact incoherent light-wave sensing (LWS) technology. Given theone-dimensional (1D) nature of the data, we employed a 1D convolutional neuralnetwork (1D-CNN) for classification purposes. Genetic algorithm was employed tooptimize the 1D-CNN architecture to maximize classification accuracy.Addressing the computational complexity associated with training the 1D-CNNacross multiple generations, we implemented transfer learning from apre-trained model. This approach significantly reduced the computational timerequired for training, thereby enhancing the efficiency of the optimizationprocess. This study contributes valuable insights into the potentialapplications of deep learning methodologies for enhancing respiratory anomalydetection through precise and efficient respiration classification.

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