Deep‐SQA: A deep learning model using motor activity data for objective sleep quality assessment assisting digital wellness in healthcare 5.0

Abstract

AbstractWearable sensor‐based devices like actigraphs collect motor activity data which provide objective measures of physical activity. This research puts forward a novel methodology for assessment of objective sleep quality using actigraph recordings of motor activity. High level features of sequential motor activity data are extracted using Long‐Short Term Memory (LSTM) model which are then paired with a significant statistical feature namely, zero percent which describes the percentage of events with zero activity over a series. Overlapping sliding window is used to input sequences into LSTM to capture superior features in activity recordings. The predictive ability of the combined feature vector is evaluated using support vector machine (SVM) classifier. This hybrid LSTM‐SVM framework is validated on a benchmark dataset namely, the MESA Actigraphy dataset and achieves an accuracy of 85.62% for sleep quality prediction. Effectiveness of overlapping sliding window and statistical feature are evaluated, and their significance is validated. It is validated that the concept of overlapping sliding window improves the performance accuracy by 3.51% and the use of discriminative statistical feature improves sleep quality prediction task by 2.95%. Comparison with state of the art validates that this is the first study using objective sleep quality indicator for assessment of sleep quality via actigraph‐based motor activity data.