Evaluation of body movement during sleep by thermopile using wavelet and neuro-fuzzy

Body movement is one of the important factors in sleep analysis. Instant body movement signals were evaluated for the upper, lower, and entire part of the body from a combination of the eighth scale detail signals using the Haar wavelet. These signals show the points of time when the upper-body or lower-body movement occurred and the level of body movement. Additionally, partial body movement was decomposed to three parts of body movement comprising head-only, whole body, and leg-only movement using the ANFIS. After training data for 30 epochs, the three parts of the body movement data were acquired with minimized RMSE, 23.4, 12.1, and 20.8 respectively. Finally, three subject´s data were evaluated for 60 minutes, and the detection rates of instant and partial body movement, on average, were 96.3% and 89.2%, respectively.