By Topic

back to article  |  Figures
All Figures

Wireless Wearable Multisensory Suite and Real-Time Prediction of Obstructive Sleep Apnea Episodes

Figure 1

Figure 1
Overview of the approach for OSA episode prediction.

Figure 2

Figure 2
Screenshot of 3-channel streaming VCG, 3-D color coded dynamic VCG, and 12-lead transformed ECG signals.

Figure 3

Figure 3
A prototype of the wireless wearable multisensory suite.

Figure 4

Figure 4
A multisensory suite with portable sleep monitoring device.

Figure 5

Figure 5
KS statistic variations of extracted features. KS statistic indicates the maximal feature distribution differences between sleep apnea and non-apnea groups.

Figure 6

Figure 6
(a) Distribution of apnea and nonapnea events in 2D feature space (NPSD and LVM). (b) The classification boundary of the selected Gaussian RBF kernel used as part of the SVM classifier.

Figure 7

Figure 7
Observation from 300th to 380th min and multiple step-ahead predictions from 341th to 380th min of sleep apnea status, LVM, and NPSD features from patient a05.

Figure 8

Figure 8
Real-time sound signal, sleep stage pattern, and one-minute ahead prediction of sleep apnea in subject ID008 from the starting of sleep to 350th min.