K-Complex Detection Based on Synchrosqueezing Transform

K-complex is an underlying pattern in the sleep EEG. Due to the role of sleep studies inneurophysiologic and cognitive disorders diagnosis, reliable methods for analysis and detection of this patternare of great importance. In our previous work, Synchrosqueezing Transform (SST) was proposed for analysisof this pattern. SST is an EMD-like tool, which benefits from wavelet transform and reallocation approaches.This method is able to decompose signals into their time-varying oscillatory ingredients. In addition, itprovides a time-frequency representation with less blurring compared to wavelet transform. In this paper,firstly, the ability of SST is investigated by applying the ANOVA test, which is approved by proper p-values.This paper proposes SST for K-complex detection. The proposed method is based on a so-called “detectionof K-complexes and sleep spindles” (DETOKS) framework. DETOKS is based on spares optimizationand decomposes signals into four components, namely transient, low frequency, oscillatory, and a residual.Applying the Teager-Kaiser energy operator and setting a threshold on the low-frequency component resultin K-complex detection. We modify DETOKS using SST. The proposed method is applied to DREAMSdataset. The dataset provides two visual scorings accompanied by an automatic one. As the visual labels wereextremely different, the automatic detection is considered as the third expert’s scoring and data is re-labeledby a voting approach among three experts. For DETOKS, DETOKS modified by CWT, and the proposedmethod, MCC measure is 0.62, 0.71, and 0.76, respectively. It shows superiority of the proposed method.