Automatic Sleep Spindle Detection Using SMOTE and Composite Features with SWT and Adaboost

Sleep Spindles contribute to diagnosing several brain-related diseases like sleep apnea, major depression, etc.Hence, sleep spindle detection from Electroencephalogram (EEG) has gained significant research interest in the bio-medical signaling field.Existing methods use template matching and machine learning algorithms for spindle detection.In the template matching methods, the additional and continuous tuning of the threshold creates an unnecessary computational burden.In the machine learning-based method, significant problems such as data imbalance and less discrimination due to fewer and inappropriate features are addressed.To address these issues, this research presents a novel automatic spindle recognition approach that uses the Synthetic Minority Oversampling Technique (SMOTE) to balance the dataset and integrates time-domain and frequency-domain information for effective feature extraction.The Synchrosqueezed Wavelet Transform (SWT) is utilized for accurate frequency domain feature extraction, while the Adaboost(Adaptive Boosting)algorithm is implemented for classification.This method, evaluated using the publicly accessible Montreal Archives of Sleep Studies Cohort 1 (MASS-C1) dataset, significantly outperforms existing methods like as SpindleU-Net, Convolutional MIL (Multiple Instance Learning), SST-RUSBoost (Synchrosqueezed Transform -Random Under-Sampling Boosting), and MuFF-E(Multi-Feature Fusion and Ensemble), with an F-score of 75%, Sensitivity of 78%, and Positive Predictive Value of 73%.The findings illustrate the superiority of the proposed method in addressing data imbalance and improving detection accuracy.