کد مقاله کد نشریه سال انتشار مقاله انگلیسی ترجمه فارسی نسخه تمام متن
5126 341 2016 8 صفحه PDF ندارد دانلود کنید
عنوان انگلیسی مقاله
Automatic sleep scoring using statistical features in the EMD domain and ensemble methods
ترجمه فارسی عنوان
نمره خودکار خواب با استفاده از ویژگی های آماری در دامنه EMD و روش های گروهی
کلمات کلیدی
EEG؛ آدابوست؛ آموزش گروه؛ نمره خواب؛ EMD
موضوعات مرتبط
مهندسی و علوم پایه مهندسی شیمی بیو مهندسی (مهندسی زیستی)
چکیده انگلیسی

An automatic sleep scoring method based on single channel electroencephalogram (EEG) is essential not only for alleviating the burden of the clinicians of analyzing a high volume of data but also for making a low-power wearable sleep monitoring system feasible. However, most of the existing works are either multichannel or multiple physiological signal based or yield poor algorithmic performance. In this study, we propound a data-driven and robust automatic sleep staging scheme that uses single channel EEG signal. Decomposing the EEG signal segments using Empirical Mode Decomposition (EMD), we extract various statistical moment based features. The effectiveness of statistical features in the EMD domain is inspected. Statistical analysis is performed for feature selection. We then employ Adaptive Boosting and decision trees to perform classification. The performance of our feature extraction scheme is studied for various choices of classification models. Experimental outcomes manifest that the performance of the proposed sleep staging algorithm is better than that of the state-of-the-art ones. Furthermore, the proposed method's non-REM 1 stage detection accuracy is better than most of the existing works.

ناشر
Database: Elsevier - ScienceDirect (ساینس دایرکت)
Journal: Biocybernetics and Biomedical Engineering - Volume 36, Issue 1, 2016, Pages 248–255
نویسندگان
, ,