Search Articles

View query in Help articles search
e.g. mhealth

Search Results (1 to 2 of 2 Results)

Download search results: CSV END BibTex RIS

Automated Sleep Stages Classification Using Convolutional Neural Network From Raw and Time-Frequency Electroencephalogram Signals: Systematic Evaluation Study

Automated Sleep Stages Classification Using Convolutional Neural Network From Raw and Time-Frequency Electroencephalogram Signals: Systematic Evaluation Study

STFT is a time-frequency decomposition method that performs a Fourier transform within a moving window along the time series with some overlap to generate a spectrogram for each epoch of time series data [32]. Unlike the STFT method, the wavelet analyses use a different time window length for each frequency, that is, longer windows applied to lower frequencies and shorter windows applied to higher frequencies [32,33]; therefore, CWT is an effective method for nonstationary signals such as EEG [33].

Shahab Haghayegh, Kun Hu, Katie Stone, Susan Redline, Eva Schernhammer

J Med Internet Res 2023;25:e40211

Download Citation: END BibTex RIS

Download PDF Download XML

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

Novel Analgesic Index for Postoperative Pain Assessment Based on a Photoplethysmographic Spectrogram and Convolutional Neural Network: Observational Study

A spectrogram–CNN model was developed and validated through fivefold cross-validation. The developed model outputs the spectrogram–CNN index as a pain score using a PPG spectrogram as input and CNN as a pain scorer. During model development, patients and test sets were separated to prevent intrasubject interference to avoid data overlaps between the development and test sets of each fold. For model training, 90% of the development set was used as a training set and 10% as a validation set.

Byung-Moon Choi, Ji Yeon Yim, Hangsik Shin, Gyujeong Noh

J Med Internet Res 2021;23(2):e23920

Download Citation: END BibTex RIS

Download PDF Download XML