Low complexity piecewise linear LLR calculation for MIMO-BICM systems

Abstract Sleep is a physiological phenomenon and a sufficient amount of sleep is mandatory for a human for his/her health. The aim of the paper is to develop an efficient algorithm to detect the various sleep states by combining different biomedical signals. The novelty of the algorithm is that we used two piecewise linear data reduction techniques namely a new Halfwave method in time domain and Franklin transformation in frequency domain. The obtained two piecewise linear forms of signals have low complexity that still preserve the characteristics of the stages of the sleep in the signals. The components of the feature vector are generated from the parameters of the two reduced piece wise linear functions. Algorithm is tested on MIT-BIH Polysomnographic Database having more than 70 hours long term EEG, blood and nasal signals with six different sleep classes. Proposed method shows better performance in terms of average Sensitivity, Specificity, Accuracy and False Alarm Rate/hour than state of the art methods.

Download Full-text

Sleep states detection using halfwave and Franklin transformation

10.21203/rs.3.rs-27562/v1 ◽

2020 ◽

Author(s):

Yash Paul ◽

S. Fridli

Keyword(s):

False Alarm ◽

False Alarm Rate ◽

Piecewise Linear ◽

Low Complexity ◽

Piecewise Linear Function ◽

Linear Functions ◽

Sleep Stages ◽

Discrete Version ◽

Reduction Techniques ◽

Sensitivity Specificity

Abstract Sleep is a physiological phenomenon and a sufficient amount of sleep is mandatory for a human for his/her health. Three biomedical signals namely Blood, EEG and Nasal are used to identify various sleep stages. The discrete version of these signals is piecewise linear function and applied two piecewise linear data reduction techniques namely a new Halfwave method in time domain and Franklin transformation in frequency domain on the discrete versions of these selected signals. As a result we obtained two piecewise linear functions with low complexity that still preserve the characteristics of the stages of the sleep in the signals. The components of the feature vector are generated from the parameters of the two reduced piece wise linear functions. Algorithm is tested on MIT-BIH Polysomnographic Database having more than 70 hours long term EEG, Blood and Nasal signals with six different sleep classes. Proposed method shows better performance so far on such long duration data in terms of Sensitivity, Specificity, Accuracy and False Alarm Rate/hour. Algorithm achieved an average sensitivity, specificity accuracy and false alarm rate of 98.35% and 97.32%, 96.96%, 0.029 respectively for two classes, 96.62% and 97.10%, 93.94%, 0.030 for 4 classes, 96.13% and 98.33%, 93.84%, 0.016 for all (six) classes.

Download Full-text