Deep learning for sleep stages classification: modified rectified linear unit activation function and modified orthogonal weight initialisation

Abstract

Background and AimEach stage of sleep can affect human health, and not getting enough sleep at any stage may lead to sleep disorder like parasomnia, apnea, insomnia, etc. Sleeprelated diseases could be diagnosed using Convolutional Neural Network Classifier. However, this classifier has not been successfully implemented into sleep stage classification systems due to high complexity and low accuracy of classification. The aim of this research is to increase the accuracy and reduce the learning time of Convolutional Neural Network Classifier. Methodology The proposed system used a modified Orthogonal Convolutional Neural Network and a modified Adam optimisation technique to improve the sleep stage classification accuracy and reduce the gradient saturation problem that occurs due to sigmoid activation function. The proposed system uses Leaky Rectified Linear Unit (ReLU) instead of sigmoid activation function as an activation function. Results The proposed system called Enhanced Sleep Stage Classification system (ESSC) used six different databases for training and testing the proposed model on the different sleep stages. These databases are University College Dublin database (UCD), Beth Israel Deaconess Medical Center MIT database (MIT-BIH), Sleep European Data Format (EDF), Sleep EDF Extended, Montreal Archive of Sleep Studies (MASS), and Sleep Heart Health Study (SHHS). Our results show that the gradient saturation problem does not exist anymore. The modified Adam optimiser helps to reduce the noise which in turn result in faster convergence time. Conclusion The convergence speed of ESSC is increased along with better classification accuracy compared to the state of art solution.

Mixed-Input Deep Learning Approach to Sleep/Wake State Classification by Using EEG Signals

“…The final classification is performed by a conditional random field module that provides a conditional probability for the possible sleep stages. An orthogonal CNN (OCNN) architecture was modified and its performance investigated in [25], where the authors included an alternate version of a rectified linear unit (ReLU) and the Adam optimizer in the OCNN model. The authors claimed that this modification enhances feature extraction and accuracy, and it also reduces the learning time.…”

A Survey of CNN-Based Approaches for Crack Detection in Solar PV Modules: Current Trends and Future Directions

“…[58] Normalization layer maintains regularity and avoids excess fitting, while simultaneously speeding up computation by the CNN [59] Rectified Linear Unit (ReLU) Eliminates all negative digits and substitutes their values with zero. [60] Pooling layer Retrieves values from segments of images bounded by kernels. [61] Fully connected layer Linearly transforms input vectors are linearly using weight matrices in order to solve problems.…”

Automated Analysis of Sleep Study Parameters Using Signal Processing and Artificial Intelligence

“…The study deployed decision tree, support vector machine, and random forest models that were used to extract and train on statistical characteristics with varying percentages of the testing dataset with the random forest model revealing a 97.8% accuracy score. Bhusal et al [ 14 ] worked to solve the gradient saturation issue introduced by the sigmoid activation function and to enhance the accuracy with which sleep stages may be classified. The suggested system employed a modified orthogonal convolutional neural network and a modified Adam optimization technique.…”