Hessenberg Elm Autoencoder Kernel For Deep Learning

Abstract

Deep Learning (DL) is an effective way that reveals on computation capability and advantage of the hidden layer in the network models. It has pre-training phases which define the output parameters in unsupervised ways and supervised training for optimization of the pre-defined classification parameters. This study aims to perform high generalized fast training for DL algorithms with the simplicity advantage of Extreme Learning machines (ELM). The applications of the proposed classifier model were experimented on RespiratoryDatabase@TR. Hilbert-Huang Transform was applied to the 12-channel lung sounds for analyzing amplitude-time-frequency domain. The statistical features were extracted from the intrinsic mode function modulations of lung sounds. The feature set was fed into the proposed Deep ELM with the HessELM-AE. The proposed model was structured with 2 hidden layers (340,580 neurons) to classify the lung sounds for separating Chronic Obstructive Pulmonary Disease and healthy subjects. The classification performance was tested using 6-fold cross-validation with proposed Deep. HessELM-AE has achieved an influential accuracy rate of 92.22% whereas the conventional ELM-AE has reached an accuracy rate of 80.82%.