Generative Autoencoder Kernels on Deep Learning for Brain Activity Analysis
Journal Title: Natural and Engineering Sciences - Year 2018, Vol 3, Issue 3
Abstract
Deep Learning (DL) is a two-step classification model that consists feature learning, generating feature representations using unsupervised ways and the supervised learning stage at the last step of model using at least two hidden layers on the proposed structures by fully connected layers depending on of the artificial neural networks. The optimization of the predefined classification parameters for the supervised models eases reaching the global optimality with exact zero training error. The autoencoder (AE) models are the highly generalized ways of the unsupervised stages for the DL to define the output weights of the hidden neurons with various representations. As alternatively to the conventional Extreme Learning Machines (ELM) AE, Hessenberg decomposition-based ELM autoencoder (HessELM-AE) is a novel kernel to generate different presentations of the input data within the intended sizes of the models. The aim of the study is analyzing the performance of the novel Deep AE kernel for clinical availability on electroencephalogram (EEG) with stroke patients. The slow cortical potentials (SCP) training in stroke patients during eight neurofeedback sessions were analyzed using Hilbert-Huang Transform. The statistical features of different frequency modulations were fed into the Deep ELM model for generative AE kernels. The novel Deep ELM-AE kernels have discriminated the brain activity with high classification performances for positivity and negativity tasks in stroke patients.
Authors and Affiliations
Gokhan Altan, Yakup Kutlu
Keywords
Related Articles
- EP ID EP404417
- DOI 10.28978/nesciences.468978
- Views 126
- Downloads 0
Length-Weight Relationship and Condition Factor of Spotted Flounder Citharus linguatula (Linnaeus, 1758) in Iskenderun Bay, North-eastern Mediterranean, Turkey
A total of 252 spotted flounder, Citharus linguatula (Linnaeus, 1758) were caught in the Iskenderun Bay from October 2012 to September 2013 using a commercial bottom trawler. Length-weight relationships (LWRs), sex ratio...
A Checklist of the Non-indigenous Fishes in Turkish Marine Waters
A checklist of non-indigenous marine fishes including bony, cartilaginous and jawless distributed along the Turkish Marine Waters was for the first time generated in the present study. The number of records of non-indige...
Determination of Heavy Metal Concentrations in Lessepsian Suez Puffer (Lagocephalus suezensis Clark and Gohar, 1953) from North-Eastern Mediterranean
In the present study, the heavy metal concentrations in different organs (skin and muscle tissue) were studied in Lessepsian suez puffer (Lagocephalus suezensis Clark and Gohar, 1953) collected from Iskenderun Bay, North...
Partial Purification, Characterization and Application of Bacteriocin from Bacteria Isolated Parkia biglobosa Seeds
Bacteriocins are proteinaceous toxins produced by bacteria to inhibit the growth of similar or closely related bacterial strains. Fermented Parkia biglobosa seeds (African locust bean) were screened for bacteriocin-produ...
A 5th order video band elliptic filter topology using OTRA based Fleischer Tow Biquad with MOS-C Realization
A new 5th order video band elliptic filter topology is presented. In video applications high order elliptic filters were used. The proposed 5th order lowpass filter was simulated with PSPICE simulation program. The ellip...