A feasibility study of using the neucube spiking neural network architecture for modelling Alzheimer’s disease EEG data

Elisa Capecci, Francesco Carlo Morabito, Maurizio Campolo, Nadia Mammone, Domenico Labate, Nikola Kasabov

Research output: Contribution to journalArticle

Abstract

The paper presents a feasibility analysis of a novel Spiking Neural Network (SNN) architecture called NeuCube [10] for classification and analysis of functional changes in brain activity of Electroencephalography (EEG) data collected amongst two groups: control and Alzheimer’s Disease (AD). Excellent classification results of 100% test accuracy have been achieved and these have also been compared with traditional machine learning techniques. Outputs confirmed that the Neu-Cube is better suited to model, classify, interpret and understand EEG data and the brain processes involved. Future applications of a NeuCube model are discussed including its use as an indicator of the early onset of Mild Cognitive Impairment(MCI) to study degeneration of the pathology toward AD.

Original languageEnglish
Pages (from-to)159-172
Number of pages14
JournalSmart Innovation, Systems and Technologies
Volume37
DOIs
Publication statusPublished - 2015

Fingerprint

Electroencephalography
Network architecture
Brain
Neural networks
Pathology
Learning systems
Alzheimer's disease
Modeling
Feasibility study
Impairment
Machine learning
Feasibility analysis

Keywords

  • Alzheimer’s disease
  • EEG data classification
  • NeuCube
  • Spiking neural networks

ASJC Scopus subject areas

  • Computer Science(all)
  • Decision Sciences(all)

Cite this

A feasibility study of using the neucube spiking neural network architecture for modelling Alzheimer’s disease EEG data. / Capecci, Elisa; Morabito, Francesco Carlo; Campolo, Maurizio; Mammone, Nadia; Labate, Domenico; Kasabov, Nikola.

In: Smart Innovation, Systems and Technologies, Vol. 37, 2015, p. 159-172.

Research output: Contribution to journalArticle

Capecci, Elisa ; Morabito, Francesco Carlo ; Campolo, Maurizio ; Mammone, Nadia ; Labate, Domenico ; Kasabov, Nikola. / A feasibility study of using the neucube spiking neural network architecture for modelling Alzheimer’s disease EEG data. In: Smart Innovation, Systems and Technologies. 2015 ; Vol. 37. pp. 159-172.
@article{d670d2eefbff45febf7a8585d2d8c7b0,
title = "A feasibility study of using the neucube spiking neural network architecture for modelling Alzheimer’s disease EEG data",
abstract = "The paper presents a feasibility analysis of a novel Spiking Neural Network (SNN) architecture called NeuCube [10] for classification and analysis of functional changes in brain activity of Electroencephalography (EEG) data collected amongst two groups: control and Alzheimer’s Disease (AD). Excellent classification results of 100{\%} test accuracy have been achieved and these have also been compared with traditional machine learning techniques. Outputs confirmed that the Neu-Cube is better suited to model, classify, interpret and understand EEG data and the brain processes involved. Future applications of a NeuCube model are discussed including its use as an indicator of the early onset of Mild Cognitive Impairment(MCI) to study degeneration of the pathology toward AD.",
keywords = "Alzheimer’s disease, EEG data classification, NeuCube, Spiking neural networks",
author = "Elisa Capecci and Morabito, {Francesco Carlo} and Maurizio Campolo and Nadia Mammone and Domenico Labate and Nikola Kasabov",
year = "2015",
doi = "10.1007/978-3-319-18164-6_16",
language = "English",
volume = "37",
pages = "159--172",
journal = "6th International Conference on Research into Design, ICoRD 2017",
issn = "2190-3018",
publisher = "Springer Verlag",

}

TY - JOUR

T1 - A feasibility study of using the neucube spiking neural network architecture for modelling Alzheimer’s disease EEG data

AU - Capecci, Elisa

AU - Morabito, Francesco Carlo

AU - Campolo, Maurizio

AU - Mammone, Nadia

AU - Labate, Domenico

AU - Kasabov, Nikola

PY - 2015

Y1 - 2015

N2 - The paper presents a feasibility analysis of a novel Spiking Neural Network (SNN) architecture called NeuCube [10] for classification and analysis of functional changes in brain activity of Electroencephalography (EEG) data collected amongst two groups: control and Alzheimer’s Disease (AD). Excellent classification results of 100% test accuracy have been achieved and these have also been compared with traditional machine learning techniques. Outputs confirmed that the Neu-Cube is better suited to model, classify, interpret and understand EEG data and the brain processes involved. Future applications of a NeuCube model are discussed including its use as an indicator of the early onset of Mild Cognitive Impairment(MCI) to study degeneration of the pathology toward AD.

AB - The paper presents a feasibility analysis of a novel Spiking Neural Network (SNN) architecture called NeuCube [10] for classification and analysis of functional changes in brain activity of Electroencephalography (EEG) data collected amongst two groups: control and Alzheimer’s Disease (AD). Excellent classification results of 100% test accuracy have been achieved and these have also been compared with traditional machine learning techniques. Outputs confirmed that the Neu-Cube is better suited to model, classify, interpret and understand EEG data and the brain processes involved. Future applications of a NeuCube model are discussed including its use as an indicator of the early onset of Mild Cognitive Impairment(MCI) to study degeneration of the pathology toward AD.

KW - Alzheimer’s disease

KW - EEG data classification

KW - NeuCube

KW - Spiking neural networks

UR - http://www.scopus.com/inward/record.url?scp=84930933542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84930933542&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-18164-6_16

DO - 10.1007/978-3-319-18164-6_16

M3 - Article

AN - SCOPUS:84930933542

VL - 37

SP - 159

EP - 172

JO - 6th International Conference on Research into Design, ICoRD 2017

JF - 6th International Conference on Research into Design, ICoRD 2017

SN - 2190-3018

ER -