A classifier fusion strategy to improve the early detection of neurodegenerative diseases

Shamaila Iram, Paul Fergus, Dhiya Al Jumeily, Abir Hussain, Martin Randles

Research output: Contribution to journalArticle

Abstract

People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimer's and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules (voting, product, mean, median, maximum and minimum) to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers (a single classification algorithm) using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.
Original languageEnglish
Pages (from-to)23-44
Number of pages22
JournalInternational Journal of Artificial Intelligence and Soft Computing
Volume5
Issue number1
DOIs
Publication statusPublished - 2015
Externally publishedYes

Fingerprint

Neurodegenerative diseases
Classifiers
Fusion reactions
Experiments

Cite this

@article{7c3a59f292d84907b5377afc23290067,
title = "A classifier fusion strategy to improve the early detection of neurodegenerative diseases",
abstract = "People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimer's and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules (voting, product, mean, median, maximum and minimum) to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers (a single classification algorithm) using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.",
keywords = "Combining classifiers, Pattern recognition, Behaviour classification, Machine learning, Huntington's disease, Parkinson's disease amyotrophic lateral sclerosis, ALS, Movement signals, Artificial intelligence",
author = "Shamaila Iram and Paul Fergus and Jumeily, {Dhiya Al} and Abir Hussain and Martin Randles",
year = "2015",
doi = "10.1504/IJAISC.2015.067525",
language = "English",
volume = "5",
pages = "23--44",
journal = "International Journal of Artificial Intelligence and Soft Computing",
issn = "1755-4950",
publisher = "Inderscience",
number = "1",

}

A classifier fusion strategy to improve the early detection of neurodegenerative diseases. / Iram, Shamaila; Fergus, Paul; Jumeily, Dhiya Al; Hussain, Abir; Randles, Martin.

In: International Journal of Artificial Intelligence and Soft Computing, Vol. 5, No. 1, 2015, p. 23-44.

Research output: Contribution to journalArticle

TY - JOUR

T1 - A classifier fusion strategy to improve the early detection of neurodegenerative diseases

AU - Iram, Shamaila

AU - Fergus, Paul

AU - Jumeily, Dhiya Al

AU - Hussain, Abir

AU - Randles, Martin

PY - 2015

Y1 - 2015

N2 - People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimer's and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules (voting, product, mean, median, maximum and minimum) to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers (a single classification algorithm) using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.

AB - People in developed countries are living longer, and this has resulted in the prevalence of age-related diseases like Alzheimer's and dementia. Many believe that the early detection of neurodegenerative diseases will provide a much more sustainable framework for dealing with age-related diseases in the future. This paper considers this idea and proposes a new classifier fusion strategy that combines classification algorithms and rules (voting, product, mean, median, maximum and minimum) to measure specific behaviours in people suffering with neurodegenerative diseases. More specifically, the fusion strategy analyses the stride-to-stride intervals in gait and its correlation with neurological functions. This approach is compared with base level classifiers (a single classification algorithm) using a set of feature vectors associated with gait patterns obtained from neurodegenerative patients and healthy people. The results show that the fusion strategy improves classification. Our experiments successfully show that a fusion strategy generates better results and classifies subjects more accurately than base level classifiers.

KW - Combining classifiers

KW - Pattern recognition

KW - Behaviour classification

KW - Machine learning

KW - Huntington's disease

KW - Parkinson's disease amyotrophic lateral sclerosis

KW - ALS

KW - Movement signals

KW - Artificial intelligence

UR - http://www.inderscience.com/jhome.php?jcode=ijaisc

U2 - 10.1504/IJAISC.2015.067525

DO - 10.1504/IJAISC.2015.067525

M3 - Article

VL - 5

SP - 23

EP - 44

JO - International Journal of Artificial Intelligence and Soft Computing

JF - International Journal of Artificial Intelligence and Soft Computing

SN - 1755-4950

IS - 1

ER -