1st International ICST Worksop on Situation Recognition and Medical Data Analysis in Pervasive Health Environments

Research Article

Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis

Download
  • @INPROCEEDINGS{10.4108/ICST.PERVASIVEHEALTH2009.6053,
        author={Mingjing Yang and Huiru Zheng and Haiying Wang and Sally McClean},
        title={Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis},
        proceedings={1st International ICST Worksop on Situation Recognition and Medical Data Analysis in Pervasive Health Environments},
        proceedings_a={PERVASENSE},
        year={2009},
        month={8},
        keywords={feature selection, feature construction, classification, neurodegenerative diseases},
        doi={10.4108/ICST.PERVASIVEHEALTH2009.6053}
    }
    
  • Mingjing Yang
    Huiru Zheng
    Haiying Wang
    Sally McClean
    Year: 2009
    Feature selection and construction for the discrimination of neurodegenerative diseases based on gait analysis
    PERVASENSE
    IEEE
    DOI: 10.4108/ICST.PERVASIVEHEALTH2009.6053
Mingjing Yang1,*, Huiru Zheng1,*, Haiying Wang1,*, Sally McClean1,*
  • 1: Faculty of Computing and Engineering, University of Ulster, N. Ireland, UK
*Contact email: Yang-m@email.ulster.ac.uk, h.zheng@ulster.ac.uk, hy.wang@ulster.ac.uk, si.mcclean@ulster.ac.uk

Abstract

Gait disorder is one symptom of neurodegenerative disease. Using wearable motion sensors to monitor the motor function of patients with neurodegenerative disease has attracted more attention. Research has shown that machine learning techniques can be applied to the classification of neurodegenerative diseases from the gait data recorded by footswitches. In order to identify the most valuable features from 10 raw temporal variables extracted from gait cycles to improve the classification performance, we examine four types of feature selection and construction methods, namely, maximum signal-to-noise ratio based feature selection method, maximum signal-to-noise ratio combined with minimum correlation based feature selection method, maximum prediction power combined with minimum correlation based feature selection method and principal component analysis. Results show that using a set of four features, a relatively high prediction performance has been achieved with classification accuracies ranging from 79.04% to 93.96%. The continual increase of the number of features does not significantly contribute to the improvement of classification performance. This is consistent with clustering-based feature analysis.