Local Pattern Transformation Based Feature Extraction for Recognition of Parkinson’s Disease Based on Gait Signals

S Jeba Priya,Mazin Abed Mohammed,Robertas Damaševičius,Arockia Jansi Rani,Neha Ubendran,M S P Subathra

doi:10.3390/diagnostics11081395

Abstract

Parkinson’s disease (PD) is a neuro-degenerative disorder primarily triggered due to the deterioration of dopamine-producing neurons in the substantia nigra of the human brain. The early detection of Parkinson’s disease can assist in preventing deteriorating health. This paper analyzes human gait signals using Local Binary Pattern (LBP) techniques during feature extraction before classification. Supplementary to the LBP techniques, Local Gradient Pattern (LGP), Local Neighbour Descriptive Pattern (LNDP), and Local Neighbour Gradient Pattern (LNGP) were utilized to extract features from gait signals. The statistical features were derived and analyzed, and the statistical Kruskal–Wallis test was carried out for the selection of an optimal feature set. The classification was then carried out by an Artificial Neural Network (ANN) for the identified feature set. The proposed Symmetrically Weighted Local Neighbour Gradient Pattern (SWLNGP) method achieves a better performance, with 96.28% accuracy, 96.57% sensitivity, and 95.94% specificity. This study suggests that SWLNGP could be an effective feature extraction technique for the recognition of Parkinsonian gait.

Highlights

Parkinson’s disease (PD) is a neurological condition located in the basal ganglia and brainstem due to a lack of dopaminergic activity [1]
This paper focuses on the role of pattern recognition approaches, namely Local Binary Pattern (LBP), Local Gradient Pattern, Local Neighbour Gradient Pattern and, Local Neighbour Descriptive Pattern, to detect PD
Eight different pattern recognition techniques were used for the feature extraction, which leads to a good performance in identifying PD in its early stage

Summary

Introduction

Parkinson’s disease (PD) is a neurological condition located in the basal ganglia and brainstem due to a lack of dopaminergic activity [1]. It is a chronic disorder of adult onset, which becomes more common with age [2]. PD motor disorders are diagnosed using freezing of gait [7], foot pressure analysis, finger motion analysis, voice and speech disorders [8,9], brain dopaminergic imaging, and handwriting studies. The dopaminergic image in the brain is considered as an authentic method for the identification of PD [12]

Objectives

Methods

Results

Conclusion