Frequency analysis of gait signals for detection of neurodegenerative diseases

Movement disorders occurring due to improper functioning of neurons are termed as neurodegenerative diseases. Among the neurodegenerative diseases, amyotropic lateral sclerosis (ALS), huntingtons disease (HD) and Parkinson's disease (PD) are important. As these diseases are progressive, early diagnosis has significance in managing the diseases. Gait signal is movement signal which can be obtained from force sensitive resistors placed under the foot. Left stride, right stride and left swing signals are selected, frequency spectra and power spectral density of signals are obtained. After dividing the obtained spectra into ten parts, statistical features of mean, variance, skewness and kurtosis are computed. Ability of artificial neural network, support vector machine and naive Bayes classifier are tested for classifying the diseases using the selected statistical features.