Prediction of Parkinson's disease using Local Ternary Pattern for Gait Signals

Parkinson's disease (PD) is one of the common neurodegenerative diseases. The severity of the disease increases with age. The primary reason for Parkinson's disease is the deterioration of dopamine-producing brain cells in substantia. The cardinal symptoms of PD comprise of bradykinesia, tremor and rigidness which can be detected by the gait movements. In this study, the pattern recognition technique was utilized for feature extraction and classification using ANN showed virtuous accurateness when LTP technique was used. Eight statistical features were taken for the classification. The performance parameters such as accuracy, sensitivity, specificity and F1 score achieved for the lower bound are 97.02%, 96.55%, 99.57%, 97.09 % respectively.