Parkinson's disease is the second most prevalent neurodegenerative disease in the elderly, although its prevalence and incidence vary according to age, gender and race/ethnicity. Studies show that the prevalence increases with age, with an estimated 5 to 26 cases per 100,000 people per year, approximately 1% among individuals aged 65 to 69 and ranging from 3% to 14.3% among the elderly over 85. The most common clinical signs of the inflammatory process include the presence of resting tremor, muscle rigidity, bradykinesia and postural instability. Diagnosing the disease is not a simple task, as it is known that there are patterns of stages in the progression of the disease in the human body. However, many patients do not follow this progression due to the heterogeneity of manifestations that can arise. Gait analysis has become an attractive and non-invasive quantitative mechanism that can help in the detection and monitoring of PD sufferers. Feature extraction is an extremely important task for the quality of the data to be used by ML algorithms, with the main objective being to reduce the dimensionality of the data in a classification process.