Machine learning approaches to identify Parkinson$$s disease using voice signal features.

Parkinson$$s Disease $($PD$)$ is the second most common age$-$related neurological disorder that leads to a range of motor and cognitive symptoms. A PD diagnosis is difficult since its symptoms are quite like those of other disorders, such as normal aging and essential tremor. When people reach $50,$ visible symptoms such as difficulties walking and communicating begin to emerge. Even though there is no cure for PD$,$ certain medications can relieve some of the symptoms. Patients can maintain their lifestyles by controlling the complications caused by the disease. At this point, it is essential to detect this disease and prevent it from progressing. The diagnosis of the disease has been the subject of much research. In this HW$,$ your objective is to detect PD using Machine Learning $($ML$)$ model such as K$-$Nearest Neighbor $($KNN$),$ to differentiate between healthy and PD patients by voice signal features.

Dataset

The study included voice recordings from $31$ people, including $23$ people with Parkinson$$s Disease $($PD$)(16$ males and $7$ females$)$ and eight Healthy Controls $($HC$)($males $=3$ and females $=5).$ The dataset contains $195$ records, $24$ columns, and as presented in Table $1,$ a series of biomedical voice measurements. Table $1$ is divided into columns that represent each of the voice measurements and rows which represent vocal recordings from individuals $($the $$name$$ column$).$ An average of six recordings were made for each patient; six recordings were taken from $22$ patients, and seven recordings were taken from nine patients. The patients$$ ages ranged from $46$ to $85$ years $($mean $65\mathrm{.}8,$ standard deviation $9\mathrm{.}8),$ and the time since diagnosis ranged from $0$ to $28$ years. Each row corresponds to one voice recording for $36$ s$.$ The voice was recorded in an industrial acoustic company sound$-$treated booth by a microphone placed $8$cm from the mouth. In the dataset, the $$status$$ column is set to $0$ for HC and $1$ for those with PD$,$ to distinguish healthy individuals from those with PD$.$

Table $1$ Matrix column entries $($attributes$)$:

name $-$ ASCII subject name and recording number

MDVP:Fo$($Hz$)-$ Average vocal fundamental frequency

MDVP:Fhi$($Hz$)-$ Maximum vocal fundamental frequency

MDVP:Flo$($Hz$)-$ Minimum vocal fundamental frequency

MDVP:Jitter$(\%),$ MDVP:Jitter$($Abs$),$ MDVP:RAP, MDVP:PPQ$,$ Jitter:DDP $-$ Several

measures of variation in fundamental frequency

MDVP:Shimmer, MDVP:Shimmer$($dB$),$ Shimmer:APQ$3,$ Shimmer:APQ$5,$ MDVP:APQ, Shimmer:DDA $-$ Several measures of variation in amplitude

NHR$,$ HNR $-$ Two measures of ratio of noise to tonal components in the voice

status $-$ Health status of the subject $($one$)-$ Parkinson's, $($zero$)-$ healthy

RPDE, D$2-$ Two nonlinear dynamical complexity measures

DFA $-$ Signal fractal scaling exponent

spread$1,$ spread$2,$ PPE $-$ Three nonlinear measures of fundamental frequency variation

Use the Machine Learning algorithm K$-$Nearest Neighbor $($KNN$),$ and the DB$\_$Voice$\_$Features.csv database to discriminate and evaluate classification performance of healthy and PD patients by voice signal features.

Use:dvs python

a$)$ Parameter optimization $(80$ pts$)$

c$)$ Discuss the results obtained $($different metrics$),(20)$