Auto-Regressive model in Matlab?

I have (emg) signal . I need to use an Auto-regressive model for this signal. AR model is used to extract the data from (emg) signal. I am going to classify the (emg)signal using the AR coefficient as the features. In order to find the effective classification accuracy,

How do I determine the order of the AR model? And also how do I find the coefficient?

Perhaps, can anyone provide me the Matlab code for this?

Answer 1

[Anshuman]

To determine the order of the Auto-Regressive (AR) model and find the coefficients for your EMG signal, you can use criteria such like Akaike Information Criterion (AIC).

You can do something like this:

% Assuming emg_signal is your EMG data

% Determine the order of the AR model using AIC
max_order = 20;  % Maximum order to consider
aic = zeros(1, max_order);

for order = 1:max_order
    model = ar(emg_signal, order, 'aic');
    aic(order) = model.Report.Fit.AIC;
end

% Find the order with the minimum AIC
[~, best_order] = min(aic);

% Estimate the AR coefficients
[ar_coeffs, noise_variance] = aryule(emg_signal, best_order);

Please refer to the following documenation links for more information:

• https://in.mathworks.com/help/ident/ref/ar.html
• https://in.mathworks.com/help/signal/ref/aryule.html

Hope it helps!