Building a KNN classifier with multiple classes that identifies different audio - matlab

Question

I am in the process of building a KNN algorithm with the purpose of identifying and categorizing common engine problems in Matlab. I have been using the builds from the book 'An Introduction To audio Analysis: A Matlab Approach' which contains exactly what I need to continue my experiment. The problem is that when I identify where the audio samples are kept on my computer, the system claims that it gives out the message "audio sample path is not valid!" Below is the original algorithm the authors of the book have supplied
function kNN_model_add_class(modelName, className, classPath, ...
listOfStatistics, stWin, stStep, mtWin, mtStep)
%
% function kNN_model_add_class(modelName, className, classPath, ...
% listOfStatistics, stWin, stStep, mtWin, mtStep)
%
% This function adds an audio class to the kNN classification model
%
% ARGUMENTS;
% - modelName: the filename of the model (mat file)
% - className: the name of the audio class to be added to the model
% - classPath: the path of the directory where the audio segments of the
% new class are stored
% - listOfStatistics: list of mid-term statistics (cell array)
% - stWin, stStep: short-term window size and step
% - mtWin, mtStep: mid-term window size and step
%
% Example:
% kNN_model_add_class('modelSpeech.mat', 'speech', './Music/', ...
% {'mean','std',}, 0.050, 0.025, 2.0, 1.0);
%
if ~exist(classPath,'dir')
error('Audio sample path is not valid!');
else
classPath = [classPath filesep];
end
% check if the model elaready exists:
fp = fopen(modelName, 'r');
if fp>0 % check if file already exists
load(modelName);
end
% Feature extraction:
D = dir([classPath '*.wav']);
F = [];
for (i=1:length(D)) % for each wav file in the given path:
curFileName = [classPath D(i).name];
FileNamesTemp{i} = curFileName;
% mid-term feature extraction for each wav file:
midFeatures = featureExtractionFile(curFileName, ...
stWin, stStep, mtWin, mtStep, listOfStatistics);
% long-term averaging:
longFeatures = mean(midFeatures,2);
F = [F longFeatures];
end
% save the model:
Statistics = listOfStatistics;
fp = fopen(modelName, 'r');
if fp<0 % model does not exist --> generate
ClassNames{1} = className;
Features{1} = F;
FileNames{1} = FileNamesTemp;
save(modelName, 'ClassNames', 'Features', ...
'Statistics', 'stWin', 'stStep', 'mtWin', 'mtStep', 'FileNames');
else
load(modelName);
ClassNames{end+1} = className;
Features{end+1} = F;
FileNames{end+1} = FileNamesTemp;
save(modelName, 'ClassNames', 'Features', ...
'Statistics', 'stWin', 'stStep', 'mtWin', 'mtStep', 'FileNames');
end
Here is the way that I have implemented it into my own project.
%Knn algorithm training
%path to folder containing the audio segements
strDir ='/Users/itsolutions/Documents/MATLAB/Wav_engine_edits ';
%mid-term statistics to be used:
Statistics = {'mean','median','std','stdbymean','max','min'};
%short-term and mid-term, processing windon length and step:
stWin = 0.040; stStep = 0.040;
mtWin = 2.0; mtStep = 1.0;
%perform feature extraction
kNN_model_add_class ('model8.mat','connection rod noise', [ strDir '/Connection_rod_edits/'],Statistics, stWin, stStep, mtWin, mtStep);
kNN_model_add_class ('model8.mat','detonation noise', [strDir ' /Detonation_noise_edits/'],Statistics, stWin, stSteo, mtWin, mtStep)
%kNN_model_add_class ('model8.mat','Engine bearing noise' [strDir '/Engine Bearing Noise edits/'],Statistics, stWin, stStep, mtWin, mtStep);
Any ideas? I have looked into the objects present in the function knn_model_add_class() and have found that it is still using wavread, which in the 2016b version of matlab in invalid syntax now.
Could anyone give me a hand? Seems like I am going in circles and it is something really obvious that i can't see.
Regards
M.Brown
Edit:
Using the process of elimination I have found that the error comes from this piece of code
if ~exist(classPath,'dir')
error('Audio sample path is not valid!');
else
classPath = [classPath filesep];
end
The code cannot seem to find the audio samples in question. I have contacted the author of the book, but until then does anybody know why the matlab file path won't recognize the wav files?