# Signal Classification and the FFT.

 Problem 1 Create a New Project called SigFourier (You must select: Multi-layer Network and Classification in the New Project Dialog) classify four signals in the frequency domain. Edit the BulidTrainSet.lab file to build an appropriate training set for the classification of the four signals. Your training set will include clean and noisy signals as described below using a random phase to build each case. The table indicates the number of training cases for each signal. (a) In the time domain, (b) in the frequency domain (using the Fourier Transform).

 Signal Clean 10% Noise 20% Noise 30% Noise Sine 150 150 150 150 Saw tooth 150 150 150 150 Triangular 150 150 150 150 Squared 150 150 150 150 Reject 100 100 100 100

 Hint To keep your files organized use the file names as described in the table below.

 Test Time Domain Frequency Domain Build Train Set BuidTrainSetT.lab BuildTrainSetF.lab Training Set trainSetInputT.csv, trainSetTarget.csv trainSetInputF.csv, trainSetTarget.csv Build Validation Set BuidValidSetT.lab BuildValidSetF.lab Validation Set validSetT.csv, validSetTarget.csv validSetF.csv, validSetTarget.csv Training TrainT.lab TrainF.lab Check Training CheckTrainingT.lab CheckTrainingF.lab (Trainining) Confusion Matrix trainConfT.emf trainConfF.emf Validation ValidationT.lab ValidationF.lab (Validation) Confusion Matrix validConfT.emf validConfF.emf

 Problem 2 Edit the BuilValidSetT.lab file and the BuilValidSetF.lab file to build an appropriate validation set for problem 1 using random phase. The table below describes the number of validation cases for each shape.

 Signal Clean 10% Noise 20% Noise 30% Noise Sine 100 100 100 100 Saw tooth 50 50 50 50 Triangular 40 40 40 40 Squared 70 70 70 70 Reject 60 60 60 60

 Problem 3 Edit the TrainT.lab file and the TrainF.lab file to design and train an ANN for the classification of the signals.

 Problem 4 Edit the CheckTrainingT.lab file and the CheckTrainingF.lab file to check the training: (a) Compute the confusion matrix using the training set. (b) Plot the error for each network output. (c) Save the confusion matrix as a vector image (trainConfT.emf and trainConfF.emf).

 Problem 5 Edit the ValidationT.lab file and the ValidationF.lab file to perform the validation of the ANN. (a) Compute the confusion matrix using the validation set. (b) Plot the error for each network output. (c) Save the confusion matrix as a vector image (validConfT.emf and validConfF.emf).

 Problem 6 Generate a report in Microsoft Word. Write some conclusions in the report trying to compare your results using data in the time domain with the data in the frequency domain.