Algorithm 2: FHR Classsification using Multi Layer Perceptron

Input: $X=\left[x_1,\dots .,x_{10}\right]$, class labels, initial weight vector $w={\left[w_i\right]}^T$

Step 1: Weighted sum of the input features

$g\left(x\right)\leftarrow {\displaystyle {\displaystyle \sum }_{i=1}^{n10}}{w}_i{x}_i$

Step2: Pass the value to the sigmoid activation function f.

Step3: Produce the output

$y\leftarrow f\left(g\left(x\right)\right)$

Step4: Compute the error $e_i=h_i-y_i$

Step5: Adjust$w$to minimize $e_i$.

Output:

$\hat{y}=\frac{{{\displaystyle \sum }}_{i=1}^{10}{w}_i{f}_i}{{{\displaystyle \sum }}_{i=1}^{10}{w}_i}$