A Comparative Study between Artificial Intelligence Techniques in an Automatic Infant's Pain Cry Identification System

Comparative study of logistic regression and artificial neural networks on predicting breast cancer cytology

“…The first one is Multilayer Perceptron (MLP) network as shown in Figure 1 which is a well known network architecture has been used in medical, engineering, mathematical modeling research. In MLP, a fixed value (bias) along with weighted sum of inputs are propagated to the hidden layer via a transfer function to generate the output, and the topology of feed-forward layers arrangement of units is called Feed Forward Neural Network (FFNN) [21]. The learning ability of the MLP is highly increased by the hidden layer.…”

“…The widely used metric in classification process is accuracy [21,24,25]. It is the rate of correctly classified test samples [21,25].…”

“…The widely used metric in classification process is accuracy [21,24,25]. It is the rate of correctly classified test samples [21,25]. Sensitivity is the ability of a model to correctly identify true positive instances and is called true positive rate whereas specificity is the ability of the model or test to correctly identify the true negative instances and is called true negative rate.…”