Noise-Induced Hearing Loss (NIHL) Prediction in Humans Using a Modified Back Propagation Neural Network

Abstract

Noise-Induced Hearing Loss (NIHL) has become a major source of health problem in industrial workers due to continuous exposure to high frequency sounds emitting from the machines. In the past, several studies have been carried-out to identify NIHL industrial workers. Unfortunately, these studies neglected some important factors that directly affect hearing ability in human. Artificial Neural Network (ANN) provides very effective way to predict hearing loss in humans. However, the training process for an ANN required the designers to arbitrarily select parameters such as network topology, initial weights and biases, learning rate value, the activation function, value for gain in activation function and momentum. An improper choice of any of these parameters can result in slow convergence or even network paralysis, where the training process comes to a standstill or get stuck at local minima. Therefore, this current study focuses on proposing a new framework on using Gradient Descent Back Propagation Neural Network model with an improvement on the momentum value to identify the important factors that directly affect the hearing ability of industrial workers. Results from the prediction will be used in determining the environmental health hazards which affect the workers health.