Prediction of Composition parameters of Cortical bone using Artificial Neutral Network

The goal of this article is to look at the viability of employing artificial neural network programming to forecast cortical bone composition characteristics. The neural network's input parameters were the experimentally determined composition parameters, which included size, location, orientation, wet density, dry density, ash, mineral, organic (wet), organic (dry), and water content. A feed forward neural network underpins the model. This paper describes the proposed ANN in depth, including its design, training, and validation. The trained ANN's efficacy is assessed by comparing its answers to the experimental data utilized in the training process. The findings reveal that the ANN model can properly predict the composition characteristics of a cortical bone.