Application of Artificial Neural Networks in Fall Prediction

The problem of fall is still unsolved even though it is a serious problem, especially in group of elderly. Also, another difficulty is to analyse falls that occur in day-to-day life. Those events are hard to observe by specialists and so it is hard to analyse them. Following work contains a description of experimental process for external force-caused fall observation with the use of motion capture system and dynamometric platforms. Data collected according to this protocol were later used for time series neural networks. Obtained results of analysis were compared to popular model of human stability. Conducted inquiry proves that it is possible to detect fall even before it occurs and while it is external force-caused fall the loss of stability develops earlier than it was assumed.