Time Warping techniques in clustering time series

The problem of obtaining an accurate forecast is becoming more and more significant as the production possibilities and technologies evolve. The accuracy of a forecast mainly depends on the dataset used for forecasting as well as on the methods employed. This study is devoted to the time series analysis. A set of known methods and techniques are used for analysing the time series; one of them is the Kohonen's self-organising maps. The Time Warping techniques enable SOM to cluster time series of different length, which is highly significant in product life cycle analysis and phase switching tasks. The main goal of the research is to perform a set of experiments aimed to compare the efficiency of several Time Warping techniques and to study how the chosen topology of neurons in the Self-organising map influences the final forecasting result.