Classification of Spatio-temporal Data

This paper presents a new approach in spatio-temporal data classification. This classification can be used in many branches including robotics, computer vision or medical data analysis. Due to easy transformation of time dimension of spatio-temporal data into the phase of complex number, the presented approach uses complex numbers. The classification is based on a complex-valued neural network with multilayer topology. The paper proposes an extension of complexvalued backpropagation algorithm, which uses activation function applying nonlinearity on the amplitude only (preserving the phase) instead of commonly used activation function applying non-linearities on the real and the imaginary part separately. In order to transform the input data into complex numbers, a new coding technique is presented. It encodes the time-dimension into phase of complex number and space-dimensions into amplitude of complex numbers. Another task is to develop output coding, that would allow the classification from complex numbers. It is solved with introduction of one-of-N coding extension into complex numbers, which is used as network’s output coding. This approach is verified in application of hand-written character recognition, using the data collected during the writing process. The simulation results of this application are presented in the paper.