LTR-MDTS structure - a structure for multiple dependent time series prediction

Abstract

The subject of research presented in this paper is to model a neural network structure and appropriate training algorithm that is most suited for multiple dependent time series prediction / deduction. The basic idea is to take advantage of neural networks in solving the problem of prediction of synchronized basketball referees' movement during a basketball action. Presentation of time series stemming from the aforementioned problem, by using traditional Multilayered Perceptron neural networks (MLP), leads to a sort of paradox of backward time lapse effect that certain input and hidden layers nodes have on output nodes that correspond to previous moments in time. This paper describes conducted research and analysis of different methods of overcoming the presented problem. Presented paper is essentially split into two parts. First part gives insight on efforts that are put into training set configuration on standard Multi Layered Perceptron back propagation neural networks, in order to decrease backwards time lapse effects that certain input and hidden layers nodes have on output nodes. Second part of paper focuses on the results that a new neural network structure called LTR-MDTS provides. Foundation of LTR-MDTS design relies on a foundation on standard MLP neural networks with certain, left-to-right synapse removal to eliminate aforementioned backwards time lapse effect on the output nodes.

Classification Based on Missing Features in Deep Convolutional Neural Networks

“…Instead of training on missing features we want to introduce a new idea of negative learning or telling the network what surely is not the desired output. One example that is familiar to us is the basketball referee problem [16,17] where the position of basketball referees needs to be decided based on the position of the ball and the players. There, we sometimes do not know the best positions for referees but we are certain what are the bad positions (where referees cannot see the ball), and we believe that making a model that can take this information into consideration will perform better than traditional model.…”

Two Faces of the Framework for Analysis and Prediction, Part 2 - Research

“…Many modern research and practice scenarios are faced with large quantities of data in the form of time series [8,43]. Therefore, numerous techniques and procedures are constantly developed and implemented for time-series processing, as well as exploring and explaining the phenomena from which they originate.…”