Title: Factors important for good visualisation of time series

Authors: Tzai-Der Wang; Xiaochuan Wu; Colin Fyfe

Addresses: Department of Industrial Engineering and Management, Cheng Shiu University, Kaohsiung City, Taiwan ' University of the West of Scotland, High Street, Paisley, UK ' University of the West of Scotland, High Street, Paisley, UK

Abstract: We create an artificial neural network which is a version of echo state networks, ESNs. ESNs are recurrent neural networks but unlike most recurrent networks, they come with an efficient training method. We have previously (Wang et al., 2011) adapted this method using ideas from neuroscale (Tipping, 1996) so that the network can be used for projecting multivariate time series data onto a low dimensional manifold so that the structure in the time series can be identified by eye. In this paper, we review work on a minimal architecture echo state machine (Wang et al., 2011) in the context of visualisation and show that it does not perform as well as the original. We then discuss three factors which may affect the capability of the network - its structure, size and sparsity - and show that, of these three, by far the most important is the size of the reservoir of neurons.

Keywords: echo state machines; visualisation; multidimensional scaling; time series; artificial neural networks; ANNs.

DOI: 10.1504/IJCSE.2016.074561

International Journal of Computational Science and Engineering, 2016 Vol.12 No.1, pp.17 - 28

Received: 10 Jul 2012
Accepted: 04 Mar 2013
Published online: 06 Feb 2016 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article