Spectral forecast is a novel general-purpose prediction model recently published in the journal CHAOS. The model revolves around three known states: two extreme outcomes (A and B) and one measurement (P). These states are represented by either vectors or matrices that include sets of homologous parameters. An information spectrum is described as a series of predicted states (M1, M2, M3, …, Md) generated between the two extreme outcomes (A and B). These states are successively calculated using the spectral forecast equation. The predicted states are compared with a known state (P) from the measurements to generate a series of similarity index values. The trend generated by the values of the similarity index shows how a system may behave against these two extreme outcomes (A and B). Note that the construction and theory behind the chart of this application can be found here.

Please read more about Spectral Forecast here:

• Spectral forecast: A general purpose prediction model as an alternative to classical neural networks

• Algorithms in Bioinformatics: Theory and Implementation

Live demo: https://gagniuc.github.io/Spectral-Forecast-model-for-signals/

• Paul A. Gagniuc et al. Spectral forecast: A general purpose prediction model as an alternative to classical neural networks. Chaos 30, 033119 (2020).

• Paul A. Gagniuc. Algorithms in Bioinformatics: Theory and Implementation. John Wiley & Sons, Hoboken, NJ, USA, 2021, ISBN: 9781119697961.