Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feed-forward neural networks, fuzzy logic, and a local nonlinear predictor

Abstract

Forecasting of aperiodic time series is a compelling challenge for science. In this work, we analyze aperiodic spectrophotometric data, proportional to the concentrations of two forms of a thermoreversible photochromic spiro-oxazine, that are generated when a cuvette containing a solution of the spiro-oxazine undergoes photoreaction and convection due to localized ultraviolet illumination. We construct the phase space for the system using Takens' theorem and we calculate the Lyapunov exponents and the correlation dimensions to ascertain the chaotic character of the time series. Finally, we predict the time series using three distinct methods: a feed-forward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.

Processing Binary and Fuzzy Logic by Chaotic Time Series Generated by a Hydrodynamic Photochemical Oscillator

“…Artificialn eural networks, such as feed-forward neuraln etworks, are more powerful in this respect. [31] However,t he fuzzy logic system can be really useful in the field of computational linguistics, whichi sc oncerned with the development of systemss uitable for generating texts in natural language from numerical data. [13] Such data-to-texts ystems are playing ar ole in field of artificial intelligence and promise to be useful for making decisions in complex situations.…”

Photo‐Controlled Waves and Active Locomotion

“…[22] Because molecular iodine is ak ey species, the CDIMAr eactioni sq uite photosensitive, and there exist good models for the reaction [23] and for the effect of light on it [24] at various levels of sophistication. [28] In am ore directly biological context, Magome et al [29] introduced azobenzene into ap reparation of cultured cardiomyocytes and were able to control the excitability of the tissue by selective illumination at wavelengths that favored either the cis (no effect) or trans (suppression of oscillations) isomerso fa zobenzene. [25] More relevant for this article are experiments and simulations in which the light source moves relative to the pattern,a nd in which propagating waves are modulated by light.…”

Polypyridyl-imidazole based smart Ru(II) complex mimicking advanced Boolean and Fuzzy logic functions

“…Enormous efforts had recently been devoted to develop artificial intelligence with vague and incomplete information. But only a few FIS-superimposed infinite-valued molecular logic systems have been reported to date [7,[64][65][66][67][68][69][70][71]. Moreover, to the best of our knowledge, there is no report on Fuzzy logic system (FLS) based on Ru(II) complex with excellent photophysical properties in the visible region.…”

“…But in most of the practical systems, there are some intermediate states which lie in between. The Fuzzy logic system (FLS) is thought to be a potential alternative of Boolean logic to characterize the intermediate values between completely true (1) and completely false (0) [7,[64][65][66][67][68][69][70][71]. The motivation behind developing the FLS is based on the notion that human reasoning and decision making process is too complex to be precisely defined and believed to act as automatic fine-tuning control systems that can handle several middle steps with varying degrees of truth.…”