Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feedforward 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 spirooxazine, that are generated when a cuvette containing a solution of the spirooxazine 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 feedforward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.
 Authors:
 Department of Chemistry, Biology and Biotechnology, University of Perugia, 06123 Perugia (Italy)
 Department of Mechanical Engineering, Ritsumeikan University, 111 Nojihigashi, Kusatsushi, Shiga 5258577 (Japan)
 Department of Chemistry, Brandeis University, Waltham, Massachusetts 024549110 (United States)
 Publication Date:
 OSTI Identifier:
 22402521
 Resource Type:
 Journal Article
 Resource Relation:
 Journal Name: Chaos (Woodbury, N. Y.); Journal Volume: 25; Journal Issue: 1; Other Information: (c) 2015 AIP Publishing LLC; Country of input: International Atomic Energy Agency (IAEA)
 Country of Publication:
 United States
 Language:
 English
 Subject:
 71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSICS; ABUNDANCE; CHAOS THEORY; CONVECTION; FORECASTING; FUZZY LOGIC; ILLUMINANCE; LYAPUNOV METHOD; NEURAL NETWORKS; NONLINEAR PROBLEMS; OSCILLATIONS; PHASE SPACE; PHOTOCHROMIC MATERIALS; SPECTROPHOTOMETRY; TIMESERIES ANALYSIS; ULTRAVIOLET RADIATION
Citation Formats
Gentili, Pier Luigi, Email: pierluigi.gentili@unipg.it, Gotoda, Hiroshi, Dolnik, Milos, and Epstein, Irving R.. Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feedforward neural networks, fuzzy logic, and a local nonlinear predictor. United States: N. p., 2015.
Web. doi:10.1063/1.4905458.
Gentili, Pier Luigi, Email: pierluigi.gentili@unipg.it, Gotoda, Hiroshi, Dolnik, Milos, & Epstein, Irving R.. Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feedforward neural networks, fuzzy logic, and a local nonlinear predictor. United States. doi:10.1063/1.4905458.
Gentili, Pier Luigi, Email: pierluigi.gentili@unipg.it, Gotoda, Hiroshi, Dolnik, Milos, and Epstein, Irving R.. 2015.
"Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feedforward neural networks, fuzzy logic, and a local nonlinear predictor". United States.
doi:10.1063/1.4905458.
@article{osti_22402521,
title = {Analysis and prediction of aperiodic hydrodynamic oscillatory time series by feedforward neural networks, fuzzy logic, and a local nonlinear predictor},
author = {Gentili, Pier Luigi, Email: pierluigi.gentili@unipg.it and Gotoda, Hiroshi and Dolnik, Milos and Epstein, Irving R.},
abstractNote = {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 spirooxazine, that are generated when a cuvette containing a solution of the spirooxazine 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 feedforward neural network, fuzzy logic, and a local nonlinear predictor. We compare the performances of these three methods.},
doi = {10.1063/1.4905458},
journal = {Chaos (Woodbury, N. Y.)},
number = 1,
volume = 25,
place = {United States},
year = 2015,
month = 1
}

A neural fuzzybased and a backpropagation neural networkbased fault classifier for a threephase motor will be described in this paper. In order to acquire knowledge, the neural fuzzy classifier incorporates a learning technique to automatically generate membership functions for fuzzy rules, and the backpropagation algorithm is used to train the neural network model. Therefore, in this paper, the preprocessing of signals, fuzzy and neural models, training methods, implementations for realtime response and testing results will be discussed in detail. Furthermore, the generalization capabilities of the neural fuzzy and backpropagationbased classifiers for waveforms with varying magnitudes, frequencies, noises and positions ofmore »

Fuzzy logic and neural networks
Combine fuzzy logic`s fuzzy sets, fuzzy operators, fuzzy inference, and fuzzy rules  like defuzzification  with neural networks and you can arrive at very unfuzzy realtime control. Fuzzy logic, cursed with a very whimsical title, simply means multivalued logic, which includes not only the conventional twovalued (true/false) crisp logic, but also the logic of three or more values. This means one can assign logic values of true, false, and somewhere in between. This is where fuzziness comes in. Multivalued logic avoids the blackandwhite, allornothing assignment of true or false to an assertion. Instead, it permits the assignment of shadesmore » 
Validating realtime implementations of diagonal recurrent neural network and fuzzy logic controllers for nuclear reactor control
A diagonal recurrent neural network (DRNN) and a fuzzy logic controller (FLC) were designed for optimal temperature control. The DRNN and FLC utilize the response of a fifthorder, one delayed neutron group linear model to an optimal controller that was previously designed. In this paper, the results of testing a realtime implementation of the DRNN and FLC are presented. The method of testing that was utilized is called hardware in loop simulation (HILS). Here, a distributed simulation of a highly nonlinear model of the reactor on a network of workstations is used in the final step of testing prior tomore » 
The KnowledgeBased Technology Applications Center (KBTAC) seminar series. Volume 4, Introduction to neural networks and fuzzy logic: Final report
Neural Networks are adaptive systems that allow users to model complex systems, classify patterns, filter data or control processes with little or no apriori knowledge. Neural networks represent a branch of artificial intelligence technology. Fuzzy logic is a generalization of formalized mathematical logic that allows representation of uncertainty by providing a smooth transition from true to false, instead of a step change. It allows for a proposition to be both true and false, to different degrees at the same time. This allows representation of approximate reasoning concepts that occur frequently in everyday experience, such as ``somewhat true,`` or ``not verymore » 
Modeling of quasistatic magnetic hysteresis with feedforward neural networks
A modeling technique for rateindependent (quasistatic) scalar magnetic hysteresis is presented, using neural networks. Based on the theory of dynamic systems and the wipingout and congruency properties of the classical scalar Preisach hysteresis model, the choice of a feedforward neural network model is motivated. The neural network input parameters at each time step are the corresponding magnetic field strength and memory state, thereby assuring accurate prediction of the change of magnetic induction. For rateindependent hysteresis, the current memory state can be determined by the last extreme magnetic field strength and induction values, kept in memory. The choice of a networkmore »