Recurrent neural networks have been established as a general tool for tting sequential input=output data. On the other hand, Fourier analysis is a useful tool for time series analysis. In this paper, these two elds are linked together to form a new interpretation to recurrent networks for time series prediction. Fourier analysis of a time series is applied to construct a complex-valued recurren...

This paper suggests the application of advanced methods from Fourier Analysis in order to describe ultra-high frequent data in limit order books. Using Lomb’s normalized periodogram and Scargle’s Discrete Fourier Transforms to take account of the irregularity in spacing, the power spectra of different time series processes can be easily estimated, without immense computational effort caused by ...

This manuscript is the result of research conducted towards the production of meta-data to be used as inputs to neural networks. It is essentially a preliminary attempt towards the use of an evolutionary approach to interpret the significance which time series data pose on the behavior of mountainous water supplies, proposing a model which could be effectively used in the estimation of the aver...

based on three-dimensional theory of elasticity, static analysis of functionally graded carbon nanotube reinforced composite (fg-cntrc) cylindrical panel subjected to mechanical uniformed load with simply supported boundary conditions is carried out. in the process, stress and displacement fields are expanded according to the fourier series along the axial and circumferential coordinates. from ...

Presented paper deals with comparison of various methods for time-frequency representation of a signal with time-varying behavior. We choose methods such as wavelet analysis, multiple window method using Slepian sequences, time-frequency varying autoregressive process estimation and time-frequency Fourier transform representation (periodogram). We apply these methods first on the simple simulat...