Robustness of LSTM neural networks for multi-step forecasting of chaotic time series
M Sangiorgio, F Dercole - Chaos, Solitons & Fractals, 2020 - Elsevier
Recurrent neurons (and in particular LSTM cells) demonstrated to be efficient when used as
basic blocks to build sequence to sequence architectures, which represent the state-of-the …
basic blocks to build sequence to sequence architectures, which represent the state-of-the …
[PDF][PDF] A comprehensive review of optimization techniques applied for placement and sizing of custom power devices in distribution networks
M Farhoodnea, A Mohamed, H Shareef… - Przegląd …, 2012 - academia.edu
Custom power devices (CPD) are used to protect conventional and sensitive loads against
power quality disturbances such as voltage sag/swell and harmonic distortion in power …
power quality disturbances such as voltage sag/swell and harmonic distortion in power …
Assessment of leakage degree of underground heating primary pipe network based on chaotic simulated annealing neural network
SB Jiao, L Fan, PY Wu, L Qiao… - 2017 Chinese …, 2017 - ieeexplore.ieee.org
The research shows that primary pipe network leak will cause the fluctuations of temperature
and conductance around the leak point. There is a complex non-linear relationship between …
and conductance around the leak point. There is a complex non-linear relationship between …
EEG Signal Recognition Based on Wavelet Transform and ACCLN Network
X Qin, J Deng, M Wang, Y Zhang, P Wang - 2016 - preprints.org
The electroencephalogram (EEG) is a record of brain activity. Brain Computer Interface (BCI)
technology formed by the EEG signal has become one of the hotspots at present. How to …
technology formed by the EEG signal has become one of the hotspots at present. How to …
Modeling and predicting chaotic circuit data
Analyzing chaotic observations generated from some unknown nonlinear dynamics
presents significant challenges for modeling the process and predicting future evolutions …
presents significant challenges for modeling the process and predicting future evolutions …
Power cable fault recognition based on an annealed chaotic competitive learning network
X Qin, M Wang, JS Lin, X Li - Algorithms, 2014 - mdpi.com
In electric power systems, power cable operation under normal conditions is very important.
Various cable faults will happen in practical applications. Recognizing the cable faults …
Various cable faults will happen in practical applications. Recognizing the cable faults …
Introduction to Chaotic Dynamics' Forecasting
Chaotic dynamics are the paradigm of complex and unpredictable evolution due to their built-
in feature of amplifying arbitrarily small perturbations. The forecasting of these dynamics has …
in feature of amplifying arbitrarily small perturbations. The forecasting of these dynamics has …
Self-organized critical CMOS circuits and methods for computation and information processing
KL Wang, HY Chang - US Patent 10,147,045, 2018 - Google Patents
A circuit that makes use of chaos or self-organized criticality to generate a matrix of bits for
computation and information processing. The example embodiment utilizes CMOS circuitry …
computation and information processing. The example embodiment utilizes CMOS circuitry …
Predictive Analytics for Maintaining Power System Stability in Smart Energy Communities
AM Pirbazari - 2021 - uis.brage.unit.no
This dissertation is submitted in partial fulfillment of the requirement for the degree of
Philosophiae Doctor (PhD) at the University of Stavanger, Norway. The study was carried …
Philosophiae Doctor (PhD) at the University of Stavanger, Norway. The study was carried …
[PDF][PDF] Permutation, Linear Combination and Complexity of Short Time Series
Z Rajilic - academia.edu
A new manner of estimating complexity, suitable for short time series, is proposed. Final part
of a time series we represent as linear combination of previous subseries. Permutations …
of a time series we represent as linear combination of previous subseries. Permutations …