A Python Package For System Identification Using NARMAX Models

A python multi-variate time series prediction library working with sklearn

Deep Learning using Neural Network Toolbox + Finance Portfolio Selection with MorningStar

The project uses a nonlinear autoregressive exogenous (NARX), model to make time-series prediction on data obtained from drive cycling testing on buses

Level controle in the Facotry IO. Code written in LAD, SCL in TIA Portal

Air-quality forecasting in Belgium using Deep Neural Networks, Neuroevolution and distributed Island T​ranspeciation

Dual-Stage Attention-Based Recurrent Neural Net for Time Series Prediction

Nonlinear autoregressive exogenous model library. NarxSim ported to U++.

Performed a nonlinear model identification using both the FROE method with polynomial NARX models and feedforward neural networks.

Final project for the Time Series course on two different time series, one on the evolution of the BTC price (series with trend) and the other on the Indian weather (series with trend and seasonality).

Neural Network Lecture Projects.

Code, figures, animations for a NARX-EFE based agent.

Explore the double-descent phenomena in the context of system identification. Companion code to the paper (https://arxiv.org/abs/2012.06341):

This repository contains code for energy forecasting using multilayer neural networks (MLPs) with autoregressive (AR) and nonlinear autoregressive exogenous (NARX) approaches. The goal is to predict the next-day electricity consumption for a specific case study, utilizing real dataset from a real-life organization.

An active inference agent based on expected free energy minimization with a nonlinear autoregressive exogenous model.

GUI for System Identification using NARX and NARMAX models