data-driven-modeling

Learn stochastic differential equations (Langevin dynamics: drift/force and diffusion) from time series and trajectory data. Python + JAX.

This repository contains the code and dataset for the paper "Data-Driven Modeling of Three-Phase IGBT Two-Level Inverter for Electrical Drives using ANNs". The project employs MATLAB to develop and train Artificial Neural Networks (ANNs) to model a three-phase IGBT two-level inverter for electrical drives.

IC-SHM2022-project3 by Mr. Shuo Hao, Mr. Gao-Feng Jiang and Dr. Hong-Wei Li.

The Dig4Bio worskhop series

This repository contains the codes for framework for equation discovery by combining Neural Networks with Characteristic Curves (NN-CC), Symmetry Constraints, and Post-Symbolic Regression (Post-SR). It also incorporates implementations of SINDy and pySR within the CC-based formalism.

This repository contains Jupyter notebooks from my learning journey with Physics-Informed Neural Networks (PINNs). These are not complete projects but serve as educational resources to explore core and intermediate concepts in applying neural networks to solve partial differential equations (PDEs).

Multi-language implementation of real-time fluid temperature predictors for embedded systems in gas water heaters. Includes datasets, models, and system diagrams.

Data-driven framework for Dynamic Mode Decomposition (DMD) and Koopman-based analysis of dynamical systems, with applications to noisy and low-resolution data.

D-FENSE project deals with Dengue Virus (DENV) epidemics in Brazil, enabling predictive modeling and data visualization to support decision-making in public health.

CLiDENGO26-Chikungunya is a forecasting model for Chikungunya dynamics through a mechanistic, stochastic climate-modulated β-logistic growth model for weekly chikungunya cases at the state (UF) level.

A data-driven analysis applying Dynamic Mode Decomposition (DMD) to model complex dynamical systems for financial price prediction

Reinforsment learning, dara-driven modeling, genetic algorithms

Data-driven model discovery of dynamic maximum entropy latent space variables

Simulation-based study of cinema ticket and food queues using FlexSim. Models multiple service-point configurations to identify bottlenecks and evaluate queue optimization strategies, applying data-driven modelling, experiment design, validation and statistical analysis.