Generating Stochastic Processes Through Convolutional Neural Networks
| Autor: | Rodrigo de Losso da Silveira Bueno, Fernando Fernandes, Pedro Delano Cavalcanti, Alemayehu S. Admasu |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Test data generation Computer science 020209 energy Energy Engineering and Power Technology 02 engineering and technology Machine learning computer.software_genre Convolutional neural network Fault detection and isolation symbols.namesake 020901 industrial engineering & automation 0202 electrical engineering electronic engineering information engineering Reinforcement learning Autoregressive integrated moving average Electrical and Electronic Engineering business.industry Computer Science Applications Generative model Autoregressive model Control and Systems Engineering symbols Artificial intelligence business computer Gibbs sampling |
| Zdroj: | Journal of Control, Automation and Electrical Systems. 31:294-303 |
| ISSN: | 2195-3899 2195-3880 |
| DOI: | 10.1007/s40313-020-00567-y |
| Popis: | The present work establishes the use of convolutional neural networks as a generative model for stochastic processes that are widely present in industrial automation and system modelling such as fault detection, computer vision and sensor data analysis. This enables researchers from a broad range of fields—as in medical imaging, robotics and control engineering—to develop a general tool for artificial data generation and simulation without the need to identify or assume a specific system structure or estimate its parameters. We demonstrate the approach as a generative model on top of data retrieved from a wide set of classic, simplest to the most complex, deterministic and stochastic data generation processes of technological importance—from damped oscillators to autoregressive conditional heteroskedastic and jump-diffusion models. Also, a nonparametric estimation and forecast was carried out for the traditional benchmark “Fisher River” time-series dataset, yielding the superior mean absolute prediction error results compared to a standard ARIMA model. This approach can have potential applications as an alternative to simulation tools such as Gibbs sampling and Monte Carlo-based methods, in the enhancement of the understanding of generative adversarial networks (GANs) and in data simulation for training Reinforcement Learning algorithms. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink