Predictive models on 1D signals in a small-data environment - Archive ouverte HAL Access content directly
Reports (Research Report) Year : 2021

Predictive models on 1D signals in a small-data environment


This report is concerned by one project done during the Semaine d'Études Mathématiques et Entreprises (SEME) at the Institut de Mathématiques de Bordeaux. The subject, proposed by the company, concerns the use of machine learning algorithms and data augmentation techniques, applied to small datasets composed of 1D signals measurements. The target variable is supposed to be continuous, i.e., a regression problem. By first reviewing the literature and existing methods on data augmentation, we propose two procedures to tackle this problem: one allows to create synthetic observations for a specific range of target values and it is based on a perturbation method in Fourier/Wavelet space; the other is based on neural networks and uses a particular version of the Variational Autoencoder known as LSTM-VAE. Our methods are applied to an open dataset, available at the UCI repository, and show encouraging results for a common class of machine learning algorithms.
Fichier principal
Vignette du fichier
Predictive_models_on_1D_signals_in_a_small_data_environment.pdf (525.79 Ko) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03211100 , version 1 (28-04-2021)


  • HAL Id : hal-03211100 , version 1


Fabio Coppini, Yiye Jiang, Sonia Tabti. Predictive models on 1D signals in a small-data environment. [Research Report] IMB - Institut de Mathématiques de Bordeaux. 2021. ⟨hal-03211100⟩
168 View
976 Download


Gmail Facebook Twitter LinkedIn More