SANNI

This repository is related to the SANNI (Snippet and Artificial Neural Network-basedImputation) or the recovery of missing values in multivariate time series coming online. SANNI leverages behavioral patterns (called snippets) that are subsequences representing an actor’s typical activities, which are reflected by the time series. SANNI is authored by Alexey Yurtin (iurtinaa@susu.ru) and Mikhail Zymbler (mzym@susu.ru), South Ural State University, Chelyabinsk, Russia.

Acknowledgement

This work was financially supported by the Russian Science Foundation (grant no. 23-21-00465). The research is carried out using the supercomputer resources of South Ural State University (Chelyabinsk, Russia)

Citation

@article{SANNIYurtinZymbler24,
  title     = {SANNI: Online Imputation of Missing Values in Multivariate Time Series Based on Deep Learning and Behavioral Patterns},
  author    = {Yurtin, A A},
  journal   = {Lobachevskii Journal of Mathematics},
  volume    = {45},
  number    = {11},
  pages     = {5948-5966},
  year      = {2024},
  doi       = {10.1134/S1995080224606854},
  pages     = {5948--5966},
  year      = {2024},
}