CBRi: A Case Based Reasoning-Inspired Approach for Univariate Time Series Imputation

Flores, Anibal; Tito, Hugo; Silva, Carlos

doi:10.1109/la-cci47412.2019.9036761

Cited by 10 publications

(21 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The analysis performed in Fig. 1 with the application of the LANN algorithm and the improvement detected on GRU predictions motivate the application of another imputation algorithm known as Case Base Reasoning Imputation (CBRi) "in press" [6]. (IJACSA) International Journal of Advanced Computer Science and Applications, Vol.…”

Section: Introductionmentioning

confidence: 91%

“…The results achieved in this work show that, in the first case, LANN in [1] allowed to considerably improve the results provided by Gated Recurrent Unit (GRU). In the second case, it is experimented with CBRi, taking as a reference the results shown "in press" [6], where CBRi manages to overcome LANN results, however, in this work GRU+CBRi does not surpass GRU+LANN.…”

Section: Introductionmentioning

confidence: 92%

“…CBRi "in press" [6] is an imputation technique for univariate time series inspired by Case Based Reasoning that allows to calculate a NA value from a base of cases that stores historical values of a time series. Fig.…”

Section: Case Based Reasoning Imputation (Cbri)mentioning

confidence: 99%

“…CBRi algorithm is used to impute NA values according adaptation made in [24] for over 2 NA values. Base of cases corresponds to 9 years (from 2007 to 2015) and it was implemented for CBRi "in press" [6].…”

Section: Applying Lann/cbrimentioning

confidence: 99%

“…As it can be seen in [1] the insertion of different NA values in the results produced by LSTM with different gap-sizes and the subsequent recalculation of the NA values produced an improvement in the precision of the LSTM results. Thus, in this work, it is experimented with the results produced by GRU, but instead of just using the Local Average of Nearest Neighbors (LANN) [5] imputation technique, we also experiment with another technique known as Case Based Reasoning Imputation (CBRi) "in press" [6].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Improving Gated Recurrent Unit Predictions with Univariate Time Series Imputation Techniques

Flores¹,

Tito²,

Centty³

2019

IJACSA

Self Cite

View full text Add to dashboard Cite

The work presented in this paper has its main objective to improve the quality of the predictions made with the recurrent neural network known as Gated Recurrent Unit (GRU). For this, instead of making different adjustments to the architecture of the neural network in question, univariate time series imputation techniques such as Local Average of Nearest Neighbors (LANN) and Case Based Reasoning Imputation (CBRi) are used. It is experimented with different gap-sizes, from 1 to 11 consecutive NAs, resulting in the best gap-size of six consecutive NA values for LANN and for CBRi the gap-size of two NA values. The results show that both imputation techniques allow improving prediction quality of Gated Recurrent Unit, being LANN better than CBRi, thus the results of the best configurations of LANN and CBRi allowed to surpass the techniques with which they were compared.

show abstract

Section: Introductionmentioning

confidence: 91%

Section: Introductionmentioning

confidence: 92%

Section: Case Based Reasoning Imputation (Cbri)mentioning

confidence: 99%

Section: Applying Lann/cbrimentioning

confidence: 99%