Imputing Missing Observations with Time Sliced Synthetic Minority Oversampling Technique

01/14/2022
by   Andrew Baumgartner, et al.
0

We present a simple yet novel time series imputation technique with the goal of constructing an irregular time series that is uniform across every sample in a data set. Specifically, we fix a grid defined by the midpoints of non-overlapping bins (dubbed "slices") of observation times and ensure that each sample has values for all of the features at that given time. This allows one to both impute fully missing observations to allow uniform time series classification across the entire data and, in special cases, to impute individually missing features. To do so, we slightly generalize the well-known class imbalance algorithm SMOTE <cit.> to allow component wise nearest neighbor interpolation that preserves correlations when there are no missing features. We visualize the method in the simplified setting of 2-dimensional uncoupled harmonic oscillators. Next, we use tSMOTE to train an Encoder/Decoder long-short term memory (LSTM) model with Logistic Regression for predicting and classifying distinct trajectories of different 2D oscillators. After illustrating the the utility of tSMOTE in this context, we use the same architecture to train a clinical model for COVID-19 disease severity on an imputed data set. Our experiments show an improvement over standard mean and median imputation techniques by allowing a wider class of patient trajectories to be recognized by the model, as well as improvement over aggregated classification models.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/08/2023

Enhancing Missing Data Imputation of Non-stationary Signals with Harmonic Decomposition

Dealing with time series with missing values, including those afflicted ...
research
10/13/2015

Comparison of different Methods for Univariate Time Series Imputation in R

Missing values in datasets are a well-known problem and there are quite ...
research
10/25/2021

Time series signal recovery methods: comparative study

Signal data often contains missing values. Effective replacement (imputa...
research
08/15/2018

Development and Evaluation of Recurrent Neural Network based Models for Hourly Traffic Volume and AADT Prediction

The prediction of high-resolution hourly traffic volumes of a given road...
research
11/15/2019

Imputing missing values with unsupervised random trees

This work proposes a non-iterative strategy for missing value imputation...
research
10/05/2022

Tripletformer for Probabilistic Interpolation of Asynchronous Time Series

Asynchronous time series are often observed in several applications such...
research
03/28/2019

Correlating Paleoclimate Time Series: Sources of Uncertainty and Potential Pitfalls

Comparing paleoclimate time series is complicated by a variety of typica...

Please sign up or login with your details

Forgot password? Click here to reset