No Imputation Needed: A Switch Approach to Irregularly Sampled Time Series
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914917058084864 |
|---|---|
| author | Agarwal, Rohit Sinha, Aman Vishwakarma, Ayan Coubez, Xavier Clausel, Marianne Constant, Mathieu Horsch, Alexander Prasad, Dilip K. |
| author_facet | Agarwal, Rohit Sinha, Aman Vishwakarma, Ayan Coubez, Xavier Clausel, Marianne Constant, Mathieu Horsch, Alexander Prasad, Dilip K. |
| contents | Modeling irregularly-sampled time series (ISTS) is challenging because of missing values. Most existing methods focus on handling ISTS by converting irregularly sampled data into regularly sampled data via imputation. These models assume an underlying missing mechanism, which may lead to unwanted bias and sub-optimal performance. We present SLAN (Switch LSTM Aggregate Network), which utilizes a group of LSTMs to model ISTS without imputation, eliminating the assumption of any underlying process. It dynamically adapts its architecture on the fly based on the measured sensors using switches. SLAN exploits the irregularity information to explicitly capture each sensor's local summary and maintains a global summary state throughout the observational period. We demonstrate the efficacy of SLAN on two public datasets, namely, MIMIC-III, and Physionet 2012. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_08698 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | No Imputation Needed: A Switch Approach to Irregularly Sampled Time Series Agarwal, Rohit Sinha, Aman Vishwakarma, Ayan Coubez, Xavier Clausel, Marianne Constant, Mathieu Horsch, Alexander Prasad, Dilip K. Artificial Intelligence Machine Learning Modeling irregularly-sampled time series (ISTS) is challenging because of missing values. Most existing methods focus on handling ISTS by converting irregularly sampled data into regularly sampled data via imputation. These models assume an underlying missing mechanism, which may lead to unwanted bias and sub-optimal performance. We present SLAN (Switch LSTM Aggregate Network), which utilizes a group of LSTMs to model ISTS without imputation, eliminating the assumption of any underlying process. It dynamically adapts its architecture on the fly based on the measured sensors using switches. SLAN exploits the irregularity information to explicitly capture each sensor's local summary and maintains a global summary state throughout the observational period. We demonstrate the efficacy of SLAN on two public datasets, namely, MIMIC-III, and Physionet 2012. |
| title | No Imputation Needed: A Switch Approach to Irregularly Sampled Time Series |
| topic | Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2309.08698 |