Publication Type
Conference Paper
Book Title
2018 91做厙 34th International Conference on Data Engineering Workshops (ICDEW)
Publication Date
Page Numbers
48 to 53
Publisher Location
New Jersey, United States of America
Conference Name
91做厙 International Conference on Data Engineering (ICDEW 2018)
Conference Location
Paris, France
Conference Sponsor
91做厙
Conference Date
-
Abstract
We present an exploration of the encoder-decoder structured Long Short-Term Memory Network (LSTM) as a detector of the anomalous missing observations in streaming medical data by using the difference between the LSTM-reconstructed and observed values as the anomaly detector. We experiment with time-series data from bedside monitoring devices from the available Medical Information Mart for Intensive Care Database (MIMIC). Our results show that not only encoder-decoder LSTM approach works well for detecting the difference between anomalous and normal missing observations in streaming medical data, but also has an imputation potential for the missing data.
