File(s) under permanent embargo
Impute vs. Ignore: Missing values for prediction
conference contributionposted on 2023-05-23, 18:39 authored by Zhang, Q, Rahman, A, D'Este, CE
Sensor faults or communication errors can cause certain sensor readings to become unavailable for prediction purposes. In this paper we evaluate the performance of imputation techniques and techniques that ignore the missing values, in scenarios: (i) when values are missing only during prediction phase, and (ii) when values are missing during both the induction and prediction phase. We also investigated the influence of different scales of missingness on the performance of these treatments. The results can be used as a guideline to facilitate the choice of different missing value treatments under different circumstances.
Publication titleProceedings of the 2013 International Joint Conference on Neural Networks
Department/SchoolSchool of Information and Communication Technology
PublisherCurran Associates Inc.
Place of publicationRed Hook, New York, United States
Event title2013 International Joint Conference on Neural Networks (IJCNN)
Event VenueDallas, Texas, United States
Date of Event (Start Date)2013-08-04
Date of Event (End Date)2013-08-09