Evaluation of Source-wise Missing Data Techniques for the Prediction of Parkinson’s Disease Using Smartphones
- Resource Type
- Conference
- Authors
- Prince, John; Andreotti, Fernando; De Vos, Maarten
- Source
- ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2019 - 2019 IEEE International Conference on. :3927-3930 May, 2019
- Subject
- Bioengineering
Communication, Networking and Broadcast Technologies
Signal Processing and Analysis
Feature extraction
Parkinson's disease
Data models
Training
Logistics
Smart phones
Source-wise missing data
Parkinson’s disease
sensor fusion
source-wise imputation
multi-modal autoencoding
- Language
- ISSN
- 2379-190X
Multi-source datasets often present the challenge of source-wise missing data which can render large portions of the dataset inaccessible. The applicability of traditional missing data techniques on multi-source datasets is poorly understood. We present the first quantitative evaluation of the state-of-the-art missing data techniques as applied to a freely available dataset of smart-phone recordings from Parkinsonian patients wherein source-wise missing data is simulated. The classification accuracy and imputation error of five missing data techniques, including a multi-modal autoencoder and multi-source ensemble learning, are compared at varying levels of missingness. These results demonstrate the relative applicability of each technique under different conditions and subsequently highlight the challenges of source-wise missing on remotely collected datasets. Specifically, multi-source ensemble learning proves to be a highly successful alternative to the traditional imputation techniques when a majority of observations possess missing data.