PREDICTING THE ARRIVAL OF EMERGENT PATIENT BY AFFINITY SET

Yuh-Wen Chen, Moussa Larbani, Chao-Wen Chen

2008

Abstract

Predicting the time series of emergent patient arrival is valuable in monitoring/tracking the daily patient flow because these efforts keep doctors alarmed in advance. A prediction problem of the time series generated by actual arrival of emergent patient is considered here. Traditionally, such a problem is analyzed by moving average method, regression method, exponential smoothing method or some existed evolutionary methods. However, we propose a new affinity model to accomplish this goal. Our data of time series is actually recorded from hour to hour (hourly data) for three days: the data of the first two days are used to generate/train prediction model; after that, the data of the final/third day is used to test our prediction results. Two types of model: affinity model and neural network model are used for comparing their performances. Interestingly, the affinity model performs better prediction results. This hints there could be a special pattern within the time series generated by actual arrival of emergent patient.

Paper Citation

in Harvard Style

Chen Y., Larbani M. and Chen C. (2008). PREDICTING THE ARRIVAL OF EMERGENT PATIENT BY AFFINITY SET . In Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: CIAS, (ICEIS 2008) ISBN 978-989-8111-39-5, pages 273-277. DOI: 10.5220/0001723402730277

in Bibtex Style

@conference{cias08,
author={Yuh-Wen Chen and Moussa Larbani and Chao-Wen Chen},
title={PREDICTING THE ARRIVAL OF EMERGENT PATIENT BY AFFINITY SET},
booktitle={Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: CIAS, (ICEIS 2008)},
year={2008},
pages={273-277},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001723402730277},
isbn={978-989-8111-39-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the Tenth International Conference on Enterprise Information Systems - Volume 4: CIAS, (ICEIS 2008)
TI - PREDICTING THE ARRIVAL OF EMERGENT PATIENT BY AFFINITY SET
SN - 978-989-8111-39-5
AU - Chen Y.
AU - Larbani M.
AU - Chen C.
PY - 2008
SP - 273
EP - 277
DO - 10.5220/0001723402730277