Extreme learning machine for predicting number of outpatient visitors.
In: AIP Conference Proceedings, Jg. 2720 (2023-05-18), Heft 1, S. 1-9
Konferenz
Zugriff:
As the population of Indonesia increases, it is estimated that the number of outpatient visits will also increase, including residents in Riau, especially in Mandau District. If the number of outpatient visitors for treatment can be predicted accurately, it will assist agencies in planning and making decisions for the future. The prediction method for historical data analysis, which helps determine future events. This study uses the Extreme Learning Machine (ELM) method to see the accuracy in predicting as measured by Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Since the ELM method is a learning-based process, the more train data, the smaller the error generated. This research produces the best model with a percentage of train data of 85% of the total data set. Meanwhile, the network structure consists of 12 nodes on the input layer and 17 nodes on the hidden layer and gives RMSE and MAPE of 1557.5 and 11.4%, respectively. [ABSTRACT FROM AUTHOR]
Titel: |
Extreme learning machine for predicting number of outpatient visitors.
|
---|---|
Autor/in / Beteiligte Person: | Utari, Dina Tri ; Putri, Aufa Qorina |
Zeitschrift: | AIP Conference Proceedings, Jg. 2720 (2023-05-18), Heft 1, S. 1-9 |
Quelle: | 2023, Vol. 2720 Issue 1, p1-9. 9p.; Jg. 2720 (2023-05-18) 1, S. 1-9 |
Veröffentlichung: | 2023 |
Medientyp: | Konferenz |
ISSN: | 0094-243X (print) |
DOI: | 10.1063/5.0136973 |
Schlagwort: |
|
Sonstiges: |
|