MULTIVARIATE TIME SERIES FORECASTING TANDA VITAL PASIEN UNIT PERAWATAN INTENSIF MENGGUNAKAN DEEP LEARNING

JULIAN, FERNANDO and Tutuko, Bambang and Firdaus, Firdaus (2023) MULTIVARIATE TIME SERIES FORECASTING TANDA VITAL PASIEN UNIT PERAWATAN INTENSIF MENGGUNAKAN DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924087.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011381924087_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
Preview	Text RAMA_56201_09011381924087_0012016003_0221017801_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB) | Preview
	Text RAMA_56201_09011381924087_0012016003_0221017801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (368kB) | Request a copy
	Text RAMA_56201_09011381924087_0012016003_0221017801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (288kB) | Request a copy
	Text RAMA_56201_09011381924087_0012016003_0221017801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381924087_0012016003_0221017801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (11kB) | Request a copy
	Text RAMA_56201_09011381924087_0012016003_0221017801_07_lamp.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (241kB) | Request a copy
	Text RAMA_56201_09011381924087_0012016003_0221017801_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (83kB) | Request a copy

Abstract

Time series forecasting (TSF) is the task of predicting future values of a particular time sequence. It used in various fields including forecast vital signs data. Vital signs data that are include five parameters; heart rate, blood pressure, oxygen saturation, respiratory rate, and body temperature. Abnormal vital signs help medical practitioners about potential health problems. This research develops a model for forecasting vital signs data in the future. The proposed forecast model is developed by using long-short term memory. The data used to build the model is a vital sign dataset taken from the MIMIC-III database. Missing values are filled in using autoencoder techniques. The proposed model is compared with the Bidirectional Long-Short Term Memory model. The input data is developed by creating a window with one value from a predetermined forecast range. The model was successfully developed with an RMSE value of 0.025615 for 60 minutes of data and 30 minutes of prediction range.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Tanda Vital, Long-short term memory, Deep Learning, MIMIC Database, Multivariate
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Users 17893 not found.
Date Deposited:	21 Feb 2023 02:13
Last Modified:	21 Feb 2023 02:14
URI:	http://repository.unsri.ac.id/id/eprint/88458

Actions (login required)

View Item