PRAKIRAAN TANDA VITAL DARI DATA MULTIVARIATE TIME SERIES PASIEN UNIT PERAWATAN INTENSIF MENGGUNAKAN DEEP LEARNING

KRISTIANTO, DIMAS ADITYA and Firdaus, Firdaus and Sutarno, Sutarno (2022) PRAKIRAAN TANDA VITAL DARI DATA MULTIVARIATE TIME SERIES PASIEN UNIT PERAWATAN INTENSIF MENGGUNAKAN DEEP LEARNING. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011281823132.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011281823132_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
Preview	Text RAMA_56201_09011281823132_0221017801_0201117802_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (503kB) | Preview
	Text RAMA_56201_09011281823132_0221017801_0201117802_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (338kB) | Request a copy
	Text RAMA_56201_09011281823132_0221017801_0201117802_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (635kB) | Request a copy
	Text RAMA_56201_09011281823132_0221017801_0201117802_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (117kB) | Request a copy
	Text RAMA_56201_09011281823132_0221017801_0201117802_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7kB) | Request a copy
	Text RAMA_56201_09011281823132_0221017801_0201117802_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (83kB) | Request a copy
	Text RAMA_56201_09011281823132_0221017801_0201117802_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy

Abstract

The vital signs recorded by the device at the patient's bedside are values commonly used in the medical field. Proper and accurate monitoring of vital signs is very important to ensure that the patient's health condition improves or worsens in the hospital. There are five vital signs often used: heartrate, blood pressure, oxygen saturation, respiratory rate, and body temperature. The use of vital signs as an indication of an event has been introduced in the medical industry more than a century ago. Even so, there is still a lot of research being done to improve the quality of clinical performance. The method used in this research is the deep learning method. The deep learning methods used are Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (Bi-LSTM). In this study, the vital sign dataset used is a dataset taken from the MIMIC (Medical Information Mart for Intensive Care) database and then processed by making the data per window with one value from a predetermined forecast range. Each of these data, models will be built with various combinations of batch size and learning rate parameter settings so that they get good settings. The best model is the Bi-LSTM model with a batch size 16 parameter setting and a learning rate of 0.001 so that the RMSE value is 0.0171.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Tanda vital, Multivariate, Deep Learning, Long Short-Term Memory, MIMIC Database
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:	Dimas Aditya Kristianto
Date Deposited:	15 Sep 2022 02:09
Last Modified:	15 Sep 2022 02:09
URI:	http://repository.unsri.ac.id/id/eprint/78605

Actions (login required)

View Item