Text

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2207003764	T78605	T786052022	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T786052022

Publisher

Inderalaya : Jurusan Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2022

Collation

xiii, 45 hlm.; ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

005.707

Content Type

-

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Data dalam sistem komputer
Jurusan Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment