Article Per Year (5 Year)
p-Index From 2019 - 2024
0.23
P-Index
This Author published in this journals
All Journal Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Mohammad Hafidh Wildan Maulana
Fakultas Ilmu Komputer, Universitas Brawijaya
Computer Science & IT Control & Systems Engineering Education Electrical & Electronics Engineering Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Sistem Deteksi Stres berdasarkan Detak Jantung dan Kelenjar Keringat menggunakan Metode K-Nearest Neighbours Mohammad Hafidh Wildan Maulana; Edita Rosana Widasari
Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer Vol 7 No 3 (2023): Maret 2023
Publisher : Fakultas Ilmu Komputer (FILKOM), Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Stress is a state of pressure on a person due to something that happens not as expected or unwanted. Stress can risk disrupting a person's health, both physical aspect and mental aspect, and reduce their quality of life as well if not treated immediately. A person's heart rate and GSR (Galvanic Skin Response) can be used as features to detect stress. Both features are influenced by sympathetic nerves that regulate a person's response to emotions so that they can be used to identify a person's stress level. The K-Nearest Neighbor (k-NN) method is used as a classification method because it has advantages in accuracy using data with few parameters and a large amount of data. The tool uses Arduino Uno as a microcontroller, MAX30102 sensor to measure heart rate, Grove GSR sensor to measure GSR, and LCD to display the output. Testing was carried out using 10 subjects as test data, and using 70 training data. The results of system testing in this study are based on the accuracy of the tool's readings compared to the results of the subject's questionnaire. The accuracy produced by this stress detection system is 70%. For the results of testing the k-NN method on this system has an accuracy of 64.29% for 70 training data. While the results of testing the computation time of the system get an average computation time of 13.3 ms.
Co-Authors Edita Rosana Widasari