Wearable Device Pendeteksi Jatuh Berbasis Fitur Statistik Varian Menggunakan 3-Axis Accelerometer

Noviandy, Muhammad Rizal (2020) Wearable Device Pendeteksi Jatuh Berbasis Fitur Statistik Varian Menggunakan 3-Axis Accelerometer. Other thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 07211440000010-Undergraduate_Thesis.pdf] Text
07211440000010-Undergraduate_Thesis.pdf - Accepted Version

Download (8MB)

Abstract

Dalam melakukan aktivitas keseharian potensi terjadinya hal buruk seperti jatuh cukup besar khususnya yang mengalami keterbatasan fungsi gerak kaki. Pengawasan dari orang terdekat tentu tidak dapat dilakukan langsung selama 24 jam penuh. Sehingga dibutuhkan sebuah perangkat yang dapat mengenali kejadian jatuh pada pemakaianya. Perangkat ini dilengkapi dengan mikrokontroller sebagai pengendali utama dan akselerometer sebagai sensor jatuh. Sistem pada perangkat ini diharapkan dapat membedakan antara rutinitas biasa atau gerakan jatuh. Metode yang digunakan adalah menghitung varian dari percepatan tiga sumbu akselerometer kemudian menjumlahkannya. Hasil tersebut kemudian dibandingkan dengan nilai threshold yang telah dihitung dengan beberapa percobaan sebelumnya sebagai penentu gerakan jatuh. Dari 120 kali total gerakan jatuh yang diujikan, didapatkan rata-rata akurasi alat sebesar 84.14%.
=====================================================================================================================================
In carrying out daily activities, there is a great potential of the occurrence of bad things such as falling, especially for those who experience limited footwork. Direct supervision from the closest one certainly cannot be done for 24 hours. So it takes a device that can recognize falling events on its use. This device is equipped with a microcontroller as the main controller and accelerometer as the fall sensor. The system on this device is expected to be able to distinguish between ordinary routines or falling movements. The method used is variance calculation of three axes acceleration from the sensor. Then these sum values are compared with the threshold that has been calculated with several previous experiments as a determinant of falling movements. From 120 times the total falling movement tested, an average accuracy of 84.14% was obtained.

Item Type: Thesis (Other)
Additional Information: 3100020084593 RSKom 005.269 Nov w-1
Uncontrolled Keywords: Akselerometer, Mikrokontroller, Varian, Gerakan Jatuh, Accelerometer, Microcontroller, Variance, and Fa�lling Movement
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5102.9 Signal processing.
T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7871.674 Detectors. Sensors
Divisions: Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Computer Engineering > 90243-(S1) Undergraduate Thesis
Depositing User: Muhammad Rizal Noviandy
Date Deposited: 20 Dec 2022 08:53
Last Modified: 20 Dec 2022 08:53
URI: http://repository.its.ac.id/id/eprint/74657

Actions (login required)

View Item View Item