TELKOMNIKA Telecommunication Computing Electronics and Control
ALZO: an outdoor Alzheimer's patient tracking system using internet of things
Dublin Core
Title
TELKOMNIKA Telecommunication Computing Electronics and Control
ALZO: an outdoor Alzheimer's patient tracking system using internet of things
ALZO: an outdoor Alzheimer's patient tracking system using internet of things
Subject
Alzheimer
Fall detection
Internet of things
Outdoor tracking system
Wearable device
Fall detection
Internet of things
Outdoor tracking system
Wearable device
Description
Alzheimer's patients have an abnormal brain that affects some functionalities such as memory and motoric function. Some patients experience disorientation, such as losing their way back home, and impaired lower body motoric function, leading to stumbling. To overcome these problems, we propose a wearable device called Alzo (Alzheimer locator) for tracking Alzheimer patients during outdoor activities. Alzo can detect the patient's location and is also equipped with a fall detection algorithm. The sensor produces an accelerometer and quaternion value, which are used for calculating alpha (represents activity acceleration) and theta (represents body orientation). The location and the patient's fall condition could be monitored using a mobile-based application. The experiments were conducted by operating the Alzo system to detect the patient's location and fall condition. The results showed that Alzo worked for about 3 hours and sent location data 1-5 times if lost or fall detected. Furthermore, thresholds for the fall detection algorithm were 235 m/s2
(lower-alpha), 8,108 m/s2 (higher-alpha), and 70βΈ°(theta). These thresholds were determined based on the experiment which includes standing up, walking, jumping, sitting down, cycling, Logging, bowing, and squatting. From the experiment, the fall detection algorithm achieved 93.33% of accuracy.
(lower-alpha), 8,108 m/s2 (higher-alpha), and 70βΈ°(theta). These thresholds were determined based on the experiment which includes standing up, walking, jumping, sitting down, cycling, Logging, bowing, and squatting. From the experiment, the fall detection algorithm achieved 93.33% of accuracy.
Creator
Sugiarto Wibowo, Indar Sugiarto
Source
http://telkomnika.uad.ac.id
Date
Sep 22, 2023
Contributor
peri irawan
Format
pdf
Language
english
Type
text
Files
Collection
Citation
Sugiarto Wibowo, Indar Sugiarto, “TELKOMNIKA Telecommunication Computing Electronics and Control
ALZO: an outdoor Alzheimer's patient tracking system using internet of things,” Repository Horizon University Indonesia, accessed February 5, 2025, https://repository.horizon.ac.id/items/show/4645.
ALZO: an outdoor Alzheimer's patient tracking system using internet of things,” Repository Horizon University Indonesia, accessed February 5, 2025, https://repository.horizon.ac.id/items/show/4645.