Home
  • English
  • ÄŒeÅ¡tina
  • Deutsch
  • Español
  • Français
  • Gàidhlig
  • LatvieÅ¡u
  • Magyar
  • Nederlands
  • Português
  • Português do Brasil
  • Suomi
  • Log In
    New user? Click here to register. Have you forgotten your password?
Home
  • Browse Our Collections
  • Publications
  • Researchers
  • Research Data
  • Institutions
  • Statistics
    • English
    • ÄŒeÅ¡tina
    • Deutsch
    • Español
    • Français
    • Gàidhlig
    • LatvieÅ¡u
    • Magyar
    • Nederlands
    • Português
    • Português do Brasil
    • Suomi
    • Log In
      New user? Click here to register. Have you forgotten your password?
  1. Home
  2. Resources
  3. UniMAP Index Publications
  4. Publications 2021
  5. Intelligent fall detection system using traditional and non-traditional machine learning algorithm based on MQTT
 
Options

Intelligent fall detection system using traditional and non-traditional machine learning algorithm based on MQTT

Journal
AIP Conference Proceedings
ISSN
0094243X
Date Issued
2021-07-21
Author(s)
Cheong C.Y.
Lim C.C.
Chong Y.F.
Vikneswaran Vijean
Universiti Malaysia Perlis
Ahmad Faizal Salleh
Universiti Malaysia Perlis
Affandi M.
DOI
10.1063/5.0052750
Handle (URI)
https://hdl.handle.net/20.500.14170/5306
Abstract
The population of elderly people exposed to the risk of fall increases each year as reported by World Health Organization (WHO). Fall detection system presented normally is high cost, large size and not efficient. Wearable-based sensor fall detection system developed in this project which were small size, portable and low-cost. The concept of Message Queuing Telemetry Transport (MQTT) applied in this fall detection system to ease the process of data transmission from motion sensor to Raspberry Pi for classification via Wi-Fi. A small size and lightweight microcontroller (Wemos D1 mini ESP 8266) integrated with MPU6050 motion sensor to sense and publish the motion data. Raspberry Pi 3 Model B applied to carry out classification of the motion data. Machine learning algorithms used for classification in comparison were k-Nearest Neighbors (k-NN) and Long Short-Term Memory (LSTM) of Recurrent Neural Network (RNN). LSTM achieved better result at 97% than k-NN at 94%. Smartphone used to publish the notification via an application known as Blynk.
File(s)
Research repository notification.pdf (4.4 MB)
Downloads
17
Last Month
3
Acquisition Date
Jan 12, 2026
View Details
Views
1
Acquisition Date
Jan 12, 2026
View Details
google-scholar
  • About Us
  • Contact Us
  • Policies