AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications

This paper presents the implementation of an AIoT-based Human Activity Recognition (HAR) framework designed for multipurpose applications. The framework integrates sensor data from wearable IoT devices, which is then processed by AI algorithms to classify and predict human activities in real-time....

Full description

Saved in:
Bibliographic Details
Main Authors: Nanik Triwahyuni, Eni Wardihani, Aminuddin Rizal, Samuel Beta, Ricky Sambora, Rindang Oktaviani
Format: Article
Language:English
Published: Universitas Kristen Satya Wacana 2025-06-01
Series:Techne
Subjects:
Online Access:https://ojs.jurnaltechne.org/index.php/techne/article/view/514
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850220268684836864
author Nanik Triwahyuni
Eni Wardihani
Aminuddin Rizal
Samuel Beta
Ricky Sambora
Rindang Oktaviani
author_facet Nanik Triwahyuni
Eni Wardihani
Aminuddin Rizal
Samuel Beta
Ricky Sambora
Rindang Oktaviani
author_sort Nanik Triwahyuni
collection DOAJ
description This paper presents the implementation of an AIoT-based Human Activity Recognition (HAR) framework designed for multipurpose applications. The framework integrates sensor data from wearable IoT devices, which is then processed by AI algorithms to classify and predict human activities in real-time. It utilizes machine learning models, particularly machine learning techniques, to analyze complex activity. Our framework uses all open-source IDEs, which is able to replicate and modify. For this paper we give examples of how to use our framework as gamification of a workout practice. The Idea is to recognize user activity including (bicep curl, shoulder press, and front rise) using accelerometer data, and then send recognized activity to our developed online game (pop-balloon). M5StickC Plus used as the hardware which already equipped with IMU sensor and power management. Furthermore, it has small form factor fit for wearable application. Before real-time performance was taken, we evaluated 5 different machine learning model and choose which one is more optimized. The five models include Naïve Bayes, Support Vector Machine (SVM), AdaBoost, ZeroR, and Random Forest. Accuracy given for offline analysis were 97.68%, 98.97%, 41.62%, 25%, 100% respectively to the previous model.  In the final, for real-time performance we choose SVM model which most optimized even though the accuracy reduced to 89.67% for this task.
format Article
id doaj-art-39a11a3dae864064be250bf20e8a140b
institution OA Journals
issn 1412-8292
2615-7772
language English
publishDate 2025-06-01
publisher Universitas Kristen Satya Wacana
record_format Article
series Techne
spelling doaj-art-39a11a3dae864064be250bf20e8a140b2025-08-20T02:07:08ZengUniversitas Kristen Satya WacanaTechne1412-82922615-77722025-06-0124110.31358/techne.v24i1.514AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose ApplicationsNanik Triwahyuni0Eni Wardihani1Aminuddin Rizal2Samuel Beta3Ricky Sambora4Rindang Oktaviani5Politeknik Negeri SemarangPoliteknik Negeri SemarangPoliteknik Negeri SemarangPoliteknik Negeri SemarangPoliteknik Negeri SemarangPoliteknik Negeri Semarang This paper presents the implementation of an AIoT-based Human Activity Recognition (HAR) framework designed for multipurpose applications. The framework integrates sensor data from wearable IoT devices, which is then processed by AI algorithms to classify and predict human activities in real-time. It utilizes machine learning models, particularly machine learning techniques, to analyze complex activity. Our framework uses all open-source IDEs, which is able to replicate and modify. For this paper we give examples of how to use our framework as gamification of a workout practice. The Idea is to recognize user activity including (bicep curl, shoulder press, and front rise) using accelerometer data, and then send recognized activity to our developed online game (pop-balloon). M5StickC Plus used as the hardware which already equipped with IMU sensor and power management. Furthermore, it has small form factor fit for wearable application. Before real-time performance was taken, we evaluated 5 different machine learning model and choose which one is more optimized. The five models include Naïve Bayes, Support Vector Machine (SVM), AdaBoost, ZeroR, and Random Forest. Accuracy given for offline analysis were 97.68%, 98.97%, 41.62%, 25%, 100% respectively to the previous model.  In the final, for real-time performance we choose SVM model which most optimized even though the accuracy reduced to 89.67% for this task. https://ojs.jurnaltechne.org/index.php/techne/article/view/514artificial intelligence internet of things (AIoT)embedded devicehuman activity recognition (HAR)signal processing
spellingShingle Nanik Triwahyuni
Eni Wardihani
Aminuddin Rizal
Samuel Beta
Ricky Sambora
Rindang Oktaviani
AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
Techne
artificial intelligence internet of things (AIoT)
embedded device
human activity recognition (HAR)
signal processing
title AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
title_full AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
title_fullStr AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
title_full_unstemmed AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
title_short AIoT-Driven Human Activity Recognition for Versatile Framework on Multipurpose Applications
title_sort aiot driven human activity recognition for versatile framework on multipurpose applications
topic artificial intelligence internet of things (AIoT)
embedded device
human activity recognition (HAR)
signal processing
url https://ojs.jurnaltechne.org/index.php/techne/article/view/514
work_keys_str_mv AT naniktriwahyuni aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications
AT eniwardihani aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications
AT aminuddinrizal aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications
AT samuelbeta aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications
AT rickysambora aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications
AT rindangoktaviani aiotdrivenhumanactivityrecognitionforversatileframeworkonmultipurposeapplications