Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Data Sensor Fusion In Digital Twin Technology For Enhanced Capabilities In A Home Environment

Benjamin Momoh, Salisu Yahaya

TL;DR

This work demonstrates that sensor fusion can substantially improve activity recognition for home-oriented digital twins by combining accelerometer, gyroscope, and magnetometer data from a Wit Motion sensor. Through a systematic comparison of feature-level fusion, decision-level fusion, and Kalman filter fusion across RF, SVM, and GB classifiers, the study shows that feature-level fusion with Random Forest achieves the highest accuracy (~98%), while Kalman-based fusion offers smoother temporal estimates. The results highlight magnetometer data as particularly informative and establish multisensor fusion as a robust strategy, especially in real-world settings where single sensors may underperform. The findings have practical implications for reliable home monitoring and smart-environment applications, and point to future work on additional sensors, deep learning fusion, and real-time deployment in digital twins.

Abstract

This paper investigates the integration of data sensor fusion in digital twin technology to bolster home environment capabilities, particularly in the context of challenges brought on by the coronavirus pandemic and its economic effects. The study underscores the crucial role of digital transformation in not just adapting to, but also mitigating disruptions during the fourth industrial revolution. Using the Wit Motion sensor, data was collected for activities such as walking, working, sitting, and lying, with sensors measuring accelerometers, gyroscopes, and magnetometers. The research integrates Cyber-physical systems, IoT, AI, and robotics to fortify digital twin capabilities. The paper compares sensor fusion methods, including feature-level fusion, decision-level fusion, and Kalman filter fusion, alongside machine learning models like SVM, GBoost, and Random Forest to assess model effectiveness. Results show that sensor fusion significantly improves the accuracy and reliability of these models, as it compensates for individual sensor weaknesses, particularly with magnetometers. Despite higher accuracy in ideal conditions, integrating data from multiple sensors ensures more consistent and reliable results in real-world settings, thereby establishing a robust system that can be confidently applied in practical scenarios.

Data Sensor Fusion In Digital Twin Technology For Enhanced Capabilities In A Home Environment

TL;DR

This work demonstrates that sensor fusion can substantially improve activity recognition for home-oriented digital twins by combining accelerometer, gyroscope, and magnetometer data from a Wit Motion sensor. Through a systematic comparison of feature-level fusion, decision-level fusion, and Kalman filter fusion across RF, SVM, and GB classifiers, the study shows that feature-level fusion with Random Forest achieves the highest accuracy (~98%), while Kalman-based fusion offers smoother temporal estimates. The results highlight magnetometer data as particularly informative and establish multisensor fusion as a robust strategy, especially in real-world settings where single sensors may underperform. The findings have practical implications for reliable home monitoring and smart-environment applications, and point to future work on additional sensors, deep learning fusion, and real-time deployment in digital twins.

Abstract

This paper investigates the integration of data sensor fusion in digital twin technology to bolster home environment capabilities, particularly in the context of challenges brought on by the coronavirus pandemic and its economic effects. The study underscores the crucial role of digital transformation in not just adapting to, but also mitigating disruptions during the fourth industrial revolution. Using the Wit Motion sensor, data was collected for activities such as walking, working, sitting, and lying, with sensors measuring accelerometers, gyroscopes, and magnetometers. The research integrates Cyber-physical systems, IoT, AI, and robotics to fortify digital twin capabilities. The paper compares sensor fusion methods, including feature-level fusion, decision-level fusion, and Kalman filter fusion, alongside machine learning models like SVM, GBoost, and Random Forest to assess model effectiveness. Results show that sensor fusion significantly improves the accuracy and reliability of these models, as it compensates for individual sensor weaknesses, particularly with magnetometers. Despite higher accuracy in ideal conditions, integrating data from multiple sensors ensures more consistent and reliable results in real-world settings, thereby establishing a robust system that can be confidently applied in practical scenarios.

Paper Structure

This paper contains 25 sections, 19 figures, 12 tables.

Table of Contents

  1. Introduction
  2. Literature Review
  3. Digital Twin Technologies
  4. Data Fusion
  5. Methods And Techniques of Data Fusion
  6. Relation Between Input Data Sources
  7. JDL Data Fusion Classification
  8. Classification Based On The Type Of Architecture
  9. Data Fusion Challenges
  10. Fusion Quality Assessment
  11. Approach And Methodology
  12. Data Collection
  13. Data Structure
  14. Individual Sensor Models
  15. Implementaion
  16. ...and 10 more sections

Figures (19)

  • Figure 1: JDL Architecture
  • Figure 2: Types of Data Fusion Architectures
  • Figure 3: Timestamp of dataset from the three different sensors (accelerometer, gyroscope and magnetometer)
  • Figure 4: Histogram for each sensor data collected
  • Figure 5: Correlation matrix
  • ...and 14 more figures