Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

  1. Home
  3. Research Domains
  5. Information And Computing Sciences
  7. Artificial Intelligence
  9. Intelligent Robotics
  11. Efficient Deep Learning-based Device-free Indoor Localization Using Passive Infrared Sensors

Efficient Deep Learning-Based Device-Free Indoor Localization Using Passive Infrared Sensors

Sira Yongchareon1, Jian Yu1, Jing Ma1

  • 1School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland 1010, New Zealand.

Sensors (Basel, Switzerland)
|March 17, 2025

Related Experiment Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

6.7K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a new deep learning method for device-free indoor localization using Passive Infrared (PIR) sensors. The novel approach accurately estimates the locations of multiple individuals, enhancing safety and energy management applications.

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Artificial Intelligence

Background:

  • Device-free indoor localization is essential for applications like healthcare, safety, and energy management.
  • Passive Infrared (PIR) sensors offer a cost-effective, low-power, and privacy-preserving solution for human localization.
  • Existing multi-person localization methods struggle with signal quality, ambiguity, and interference from complex movements.

Purpose of the Study:

  • To propose a novel deep learning method for accurate multi-person indoor localization using PIR sensors.
  • To address the limitations of current methods in handling complex human movements and signal interference.

Main Methods:

  • A deep Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM) architecture is employed.
  • Channel separation and template-matching techniques are utilized for signal processing.
Keywords:
PIRsdeep learning-based localizationdevice-free indoor localizationmulti-person localization

Related Experiment Videos

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

2.5K
Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults
04:13

Using a Real-Time Locating System to Measure Walking Activity Associated with Wandering Behaviors Among Institutionalized Older Adults

Published on: February 8, 2019

6.7K
Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.6K
  • Ensemble models with a mean bagging technique enhance localization accuracy.

    • Main Results:

    • The proposed method successfully estimates the simultaneous locations of two participants.
    • Achieved a mean distance error of 0.55 meters for localization.
    • 80% of distance errors were within 0.8 meters, demonstrating high accuracy.

    Conclusions:

    • The novel deep learning approach significantly improves multi-person localization accuracy using PIR sensors.
    • This method offers a robust solution for device-free indoor localization in complex environments.
    • The findings have implications for enhancing smart environments in healthcare, safety, and energy management.