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

IR Frequency Region: Fingerprint Region01:03

IR Frequency Region: Fingerprint Region

1.4K
IR spectra are divided into two main regions: the diagnostic region and the fingerprint region. The diagnostic region of the spectrum lies above 1500 cm−1. The absorptions resulting from single-bond vibrations of the N–H, C–H, and O–H stretch at higher wavenumbers and appear on the left side of the spectrum. The stretching absorptions of the C≡C and C≡N occur between 2100–2300 cm−1. In contrast, those arising from stretching absorptions of the...
1.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Research on Isomorphic Task Transfer Algorithm Based on Knowledge Distillation in Multi-Agent Collaborative Systems.

Sensors (Basel, Switzerland)·2024
Same author

Lightweight Knowledge Distillation-Based Transfer Learning Framework for Rolling Bearing Fault Diagnosis.

Sensors (Basel, Switzerland)·2024
Same author

Reuse Distance-Aided Resource Selection Mechanisms for NR-V2X Sidelink Communication.

Sensors (Basel, Switzerland)·2024
Same author

ROS-Based Autonomous Navigation Robot Platform with Stepping Motor.

Sensors (Basel, Switzerland)·2023
Same author

Adjacent Vehicle Number-Triggered Adaptive Transmission for V2V Communications.

Sensors (Basel, Switzerland)·2018

Related Experiment Video

Updated: Oct 30, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K

Clustering-Based Noise Elimination Scheme for Data Pre-Processing for Deep Learning Classifier in Fingerprint Indoor

Shuzhi Liu1, Rashmi Sharan Sinha1, Seung-Hoon Hwang1

  • 1Division of Electronics and Electrical Engineering, Dongguk University-Seoul, Seoul 04620, Korea.

Sensors (Basel, Switzerland)
|July 2, 2021
PubMed
Summary

This study introduces a clustering-based noise elimination scheme (CNES) to improve Wi-Fi indoor positioning accuracy. CNES effectively removes noise from Received Signal Strength Indicator (RSSI) datasets, enhancing location fingerprinting success rates.

Keywords:
CNNRSSIclusteringfingerprint-based indoor positioning

More Related Videos

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.5K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Related Experiment Videos

Last Updated: Oct 30, 2025

Design and Analysis for Fall Detection System Simplification
08:05

Design and Analysis for Fall Detection System Simplification

Published on: April 6, 2020

10.9K
Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles
11:54

Microfluidic Platform with Multiplexed Electronic Detection for Spatial Tracking of Particles

Published on: March 13, 2017

9.5K
DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning
04:17

DNA Virus Detection System Based on RPA-CRISPR/Cas12a-SPM and Deep Learning

Published on: May 10, 2024

1.1K

Area of Science:

  • Computer Science
  • Electrical Engineering
  • Signal Processing

Background:

  • Wi-Fi-based indoor positioning systems are popular due to their low cost and simple setup.
  • Received Signal Strength Indicator (RSSI) from Wi-Fi signals suffer from poor stability, hindering accurate positioning with traditional datasets and deep learning.
  • Existing methods struggle with noise in RSSI data, limiting the precision of indoor localization.

Purpose of the Study:

  • To develop and evaluate a novel clustering-based noise elimination scheme (CNES) for Received Signal Strength Indicator (RSSI) datasets.
  • To enhance the accuracy and reliability of Wi-Fi-based indoor positioning systems by mitigating signal instability.
  • To improve the performance of deep learning classifiers in indoor localization tasks by preprocessing RSSI data.

Main Methods:

  • Implemented a clustering-based noise elimination scheme (CNES) utilizing density-based spatial clustering of applications with noise (DBSCAN).
  • Preprocessed RSSI-based datasets by applying CNES to remove noise samples, focusing on region-based clustering.
  • Evaluated CNES performance in a dynamic environment using deep learning classifiers and compared lab simulation results with real-time testing.

Main Results:

  • CNES significantly increased the success probability of fingerprint location by eliminating noise from RSSI datasets.
  • Lab simulations showed improvements in average positioning accuracy: 17.78% (zero-meter error), 7.24% (two-meter error), and 4.75% (four-meter error).
  • Real-time testing confirmed CNES enhanced average positioning accuracy by 22.43% (zero-meter error), 9.15% (two-meter error), and 5.21% (four-meter error).

Conclusions:

  • The proposed CNES is an effective method for preprocessing RSSI data to improve Wi-Fi indoor positioning accuracy.
  • Noise elimination through clustering enhances the reliability of Received Signal Strength Indicator (RSSI) data for localization.
  • CNES demonstrates a practical and effective solution for overcoming signal instability challenges in Wi-Fi positioning systems.