Automated detection of commissioning changes in connected lighting systems

Shuai Li, Ashish Pandharipande, Beatrice Masini, David Caicedo

Research output: Contribution to journalArticleAcademicpeer-review

1 Citation (Scopus)

Abstract

We consider the problem of detecting commissioning changes in connected lighting systems. Commissioning changes can occur due to repositioning of luminaires/sensors or space renovation. This results in incorrect commissioning mapping of devices to areas, thereby impacting analysis and interpretation of data from such devices. We propose an automated method to detect changes in commissioning mapping using occupancy sensor data. We use similarity features across occupancy sensors and employ a random forest binary classifier to detect changes. The proposed method is evaluated using data from a simulated office environment and an experimental testbed, and is shown to have high accuracy.

LanguageEnglish
Article number8436019
Pages898-905
Number of pages8
JournalIEEE Internet of Things Journal
Volume6
Issue number1
DOIs
StatePublished - 1 Feb 2019

Fingerprint

Lighting
Sensors
Lighting fixtures
Testbeds
Classifiers

Keywords

  • Commissioning
  • connected lighting systems
  • occupancy sensors
  • random forest classifier

Cite this

Li, Shuai ; Pandharipande, Ashish ; Masini, Beatrice ; Caicedo, David. / Automated detection of commissioning changes in connected lighting systems. In: IEEE Internet of Things Journal. 2019 ; Vol. 6, No. 1. pp. 898-905
@article{7651bf398a2e4a74b4e71539fdcb81d5,
title = "Automated detection of commissioning changes in connected lighting systems",
abstract = "We consider the problem of detecting commissioning changes in connected lighting systems. Commissioning changes can occur due to repositioning of luminaires/sensors or space renovation. This results in incorrect commissioning mapping of devices to areas, thereby impacting analysis and interpretation of data from such devices. We propose an automated method to detect changes in commissioning mapping using occupancy sensor data. We use similarity features across occupancy sensors and employ a random forest binary classifier to detect changes. The proposed method is evaluated using data from a simulated office environment and an experimental testbed, and is shown to have high accuracy.",
keywords = "Commissioning, connected lighting systems, occupancy sensors, random forest classifier",
author = "Shuai Li and Ashish Pandharipande and Beatrice Masini and David Caicedo",
year = "2019",
month = "2",
day = "1",
doi = "10.1109/JIOT.2018.2865315",
language = "English",
volume = "6",
pages = "898--905",
journal = "IEEE Internet of Things Journal",
issn = "2327-4662",
publisher = "Institute of Electrical and Electronics Engineers",
number = "1",

}

Automated detection of commissioning changes in connected lighting systems. / Li, Shuai; Pandharipande, Ashish; Masini, Beatrice; Caicedo, David.

In: IEEE Internet of Things Journal, Vol. 6, No. 1, 8436019, 01.02.2019, p. 898-905.

Research output: Contribution to journalArticleAcademicpeer-review

TY - JOUR

T1 - Automated detection of commissioning changes in connected lighting systems

AU - Li,Shuai

AU - Pandharipande,Ashish

AU - Masini,Beatrice

AU - Caicedo,David

PY - 2019/2/1

Y1 - 2019/2/1

N2 - We consider the problem of detecting commissioning changes in connected lighting systems. Commissioning changes can occur due to repositioning of luminaires/sensors or space renovation. This results in incorrect commissioning mapping of devices to areas, thereby impacting analysis and interpretation of data from such devices. We propose an automated method to detect changes in commissioning mapping using occupancy sensor data. We use similarity features across occupancy sensors and employ a random forest binary classifier to detect changes. The proposed method is evaluated using data from a simulated office environment and an experimental testbed, and is shown to have high accuracy.

AB - We consider the problem of detecting commissioning changes in connected lighting systems. Commissioning changes can occur due to repositioning of luminaires/sensors or space renovation. This results in incorrect commissioning mapping of devices to areas, thereby impacting analysis and interpretation of data from such devices. We propose an automated method to detect changes in commissioning mapping using occupancy sensor data. We use similarity features across occupancy sensors and employ a random forest binary classifier to detect changes. The proposed method is evaluated using data from a simulated office environment and an experimental testbed, and is shown to have high accuracy.

KW - Commissioning

KW - connected lighting systems

KW - occupancy sensors

KW - random forest classifier

UR - http://www.scopus.com/inward/record.url?scp=85051640789&partnerID=8YFLogxK

U2 - 10.1109/JIOT.2018.2865315

DO - 10.1109/JIOT.2018.2865315

M3 - Article

VL - 6

SP - 898

EP - 905

JO - IEEE Internet of Things Journal

T2 - IEEE Internet of Things Journal

JF - IEEE Internet of Things Journal

SN - 2327-4662

IS - 1

M1 - 8436019

ER -