A novel lambertian-RBFNN for office light modeling

Wa Si, Xun Pan, Harutoshi Ogai, Katsumi Hirai

Research output: Contribution to journalArticle

Abstract

In lighting control systems, accurate data of artificial light (lighting coefficients) are essential for the illumination control accuracy and energy saving efficiency. This research proposes a novel Lambertian-Radial Basis Function Neural Network (L-RBFNN) to realize modeling of both lighting coefficients and the illumination environment for an of-fice. By adding a Lambertian neuron to represent the rough theoretical illuminance distribution of the lamp and modifying RBF neurons to regulate the distribution shape, L-RBFNN successfully solves the instability problem of conventional RBFNN and achieves higher modeling accuracy. Simulations of both single-light modeling and multiple-light modeling are made and compared with other methods such as Lambertian function, cubic spline interpolation and conventional RBFNN. The results prove that: 1) L-RBFNN is a successful modeling method for artificial light with imperceptible modeling error; 2) Compared with other existing methods, LRBFNN can provide better performance with lower modeling error; 3) The number of training sensors can be reduced to be the same with the number of lamps, thus making the modeling method easier to apply in real-world lighting systems.

Original languageEnglish
Pages (from-to)1742-1752
Number of pages11
JournalIEICE Transactions on Information and Systems
VolumeE99D
Issue number7
DOIs
Publication statusPublished - 2016 Jul 1

Fingerprint

Lighting
Neural networks
Electric lamps
Neurons
Splines
Interpolation
Energy conservation
Control systems
Sensors

Keywords

  • Illumination modeling
  • Lambertian function
  • RBFNN

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Software
  • Artificial Intelligence
  • Hardware and Architecture
  • Computer Vision and Pattern Recognition

Cite this

A novel lambertian-RBFNN for office light modeling. / Si, Wa; Pan, Xun; Ogai, Harutoshi; Hirai, Katsumi.

In: IEICE Transactions on Information and Systems, Vol. E99D, No. 7, 01.07.2016, p. 1742-1752.

Research output: Contribution to journalArticle

@article{6c16af3d94d5493ba8560070bf129fce,
title = "A novel lambertian-RBFNN for office light modeling",
abstract = "In lighting control systems, accurate data of artificial light (lighting coefficients) are essential for the illumination control accuracy and energy saving efficiency. This research proposes a novel Lambertian-Radial Basis Function Neural Network (L-RBFNN) to realize modeling of both lighting coefficients and the illumination environment for an of-fice. By adding a Lambertian neuron to represent the rough theoretical illuminance distribution of the lamp and modifying RBF neurons to regulate the distribution shape, L-RBFNN successfully solves the instability problem of conventional RBFNN and achieves higher modeling accuracy. Simulations of both single-light modeling and multiple-light modeling are made and compared with other methods such as Lambertian function, cubic spline interpolation and conventional RBFNN. The results prove that: 1) L-RBFNN is a successful modeling method for artificial light with imperceptible modeling error; 2) Compared with other existing methods, LRBFNN can provide better performance with lower modeling error; 3) The number of training sensors can be reduced to be the same with the number of lamps, thus making the modeling method easier to apply in real-world lighting systems.",
keywords = "Illumination modeling, Lambertian function, RBFNN",
author = "Wa Si and Xun Pan and Harutoshi Ogai and Katsumi Hirai",
year = "2016",
month = "7",
day = "1",
doi = "10.1587/transinf.2015EDP7411",
language = "English",
volume = "E99D",
pages = "1742--1752",
journal = "IEICE Transactions on Information and Systems",
issn = "0916-8532",
publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
number = "7",

}

TY - JOUR

T1 - A novel lambertian-RBFNN for office light modeling

AU - Si, Wa

AU - Pan, Xun

AU - Ogai, Harutoshi

AU - Hirai, Katsumi

PY - 2016/7/1

Y1 - 2016/7/1

N2 - In lighting control systems, accurate data of artificial light (lighting coefficients) are essential for the illumination control accuracy and energy saving efficiency. This research proposes a novel Lambertian-Radial Basis Function Neural Network (L-RBFNN) to realize modeling of both lighting coefficients and the illumination environment for an of-fice. By adding a Lambertian neuron to represent the rough theoretical illuminance distribution of the lamp and modifying RBF neurons to regulate the distribution shape, L-RBFNN successfully solves the instability problem of conventional RBFNN and achieves higher modeling accuracy. Simulations of both single-light modeling and multiple-light modeling are made and compared with other methods such as Lambertian function, cubic spline interpolation and conventional RBFNN. The results prove that: 1) L-RBFNN is a successful modeling method for artificial light with imperceptible modeling error; 2) Compared with other existing methods, LRBFNN can provide better performance with lower modeling error; 3) The number of training sensors can be reduced to be the same with the number of lamps, thus making the modeling method easier to apply in real-world lighting systems.

AB - In lighting control systems, accurate data of artificial light (lighting coefficients) are essential for the illumination control accuracy and energy saving efficiency. This research proposes a novel Lambertian-Radial Basis Function Neural Network (L-RBFNN) to realize modeling of both lighting coefficients and the illumination environment for an of-fice. By adding a Lambertian neuron to represent the rough theoretical illuminance distribution of the lamp and modifying RBF neurons to regulate the distribution shape, L-RBFNN successfully solves the instability problem of conventional RBFNN and achieves higher modeling accuracy. Simulations of both single-light modeling and multiple-light modeling are made and compared with other methods such as Lambertian function, cubic spline interpolation and conventional RBFNN. The results prove that: 1) L-RBFNN is a successful modeling method for artificial light with imperceptible modeling error; 2) Compared with other existing methods, LRBFNN can provide better performance with lower modeling error; 3) The number of training sensors can be reduced to be the same with the number of lamps, thus making the modeling method easier to apply in real-world lighting systems.

KW - Illumination modeling

KW - Lambertian function

KW - RBFNN

UR - http://www.scopus.com/inward/record.url?scp=84976908644&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84976908644&partnerID=8YFLogxK

U2 - 10.1587/transinf.2015EDP7411

DO - 10.1587/transinf.2015EDP7411

M3 - Article

AN - SCOPUS:84976908644

VL - E99D

SP - 1742

EP - 1752

JO - IEICE Transactions on Information and Systems

JF - IEICE Transactions on Information and Systems

SN - 0916-8532

IS - 7

ER -