Advertisement

Utilization Factor Calculation Method Based on Adam Algorithm and Neural Network

  • Lu Weizhong
  • Tang YeEmail author
  • Chen Cheng
  • Huang Hongmei
Conference paper
  • 34 Downloads
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 1060)

Abstract

A neural network model consisting of a fixed network and a flexible network and optimized by Adam algorithm is designed to calculate the utilization factor when the floor reflectance ratio is 0.2 and the correction factor when it is not 0.2. Comparing with traditional illumination calculation methods, the proposed method can reduce the computational time and complexity, while reducing the calculation error and improving accuracy, resulting in a higher applicability in practice.

Keywords

Adam algorithm Neural network Illumination calculation Utilization factor 

Notes

Acknowledgements

This work was supported by National Natural Science Foundation (no. 61672371), Natural Science Research Project of Jiangsu Provincial Department of Education (no. 08KJD510007), and Foundation of Key Laboratory (no. SZS201609) in Science and Technology Development Project of Suzhou.

References

  1. 1.
    Adiga CS, Aithal RS, Shanbhag RS. Energy conservation in lighting systems using neuro-expert system. In: National conference on advanced lighting concepts towards energy conservation; 2001.Google Scholar
  2. 2.
    Mangeni G, Tan RHG, Tan TH, et al. Photovoltaic module cell temperature measurements using linear interpolation technique. In: Instrumentation and measurement technology conference. IEEE; 2017. p. 1–6.Google Scholar
  3. 3.
    Shanbhag RS, Chandrashekara AS, Radhakrishna AS. Application of neural networks in lighting system design: an evaluation of the utilization factor. J Polym Sci A Poly Chem. 2004;8(2).Google Scholar
  4. 4.
    Jiang L, Fang L. Application of RBF neural network based on MATLAB in lighting calculation. J Illum Eng. 2014;3.Google Scholar
  5. 5.
    Jiao L, Yang S, Liu F. Neural network for 70 years: review and prospect. J Chin J Comput. 2016;39:08.Google Scholar
  6. 6.
    Zhang Y, Wang HW, Wang YB, et al. A novel optimization algorithm for BP neural network based on RS-MEA. In: International conference on image, vision and computing. IEEE; 2017.Google Scholar
  7. 7.
    Xu ZJ, Hu YG, Liu XK. The diagnosis of aero-engine’s state based on rough set and improved BP neural network. In: Prognostics and system health management conference. IEEE; 2017. p. 1–5.Google Scholar
  8. 8.
    Zhu F, Ding L. Research of character recognition based on BP neural network. In: International conference on network and information systems for computers. IEEE; 2017.Google Scholar
  9. 9.
    Xie X. Electric lighting technology. China Electric Power Press, M.; 2004.Google Scholar
  10. 10.
    Koshel RJ. Simplex optimization method for illumination design. J Opt Lett. 2005;30:6.CrossRefGoogle Scholar
  11. 11.
    Kingma DP, Ba J. Adam: a method for stochastic optimization. J Comput Sci. 2014.Google Scholar
  12. 12.
    Gao Y, Zhang R. Research on house price forecasting based on genetic algorithm and BP neural network. J Comput Eng. 2014;40:4.Google Scholar
  13. 13.
    Chu H, Lai H. An improved BP neural network algorithm and its application. J Comput Simul. 2007;24:4.Google Scholar
  14. 14.
    Zhen X, Lei J, Xia W. A BP neural network algorithm based on quickly determining the number of hidden layer neurons. J Comput Sci. 2012;39:b06.Google Scholar
  15. 15.
    Marreiros AC, Daunizeau J, Kiebel SJ, et al. Population dynamics: variance and the sigmoid activation function. J Neuroimage. 2008;42:1.CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2020

Authors and Affiliations

  • Lu Weizhong
    • 1
    • 2
    • 3
  • Tang Ye
    • 1
    • 2
    • 3
    Email author
  • Chen Cheng
    • 1
    • 2
    • 3
  • Huang Hongmei
    • 1
    • 2
    • 3
  1. 1.The School of Electronic and Information Engineering, Suzhou University of Science and TechnologySuzhouChina
  2. 2.Jiangsu Key Laboratory of Intelligent Building Energy EfficiencySuzhouChina
  3. 3.Virtual Reality Key Laboratory of Intelligent Interaction and Application Technology of SuzhouSuzhouChina

Personalised recommendations