Visible light based occupancy inference using ensemble learning
As a key component of building management and security, occupancy inference through smart sensing has attracted a lot of research attention for nearly two decades. Recently, a cutting edge technique visible light sensing (VLS) that utilizes the LED luminaires as light sensors has shown its promising...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2018
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/87733 http://hdl.handle.net/10220/45484 |
| _version_ | 1824455210958848000 |
|---|---|
| author | Hao, Jie Yuan, Xiaoming Yang, Yanbing Wang, Ran Zhuang, Yi Luo, Jun |
| author2 | School of Computer Science and Engineering |
| author_facet | School of Computer Science and Engineering Hao, Jie Yuan, Xiaoming Yang, Yanbing Wang, Ran Zhuang, Yi Luo, Jun |
| author_sort | Hao, Jie |
| collection | NTU |
| description | As a key component of building management and security, occupancy inference through smart sensing has attracted a lot of research attention for nearly two decades. Recently, a cutting edge technique visible light sensing (VLS) that utilizes the LED luminaires as light sensors has shown its promising application potentials in occupancy inference as it piggybacks on pervasive lighting infrastructure without extra equipment deployment. Although existing inference algorithms based on the VLS data set can achieve high accuracy, the performance degrades when the occupants are moving. This paper focuses on the occupancy inference issue and presents an ensemble learning algorithm to improve the inference accuracy. We use heterogeneous learning algorithms to generate diverse learners. Consequently, we adopt forward sequential pruning to enhance the ensemble that pursues inference error minimization. We conduct extensive experiments based on the field data. The experiment results show that the proposed algorithm is able to improve inference accuracy, especially for highly dynamic occupancy data set. |
| first_indexed | 2025-02-19T03:34:36Z |
| format | Journal Article |
| id | ntu-10356/87733 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:34:36Z |
| publishDate | 2018 |
| record_format | dspace |
| spelling | ntu-10356/877332020-03-07T11:48:59Z Visible light based occupancy inference using ensemble learning Hao, Jie Yuan, Xiaoming Yang, Yanbing Wang, Ran Zhuang, Yi Luo, Jun School of Computer Science and Engineering Occupancy Inference Ensemble As a key component of building management and security, occupancy inference through smart sensing has attracted a lot of research attention for nearly two decades. Recently, a cutting edge technique visible light sensing (VLS) that utilizes the LED luminaires as light sensors has shown its promising application potentials in occupancy inference as it piggybacks on pervasive lighting infrastructure without extra equipment deployment. Although existing inference algorithms based on the VLS data set can achieve high accuracy, the performance degrades when the occupants are moving. This paper focuses on the occupancy inference issue and presents an ensemble learning algorithm to improve the inference accuracy. We use heterogeneous learning algorithms to generate diverse learners. Consequently, we adopt forward sequential pruning to enhance the ensemble that pursues inference error minimization. We conduct extensive experiments based on the field data. The experiment results show that the proposed algorithm is able to improve inference accuracy, especially for highly dynamic occupancy data set. Published version 2018-08-06T08:29:29Z 2019-12-06T16:48:16Z 2018-08-06T08:29:29Z 2019-12-06T16:48:16Z 2018 Journal Article Hao, J., Yuan, X., Yang, Y., Wang, R., Zhuang, Y., & Luo, J. (2018). Visible light based occupancy inference using ensemble learning. IEEE Access, 6, 16377-16385. https://hdl.handle.net/10356/87733 http://hdl.handle.net/10220/45484 10.1109/ACCESS.2018.2809612 en IEEE Access © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. 9 p. application/pdf |
| spellingShingle | Occupancy Inference Ensemble Hao, Jie Yuan, Xiaoming Yang, Yanbing Wang, Ran Zhuang, Yi Luo, Jun Visible light based occupancy inference using ensemble learning |
| title | Visible light based occupancy inference using ensemble learning |
| title_full | Visible light based occupancy inference using ensemble learning |
| title_fullStr | Visible light based occupancy inference using ensemble learning |
| title_full_unstemmed | Visible light based occupancy inference using ensemble learning |
| title_short | Visible light based occupancy inference using ensemble learning |
| title_sort | visible light based occupancy inference using ensemble learning |
| topic | Occupancy Inference Ensemble |
| url | https://hdl.handle.net/10356/87733 http://hdl.handle.net/10220/45484 |
| work_keys_str_mv | AT haojie visiblelightbasedoccupancyinferenceusingensemblelearning AT yuanxiaoming visiblelightbasedoccupancyinferenceusingensemblelearning AT yangyanbing visiblelightbasedoccupancyinferenceusingensemblelearning AT wangran visiblelightbasedoccupancyinferenceusingensemblelearning AT zhuangyi visiblelightbasedoccupancyinferenceusingensemblelearning AT luojun visiblelightbasedoccupancyinferenceusingensemblelearning |