Deep learning for building occupancy estimation using environmental sensors

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Standard

Deep learning for building occupancy estimation using environmental sensors. / Chen, Zhenghua; Jiang, Chaoyang; Masood, Mustafa K.; Soh, Yeng Chai; Wu, Min; Li, Xiaoli.

Deep learning: algorithms and applications. ed. / Witold Pedrycz; Shyi-Ming Chen. 2020. p. 335-357 (Studies in Computational Intelligence; Vol. 865).

Research output: Chapter in Book/Report/Conference proceedingChapterScientificpeer-review

Harvard

Chen, Z, Jiang, C, Masood, MK, Soh, YC, Wu, M & Li, X 2020, Deep learning for building occupancy estimation using environmental sensors. in W Pedrycz & S-M Chen (eds), Deep learning: algorithms and applications. Studies in Computational Intelligence, vol. 865, pp. 335-357. https://doi.org/10.1007/978-3-030-31760-7_11

APA

Chen, Z., Jiang, C., Masood, M. K., Soh, Y. C., Wu, M., & Li, X. (2020). Deep learning for building occupancy estimation using environmental sensors. In W. Pedrycz, & S-M. Chen (Eds.), Deep learning: algorithms and applications (pp. 335-357). (Studies in Computational Intelligence; Vol. 865). https://doi.org/10.1007/978-3-030-31760-7_11

Vancouver

Chen Z, Jiang C, Masood MK, Soh YC, Wu M, Li X. Deep learning for building occupancy estimation using environmental sensors. In Pedrycz W, Chen S-M, editors, Deep learning: algorithms and applications. 2020. p. 335-357. (Studies in Computational Intelligence). https://doi.org/10.1007/978-3-030-31760-7_11

Author

Chen, Zhenghua ; Jiang, Chaoyang ; Masood, Mustafa K. ; Soh, Yeng Chai ; Wu, Min ; Li, Xiaoli. / Deep learning for building occupancy estimation using environmental sensors. Deep learning: algorithms and applications. editor / Witold Pedrycz ; Shyi-Ming Chen. 2020. pp. 335-357 (Studies in Computational Intelligence).

Bibtex - Download

@inbook{eeac8875d24545d890920b467cfb6fee,
title = "Deep learning for building occupancy estimation using environmental sensors",
abstract = "Building Energy efficiency has gained more and more attention in last few years. Occupancy level is a key factor for achieving building energy efficiency, which directly affects energy-related control systems in buildings. Among varieties of sensors for occupancy estimation, environmental sensors have unique properties of non-intrusion and low-cost. In general, occupancy estimation using environmental sensors contains feature engineering and learning. The traditional feature extraction requires to manually extract significant features without any guidelines. This handcrafted feature extraction process requires strong domain knowledge and will inevitably miss useful and implicit features. To solve these problems, this chapter presents a Convolutional Deep Bi-directional Long Short-Term Memory (CDBLSTM) method that consists of a convolutional neural network with stacked architecture to automatically learn local sequential features from raw environmental sensor data from scratch. Then, the LSTM network is used to encode temporal dependencies of these local features, and the Bi-directional structure is employed to consider the past and future contexts simultaneously during feature learning. We conduct real experiments to compare the CDBLSTM and some state-of-the-art approaches for building occupancy estimation. The results indicate that the CDBLSTM approach outperforms all the state-of-the-arts.",
keywords = "Building occupancy estimation, CDBLSTM, Deep learning, Environmental sensors",
author = "Zhenghua Chen and Chaoyang Jiang and Masood, {Mustafa K.} and Soh, {Yeng Chai} and Min Wu and Xiaoli Li",
year = "2020",
month = "10",
day = "24",
doi = "10.1007/978-3-030-31760-7_11",
language = "English",
isbn = "978-3-030-31759-1",
series = "Studies in Computational Intelligence",
pages = "335--357",
editor = "Witold Pedrycz and Shyi-Ming Chen",
booktitle = "Deep learning: algorithms and applications",

}

RIS - Download

TY - CHAP

T1 - Deep learning for building occupancy estimation using environmental sensors

AU - Chen, Zhenghua

AU - Jiang, Chaoyang

AU - Masood, Mustafa K.

AU - Soh, Yeng Chai

AU - Wu, Min

AU - Li, Xiaoli

PY - 2020/10/24

Y1 - 2020/10/24

N2 - Building Energy efficiency has gained more and more attention in last few years. Occupancy level is a key factor for achieving building energy efficiency, which directly affects energy-related control systems in buildings. Among varieties of sensors for occupancy estimation, environmental sensors have unique properties of non-intrusion and low-cost. In general, occupancy estimation using environmental sensors contains feature engineering and learning. The traditional feature extraction requires to manually extract significant features without any guidelines. This handcrafted feature extraction process requires strong domain knowledge and will inevitably miss useful and implicit features. To solve these problems, this chapter presents a Convolutional Deep Bi-directional Long Short-Term Memory (CDBLSTM) method that consists of a convolutional neural network with stacked architecture to automatically learn local sequential features from raw environmental sensor data from scratch. Then, the LSTM network is used to encode temporal dependencies of these local features, and the Bi-directional structure is employed to consider the past and future contexts simultaneously during feature learning. We conduct real experiments to compare the CDBLSTM and some state-of-the-art approaches for building occupancy estimation. The results indicate that the CDBLSTM approach outperforms all the state-of-the-arts.

AB - Building Energy efficiency has gained more and more attention in last few years. Occupancy level is a key factor for achieving building energy efficiency, which directly affects energy-related control systems in buildings. Among varieties of sensors for occupancy estimation, environmental sensors have unique properties of non-intrusion and low-cost. In general, occupancy estimation using environmental sensors contains feature engineering and learning. The traditional feature extraction requires to manually extract significant features without any guidelines. This handcrafted feature extraction process requires strong domain knowledge and will inevitably miss useful and implicit features. To solve these problems, this chapter presents a Convolutional Deep Bi-directional Long Short-Term Memory (CDBLSTM) method that consists of a convolutional neural network with stacked architecture to automatically learn local sequential features from raw environmental sensor data from scratch. Then, the LSTM network is used to encode temporal dependencies of these local features, and the Bi-directional structure is employed to consider the past and future contexts simultaneously during feature learning. We conduct real experiments to compare the CDBLSTM and some state-of-the-art approaches for building occupancy estimation. The results indicate that the CDBLSTM approach outperforms all the state-of-the-arts.

KW - Building occupancy estimation

KW - CDBLSTM

KW - Deep learning

KW - Environmental sensors

UR - http://www.scopus.com/inward/record.url?scp=85074717771&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-31760-7_11

DO - 10.1007/978-3-030-31760-7_11

M3 - Chapter

SN - 978-3-030-31759-1

T3 - Studies in Computational Intelligence

SP - 335

EP - 357

BT - Deep learning: algorithms and applications

A2 - Pedrycz, Witold

A2 - Chen, Shyi-Ming

ER -

ID: 38745879