Deep learning for building occupancy estimation using environmental sensors

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussavertaisarvioitu

Tutkijat

Organisaatiot

  • Agency for Science, Technology and Research
  • Beijing Institute of Technology
  • Nanyang Technological University

Kuvaus

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.

Yksityiskohdat

AlkuperäiskieliEnglanti
OtsikkoDeep learning: algorithms and applications
ToimittajatWitold Pedrycz, Shyi-Ming Chen
TilaSähköinen julkaisu (e-pub) ennen painettua julkistusta - 24 lokakuuta 2020
OKM-julkaisutyyppiA3 Kirjan osa tai toinen tutkimuskirja

Julkaisusarja

NimiStudies in Computational Intelligence
Vuosikerta865
ISSN (painettu)1860-949X
ISSN (elektroninen)1860-9503

ID: 38745879