Using Deep Learning Methods to Monitor Non-Observable States in a Building
Permanent lenke
https://hdl.handle.net/10037/21194Dato
2020-02-06Type
Conference objectKonferansebidrag
Sammendrag
This paper presents results from ongoing research
with a goal to use a combination of time series from
non-intrusive ambient sensors and deep recurrent
neural networks to predict room usage at a university campus. Training data was created by collecting measurements from ambient sensors measuring
room CO2, humidity, temperature, light, motion
and sound, while the ground-truth counts was created manually by human observers. Results include
analyses of relationships between different sensor
data sequences and recommendations for a prototype predictive model using deep recurrent neural
networks.
Er en del av
Tangrand, K.M. (2023). Some new Contributions to Neural Networks and Wavelets with Applications. (Doctoral thesis). https://hdl.handle.net/10037/28699.Forlag
SeptentrioSitering
Tangrand, Bremdal. Using Deep Learning Methods to Monitor Non-Observable States in a Building. Proceedings of the Northern Lights Deep Learning Workshop. 2020Metadata
Vis full innførsel
Copyright 2020 The Author(s)