Exportar Publicação

Labiadh, M., Obrecht, C., Ferreira da Silva, C. & Ghodous, P. (2021). A microservice-based framework for exploring data selection for cross-building knowledge transfer. Service Oriented Computing and Applications. 15 (2), 97-107

M. Labiadh et al.,  "A microservice-based framework for exploring data selection for cross-building knowledge transfer", in Service Oriented Computing and Applications, vol. 15, no. 2, pp. 97-107, 2021

@article{labiadh2021_1734804484066,
	author = "Labiadh, M. and Obrecht, C. and Ferreira da Silva, C. and Ghodous, P.",
	title = "A microservice-based framework for exploring data selection for cross-building knowledge transfer",
	journal = "Service Oriented Computing and Applications",
	year = "2021",
	volume = "15",
	number = "2",
	doi = "10.1007/s11761-020-00306-w",
	pages = "97-107",
	url = "https://www.springer.com/journal/11761"
}

TY  - JOUR
TI  - A microservice-based framework for exploring data selection for cross-building knowledge transfer
T2  - Service Oriented Computing and Applications
VL  - 15
IS  - 2
AU  - Labiadh, M.
AU  - Obrecht, C.
AU  - Ferreira da Silva, C.
AU  - Ghodous, P.
PY  - 2021
SP  - 97-107
SN  - 1863-2386
DO  - 10.1007/s11761-020-00306-w
UR  - https://www.springer.com/journal/11761
AB  - Supervised deep learning has achieved remarkable success in various applications. Successful machine learning application however depends on the availability of sufficiently large amount of data. In the absence of data from the target domain, representative data collection from multiple sources is often needed. However, a model trained on existing multi-source data might generalize poorly on the unseen target domain. This problem is referred to as domain shift. In this paper, we explore the suitability of multi-source training data selection to tackle the domain shift challenge in the context of domain generalization. We also propose a microservice-oriented methodology for supporting this solution. We perform our experimental study on the use case of building energy consumption prediction. Experimental results suggest that minimal building description is capable of improving cross-building generalization performances when used to select energy consumption data. 
ER  -