| KEYWORD |
Kriging neural network for spatial-temporal energy modelling of smart buildings
keywords ARTIFICIAL INTELLIGENCE, ARTIFICIAL NEURAL NETWORKS, DEEP NEURAL NETWORKS
Reference persons EDOARDO PATTI
External reference persons Alessandro Aliberti (alessandro.aliberti@polito.it)
Research Groups DAUIN - GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ELECTRONIC DESIGN AUTOMATION - EDA, Energy Center Lab, GR-06 - ELECTRONIC DESIGN AUTOMATION - EDA, ICT4SS - ICT FOR SMART SOCIETIES
Thesis type EXPERIMENTAL
Description In statistics, originally in geostatistics, kriging or Gaussian process regression is a method of interpolation for which the interpolated values are modeled by a Gaussian process governed by prior covariances. Under suitable assumptions on the priors, kriging gives the best linear unbiased prediction of the intermediate values. Interpolating methods based on other criteria such as smoothness (e.g., smoothing spline) may not yield the most likely intermediate values. The method is widely used in the domain of spatial analysis and computer experiments. The technique is also known as Wiener–Kolmogorov prediction, after Norbert Wiener and Andrey Kolmogorov.
This thesis is aimed at developing an innovative spatial-temporal energy model technique by exploiting Artificial Neural Networks and Kriging techniques in the field of Smart Buildings.
By addressing the problem of spatial-temporal energy modelling, the student will analyze the literature solution to explore the state-of-art methodologies. Then, based on a real demonstrator, the student will explore and design one (or more) Kriging neural network solution.
Required skills Python
Deadline 18/10/2020
PROPONI LA TUA CANDIDATURA