Cooperative and interactive Learning to estimate Human Behaviours for Energy Applications

30 de setembro de 2021

To reduce the environmental impact of the residential sector, it is crucial to find ways to enhance sustainable energy behaviours. A new supervised learning approach is proposed to classify different instances related to human behaviour in a household context. It is based on a combination of Interactive Learning and Cooperative Learning relying only on timed data from a selected set of sensors and feedback from the occupants (labels) to collect the training data. The privacy of occupants is granted by avoiding the use of cameras and this approach can adapt not only to different household contexts but also, to distinct perspectives of the same reality (many profiles of users) and different types of data (numerical and non-numerical). A new method was introduced to assess and correct inconsistent labels, which assesses the errors and requests new information to the same context (updates). The methodology was tested for both occupancy and activity recognition, settling that using non-numerical labels leads to a more subjective environment but still reliable. Further, two different interaction criteria were analysed: density and spread rate; confirming that the optimal sensors/features selected depend not only on the household characteristics but also on the interaction criteria applied. The proposed methodology can be used to promote sustainable behavioural changes by sending suggestions to the occupants and also to study the impact of those suggestions in individual and energy community contexts (flexibility). It can be very useful in energy management systems improving energy efficiency and performing active demand-side management.

Autores da comunidade :

• 

  J

  Joana Nunes Nicolau Baptista da Silva

  ist425762

Orientadores desta instituição:

• 

  C

  Carlos Augusto Santos Silva

  ist23960

mechanical-engineering - Engenharia Mecânica

por - Português

Instituto Superior Técnico