Titulo Estágio
Recognition of Electrical Applicances in a Smart Home
Área Tecnológica
Reconhecimento de Padrões
Local do Estágio
DEI - Departamento de Engenharia Informática
Enquadramento
The reduction of residential electrical consumption is one important concern of individuals and institutions (European Union) regarding energy efficiency and financial savings. To provide useful feedback to consumers, with respect to behavior changes and reduction of energy, several solutions have recently been adopted. One of these solutions is the non-intrusive load monitoring (NILM) which performs the disaggregation of whole-home electrical consumption and associates the electrical signals to each respective home appliance.
Objetivo
The main goal of this work is to implement a classifier able to classify electrical consumption signals associated to each home electrical device. These signals are provided by a NILM system that is currently being developed. For the purpose of the main line of the work, time series analysis, feature extraction and feature selection as well as the choice of appropriated classification methods will be required.
Plano de Trabalhos - Semestre 1
1) State-of-the-art revision: Sep-Oct 2013
2) Feature extraction and feature selection methods will be studied and preliminary tests done for the model being developed: Nov-Dec 2013
3) Empirical experimentation and analysis of results: Jan 2013
4) Intermediate report and plan of possible extensions or alternatives: Jan 2013
Plano de Trabalhos - Semestre 2
1) Model Classification proposal and implementation: Feb-May 2013
2) Empirical Experimentation and Validation: Mar-May 2013
3) MSc thesis writing: May-Jun 2013
Condições
Strong skills in programming (Java, Matlab, Python, C/C++).
Other interesting (optional) skills/interests include Machine Learning and Pattern Recognition
Observações
The candidate curriculum is required.
Orientador
Bernardete Ribeiro e Marisa Figueiredo
bribeiro@dei.uc.pt 📩