The aim of the project is to build a model that can analyze data from domotic sensors in order to predict the behavior of a user. To this end, two approaches have been used. One with the Hidden Markov Chain model, made with larsmans libraries(link) and the other with a Neural Networks model, made with keras. The models have been trained and tested with the Milan dataset (link).
This project was developed on Python 3.6 and needs the following libraries:
- Cython
- numpy
- scipy
- scikit-learn
- seqlearn
- keras