Personal tools
You are here: Home Events ANC Workshop: Mingjun Zhong, Chair: Amos Storkey

ANC Workshop: Mingjun Zhong, Chair: Amos Storkey

— filed under:

Signal Aggregate Constraints in Additive Factorial HMMs, with Application to Energy Disaggregation

  • ANC Workshop Talk
When Mar 04, 2014
from 11:00 AM to 12:00 PM
Where IF 4.31/4.33
Add event to calendar vCal

Blind source separation problems are difficult because they are inherently unidentifiable, yet the entire goal is to identify meaningful sources. We introduce a way of incorporating domain knowledge into this problem, called signal aggregate constraints (SACs). SACs encourage the total signal for each of the unknown sources to be close to a specified value. This is based on the observation that the total signal often varies widely across the unknown sources, and we often have a good idea of what total values to expect.

We present a new inference algorithm for incorporating SACs into an additive factorial hidden Markov model (AFHMM). The algorithm is based on a dual decomposition framework with a novel choice of auxiliary variables. On a real world energy disaggregation data set, we show that the use of SACs dramatically improves the original FHMM, and significantly improves over a recent state-of-the-art approach.