File(s) under permanent embargo
The hidden permutation model and location-based activity recognition
conference contribution
posted on 2008-01-01, 00:00 authored by H Bui, Quoc-Dinh Phung, Svetha VenkateshSvetha Venkatesh, H PhanPermutation modeling is challenging because of the combinatorial nature of the problem. However, such modeling is often required in many real-world applications, including activity recognition where subactivities are often permuted and partially ordered. This paper introduces a novel Hidden Permutation Model (HPM) that can learn the partial ordering constraints in permuted state sequences. The HPM is parameterized as an exponential family distribution and is flexible so that it can encode constraints via different feature functions. A chain-flipping Metropolis-Hastings Markov chain Monte Carlo (MCMC) is employed for inference to overcome the O(n!) complexity. Gradient-based maximum likelihood parameter learning is presented for two cases when the permutation is known and when it is hidden. The HPM is evaluated using both simulated and real data from a location-based activity recognition domain. Experimental results indicate that the HPM performs far better than other baseline models, including the naive Bayes classifier, the HMM classifier, and Kirshner's multinomial permutation model. Our presented HPM is generic and can potentially be utilized in any problem where the modeling of permuted states from noisy data is needed.
History
Event
AAAI Conference on Artificial Intelligence (23rd : 2008 : Chicago, Ill.)Pagination
1345 - 1350Publisher
AAAILocation
Chicago, Ill.Place of publication
[Chicago, Ill.]Start date
2008-07-13End date
2008-07-17ISBN-13
9781577353683Language
engPublication classification
E1.1 Full written paper - refereedCopyright notice
2008, American Association for Artificial IntelligenceTitle of proceedings
AAAI 2008 : Proceedings of the 23rd AAAI Conference on Artificial IntelligenceUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC