Estimation of immeasurable economic values by means of Hidden Markov models

Internet traffic modeling by means of Hidden Markov Models

In this work, we propose a Hidden Markov Model for Internet traffic sources at packet level, jointly analyzing Inter Packet Time and Packet Size. We give an analytical basis and the mathematical details regarding the model, and we test the flexibility of the proposed modeling approach with real traffic traces related to common Internet services with strong differences in terms of both applicati...

Spectral Estimation of Hidden Markov Models

This thesis extends and improves methods for estimating key quantities of hidden Markov models through spectral method-of-moments estimation. Unlike traditional estimation methods like EM and Gibbs sampling, the set of estimation methods, which we call spectral HMMs (sHMMs), are incredibly fast, do not require multiple restarts, and come with provable guarantees. Our first result improves upon ...

Estimation of nonstationary hidden Markov models by MCMC sampling

Hidden Markov models are very important for analysis of signals and systems. In the past two decades they have been attracting the attention of the speech processing community, and recently they have become the favorite models of biologists. Major weakness of conventional hidden Markov models is their inflexibility in modeling state duration. In this paper, we analyze nonstationary hidden Marko...

Maximum-likelihood estimation for hidden Markov models

Hidden Markov models assume a sequence of random variables to be conditionally independent given a sequence of state variables which forms a Markov chain. Maximum-likelihood estimation for these models can be performed using the EM algorithm. In this paper the consistency of a sequence of maximum-likelihood estimators is proved. Also, the conclusion of the Shannon-McMillan-Breiman theorem on en...

Adaptive Estimation Techniques for Hidden Markov Models