hmmus 0.2.16

The hmmus project has some HMM algorithms implemented in C, and it is meant to be useful under the following conditions:<br /><br />* The sequence of observations to be analyzed is so long that it does not fit conveniently in RAM.<br />* Likelihoods per hidden state per position have been precalculated.<br />* Numerical stability is important, but is not so important that error bounds on the output are required.<br />* The number of hidden states is small.<br />* The matrix of probabilities of transitions between hidden states is dense.<br />* Binary data files are acceptable as input and output.<br /><br />This project would be especially useless in the following cases:<br /><br />* User friendly or pedagogically informative software is desired.<br />* All of the data can fit in RAM and numerical stability is not an issue.<br />* The hidden state transitions are defined by a large sparse graph.<br />* The emission distributions are uncomplicated (e.g. finite or normal).<br /><br />Operating system requirements:<br /><br />* This project was developed using Ubuntu, so it will probably work on Debian-based Linux distributions.<br />* It might work with non-Debian-based Unix variants.<br />* It probably will not work on Windows.<br /><br />Major dependencies:<br /><br />* A C compiler which is not too different from gcc.<br /><br />#md5=fc7da06ebda206dc0a4e3bccf621bff8

Requirements:	No special requirements
Platforms:	*nix, Linux
Keyword:	Defined,  Distributions,  Emission,  Friendly,  Graph,  Hidden,  Hmmus,  Important,  Large,  Numerical,  Pedagogically,  Project,  Sparse,  Stability,  State,  States,  Transitions
Users rating:	0/10