A Novel Algorithm for Training Hidden Markov Models with Positive and Negative Examples

In this paper, we present a novel training method based on Baum-Welch algorithm for hidden Markov models (HMM), named as Comprehensive HMM (CompHMM), which changes the traditional approach of training HMM from positive examples only to be able to utilize both positive and negative examples in training HMMs. By comparison, our method outperformed the standard Baum-Welch method and another HMM discriminative training method significantly through both synthetic and real data in membership prediction task.

[1]  Jung-Youn Lee,et al.  Detecting De Novo Plasmodesmata Targeting Signals and Identifying PD Targeting Proteins , 2019, ICCABS.

[2]  Hiroshi Mamitsuka,et al.  A Learning Method of Hidden Markov Models for Sequence Discrimination , 1996, J. Comput. Biol..

[3]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[4]  L. Baum,et al.  Growth transformations for functions on manifolds. , 1968 .

[5]  Robert D. Finn,et al.  HMMER web server: interactive sequence similarity searching , 2011, Nucleic Acids Res..

[6]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[7]  Pierre Baldi,et al.  Smooth On-Line Learning Algorithms for Hidden Markov Models , 1994, Neural Computation.

[8]  Hossein Nezamabadi-pour,et al.  Predicting CpG Islands and Their Relationship with Genomic Feature in Cattle by Hidden Markov Model Algorithm , 2016 .

[9]  J. Hanley,et al.  The meaning and use of the area under a receiver operating characteristic (ROC) curve. , 1982, Radiology.

[10]  Lalit R. Bahl,et al.  Maximum mutual information estimation of hidden Markov model parameters for speech recognition , 1986, ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing.

[11]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[12]  Alex Bateman,et al.  An introduction to hidden Markov models. , 2007, Current protocols in bioinformatics.

[13]  L. Baum,et al.  An inequality and associated maximization technique in statistical estimation of probabilistic functions of a Markov process , 1972 .

[14]  David Haussler,et al.  Exploiting Generative Models in Discriminative Classifiers , 1998, NIPS.