By modeling the hiding process as additive noise, histogram characteristic function (HCF) is introduced in [10] to detect LSB, spread spectrum, and discrete cosine transform (DCT) hiding methods.
Other modeling issues covered include: modeling of joint data (e.g., PKPD models), covariate models, mixture models, hidden Markov models, and stochastic differential equation-based models.
It is thus desired that machine learning methods can be used to model the complex patterns hidden in the available structural data, and the resulting classifier can be applied to reliable identification of DNA-binding residues in protein sequences.
In particular, we will first apply the hidden Markov model (HMM) to model spatio-temporal behavior patterns and use the expectation-maximization (EM) method to learn the parameters of the model.
They then used a well-known statistical method called the hidden Markov model, which was developed in the 1960s for speech recognition, to help them identify subtle patterns in the genomes of apes and humans.
The methods used were: (i) the neural network algorithm of SignalP v3.0 [51], (ii) the hidden Markov model of SignalP v3.0 [51], and (iii) the Sigcleave algorithm at EMBOSS [52].
The methodologies used were: (i) the neural network (NN) algorithm of SignalP v3.0 [72], (ii) the hidden Markov model (HMM) of SignalP v3.0 [72], and (iii) the SigCleave algorithm [73] at EMBOSS [74].
But, most of the current methods in microarray data analysis are black box methods; these models can not satisfactorily reveal the hidden information in the data.
In the developed SaE-ELM model, the network hidden node parameters of the ELM are optimized using SaE algorithm.
This enables the designer to focus on modeling the domain concepts and hiding irrelevant UML-related properties which are not needed.
