Softwares

If you find any bug in the source codes please report to me: fasouza AT isr DOT uc DOT pt.

·Mixture partial least square experts (Mix-PLS)
The Mix-PLS is a mixture of experts models based on the partial least squares (PLS) algorithm. It was designed to be applied in prediction settings composed by multiple operating modes and/or non-linear carachteristics. The MIX-PLS can be downloaded below.

• Source code (Matlab implementation) In case of publication please cite the original paper: Francisco Souza, Rui Araújo. Mixture of Partial Least Squares Experts and Application in Prediction Settings with Multiple Operating Modes. Chemometrics and Intelligent Laboratory Systems. 130:192–202, January 2014. [doi; pdf; bib].
  

·Optimized extreme learning machine (O-ELM)
The O-ELM is a extreme learning machine (ELM) based model where the input connections and the hidden layers are selected based on genetic algorithms in a way to optmize the ELM model performance. The O-ELM-PLS can be downloaded below.

• Source code (Matlab implementation)
  In case of publication please cite the paper: Tiago Matias, Francisco Souza, Rui Araújo, Carlos Henggeler Antunes. Learning of a Single-hidden Layer Feedforward Neural Network using an Optimized Extreme Learning Machine. Neurocomputing. (In Press.) [doi; pdf; bib].