A linear structured approach and a refined fitness function in genetic programming for multi-class object classification

Abstract: This paper describes an approach to the use of genetic programming (GP) to multi-class object recognition problems. Rather than using the standard tree structures to represent evolved classifier programs which only produce a single output value that must be further translated into a set of class labels, this approach uses a linear structure to represent evolved programs, which use multiple target registers each for a single class. The simple error rate fitness function is refined and a new fitness function is introduced to approximate the true feature space of an object recognition problem. This approach is examined and compared with the tree based GP on three data sets providing object recognition problems of increasing difficulty. The results showthat this approach outperforms the standard tree based GP approach on all the tasks investigated here and that the programs evolved by this approach are easier to interpret. The investigation into the extra target registers and program length results in heuristic guidelines for initially setting system parameters.

  @Article{zhang2007a,
  author =   {Mengjie Zhang and Christopher Fogelberg and Yuejin Ma},
  title =    {A linear structured approach and a refined fitness function in genetic programming for multi-class
              object classification},
  journal =  {Connection Science},
  year =     2007,
  volume =   19,
  number =   4,
  pages =    {339--359},
  month =    {December},
  citeulike-article-id = {2932872},
  publisher = {Taylor and Francis Ltd},
  url = {http://dx.doi.org/10.1080/09540090701725557},
  doi = {10.1080/09540090701725557},
  issn = {0954-0091},
  keywords = {lgp, multiclass classification, fitness function}
}

Available here.