• DocumentCode
    2926387
  • Title

    Flies species recognition for maggot therapy using neural-expert technique

  • Author

    Yusoff, Nursyafinaz Md ; Hamid, Nurzeatul Hamimah Abdul ; Halim, Shamimi A.

  • Author_Institution
    Fac. of Comput. & Math. Sci., Univ. Teknol. MARA, Shah Alam, Malaysia
  • fYear
    2011
  • fDate
    14-16 Nov. 2011
  • Firstpage
    1
  • Lastpage
    4
  • Abstract
    Maggot Debridement Therapy (MDT) has been recognized as one of the effective alternative treatment to enhance healing and to decrease the mortality associated with underlying injury. One of the most important procedures in performing MDT is to use the correct maggot from suitable species. In this case, maggots from the incorrect species would consume the live tissue instead of the dead tissue. Hence, this is highlighted as one of the difficulties in implementing MDT. Currently the process of identifying flies is done manually by experts or by using DNA traits. We explored and developed another procedure to recognize the species using hybrid neuro-expert technique. The percentage of correctness using standard back propagation neural network yields 94.4% accuracy. By adapting the neuro-expert technique, the prototype accuracy is 100%.
  • Keywords
    DNA; backpropagation; biological tissues; injuries; medical expert systems; molecular biophysics; neural nets; patient treatment; DNA traits; MDT; dead tissue; fly species recognition; healing; hybrid neuroexpert technique; injury; live tissue; maggot debridement therapy; mortality; prototype accuracy; standard back propagation neural network; Accuracy; Artificial neural networks; Biomedical imaging; Expert systems; Medical treatment; Testing; Wounds; Back Propagation Neural Network (BPNN); Flies recognition; Maggot Debridement Therapy (MDT); Neuro-expert;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Information Technology and Multimedia (ICIM), 2011 International Conference on
  • Conference_Location
    Kuala Lumpur
  • Print_ISBN
    978-1-4577-0988-3
  • Type

    conf

  • DOI
    10.1109/ICIMU.2011.6122755
  • Filename
    6122755