Optimising neural networks for identification of wood defects using the bees algorithm


Pham D., Soroka A. J., Ghanbarzadeh A., KOÇ E., Otri S., Packianather M.

2006 IEEE International Conference on Industrial Informatics, INDIN'06, Singapore, Singapur, 16 - 18 Ağustos 2006, ss.1346-1351, (Tam Metin Bildiri)

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/indin.2006.275855
  • Basıldığı Şehir: Singapore
  • Basıldığı Ülke: Singapur
  • Sayfa Sayıları: ss.1346-1351
  • Boğaziçi Üniversitesi Adresli: Hayır

Özet

This paper presents an application of the Bees Algorithm (BA) to the optimisation of neural networks for wood defect detection. This novel population-based search algorithm mimics the natural foraging behaviour of swarms of bees. In its basic version, the algorithm performs a kind of neighbourhood search combined with random search. Following a brief description of the algorithm, the paper gives the results obtained for the wood defect identification problem demonstrating the efficiency and robustness of the new algorithm. ©2006 IEEE.