Recognition of Huffman codewords with a genetic-neural hybrid system

  • Authors:

  • Eugène C. Ezin;Orion Fausto Reyes-Galaviz;Carlos A. Reyes-García

  • Affiliations:

  • Université d'Abomey-Calavi, Institut de Mathématiques et de Sciences Physiques, Unité de Recherche en Informatique et Sciences Appliquées, Porto-Novo, Bénin;Universidad Autónoma de Tlaxcala, Facultad de Ciencias Básicas, Ingeniería y Tecnología;Instituto Nacional de Astrofísica, Óptica y Electrónica, Puebla, México

  • Venue:
  • MICAI'10 Proceedings of the 9th Mexican international conference on Artificial intelligence conference on Advances in soft computing: Part II
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Character classification is known to be one of many basic applications in the field of artificial neural networks (ANN), while data transmission with low size is important in the field of source coding. In this paper, we constructed an alphabet of 36 letters which are encoded with the Huffman algorithm and then classified with a back-propagation Feed Forward artificial neural network. Since an ANN is initialized with random weights, the performance is not always optimal. Therefore, we designed a simple genetic algorithm (SGA) that choses an ANN and optimizes its architecture to improve the recognition accuracy. The performance evaluation is given to show the effectiveness of the procedure used, where we reached an accuracy of 100%.