Lossless data compression methods based on neural network

Author

Guowei, Yang ; Zhengxi, Li ; Xuyan, Tu

Author_Institution

Comput. Center, Teacher´´s Coll. of Qingdao Univ., China

Volume

2

fYear

2003

Firstpage

1899

Abstract

No lossless data compression method based on neural network has been found before. A lossless compression method based on BP network for the long character-string of 0 and 1 is given by establishing specific mapping Y and specific integer function and with the non-linear approximation capability of concrete three-layer BP network in this paper. The compression and decompression algorithms of the lossless compression method are provided. Experiments show that the compression ratio of the lossless compression method is usually around 16/11 and the method can effectively compress the data which have been compressed by Huffman coding, arithmetic coding or dictionary coding.

Keywords

Huffman codes; arithmetic codes; backpropagation; data compression; image coding; neural nets; transform coding; Huffman coding; arithmetic coding; compression algorithm; compression ratio; decompression algorithm; dictionary coding; integer function; lossless data compression method; neural network; nonlinear approximation capability; three-layer BP network; Application software; Computer networks; Concrete; Data compression; Decoding; Dictionaries; Educational institutions; Huffman coding; Image coding; Neural networks;

fLanguage

English

Publisher

ieee

Conference_Titel

Communication Technology Proceedings, 2003. ICCT 2003. International Conference on

Print_ISBN

7-5635-0686-1

Type

conf

DOI

10.1109/ICCT.2003.1209899

Filename

1209899