Abstract | ||
---|---|---|
In this paper we analyze a framework for an ECOC classification system founded on the use of LPDC codes, a class of codes well-known in Coding Theory. Such approach provides many advantages over traditional ECOC codings. First, codewords are generated in an algebraic way without requiring any selection of rows and columns of the coding matrix. Second, the decoding phase can be improved by exploiting the algebraic properties of the code. In particular, it is possible to detect and recover possible errors produced by the dichotomizers through an iterative mechanism. Some experiments have been accomplished with the focus on the parity-check matrix used to define the codewords of the LDPC code, so as to determine how the code parameters influence the performance of the proposed approach. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1007/978-3-662-44415-3_46 | Lecture Notes in Computer Science |
Keywords | Field | DocType |
ECOC,LDPC codes,Ensemble Methods | Row and column spaces,Concatenated error correction code,Matrix (mathematics),Low-density parity-check code,Algorithm,Theoretical computer science,Coding (social sciences),Coding theory,Linear code,Decoding methods,Mathematics | Conference |
Volume | ISSN | Citations |
8621 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 15 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Claudio Marrocco | 1 | 84 | 17.53 |
Francesco Tortorella | 2 | 370 | 43.39 |