Name
Abstract | ||
|---|---|---|
We propose a new string kernel based on variable-length-don't-care patterns(VLDC patterns). A VLDC pattern is an element of (Σ茂戮驴 { 茂戮驴 })*, where Σis an alphabet and 茂戮驴 is the variable-length-don't-care symbol that matches any string in Σ*. The number of VLDC patterns matching a given string sof length nis O(22n). We present an O(n5 ) algorithm for computing the kernel value. We also propose variations of the kernel which modify the relative weights of each pattern. We evaluate our kernels using a support vector machine to classify spam data. |
Year | DOI | Venue |
|---|---|---|
2008 | 10.1007/978-3-540-88411-8_29 | Discovery Science |
Keywords | Field | DocType |
vldc pattern,support vector machine,string sof length,relative weight,variable-length-don t-care symbol,spam data,variable-length-don t-care pattern,variable-length-don t-care patterns,new string kernel,kernel value,string kernel,pattern matching | Kernel (linear algebra),Commentz-Walter algorithm,Symbol,Computer science,Support vector machine,Theoretical computer science,Artificial intelligence,String kernel,Machine learning,Alphabet | Conference |
Volume | ISSN | Citations |
5255 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 12 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Kazuyuki Narisawa | 1 | 33 | 6.82 |
| Hideo Bannai | 2 | 620 | 79.87 |
| Hatano, Kohei | 3 | 88 | 21.16 |
| Shunsuke Inenaga | 4 | 595 | 79.02 |
| Masayuki Takeda | 5 | 902 | 79.24 |