Abstract | ||
---|---|---|
With the sharp increase of digital data emerging at present, the data in new applications are generated fast. Continuous cumulative data have gradually become massive and difficult to be handled due to limited workspace and limited amount of time. The conventional learning conditional preference networks' algorithm cannot successfully process the data streams. In this paper, we introduce the model of learning CP-nets from preference data streams and formalize the question. Then, an incremental approach is presented through which we can learn the CP-nets with gradually increasing data streams. The proposed method is verified on simulated data and real data, and it is also compared with other works. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1109/ACCESS.2018.2873087 | IEEE ACCESS |
Keywords | Field | DocType |
Preference learning,dynamic CP-net,data streams,incremental approach | Data mining,Data modeling,Data stream mining,Microsoft Windows,Computer science,Workspace,Cluster analysis,Digital data,Distributed computing | Journal |
Volume | ISSN | Citations |
6 | 2169-3536 | 0 |
PageRank | References | Authors |
0.34 | 0 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Zhao-Wei Liu | 1 | 3 | 2.74 |
Zhaolin Zhong | 2 | 0 | 0.68 |
Chenghui Zhang | 3 | 268 | 38.20 |
Yanwei Yu | 4 | 82 | 12.78 |
Jinglei Liu | 5 | 0 | 0.34 |