Name
Abstract | ||
|---|---|---|
In this paper we derive a novel smooth component analysis algorithm applied for prediction improvement. When many prediction models are tested we can treat their results as multivariate variable with the latent components having constructive or destructive impact on prediction results. The filtration of those destructive components and proper mixing of those constructive should improve final prediction results. The filtration process can be performed by neural networks with initial weights computed from smooth component analysis. The validity and high performance of our concept is presented on the real problem of energy load prediction. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1007/11840930_14 | ICANN (2) |
Keywords | Field | DocType |
neural network,filtration process,destructive component,latent component,prediction result,energy load prediction,novel smooth component analysis,prediction model,destructive impact,prediction improvement,final prediction result | Constructive,Multivariate statistics,Computer science,Algorithm,Filtration,Independent component analysis,Network analysis,Component analysis,Artificial neural network,Blind signal separation | Conference |
Volume | ISSN | ISBN |
4132 | 0302-9743 | 3-540-38871-0 |
Citations | PageRank | References |
1 | 0.45 | 9 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Ryszard Szupiluk | 1 | 38 | 8.97 |
| Piotr Wojewnik | 2 | 20 | 6.32 |
| Tomasz Zabkowski | 3 | 32 | 11.28 |