Abstract
In multimodal classification, we look for a set of strategies for mining and exploiting the most informative modalities for a given situation. These strategies are computations performed by the algorithms. In this paper, we propose to consider strategies as advice given to an algorithm by "expert." There can be several classification strategies. Each strategy makes different assumptions regarding the fidelity of a sensor modality and uses different data to arrive at its estimates. Each strategy may place different trust in a sensor at different times, and each may be better in different situations. In this paper, we introduce a novel algorithm for combining expert strategies to achieve robust classification performance in a multimodal setting. We provide experimental results using real world examples to demonstrate the efficacy of the proposed algorithm.
| Original language | English |
|---|---|
| Title of host publication | Innovative Solutions in the Field of Engineering Sciences |
| Publisher | Trans Tech Publications Ltd |
| Pages | 693-697 |
| Number of pages | 5 |
| ISBN (Print) | 9783038351511 |
| DOIs | |
| State | Published - 1 Jan 2014 |
| Event | 2014 International Conference on Applied Mechanics and Mechanical Automation, AMMA 2014 - Macao, China Duration: 20 May 2014 → 21 May 2014 |
Publication series
| Name | Applied Mechanics and Materials |
|---|---|
| Volume | 590 |
| ISSN (Print) | 1660-9336 |
| ISSN (Electronic) | 1662-7482 |
Other
| Other | 2014 International Conference on Applied Mechanics and Mechanical Automation, AMMA 2014 |
|---|---|
| Country | China |
| City | Macao |
| Period | 20/05/14 → 21/05/14 |
Fingerprint
Keywords
- Classification
- Data fusion
- Machine learning
Cite this
}
Combining expert strategies in multimodal classification. / Peng, Jing.
Innovative Solutions in the Field of Engineering Sciences. Trans Tech Publications Ltd, 2014. p. 693-697 (Applied Mechanics and Materials; Vol. 590).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Research › peer-review
TY - GEN
T1 - Combining expert strategies in multimodal classification
AU - Peng, Jing
PY - 2014/1/1
Y1 - 2014/1/1
N2 - In multimodal classification, we look for a set of strategies for mining and exploiting the most informative modalities for a given situation. These strategies are computations performed by the algorithms. In this paper, we propose to consider strategies as advice given to an algorithm by "expert." There can be several classification strategies. Each strategy makes different assumptions regarding the fidelity of a sensor modality and uses different data to arrive at its estimates. Each strategy may place different trust in a sensor at different times, and each may be better in different situations. In this paper, we introduce a novel algorithm for combining expert strategies to achieve robust classification performance in a multimodal setting. We provide experimental results using real world examples to demonstrate the efficacy of the proposed algorithm.
AB - In multimodal classification, we look for a set of strategies for mining and exploiting the most informative modalities for a given situation. These strategies are computations performed by the algorithms. In this paper, we propose to consider strategies as advice given to an algorithm by "expert." There can be several classification strategies. Each strategy makes different assumptions regarding the fidelity of a sensor modality and uses different data to arrive at its estimates. Each strategy may place different trust in a sensor at different times, and each may be better in different situations. In this paper, we introduce a novel algorithm for combining expert strategies to achieve robust classification performance in a multimodal setting. We provide experimental results using real world examples to demonstrate the efficacy of the proposed algorithm.
KW - Classification
KW - Data fusion
KW - Machine learning
UR - http://www.scopus.com/inward/record.url?scp=84904323344&partnerID=8YFLogxK
U2 - 10.4028/www.scientific.net/AMM.590.693
DO - 10.4028/www.scientific.net/AMM.590.693
M3 - Conference contribution
SN - 9783038351511
T3 - Applied Mechanics and Materials
SP - 693
EP - 697
BT - Innovative Solutions in the Field of Engineering Sciences
PB - Trans Tech Publications Ltd
ER -