Sample selection of multi-trial data for data-driven haptic texture modeling
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Sample selection of multi-trial data for data-driven haptic texture modeling. / Abdulali, Arsen; Hassan, Waseem; Jeon, Seokhee.
2017 IEEE World Haptics Conference, WHC 2017. Institute of Electrical and Electronics Engineers Inc., 2017. p. 66-71 7989878 (2017 IEEE World Haptics Conference, WHC 2017).Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Sample selection of multi-trial data for data-driven haptic texture modeling
AU - Abdulali, Arsen
AU - Hassan, Waseem
AU - Jeon, Seokhee
N1 - Funding Information: ACKNOWLEDGMENTS This research was supported by Global Frontier Program through NRF of Korea (NRF-2012M3A6A3056074) and by ERC program through NRF of Korea (2011-0030075). Publisher Copyright: © 2017 IEEE.
PY - 2017/7/21
Y1 - 2017/7/21
N2 - In data-driven haptic texture rendering, the rendering quality is highly dependent on the quality of the inputoutput model training. The data in input model should be sufficient both in terms of quantity and coverage of the input space. Furthermore, the ever increasing input dimensions, to attain more realistic rendering makes the task of model building even more difficult. In order to address these problems, this paper proposes a novel sample selection algorithm. Our algorithm provides an efficient method of combining modeling data across multiple independent trials, whereby the significant model points are selected from each independent trial while the outliers are being eliminated. This study also provides a generic haptic model which equips other haptic modeling algorithms to benefit from the sample selection algorithm. The algorithm was evaluated using two isotropic and two non isotropic haptic texture datasets. The results showed that the algorithm provides upward of a two fold compression rate for model points, while at the same time the rendering quality remains unaffected.
AB - In data-driven haptic texture rendering, the rendering quality is highly dependent on the quality of the inputoutput model training. The data in input model should be sufficient both in terms of quantity and coverage of the input space. Furthermore, the ever increasing input dimensions, to attain more realistic rendering makes the task of model building even more difficult. In order to address these problems, this paper proposes a novel sample selection algorithm. Our algorithm provides an efficient method of combining modeling data across multiple independent trials, whereby the significant model points are selected from each independent trial while the outliers are being eliminated. This study also provides a generic haptic model which equips other haptic modeling algorithms to benefit from the sample selection algorithm. The algorithm was evaluated using two isotropic and two non isotropic haptic texture datasets. The results showed that the algorithm provides upward of a two fold compression rate for model points, while at the same time the rendering quality remains unaffected.
UR - http://www.scopus.com/inward/record.url?scp=85034270993&partnerID=8YFLogxK
U2 - 10.1109/WHC.2017.7989878
DO - 10.1109/WHC.2017.7989878
M3 - Article in proceedings
AN - SCOPUS:85034270993
T3 - 2017 IEEE World Haptics Conference, WHC 2017
SP - 66
EP - 71
BT - 2017 IEEE World Haptics Conference, WHC 2017
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 7th IEEE World Haptics Conference, WHC 2017
Y2 - 6 June 2017 through 9 June 2017
ER -
ID: 388953801