Stimuli-magnitude-adaptive sample selection for data-driven haptic modeling
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Stimuli-magnitude-adaptive sample selection for data-driven haptic modeling. / Abdulali, Arsen; Hassan, Waseem; Jeon, Seokhee.
In: Entropy, Vol. 18, No. 6, 222, 06.2016.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Stimuli-magnitude-adaptive sample selection for data-driven haptic modeling
AU - Abdulali, Arsen
AU - Hassan, Waseem
AU - Jeon, Seokhee
N1 - Funding Information: This research was supported by the Global Frontier Program (NRF-2012M3A6A3056074) and the ERC program (2011-0030075) both through NRF Korea, and by the ITRC program (IITP-2016-H8501-16-1015) through IITP Korea. Publisher Copyright: © 2016 by the authors; licensee MDPI, Basel, Switzerland.
PY - 2016/6
Y1 - 2016/6
N2 - Data-driven haptic modeling is an emerging technique where contact dynamics are simulated and interpolated based on a generic input-output matching model identified by data sensed from interaction with target physical objects. In data-driven modeling, selecting representative samples from a large set of data in a way that they can efficiently and accurately describe the whole dataset has been a long standing problem. This paper presents a new algorithm for the sample selection where the variances of output are observed for selecting representative input-output samples in order to ensure the quality of output prediction. The main idea is that representative pairs of input-output are chosen so that the ratio of the standard deviation to the mean of the corresponding output group does not exceed an application-dependent threshold. This output- and standard deviation-based sample selection is very effective in applications where the variance or relative error of the output should be kept within a certain threshold. This threshold is used for partitioning the input space using Binary Space Partitioning-tree (BSP-tree) and k-means algorithms. We apply the new approach to data-driven haptic modeling scenario where the relative error of the output prediction result should be less than a perceptual threshold. For evaluation, the proposed algorithm is compared to two state-of-the-art sample selection algorithms for regression tasks. Four kinds of haptic related behavior–force datasets are tested. The results showed that the proposed algorithm outperformed the others in terms of output-approximation quality and computational complexity.
AB - Data-driven haptic modeling is an emerging technique where contact dynamics are simulated and interpolated based on a generic input-output matching model identified by data sensed from interaction with target physical objects. In data-driven modeling, selecting representative samples from a large set of data in a way that they can efficiently and accurately describe the whole dataset has been a long standing problem. This paper presents a new algorithm for the sample selection where the variances of output are observed for selecting representative input-output samples in order to ensure the quality of output prediction. The main idea is that representative pairs of input-output are chosen so that the ratio of the standard deviation to the mean of the corresponding output group does not exceed an application-dependent threshold. This output- and standard deviation-based sample selection is very effective in applications where the variance or relative error of the output should be kept within a certain threshold. This threshold is used for partitioning the input space using Binary Space Partitioning-tree (BSP-tree) and k-means algorithms. We apply the new approach to data-driven haptic modeling scenario where the relative error of the output prediction result should be less than a perceptual threshold. For evaluation, the proposed algorithm is compared to two state-of-the-art sample selection algorithms for regression tasks. Four kinds of haptic related behavior–force datasets are tested. The results showed that the proposed algorithm outperformed the others in terms of output-approximation quality and computational complexity.
KW - Data-driven modeling
KW - Haptic feedback
KW - Regression
KW - Sample selection
UR - http://www.scopus.com/inward/record.url?scp=85028513956&partnerID=8YFLogxK
U2 - 10.3390/e18060222
DO - 10.3390/e18060222
M3 - Journal article
AN - SCOPUS:85028513956
VL - 18
JO - Entropy
JF - Entropy
SN - 1099-4300
IS - 6
M1 - 222
ER -
ID: 388954226