Abstract
We present a lightweight technique with which creators can prototype force-sensitive objects by attaching a pair of piezoelectric elements: one a vibration speaker and one a contact microphone. The key idea behind our technique is that touch force, in addition to the way the object is touched, can also be observed as different resonant frequency spectra. We also show that recognition of a touch and estimation of the touch force can be implemented by using the combination of support vector classification (SVC) and support vector regression (SVR). An experiment with an additional pressure sensor revealed that our technique might perform well in estimating touch force. We also show a tool for machine learning based on our technique that uses an animated guide, allowing creators to give the system both the training data and the labels for training machine learning needed for dealing with continuous-valued output such as SVR.
| Original language | English |
|---|---|
| Title of host publication | TEI 2015 - Proceedings of the 9th International Conference on Tangible, Embedded, and Embodied Interaction |
| Publisher | Association for Computing Machinery, Inc |
| Pages | 355-358 |
| Number of pages | 4 |
| ISBN (Electronic) | 9781450333054 |
| DOIs | |
| Publication status | Published - 2015 Jan 15 |
| Externally published | Yes |
| Event | 9th International Conference on Tangible, Embedded, and Embodied Interaction, TEI 2015 - Stanford, United States Duration: 2015 Jan 15 → 2015 Jan 19 |
Other
| Other | 9th International Conference on Tangible, Embedded, and Embodied Interaction, TEI 2015 |
|---|---|
| Country | United States |
| City | Stanford |
| Period | 15/1/15 → 15/1/19 |
Fingerprint
Keywords
- Acoustic classification
- Machine learning
- Piezoelectric sensor
- Pressure
- Prototyping
- Support vector classification
- Support vector machine
- Support vector regression
- Tangential force
- Tangibles
ASJC Scopus subject areas
- Human-Computer Interaction
- Software
Cite this
Sensing touch force using active acoustic sensing. / Ono, Makoto; Shizuki, Buntarou; Tanaka, Jiro.
TEI 2015 - Proceedings of the 9th International Conference on Tangible, Embedded, and Embodied Interaction. Association for Computing Machinery, Inc, 2015. p. 355-358.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Sensing touch force using active acoustic sensing
AU - Ono, Makoto
AU - Shizuki, Buntarou
AU - Tanaka, Jiro
PY - 2015/1/15
Y1 - 2015/1/15
N2 - We present a lightweight technique with which creators can prototype force-sensitive objects by attaching a pair of piezoelectric elements: one a vibration speaker and one a contact microphone. The key idea behind our technique is that touch force, in addition to the way the object is touched, can also be observed as different resonant frequency spectra. We also show that recognition of a touch and estimation of the touch force can be implemented by using the combination of support vector classification (SVC) and support vector regression (SVR). An experiment with an additional pressure sensor revealed that our technique might perform well in estimating touch force. We also show a tool for machine learning based on our technique that uses an animated guide, allowing creators to give the system both the training data and the labels for training machine learning needed for dealing with continuous-valued output such as SVR.
AB - We present a lightweight technique with which creators can prototype force-sensitive objects by attaching a pair of piezoelectric elements: one a vibration speaker and one a contact microphone. The key idea behind our technique is that touch force, in addition to the way the object is touched, can also be observed as different resonant frequency spectra. We also show that recognition of a touch and estimation of the touch force can be implemented by using the combination of support vector classification (SVC) and support vector regression (SVR). An experiment with an additional pressure sensor revealed that our technique might perform well in estimating touch force. We also show a tool for machine learning based on our technique that uses an animated guide, allowing creators to give the system both the training data and the labels for training machine learning needed for dealing with continuous-valued output such as SVR.
KW - Acoustic classification
KW - Machine learning
KW - Piezoelectric sensor
KW - Pressure
KW - Prototyping
KW - Support vector classification
KW - Support vector machine
KW - Support vector regression
KW - Tangential force
KW - Tangibles
UR - http://www.scopus.com/inward/record.url?scp=84924020651&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84924020651&partnerID=8YFLogxK
U2 - 10.1145/2677199.2680585
DO - 10.1145/2677199.2680585
M3 - Conference contribution
AN - SCOPUS:84924020651
SP - 355
EP - 358
BT - TEI 2015 - Proceedings of the 9th International Conference on Tangible, Embedded, and Embodied Interaction
PB - Association for Computing Machinery, Inc
ER -