File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1109/SENSORS43011.2019.8956907
- Scopus: eid_2-s2.0-85078699009
- WOS: WOS:000534184600411
Supplementary
- Citations:
- Appears in Collections:
Conference Paper: Recurrent Transfer Learning by Neural Network Regression for Human Balance Sensor Calibration
Title | Recurrent Transfer Learning by Neural Network Regression for Human Balance Sensor Calibration |
---|---|
Authors | |
Keywords | balance sensor FTIR calibration regression transfer learning |
Issue Date | 2019 |
Publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1000662/all-proceedings |
Citation | Proceedings of 2019 IEEE Sensors Conference, Montreal, QC, Canada, 27-30 October 2019, p. 1-4 How to Cite? |
Abstract | This paper presents a novel human balance ability assessment device, called balance sensor, which uses the principle of Frustrated Total Internal Reflection (FTIR) to measure pressure distribution under human feet. Experiment is conducted to quantitatively calibrate the relationship between pressure and pixel value and physical model is established for this relationship. A special neural network is designed. The established physical model can be transferred into such neural network as initialization. Moreover, we invented a training paradigm called Recurrent Transfer Learning (RTL), which is especially suitable for regression by neural network. The regression performance outperforms state-of-art neural network initialization methods. |
Persistent Identifier | http://hdl.handle.net/10722/283056 |
ISBN | |
ISI Accession Number ID |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, S | - |
dc.contributor.author | Xi, N | - |
dc.date.accessioned | 2020-06-05T06:24:26Z | - |
dc.date.available | 2020-06-05T06:24:26Z | - |
dc.date.issued | 2019 | - |
dc.identifier.citation | Proceedings of 2019 IEEE Sensors Conference, Montreal, QC, Canada, 27-30 October 2019, p. 1-4 | - |
dc.identifier.isbn | 9781728116358 | - |
dc.identifier.uri | http://hdl.handle.net/10722/283056 | - |
dc.description.abstract | This paper presents a novel human balance ability assessment device, called balance sensor, which uses the principle of Frustrated Total Internal Reflection (FTIR) to measure pressure distribution under human feet. Experiment is conducted to quantitatively calibrate the relationship between pressure and pixel value and physical model is established for this relationship. A special neural network is designed. The established physical model can be transferred into such neural network as initialization. Moreover, we invented a training paradigm called Recurrent Transfer Learning (RTL), which is especially suitable for regression by neural network. The regression performance outperforms state-of-art neural network initialization methods. | - |
dc.language | eng | - |
dc.publisher | IEEE. The Journal's web site is located at https://ieeexplore.ieee.org/xpl/conhome/1000662/all-proceedings | - |
dc.relation.ispartof | IEEE Sensors Conference | - |
dc.rights | IEEE Sensors Conference. Copyright © IEEE. | - |
dc.rights | ©2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. | - |
dc.subject | balance sensor | - |
dc.subject | FTIR | - |
dc.subject | calibration | - |
dc.subject | regression | - |
dc.subject | transfer learning | - |
dc.title | Recurrent Transfer Learning by Neural Network Regression for Human Balance Sensor Calibration | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Xi, N: xining@hku.hk | - |
dc.identifier.authority | Xi, N=rp02044 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1109/SENSORS43011.2019.8956907 | - |
dc.identifier.scopus | eid_2-s2.0-85078699009 | - |
dc.identifier.hkuros | 310077 | - |
dc.identifier.spage | 1 | - |
dc.identifier.epage | 4 | - |
dc.identifier.isi | WOS:000534184600411 | - |
dc.publisher.place | United States | - |