The DOI matches its Crossref record.
Capacitive Sensing Based On-board Hand Gesture Recognition with TinyML
Abstract
Although hand gesture recognition has been widely explored with sensing modalities like IMU, electromyography and camera, it is still a challenge of those modalities to provide a compact, power-efficient on-board inferencing solution. In this work, we present a capacitive-sensing wristband surrounded by four single-end electrodes for on-board hand gesture recognition. By deploying a single convolutional hidden layer as the classifier at the sensing edge, the wristband can recognize seven hand gestures from a single user with an accuracy of 96.4%.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The deployed on-board model in Bian and Lukowicz (2021) has only 29.6 KB size in float32 mode without quantization.
“Finally, the deployed on-board model has only 29.6 KB size in float32 mode without quantization.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Bian and Lukowicz, 2021
Bian and Lukowicz (2021) devise a wrist-worn embedded prototype with 4 capacitive sensing electrodes that uses only a hidden layer as classifier with an accuracy of 96.4%.
“This study devises a wrist-worn embedded prototype having 4 capacitive sensing electrodes.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Bian and Lukowicz, 2021
The Bian and Lukowicz (2021) design uses an ARM Cortex-M4 MCU with 1 MB flash and 256 KB RAM.
“The design uses an ARM Cortex-M4 MCU with 1 MB flash and 256 KB RAM.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Bian and Lukowicz, 2021
The Bian and Lukowicz (2021) inference time is 12 ms with 26.4 mW power consumption.
“The inference time is very less i.e., 12 ms with 26.4mW power consumption.”
From A review on TinyML: State-of-the-art and prospects (2022) · cites this paper as Bian and Lukowicz, 2021
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 4
- 10.1109/PERCOM.2019.8767393 · DOI
- Sizhen Bian , Vitor F Rey , Junaid Younas , and Paul Lukowicz . 2019 . Wrist-Worn Capacitive Sensor for Activity and Physical Collaboration Recognition. In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE , Kyoto, Japan, 261–266. https://doi.org/10.1109/PERCOMW. 2019.8730581 10.1109/PERCOMW.2019.8730581 Sizhen Bian, Vitor F Rey, Junaid Younas, and Paul Lukowicz. 2019. Wrist-Worn Capacitive Sensor for Activity and Physical Collaboration Recognition. In 2019 IEEE International Conference on Pervasive Computing and Communications Workshops (PerCom Workshops). IEEE, Kyoto, Japan, 261–266. https://doi.org/10.1109/PERCOMW.2019.8730581 · DOI
- 10.1109/ISWC.2001.962092 · DOI
- 10.1145/3274783.3274854 · DOI
Cited by
Sorted by citations
A review on TinyML: State-of-the-art and prospects
Ray, P. P. (2022) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.11.019 · Cited by 460
Metadata
- Authors
- Bian, S., & Lukowicz, P.
- Affiliations
- German Research Centre for Artificial Intelligence (DE)
- Venue
- Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers
- Publisher
- ACM
- Published
- 2021-09-21
- Pages
- 4-5
- OpenAlex
- W3202659011
- Cited by
- 37
- References
- 0
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 8 · 2023: 10 · 2022: 8
- FWCI
- 4.85
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Human-Computer Interaction › Hand Gesture Recognition Systems
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Physical Sciences › Engineering › Biomedical Engineering › Advanced Sensor and Energy Harvesting Materials
- Keywords
- hand gesture recognition, capacitive sensing, wristband, on-device inference, TinyML, edge computing, convolutional neural networks
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
