The DOI matches its Crossref record.
A Smart Chair Sitting Posture Recognition System Using Flex Sensors and FPGA Implemented Artificial Neural Network
Abstract
Sitting is the most common status of modern human beings. Some sitting postures may bring health issues. To prevent the harm from bad sitting postures, a local sitting posture recognition system is desired with low power consumption and low computing overhead. The system should also provide good user experience with accuracy and privacy. This paper reports a novel posture recognition system on an office chair that can categorize seven different health-related sitting postures. The system uses six flex sensors, an Analog to Digital Converter (ADC) board and a Machine Learning algorithm of a two-layer Artificial Neural Network (ANN) implemented on a Spartan-6 Field Programmable Gate Array (FPGA). The system achieves 97.78% accuracy with a floating-point evaluation and 97.43% accuracy with the 9-bit fixed-point implementation. The ADC control logic and the ANN are constructed with a maximum propagation delay of 8.714 ns. The dynamic power consumption is 7.35 mW when the sampling rate is 5 Sample/second with the clock frequency of 5 MHz.
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?
In the citing paper
“Next, flex sensors with a FPGA implemented artificial neural network (ANN) are applied to a smart chair sitting posture recognition system.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“The flex sensor that is used in the application is FS-L-0055253-ST from Spectra Symbol with flat resistance of 25 k Ohm and bending resistance that can vary from 45 k to 125 k Ohms.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“Atwo-layer artificial neural network (ANN) is implemented as the classifier which categorizes seven different health-related sitting postures.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“The best combination of the algorithm in the application with 10-fold cross-validation is using two layers of ANN and 28 nodes in the hidden layer.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“The processing system has dynamic power consumption of 7.35 mW and a propagation delay of 8.714 ns, when the clock frequency and sampling rate are 5 Mhz and 5 sample/second respectively.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“A low power consumption system is successfully designed and implemented with good accuracy by using a 9-bit fixed point model [65].”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
In the citing paper
“The floating-point model achieved an accuracy of 97.78%, while the fixed-point model achieved an accuracy of 97.43%.”
From Embedded Intelligence on FPGA: Survey, Applications and Challenges (2021) · cites this paper as [65]
Citations
Cites
No references could be resolved yet.
Research works printed but not linked: 38
- 10.1109/ACCESS.2019.2900084 · DOI
- 10.1109/TVLSI.2012.2232321 · DOI
- 10.1109/ISCAS.2009.5118213 · DOI
- 10.1109/ICCTIM.2015.7224608 · DOI
- 10.1109/JSEN.2009.2037330 · DOI
- 10.1109/JBHI.2016.2549938 · DOI
- 10.1589/jpts.28.355 · DOI
- 2014, Common Posture Mistakes and Fixes
- holicky, 2014, Healing the Crooked Spine Solving Posture Problems
- 10.1080/00140139108967338 · DOI
- 10.1097/00007632-199601010-00015 · DOI
- 10.1179/jmt.1995.3.3.91 · DOI
- 10.1016/S0897-1897(99)80045-7 · DOI
- 10.1016/j.math.2004.07.002 · DOI
- 10.1109/TBCAS.2017.2731797 · DOI
- 10.1109/TBCAS.2018.2823275 · DOI
- 10.1109/TBCAS.2009.2031603 · DOI
- 10.1109/LMWC.2017.2678438 · DOI
- hu, 2015, Asynchronous communication for wireless sensors using ultra wideband impulse radio, Proc IEEE 58th Int Midwest Symp Circuits Syst (MWSCAS), 1
- 10.1109/THMS.2014.2325871 · DOI
- castaneda, 2018, 10 Ways Poor Posture Can Harm Your Health
- 10.1053/apmr.2003.50087 · DOI
- 10.1016/j.math.2010.06.005 · DOI
- 10.1016/0268-0033(92)90007-Q · DOI
- 10.1109/3516.951364 · DOI
- 10.4278/ajhp.25.4.exi · DOI
- 10.1016/j.spinee.2004.07.036 · DOI
- tattersall, 2003, Posture and cystic fibrosis, J Roy Soc Med, 96, 18
- 10.1111/j.1746-1561.2007.00182.x · DOI
- 10.1016/0003-6870(77)90002-3 · DOI
- 10.1016/j.math.2009.06.002 · DOI
- 10.1109/TCSII.2016.2601062 · DOI
- 10.1109/HNICEM.2017.8269473 · DOI
- 10.1109/JSEN.2014.2370945 · DOI · Paper page
- 10.3390/s18093119 · DOI
- 10.1109/ITNEC.2017.8284904 · DOI
- 10.1007/s00586-008-0586-0 · DOI
- 10.1109/CIBCB.2016.7758131 · DOI
Cited by
Sorted by citations
Toward an AI Era: Advances in Electronic Skins
Fu, X., Cheng, W., Wan, G., Yang, Z., & Tee, B. C. K. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.4c00049 · Cited by 172
Embedded Intelligence on FPGA: Survey, Applications and Challenges
Seng, K. P., Lee, P. J., & Ang, L. M. (2021) · Electronics · doi:10.3390/electronics10080895 · Cited by 105
“A FPGA with machine learning algorithm is then used to process the digital signal [65].”
MethodInfluentialA Review of Embedded Machine Learning Based on Hardware, Application, and Sensing Scheme
Biglari, A., & Tang, W. (2023) · Sensors · doi:10.3390/s23042131 · Cited by 86
Self-citationLiu, Q., Wu, X., Jiang, Y., Liu, X., Zhang, Y., Xu, X., & Qi, L. (2021) · International Journal of Intelligent Systems · doi:10.1002/int.22383 · Cited by 16
Metadata
- Authors
- Hu, Q., Tang, X., & Tang, W.
- Affiliations
- New Mexico State University (US)
- Venue
- IEEE Sensors Journal
- Published
- 2020-07-15
- Volume
- 20
- Issue
- 14
- Pages
- 8007-8016
- ISSN
- 1530-437X (ISSN-L)
- 1558-1748
- 2379-9153
- OpenAlex
- W3011842163
- Cited by
- 94
- References
- 0
- Citations by year
- 2026: 14 · 2025: 9 · 2024: 24 · 2023: 20 · 2022: 15 · 2021: 11 · 2020: 1
- FWCI
- 4.56
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Sensors Journal (publishedVersion)
- Funders
- United States National Science Foundation (ECCS-1652944)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Context-Aware Activity Recognition Systems
- Social Sciences › Human Factors and Ergonomics › Ergonomics and Musculoskeletal Disorders
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Embedded Systems and FPGA Applications
- Keywords
- sitting posture recognition, office chairs, flex sensors, FPGA implementation, artificial neural networks, fixed-point arithmetic, low-power embedded systems, health monitoring, posture recognition, propagation delay
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
