TinyDL: Edge Computing and Deep Learning Based Real-time Hand Gesture Recognition Using Wearable Sensor
Abstract
Offloading data analysis to edge devices by decentralizing processing can be used to decrease bandwidth requirements, latency, and can decrease the total transmission time required in wireless devices. This can be especially useful for compact wearable devices used for health monitoring, human activity recognition, and gesture recognition, where sending raw data over wireless protocols such as Bluetooth can be both time and power consuming. By performing analysis on the wearable device, wireless radio usage can be greatly decreased, reducing a main power consumer on the device. Deep learning (DL) methods, specifically using Tensorflow (TF) and Keras were evaluated for their usage in such a case, in this example gesture recognition. A multilayer long short-term memory (LSTM) model was trained and evaluated off of data (10 gestures, 1000 trials total, balanced) from a finger-worn ring profile device that collected acceleration data, and was found to perform with accuracy from 75-95% per gesture. The attempted conversion of the model into a compressed TF Lite format, to allow for analysis on-device did not succeed, due to current incompatibilities between the different frameworks. Future work may improve the accuracy, and potentially expand the use of neural networks on wearables for health diagnostics or as input devices.
Integrity signals
Registry
Cites
Statistics
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 [30], they did not deploy an LSTM model on the device due to lack of support by TF Lite Micro.
“Unfortunately, they did not deploy an LSTM model on the device due to the lack of support for it by TF Lite Micro.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [30]
In [30], LSTM attained 93% accuracy in training, 83% validation accuracy, and 84.5% accuracy in final evaluation; Keras model did not perform well with 19% accuracy.
“The result showed that the Keras model did not perform well, with 19% accuracy, while LSTM attained 93% accuracy in the training phase, 83% validation accuracy, and 84.5% accuracy in the final evaluation.”
From TinyML: Enabling of Inference Deep Learning Models on Ultra-Low-Power IoT Edge Devices for AI Applications (2022) · cites this paper as [30]
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · see citing works
LSTM-CNN Architecture for Human Activity Recognition
Xia, K., Huang, J., & Wang, H. (2020) · IEEE Access · doi:10.1109/access.2020.2982225 · Cited by 851 · see citing works
A CNN-LSTM Approach to Human Activity Recognition
Mutegeki, R., & Han, D. S. (2020) · 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic48513.2020.9065078 · Cited by 452 · see citing works
TinyML-Enabled Frugal Smart Objects: Challenges and Opportunities
Sanchez-Iborra, R., & Skarmeta, A. F. (2020) · IEEE Circuits and Systems Magazine · doi:10.1109/mcas.2020.3005467 · Cited by 295 · see citing works
Edge Computing for the Internet of Things
Ren, J., Pan, Y. F., Goscinski, A. M., & Beyah, R. (2018) · IEEE Network · doi:10.1109/mnet.2018.8270624 · Cited by 83 · see citing works
SensoRing: An Integrated Wearable System for Continuous Measurement of Physiological Biomarkers
Mahmud, M. S., Wang, H., & Fang, H. (2018) · International Conference on Communications · doi:10.1109/icc.2018.8423001 · Cited by 24 · see citing works
Self-citationA Comparative Research on Human Activity Recognition Using Deep Learning
Tüfek, N., & Özkaya, Ö. (2019) · Signal Processing and Communications Applications Conference (SIU) · doi:10.1109/siu.2019.8806395 · Cited by 22 · see citing works
EmbML Tool: Supporting the use of Supervised Learning Algorithms in Low-Cost Embedded Systems
da Silva, L. T., Souza, V. M. A., & Batista, G. E. A. P. A. (2019) · Proceedings - International Conference on Tools with Artificial Intelligence, TAI · doi:10.1109/ictai.2019.00238 · Cited by 17 · see citing works
Real-time Wireless Health Monitoring: An Ultra-low Power Biosensor Ring for Heart Disease Monitoring
Coffen, B., Scott, P., & Mahmud, M. S. (2020) · 2012 International Conference on Computing, Networking and Communications (ICNC) · doi:10.1109/icnc47757.2020.9049814 · Cited by 9 · see citing works
Self-citationResearch on a novel strategy for automatic activity recognition using wearable device
Wei, Z., & Bao, T. (2016) · IEEE International Conference on Communication Software and Networks · doi:10.1109/iccsn.2016.7587207 · Cited by 6 · see citing works
A Wearable Internet of Things Based System with Edge Computing for Real-Time Human Activity Tracking
Cooney, N. J., Joshi, K. P., & Minhas, A. S. (2018) · Asia-Pacific World Congress on Computer Science and Engineering (APWC on CSE) · doi:10.1109/apwconcse.2018.00013 · Cited by 5 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Alajlan, N. N., & Ibrahim, D. M. (2022) · Micromachines · doi:10.3390/mi13060851 · Cited by 224 · see citing works
“Physiological/ Behavioral Metrics Heart dataset [53] Hand gesture recorded ((Forward, Backward, Select and Abort) using fingers created by authors [30]”
BackgroundMethodInfluentialLamaakal, I., Ouahbi, I., El Makkaoui, K., Maleh, Y., Pławiak, P., & Alblehai, F. (2024) · IEEE Access · doi:10.1109/access.2024.3406631 · Cited by 34 · see citing works
TinyML in Africa: Opportunities and Challenges
Ooko, S. O., Muyonga Ogore, M., Nsenga, J., & Zennaro, M. (2021) · 2021 IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps52748.2021.9682107 · Cited by 29 · see citing works
- Authors
- Coffen, B., & Mahmud, M. S.
- Affiliations
- University of New Hampshire (US)
- ORCID
- Mahmud, Md.Shaad
- Venue
- 2020 IEEE International Conference on E-health Networking, Application & Services (HEALTHCOM)
- Publisher
- IEEE
- Published
- 2021-03-01
- Pages
- 1-6
- OpenAlex
- W3158406784
- Cited by
- 44
- References
- 11
- Citations by year
- 2026: 3 · 2025: 8 · 2024: 10 · 2023: 9 · 2022: 12 · 2021: 2
- FWCI
- 6.17
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE International Conference on e-Health Networking, Applications and Services (Healthcom) (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 › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Keywords
- hand gesture recognition, wearable sensors, edge computing, on-device deep learning, LSTM, TensorFlow Lite, model compression, accelerometer data, health monitoring, human activity recognition
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
