Low‐Cost Data Glove Based on Deep‐Learning‐Enhanced Flexible Multiwalled Carbon Nanotube Sensors for Real‐Time Gesture Recognition
Open Access
- 2 October 2022
- journal article
- research article
- Published by Wiley in Advanced Intelligent Systems
- Vol. 4 (11)
Abstract
With advancements in artificial intelligence, wearable motion recognition systems based on flexible nanomaterial sensors exhibit excellent potential for harmonious human–machine interaction. However, the sensing stability and demand of large‐scale arrays limit the application of flexible nanomaterial sensors. Herein, a data glove system based on simple multiwalled carbon nanotube (MWCNT) sensors and a lightweight deep‐learning algorithm to achieve accurate gesture recognition is proposed. A regional‐crack mechanism is introduced through the microspine structure to enhance the strain sensitivity. Moreover, an efficient signal processing strategy based on an adaptive wavelet threshold function to improve the robustness and anti‐interference of signals obtained from MWCNT sensors, which exhibit strong generalization and can be used in other nanomaterial strain sensor. Based on the depth‐wise separable convolution, a novel hybrid convolutional neural network (CNN) long short‐term memory (LSTM) model for gesture recognition is constructed. The proposed model achieves an average accuracy of 97.5% and recognition accuracy of 30 gestures with an average recognition time of 2.173 ms based on only five sensors. The fabricated data glove is a promising platform for low‐cost and wearable human–machine interaction that can be directly interfaced in applications such as robotic hands, smart cars, and first‐person shooting games.Keywords
Funding Information
- National Natural Science Foundation of China (61574086)
This publication has 54 references indexed in Scilit:
- Pneumatic actuator and flexible piezoelectric sensor for soft virtual reality glove systemScientific Reports, 2019
- Significant Stretchability Enhancement of a Crack-Based Strain Sensor Combined with High Sensitivity and Superior Durability for Motion MonitoringACS Applied Materials & Interfaces, 2019
- Realizing the potential of dielectric elastomer artificial musclesProceedings of the National Academy of Sciences, 2019
- Deep Full-Body Motion Network for a Soft Wearable Motion Sensing SuitIEEE/ASME Transactions on Mechatronics, 2018
- Robust hand gesture recognition with a double channel surface EMG wearable armband and SVM classifierBiomedical Signal Processing and Control, 2018
- A highly flexible and sensitive piezoresistive sensor based on MXene with greatly changed interlayer distancesNature Communications, 2017
- Stretchable, Skin‐Mountable, and Wearable Strain Sensors and Their Potential Applications: A ReviewAdvanced Functional Materials, 2016
- Reduction in the Number of Averages Required in BOTDA Sensors Using Wavelet Denoising TechniquesJournal of Lightwave Technology, 2011
- De-noising by soft-thresholdingIEEE Transactions on Information Theory, 1995
- Parametric control of oscillations and rotations of a compound pendulum (a swing)Journal of Applied Mathematics and Mechanics, 1993