Wearable Wristworn Gesture Recognition Using Echo State Network

Wang, Weipeng; Liang, Xiangpeng; Assaad, Maher; Heidari, Hadi

doi:10.1109/icecs46596.2019.8965219

Cited by 11 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The project also investigated how twisting the wrist would impact the accuracy of gesture recognition. In previous study [9], the researchers trained a general classifier for a larger groups of people using sensor fusion technology. In this paper, we mainly focus on train a classifier for people whose samples were collected.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Smart Wristband for Gesture Recognition

Xia

Heidari

Ghannam

2020

2020 International Conference on UK-China Emerging Technologies (UCET)

Self Cite

View full text Add to dashboard Cite

This paper is concerned with developing a smart gesture recognition wristband device. In this paper, tendon movements around the wrist are used to distinguish and classify different hand gestures. These tendon movements are measured by FSR sensors. Polydimethylsiloxane (PDMS) was used to encapsulate the sensors, which made the wristband elastic and comfortable for people with different wrist dimensions. The sensor data was subsequently collected and sent to a computer via low energy Bluetooth technology. MATLAB was used to process and classify the data using ensemble subspace discriminant classifier. The accuracy is about 99.4%. The paper also investigated how twisting the wrist would impact the accuracy of gesture recognition. The result illustrated that wrist rotation could make more gestures distinguishable. Overall, the wristband is wearable, chargeable, portable and capable of recognizing over 6 gestures with a high degree of accuracy.

show abstract

Section: Discussionmentioning

confidence: 99%

“…According to previous research, the wrist dimensions of different people could be very different. Different dimensions of wrist could have different characteristic while gesturing [9]. Therefore, the wristband's material must have adequate flexibility that can obtain similar data despite the thickness of forearm difference.…”

Section: Wristband Assemblymentioning

confidence: 99%

Smart Wristband for Gesture Recognition

Xia

Heidari

Ghannam

2020

2020 International Conference on UK-China Emerging Technologies (UCET)

Self Cite

View full text Add to dashboard Cite

show abstract

“…The complex dynamic and nonlinear transformation in the reservoir would map the input data onto higher dimensional space for classification or prediction. With the internal feedback, the past neuron states can be preserved in the fading memory to affect the computation at the current state [29][30][31]. At each time step n, the states in a standard software-based reservoir are subjected to:…”

Section: B Delay-based Reservoir Computing For Ecg Processingmentioning

confidence: 99%

A Neuromorphic Model With Delay-Based Reservoir for Continuous Ventricular Heartbeat Detection

Liang¹,

Li²,

Vučković³

et al. 2022

IEEE Trans. Biomed. Eng.

Self Cite

View full text Add to dashboard Cite

“…The force myography (FMG) approach consists of placing force sensors on the limb surface and utilizing them for detecting the volumetric changes of the superficial muscle groups. It is also possible to detect the volumetric changes caused by the movement of tendons under the skin surface [ 93 , 94 ]. The method can provide information about the user’s intended motion and grip force.…”

Section: Approaches Proven For Prosthetic Controlmentioning

confidence: 99%

Control Methods for Transradial Prostheses Based on Remnant Muscle Activity and Its Relationship with Proprioceptive Feedback

Grushko

Spurný

Černý

2020

Sensors

View full text Add to dashboard Cite

The loss of a hand can significantly affect one’s work and social life. For many patients, an artificial limb can improve their mobility and ability to manage everyday activities, as well as provide the means to remain independent. This paper provides an extensive review of available biosensing methods to implement the control system for transradial prostheses based on the measured activity in remnant muscles. Covered techniques include electromyography, magnetomyography, electrical impedance tomography, capacitance sensing, near-infrared spectroscopy, sonomyography, optical myography, force myography, phonomyography, myokinetic control, and modern approaches to cineplasty. The paper also covers combinations of these approaches, which, in many cases, achieve better accuracy while mitigating the weaknesses of individual methods. The work is focused on the practical applicability of the approaches, and analyses present challenges associated with each technique along with their relationship with proprioceptive feedback, which is an important factor for intuitive control over the prosthetic device, especially for high dexterity prosthetic hands.

show abstract

Wearable Wristworn Gesture Recognition Using Echo State Network

Cited by 11 publications

References 18 publications

Smart Wristband for Gesture Recognition

Smart Wristband for Gesture Recognition

A Neuromorphic Model With Delay-Based Reservoir for Continuous Ventricular Heartbeat Detection

Control Methods for Transradial Prostheses Based on Remnant Muscle Activity and Its Relationship with Proprioceptive Feedback

Contact Info

Product

Resources

About