Automatic EMG-based Hand Gesture Recognition System using Time-Domain Descriptors and Fully-Connected Neural Networks

Neacşu, Ana; Cioroiu, George; Rădoi, Anamaria; Burileanu, Corneliu

doi:10.1109/tsp.2019.8768831

Cited by 27 publications

(16 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Apart from the above methods, there are many other DL methods applied to sEMG pattern recognition. Because of the simplicity of the structure, fully connected neural networks (Neacsu et al, 2019 ), BP neural network, and artificial neural network (ANN) (Mane et al, 2015 ; Liu et al, 2017 ; Yang and Zhang, 2019 ; Zhang Z. et al, 2019 ) are also commonly used for offline and real-time identification of sEMG. Time delay neural network (TDNN) is an established neural network architecture for time series processing.…”

Section: Pattern Recognition-based Semgmentioning

confidence: 99%

Gesture Recognition Using Surface Electromyography and Deep Learning for Prostheses Hand: State-of-the-Art, Challenges, and Future

Shi

2021

Front. Neurosci.

102

View full text Add to dashboard Cite

Amputation of the upper limb brings heavy burden to amputees, reduces their quality of life, and limits their performance in activities of daily life. The realization of natural control for prosthetic hands is crucial to improving the quality of life of amputees. Surface electromyography (sEMG) signal is one of the most widely used biological signals for the prediction of upper limb motor intention, which is an essential element of the control systems of prosthetic hands. The conversion of sEMG signals into effective control signals often requires a lot of computational power and complex process. Existing commercial prosthetic hands can only provide natural control for very few active degrees of freedom. Deep learning (DL) has performed surprisingly well in the development of intelligent systems in recent years. The significant improvement of hardware equipment and the continuous emergence of large data sets of sEMG have also boosted the DL research in sEMG signal processing. DL can effectively improve the accuracy of sEMG pattern recognition and reduce the influence of interference factors. This paper analyzes the applicability and efficiency of DL in sEMG-based gesture recognition and reviews the key techniques of DL-based sEMG pattern recognition for the prosthetic hand, including signal acquisition, signal preprocessing, feature extraction, classification of patterns, post-processing, and performance evaluation. Finally, the current challenges and future prospects in clinical application of these techniques are outlined and discussed.

show abstract

Section: Pattern Recognition-based Semgmentioning

confidence: 99%

Gesture Recognition Using Surface Electromyography and Deep Learning for Prostheses Hand: State-of-the-Art, Challenges, and Future

Shi

2021

Front. Neurosci.

102

View full text Add to dashboard Cite

show abstract

“…For example, [16,50] employed inertial sensors that were embedded into a bracelet to recognize eating and smoking gestures while [15] integrated gyroscopes and accelerometers with a glove and utilized the glove to track subtle finger movements. Other scholars employed bracelets for fine-grained gesture recognition [5,18,61]. In [61], the Myo armband was placed on the forearm for gesture signal acquisition and duly processed and utilized as input for a fully connected network to recognize gestures.…”

Section: Gesture Recognition Technologymentioning

confidence: 99%

“…Wearable sensor-based approaches utilize inertial sensors, accelerometers, smartphones, tablets, and smartwatches for gesture recognition. In [61], the Myo armband was utilized for electromyographic (EMG) signal acquisition. A simple network structure of a fully connected neural network was employed to achieve seven specific gesture recognition.…”

Section: Introductionmentioning

confidence: 99%

RF-Eletter: A Cross-Domain English Letter Recognition System Based on RFID

Yang¹,

Liu

et al. 2021

IEEE Access

View full text Add to dashboard Cite

“…Several large companies, including Ottobock and Stepper, have made prosthetic devices that can be moved using bio-electrical signals (EMG), but the prices offered by these companies are very expensive, ranging from 250,000,000 to Rp. 750,000,000 [9] [10].…”

Section: Introductionmentioning

confidence: 99%

Hand Prosthetic Design for Transradial Amputee by Using 3D Printing Technology to Enhance Life Quality

Triwiyanto¹,

Hamzah²,

Luthfiyah³

et al. 2021

j.teknokes

View full text Add to dashboard Cite

The target for this community service program is a resident of Jl. Parikesit RT 05 RW 03 Dusun Picis, Balongdowo Village, Candi District, Sidoarjo Regency. He had a work accident in one of the industries in the city of Sidoarjo in 2010 on the left wrist up to the fingers, so the doctor suggested amputation. He is actually still in his productive age (36 years old) but because of this situation, he is unable to carry out activities in the world of work and has decreased confidence in himself and avoids socializing in society. The purpose of this community partnership program (PKM) activity is to apply 3d printing technology in the manufacture of prosthetic hands for people who have transradial amputations as an effort to improve the quality of life. The implementation methods used are: a) the measurement of several physical parameters on the amputee such as the diameter of the arm circumference, the length of the amputated part, weight and height. In addition to physical parameters, we also carry out medical measurements, including obtaining information on health conditions such as blood pressure, heart health and blood glucose levels, b) designing prosthetic hands using 3D application programs and 3D printers, c) mechanical and functional testing for perform basic movements in the form of opening and closing the palms, d) monitoring and evaluation of the use of prosthetic hands. The results obtained from this activity are that the patient can use the prosthetic hand to assist with activities in carrying out daily activities. In this PKM activity, amputees have been tested, namely the movement of holding a mineral water bottle, holding a banana, peeling a banana peel and driving a two-wheeled motorized vehicle. Monitoring shows that patients need regular exercise in using prosthetic hands so that they are able to control and condition their use. In the future, several developments can be made, including in terms of control and size of the prosthetic hand so that patients can feel the benefits of a prosthetic hand that functions like a normal hand.

show abstract

Automatic EMG-based Hand Gesture Recognition System using Time-Domain Descriptors and Fully-Connected Neural Networks

Cited by 27 publications

References 7 publications

Gesture Recognition Using Surface Electromyography and Deep Learning for Prostheses Hand: State-of-the-Art, Challenges, and Future

Gesture Recognition Using Surface Electromyography and Deep Learning for Prostheses Hand: State-of-the-Art, Challenges, and Future

RF-Eletter: A Cross-Domain English Letter Recognition System Based on RFID

Hand Prosthetic Design for Transradial Amputee by Using 3D Printing Technology to Enhance Life Quality

Contact Info

Product

Resources

About