Analysis of Contraction Effort Level in EMG-Based Gesture Recognition Using Hyperdimensional Computing

Moin, Ali; Zhou, Andy; Benatti, Simone; Rahimi, Abbas; Benini, Luca; Rabaey, Jan M.

doi:10.1109/biocas.2019.8919214

Cited by 13 publications

(9 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The density of the electrodes is limited by the obvious physical constraint on the head, arm, or face. However for some applications, like precise gesture recognition, it is better to have dense electrode arrays over certain muscles [157].…”

Section: Exg Hardware Challengesmentioning

confidence: 99%

“…sEMG is mostly used for natural dexterous control of prosthetic devices [196]. The grand challenge of sEMG-based gesture recognition is to increase the number and precision of recognized hand postures to reflect the real sensorimotor interaction with the physical world (for example, 21 classified hand gestures by utilizing a compact mobile high-density EMG grid in Reference [157]). Similarly, control of robotic devices is achieved with multi-modal ExG interfaces: Zhang et al [225] combined EOG, EEG, and EMG to operate a robotic soft hand; Tayeb et al [205] manipulated robotic hand simultaneously with sEMG and 2-label MI.…”

Section: Exg-based Applications In the Context Of Xrmentioning

confidence: 99%

See 1 more Smart Citation

Emerging ExG-based NUI Inputs in Extended Realities: A Bottom-up Survey

Shatilov

Chatzopoulos

Lee

et al. 2021

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

Incremental and quantitative improvements of two-way interactions with e x tended realities (XR) are contributing toward a qualitative leap into a state of XR ecosystems being efficient, user-friendly, and widely adopted. However, there are multiple barriers on the way toward the omnipresence of XR; among them are the following: computational and power limitations of portable hardware, social acceptance of novel interaction protocols, and usability and efficiency of interfaces. In this article, we overview and analyse novel natural user interfaces based on sensing electrical bio-signals that can be leveraged to tackle the challenges of XR input interactions. Electroencephalography-based brain-machine interfaces that enable thought-only hands-free interaction, myoelectric input methods that track body gestures employing electromyography, and gaze-tracking electrooculography input interfaces are the examples of electrical bio-signal sensing technologies united under a collective concept of ExG. ExG signal acquisition modalities provide a way to interact with computing systems using natural intuitive actions enriching interactions with XR. This survey will provide a bottom-up overview starting from (i) underlying biological aspects and signal acquisition techniques, (ii) ExG hardware solutions, (iii) ExG-enabled applications, (iv) discussion on social acceptance of such applications and technologies, as well as (v) research challenges, application directions, and open problems; evidencing the benefits that ExG-based Natural User Interfaces inputs can introduce to the area of XR.

show abstract

Section: Exg Hardware Challengesmentioning

confidence: 99%

Section: Exg-based Applications In the Context Of Xrmentioning

confidence: 99%

Emerging ExG-based NUI Inputs in Extended Realities: A Bottom-up Survey

Shatilov

Chatzopoulos

Lee

et al. 2021

ACM Trans. Interact. Intell. Syst.

View full text Add to dashboard Cite

show abstract

“…The most commonly explored way to improve gesture recognition in multiple contexts is to augment training routines with a wider range of contexts outside of perfect laboratory conditions. Works have used training sets consisting of multiple limb positions [11,19,28], as well as other types of variations including temporal variation [19] and contraction effort level [20]. Because this significantly increases initial training effort, it is beneficial to move to a continuous learning framework for gradually incorporating new contexts.…”

Section: Related Workmentioning

confidence: 99%

“…Class prototypes are calculated by superimposing all training examples from a particular class through element-wise majority, and similarity between prototypes and a query HV is measured using Hamming distance. A minimum of one prototype per output class is required, although it is also possible to store multiple different prototypes representing same class [20]. We would like to minimize the size of this AM to reduce both memory footprint and cycles of operation for similarity metric calculations.…”

Section: Classificationmentioning

confidence: 99%

Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing

Zhou,

Muller,

Rabaey

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Electromyogram (EMG) pattern recognition can be used to classify hand gestures and movements for human-machine interface and prosthetics applications, but it often faces reliability issues resulting from limb position change. One method to address this is dual-stage classification, in which the limb position is first determined using additional sensors to select between multiple position-specific gesture classifiers. While improving performance, this also increases model complexity and memory footprint, making a dual-stage classifier difficult to implement in a wearable device with limited resources. In this paper, we present sensor fusion of accelerometer and EMG signals using a hyperdimensional computing model to emulate dualstage classification in a memory-efficient way. We demonstrate two methods of encoding accelerometer features to act as keys for retrieval of position-specific parameters from multiple models stored in superposition. Through validation on a dataset of 13 gestures in 8 limb positions, we obtain a classification accuracy of up to 93.34%, an improvement of 17.79% over using a model trained solely on EMG. We achieve this while only marginally increasing memory footprint over a single limb position model, requiring 8× less memory than a traditional dual-stage classification architecture.

show abstract

“…Recognizing multiple gestures is a challenge as the recognition accuracy decreases with the increase in the number of gestures. Table 1 summarizes examples of previous literature attempting to recognize several gestures [10,[14][15][16][17][18][19][20][21][22][23][24][25].…”

Section: Int J Elec and Compmentioning

confidence: 99%

Recognition of additional myo armband gestures for myoelectric prosthetic applications

Hussain

Al-Khazzar

Raheema

2020

IJECE

View full text Add to dashboard Cite

Myoelectric prostheses are a viable solution for people with amputations. The challenge in implementing a usable myoelectric prosthesis lies in accurately recognizing different hand gestures. The current myoelectric devices usually implement very few hand gestures. In order to approximate a real hand functionality, a myoelectric prosthesis should implement a large number of hand and ﬁnger gestures. However, increasing number of gestures can lead to a decrease in recognition accuracy. In this work a Myo arm band device is used to recognize fourteen gestures (ﬁve build in gestures of Myo armband in addition to nine new gestures). The data in this research is collected from three body-able subjects for a period of 7 seconds per gesture. The proposed method uses a pattern recognition technique based on Multi-Layer Perceptron Neural Network (MLPNN). The results show an average accuracy of 90.5% in recognizing the proposed fourteen gestures.

show abstract

Analysis of Contraction Effort Level in EMG-Based Gesture Recognition Using Hyperdimensional Computing

Cited by 13 publications

References 9 publications

Emerging ExG-based NUI Inputs in Extended Realities: A Bottom-up Survey

Emerging ExG-based NUI Inputs in Extended Realities: A Bottom-up Survey

Memory-Efficient, Limb Position-Aware Hand Gesture Recognition using Hyperdimensional Computing

Recognition of additional myo armband gestures for myoelectric prosthetic applications

Contact Info

Product

Resources

About