Upper Limb Motion Detection Using Deep Neural Network

Usama, Syed Ali; Kausar, Zareena; Sattar, Neelum Yousaf

doi:10.1109/icrai54018.2021.9651388

Cited by 1 publication

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs comprise several layers, including convolutional, pooling, and fully connected layers. A few fundamental equations that are commonly used in CNNs (Li et al, 2017 ; Syed et al, 2021 ) are given as:…”

Section: Methodsmentioning

confidence: 99%

“…Subject-wise accuracies are given in Figure 8. The LDA and k-NN accuracies are extracted from the published studies that match the same sample set (Sattar et al, 2021b(Sattar et al, , 2022Syed et al, 2021). Interestingly, the sEMG intentions for the wrist flexion/extension were weak, and hence fNIRS played a significant role in the inconsistency of the accuracy.…”

Section: Classification Accuracymentioning

confidence: 99%

“…It uses near-infrared light to detect changes in blood flow in the brain, which can be used to study brain function. The application of this technology to robotic systems has proven promising and attracted increased attention in the medical field (Syed et al, 2021 ). This technique provides a way to monitor brain activity that is both indirect and non-invasive.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Deep learning-based framework for real-time upper limb motion intention classification using combined bio-signals

Syed,

Sattar,

Ganiyu

et al. 2023

Front. Neurorobot.

View full text Add to dashboard Cite

This research study proposes a unique framework that takes input from a surface electromyogram (sEMG) and functional near-infrared spectroscopy (fNIRS) bio-signals. These signals are trained using convolutional neural networks (CNN). The framework entails a real-time neuro-machine interface to decode the human intention of upper limb motions. The bio-signals from the two modalities are recorded for eight movements simultaneously for prosthetic arm functions focusing on trans-humeral amputees. The fNIRS signals are acquired from the human motor cortex, while sEMG is recorded from the human bicep muscles. The selected classification and command generation features are the peak, minimum, and mean ΔHbO and ΔHbR values within a 2-s moving window. In the case of sEMG, wavelength, peak, and mean were extracted with a 150-ms moving window. It was found that this scheme generates eight motions with an enhanced average accuracy of 94.5%. The obtained results validate the adopted research methodology and potential for future real-time neural-machine interfaces to control prosthetic arms.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Classification Accuracymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation