An efficient static gesture recognizer embedded system based on ELM pattern recognition algorithm

Cambuim, Lucas F. S.; Macieira, Rafael M.; Neto, Fernando M. de Paula; Barros, Edna; Ludermir, Teresa B.; Zanchettin, Cleber

doi:10.1016/j.sysarc.2016.06.002

Cited by 11 publications

(9 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By designing different algorithms, the static and dynamic motion states of the fingers can be collected. At the same time, the application of data gloves in rehabilitation training is discussed [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Design and Manufacture of Data Gloves for Rehabilitation Training and Gesture Recognition Based on Flexible Sensors

Guo

Zhang

Zhao

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

This work takes the production and usage scenarios of the data glove as the research object and studies the method of applying the flexible sensor to the data glove. Many studies are also devoted to exploring the transplantation of flexible sensors to data gloves. However, this type of research still lacks the display of specific application scenarios such as gesture recognition or hand rehabilitation training. A small amount of experimental data and theoretical analysis are difficult to promote the development of flexible sensors and flexible data gloves design schemes. Therefore, this study uses the self-made flexible sensor of the research group as the core sensing unit to produce a flexible data glove to monitor the bending changes of the knuckles and then use it for simple gesture recognition and rehabilitation training.

show abstract

Section: Introductionmentioning

confidence: 99%

Design and Manufacture of Data Gloves for Rehabilitation Training and Gesture Recognition Based on Flexible Sensors

Guo

Zhang

Zhao

et al. 2021

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…where u = (x,y,z) is the position of the object, φ(u) is the potentials distribution, φ ext (u) is the potentials distribution on the surface of the domain, I(u) is the alternating current pattern, σ(u) is the electrical conductivity distribution, that is, the image of interest, Ω is the domain, ∂Ω is the edge, and n(u) is the normal vector to the edge (Cambuim et al 2016;Cruz et al 2018;de Freitas et al 2019;He et al 2016).…”

Section: Electrical Impedance Tomography Problems and Reconstructionmentioning

confidence: 99%

“…ELMs have also been used in many situations with remarkably results. Examples of their applicabilities can be seen in several areas, such as image recognition (Azevedo et al 2015;Cordeiro et al 2012;de Lima et al 2014;de Lima et al 2016;de Santana et al 2018;dos Santos et al 2019;Lu et al 2014), fuzzy nonlinear regression (Goel et al 2017;He et al 2016), embedded systems (Azad et al 2017;Cambuim et al 2016;de Freitas et al 2019), and biology and bioinformatics on protein folding (Wang et al 2014). ELMs have also other features that make them suitable, especially for real-time applications, such as high learning speed, great generalization capabilities, high accuracy during the training phase, and the smallest norm of the weights (Huang et al 2004).…”

Section: Extreme Learning Machinesmentioning

confidence: 99%

Electrical impedance tomography image reconstruction based on backprojection and extreme learning machines

et al. 2020

View full text Add to dashboard Cite

Purpose Electrical impedance tomography (EIT) is an image technique based on the application of an alternating electrical current on electrodes placed on the surface of the domain, which are also responsible for measuring the resulting electrical potentials. EIT main advantages are portability, low cost, and nonuse of ionizing radiation. EIT image reconstruction depends on the resolution of the direct and inverse problems, which is nonlinear and ill-posed. Several reconstruction methods have been used to solve EIT inverse problem, from Newton-based methods to bio-and social-inspired metaheuristics. Method In this work, we propose a new approach: the use of random-weighted neural networks, specifically extreme learning machines (ELM), to approximate sinograms from electrical potential data and, therefore, use the classical backprojection algorithm for image reconstruction. We generated a database of 4000 synthetic 128 × 128 images. We trained 16 ELMs corresponding to a 16-electrode EIT system placed on a circular domain. Results Results were evaluated according to peak-to-noise ratio (PSNR) and Structural Similarity Index (SSIM), as well as visual inspection. Results are fair and similar to image reconstructions obtained by the direct application of the backprojection algorithm, in case this reconstruction problem would be a classic tomographic reconstruction. Conclusion Our work suggested the use of ELMs to create sinograms from the electrical potential data of the studied domain. Sinograms could be easily reconstructed by the backprojection technique for final image generation, where objects and domain are represented. Finally, we were able to reduce the time of EIT reconstruction, mainly due to the high speed of the ELMs, and obtain reasonable and consistent images.

show abstract

“…ELMs have also been used in many situations with remarkable results. Examples of their applications can be seen in several areas, such as image recognition [36][37][38][39][40][41][42], fuzzy nonlinear regression [43,44], embedded systems [45][46][47], biology and bioinformatics on protein folding [48]. ELMs have also other features that make them suitable, especially for real-time applications, such as high learning speed; great generalization capabilities; high accuracy during the training phase and the smallest norm of the weights [25].…”

Section: Introductionmentioning

confidence: 99%

Gauss–Seidel Extreme Learning Machines

et al. 2020

View full text Add to dashboard Cite

Extreme learning machines (ELM) were created to simplify the training phase of single-layer feedforward neural networks, where the input weights are randomly set and the only parameter is the number of neurons in the hidden layer. These networks are also known for one-shot training using Moore-Penrose pseudo-inverse. In this work, we propose Gauss-Seidel extreme learning machine (GS-ELM), an ELM based on Gauss-Seidel iterative method to solve linear equation systems. We performed tests considering databases with different characteristics and analysed its discrimination capabilities and memory consumption in comparison to the canonical ELM and the online sequential ELM. GS-ELM presented similar discrimination capabilities, but consuming significantly less memory, turning possible its application in low-memory systems and embedded solutions. Keywords Unorganized neural networks • Extreme learning machines • Random vector functional link networks • Numerical methods • Fast training neural networks * Wellington P. dos Santos

show abstract

An efficient static gesture recognizer embedded system based on ELM pattern recognition algorithm

Cited by 11 publications

References 21 publications

Design and Manufacture of Data Gloves for Rehabilitation Training and Gesture Recognition Based on Flexible Sensors

Design and Manufacture of Data Gloves for Rehabilitation Training and Gesture Recognition Based on Flexible Sensors

Electrical impedance tomography image reconstruction based on backprojection and extreme learning machines

Gauss–Seidel Extreme Learning Machines

Contact Info

Product

Resources

About