Search

Your search keyword '"Tapia, Juan A."' showing total 1,234 results
Start Over Author "Tapia, Juan A."

Refine your results

more »

more »

more »

more »
1,234 results on '"Tapia, Juan A."'

656. A novel Capsule Neural Network based model for drowsiness detection using electroencephalography signals.

Author

Guarda, Luis, Tapia, Juan E., Droguett, Enrique López, and Ramos, Marcelo

Subjects
*CAPSULE neural networks, *ARTIFICIAL neural networks, *DROWSINESS, *CONVOLUTIONAL neural networks, *DEEP learning, *BIOMEDICAL signal processing
Abstract

The early detection of drowsiness has become vital to ensure the correct and safe development of several industries' tasks. Due to the transient mental state of a human subject between alertness and drowsiness, automated drowsiness detection is a complex problem to tackle. The electroencephalography signals allow us to record variations in an individual's brain's electrical potential, where each of them gives specific information about a subject's mental state. However, due to this type of signal's nature, its acquisition, in general, is complex, so it is hard to have a large volume of data to apply techniques of Deep Learning for processing and classification optimally. Nevertheless, Capsule Neural Networks are a brand-new Deep Learning algorithm proposed for work with reduced amounts of data. It is a robust algorithm to handle the data's hierarchical relationships, which is an essential characteristic for work with biomedical signals. Therefore, this paper presents a Deep Learning-based method for drowsiness detection with CapsNet by using a concatenation of spectrogram images of the electroencephalography signals channels. The proposed CapsNet model is compared with a Convolutional Neural Network, which is outperformed by the proposed model, which obtains an average accuracy of 86,44 % and 87,57% of sensitivity against an average accuracy of 75,86% and 79,47% sensitivity for the CNN, showing that CapsNet is more suitable for this kind of datasets and tasks. • A Capsule Network for drowsiness detection method is proposed. • The system is based on spectrogram images concatenate information from Fz and Pz. • The traditional drowsiness detection methods need a big number of data. • The proposed method improves the results even with a small number of images. • The proposed method outperforms state of the art in comparison with CNN and ML. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

688. Similar synapse elimination motifs at successive relays in the same efferent pathway during development in mice

Author

Sheu, Shu-Hsien, Tapia, Juan Carlos, Tsuriel, Shlomo, and Lichtman, Jeff W

Subjects
synapse elimination, peripheral ganglia, synaptic competition, parasympathetic nerves, Mouse
Abstract

In many parts of the nervous system, signals pass across multiple synaptic relays on their way to a destination, but little is known about how these relays form and the function they serve. To get some insight into this question we ask how the connectivity patterns are organized at two successive synaptic relays in a simple, cholinergic efferent pathway. We found that the organization at successive relays in the parasympathetic nervous system strongly resemble each other despite the different embryological origin and physiological properties of the pre- and postsynaptic cells. Additionally, we found a similar developmental synaptic pruning and elaboration strategy is used at both sites to generate their adult organizations. The striking parallels in adult innervation and developmental mechanisms at the relays argue that a general strategy is in operation. We discuss why from a functional standpoint this structural organization may amplify central signals while at the same time maintaining positional targeting. DOI: http://dx.doi.org/10.7554/eLife.23193.001

Published
2017
Full Text
View/download PDF

692. High Performance Parallel Programming of a GA Using Multi-core Technology.

Author

Serrano, Rogelio, Tapia, Juan, Montiel, Oscar, Sepúlveda, Roberto, and Melin, Patricia

Abstract

Multi-core computers give the opportunity to solve high-performance applications more efficiently by using parallel computing. In this way, it is possible to achieve the same results in less time compared to the non-parallel version. Since computers continue to grow on the number of cores, we need to make our parallel applications scalable. This paper shows how a Genetic Algorithm (GA) in a non-parallel version takes long time to solve an optimization problem; in comparison, using multi-core parallel computing the processing time can be reduced significantly as the number of cores grows. The tests were made on a quad-core computer; a comparison of the speeding up in relation to the number of cores is shown. [ABSTRACT FROM AUTHOR]

Published
2008
Full Text
View/download PDF

693. Scalability Potential of Multi-core Architecture in a Neuro-Fuzzy System.

Author

Cárdenas, Martha, Tapia, Juan, Sepúlveda, Roberto, Montiel, Oscar, and Melín, Patricia

Abstract

Parallelism in hardware and software is necessary to solve aplications that require high processing. Parallel computers provide great amounts of computing power, the multi-core technology will be designed to increase performance and minimize heat. This paper shows the performance improvements with multi-core architecture and parallel programming applied in a Multiple Adaptive Neuro-Fuzzy Inference System, obtaining with this a significantly reduction of the processing time. In addition, it shows the comparison between the non-parallel and parallel implementation and the results obtained. [ABSTRACT FROM AUTHOR]

Published
2008
Full Text
View/download PDF

696. Activation of CO2on Ni/La2O3: non-isothermal kinetic study on the basis of thermogravimetric studies

Author

Gallego, Jaime, Sierra-Gallego, German, Tapia, Juan, Mondragón, Fanor, and Batiot-Dupeyrat, Catherine

Abstract

The thermo-catalytic CO2activation was studied over supported nickel catalyst (Ni/La2O3) obtained by reduction of the perovskite LaNiO3. At temperatures lower than 700 °C, a superficial CO2activation over the catalyst was observed and a partial structural change of the support to lanthanum oxycarbonate was determined by in situ XRD. The oxycarbonate species decomposed at around 750 °C, regenerating the original support La2O3and producing CO2(determined by TGA–MS). Above 750 °C, CO2consumption accompanied by CO production and a weight increase were observed by TGA–MS. These observations suggest the oxidation of metallic nickel to NiO. The oxidation process finished at around 1180 °C, the phases obtained were NiO/La2NiO4. The mechanism of oxidized species formation was proposed according to the kinetic parameters obtained by TGA–MS under CO2atmosphere. Activation energies and pre-exponential factors were calculated for the different steps of the mechanism proposed. Additionally, a kinetic compensation effect was observed for the activation of CO2on NiO/La2O3catalyst. This compensation effect exhibited a slope change at around 850 °C, which suggested a modification of the mechanism at this temperature.

Published
2016
Full Text
View/download PDF

700. Medical image segmentation with deformable models on graphics processing units.

Author

Alvarado, Rigo, Tapia, Juan, and Rolón, Julio

Subjects
*GRAPHICS processing units, *VECTOR analysis, *EVOLUTION equations, *LINEAR systems, *STANDARD deviations
Abstract

In this work, the parallel implementation of a segmentation algorithm based on the gradient vector flow (GVF) deformable model in a graphics processing unit (GPU) is presented. The proposed implementation focuses on the parallelization of the computation of the GVF field. In order to make a performance comparison of the proposed GPU algorithm, an OpenMP-based implementation is presented too. We also present an analysis of the textures and global memory performance in the computing of the GVF field. To improve the efficiency and the performance of the active contour segmentation, a novel snaxel reallocation method is proposed. The main advantage of the reallocation process is the small linear system needed to perform the segmentation and its low computational load. To assure the convergence of the active contour deformation, we propose a stopping criterion based on the root mean square error for the iterative solution of the evolution equations. [ABSTRACT FROM AUTHOR]

Published
2014
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results