Browsing by Autor "Guillermo Sahonero-Alvarez"

Now showing 1 - 13 of 13

A 3D Convolution Accelerator Implemented on FPGA Using SDSoC
(2019) Jhon Ordoñez; Guillermo Sahonero-Alvarez
Convolutional Neural Networks (CNNs) have become a popular and useful deep learning algorithm. However, the requirements of computation have also increased. As implementation of CNNs in Embedded Systems or Cyber-Physical Systems (CPS) is required, the need of efficient technologies of computation like FPGAs arise substantially. In this paper, we present a 3D convolution accelerator implemented on a Xilinx ZCU102 FPGA board. It achieves 32.08 GOP/s of performance and an efficiency of 3.58 GOP/s per Watt. This accelerator has been developed in Xilinx SDSoC environment.
A functional BCI model by the P2731 working group: control interface
(Taylor & Francis, 2021) Chuck Easttom; Luigi Bianchi; Davide Valeriani; Chang S. Nam; Ali A. Hossaini; Dariusz Zapała; Avid Roman–Gonzalez; Avinash Kumar Singh; Alberto Antonietti; Guillermo Sahonero-Alvarez
In order to facilitate communication and collaboration between researchers, Brain–computer interfaces (BCI) require a generally applicable functional model as well as a common vocabulary. The IEEE P2731 working group is in the process of developing such a functional model and a lexicon of BCI terminology. Such a functional model has multiple aspects including the control interface, physiology, transducers, etc. This current paper focuses on the control interface aspects of that model. Having a generally applicable control interface model will facilitate interdisciplinar y research and communication. The control interface is a critical part of the functional model and is described in this current paper. The control interface presented intentionally is intentionally kept general in order to be widely applicable. Some details are specific to a particular application and are thus left to those applications. It does contain the encoder (which also contains a decoder), with a feedback submodule.
A functional BCI model by the P2731 working group: psychology
(Taylor & Francis, 2021) Dariusz Zapała; Ali A. Hossaini; Mazaher Kianpour; Guillermo Sahonero-Alvarez; Aladdin Ayesh
The development of Brain-Computer Interfaces (BCI) gathers experts and specialists in various fields, such as engineering, computer science, medicine, or cognitive neuroscience. Each of these disciplines has specific terminology, which makes mutual understanding and research collaboration difficult. The IEEE P2731 working group aims to improve communication between BCI researchers by developing a functional model and standards for terminology that can be used as a common description framework for all the involved knowledge fields. This work focuses on the vocabulary of mental processes involved in BCI communication and describes their role in a Functional Model that considers their influence on BCI performance. Finally, it presents potential uses of the proposed model.
A Functional BCI Model by the P2731 Working Group: Transducer
(Taylor & Francis, 2021) Guillermo Sahonero-Alvarez; Avinash Kumar Singh; Kamran Sayrafian; Luigi Bianchi; Avid Roman–Gonzalez
A Brain-Computer Interface (BCI) can be considered as a technology that allows for alternative means of communication between humans and their environment using thoughts and intentions. The structure of this interface is composed of various stages, beginning with the acquisition of the brain signals, followed by several processing stages, and leading to the generation of feedback signals. The development of a BCI system involves a diverse set of expertise in order to produce a unique environment for continuous innovations. However, such diversity in technical background and expertise may lead to confusion in the terminology used by the community. As such, the IEEE P2731 WG has been tasked with the development of a functional model to facilitate the understanding of a BCI system. In this paper, we focus on the description of the functional elements that belong to the transducer stage of a BCI.
A Functional Model for Unifying Brain Computer Interface Terminology
(Institute of Electrical and Electronics Engineers, 2021) Chuck Easttom; Luigi Bianchi; Davide Valeriani; Chang S. Nam; Ali A. Hossaini; Dariusz Zapała; Avid Roman–Gonzalez; Avinash Kumar Singh; Alberto Antonietti; Guillermo Sahonero-Alvarez
Brain Computer Interface (BCI) technology is a critical area both for researchers and clinical practitioners. The IEEE P2731 working group is developing a comprehensive BCI lexicography and a functional model of BCI. The glossary and the functional model are inextricably intertwined. The functional model guides the development of the glossary. Terminology is developed from the basis of a BCI functional model. This paper provides the current status of the P2731 working group's progress towards developing a BCI terminology standard and functional model for the IEEE.
ADRAS: Airborne Disease Risk Assessment System for Closed Environments
(Springer Science+Business Media, 2023) Wilber Rojas; Edwin Salcedo; Guillermo Sahonero-Alvarez
Blockchain and Peace Engineering and its Relationship to Engineering Education
(2018) Guillermo Sahonero-Alvarez
Peace engineering implies taking positive and proactive actions to promote peace and jnstice. Blockchain, on the other hand, is a distributed sequence of blocks which acts like a public ledger. Motivations to develop blockchain based systems are usually related to transparency and trust. Inherently, blockchain ideals relate to peace engineering because of the way users can manage information globally: transparently and confidently. Application of blockchain in higher education may represent a fundamental change in the way professors deliver contents, manage courses, and even assess student work. Moreover, higher education institutions can find blockchain useful as it has the potential to change the way of providing certifications and the way knowledge is managed, produced, and shared. In this work, we review previous works that address blockchain implementation in higher education highlighting implementation advantages and possible disadvantages Additionally, we explore further potential applications of smart contracts as a tool in blockchain based approaches to enhance engineering education programs.
Cross-View Gait Recognition Based on U-Net
(2020) Israel Raul Tinini Alvarez; Guillermo Sahonero-Alvarez
Gait based recognition systems allow automatic subjects' recognition by using the way of walking. However, the performance of these systems is often degraded by some covariate factors such as walking direction, appearance changes, occlusions, among others. From these, it has been shown that change in appearance is the most influent covariant by drastically affecting the recognition performance. Consequently, inspired by the great successes of GANs in image translation tasks, we propose a method of gait recognition using a conditional generative model to generate view-invariant features. The proposed method is evaluated on one of the largest datasets available under the variations of view, clothing and carrying conditions: CASIA gait database B. Experimental results show that the proposed method outperforms state-of-the-art methods specially in carrying-bag and wearing-coat sequences. The full implementation and trained networks are available at https://gitlab.com/IsRaTiAl/gait.
Exploring Edge Computing for Gait Recognition
(2021) Israel Raul Tinini Alvarez; Guillermo Sahonero-Alvarez; Carlos Menacho; Josmar Suarez
Gait Recognition, as a way to identify people, is re-markably attractive for scenarios in which it is not possible to rely on subjects' collaboration. Nevertheless, from all the modalities that Gait Recognition involve, vision-based approaches are better to meet hardware and settings-limitations. Because of that, in the past years, there has been several efforts on developing robust algorithms against visual gait covariates, i.e., view, clothing and carrying variations. However, besides robustness, real-world gait recognition systems also require to be implemented considering near real-time computational demands as well as portability. In this work we propose an Edge Computing approach based on the NVIDIA Jetson Nano development board and the OpenCV OAK-D camera to perform Gait Recognition. To adapt our approach, we created two small data sets that allowed our system to particularize the system to local data. Our pipeline implies the usage of a pre-trained object detection algorithm in the OAK-D, and the execution of both the representation extraction and inference on the Jetson Nano. To test our framework, we first explore its feasibility and consistency in an offline manner. Later, we characterize the complexity and time processing when executing the procedures in an online setup. Our results show that the approach is promising as it allows online operation with an inference time of 35.8 ms.
Gait Recognition Based on Modified Gait Energy Image
(2018) Israel Raul Tinini Alvarez; Guillermo Sahonero-Alvarez
Biometric systems allow us to identify individuals from distinctive biological traits. Gait recognition is a biometric technique used to recognize humans based on the style of their walk. However, model-free based gait recognition performance is often degraded by the presence of some covariate factors such as view, clothing and carrying variations. From these, it has been shown that the change in appearance is the covariant that most affect the recognition performance. To address such issues, we propose to use a feature representation that takes both dynamic and static regions of silhouettes. This way, more robustness against covariates and better discriminative performance are expected. The proposed method is evaluated on one of the largest datasets available under the variations of clothing and carrying conditions: CASIA gait database B. Results show that the proposed method achieves correct classification rate up to 90% and outperformed state-of-the-art methods.
Implementation Issues of Student-Centered Learning based Engineering Education in Developing Countries Universities
(2018) Guillermo Sahonero-Alvarez; Humberto Calderon
Student-Centered Learning is one of the most popular and promising instruction approaches as it is supposed to enhance the active role of students on Engineering Education. Although there are multiple advantages of employing it, there are also multiple implementation issues that have been identified by previous works. Unfortunately, the focus of those works was mostly referring to developed countries context. However, due to differences technological and teaching support resources, as curricula structure, individual academic regulations and even culture, some dissimilarities are induced on the actual issues in developing countries. In this work, we explore the corresponding matters of Student-Centered Learning over Engineering Education in the context of a fraction of developing countries. An analysis of issues' similarities and differences suggests that, despite the common difficulties, developing countries may be more distant from real SCL implementation as they seem to have more complex problems than developed economies.
MAMBU: A Bolivian Case of Response to Artificial Ventilators Shortage
(2022) Fabio Richard Diaz Palacios; Jhon Ordoñez; Gabriel Antonio Rojas Silva; Miguel Angel Clavijo Quispe; Guillermo Sahonero-Alvarez; Rodrigo Ruben Botelho Oblitas; Juan Manuel Valverde Velasquez; Guillermo Enrique Manning Soria Galvarro; Renan Andres Espinar Saavedra; Anna Montevilla
COVID-19 pathology is characterized by a variety of symptoms, from respiratory to cardiac and even neuronal affections. However, from all of these manifestations, lungs’ affection remains a focus of attention due to being considered as the main cause of death. Respiratory failure is treated using different strategies, but a very common practice is to provide respiratory support through artificial ventilation to patients. Unfortunately, due to the shortage of devices capable to offer such functionality, many patients are left unattended given that public healthcare systems’ resources are not enough - the Bolivian healthcare system was not the exception. This paper reports the approach followed to develop MAMBU which stands for Mechatronic Ambulatory Medical Breathing Unit, an automation system for AMBU-based ventilation designed to face the shortage of ventilation devices in Bolivia. A MAMBU device can be manufactured and assembled in a short amount of time, with a low cost and easy transportation. Furthermore, it includes control schemes to manage the respiratory frequency, I:E ratio, PEEP, and FiO2. The device was validated through instrumental testing and in-vivo procedures following Bolivian current regulations. The results obtained show that the device is safe for human usage as well as relatively reliable (around 7% of error).
Towards Bridging the Gap Between Computational Intelligence and Neuroscience in Brain-Computer Interfaces With a Common Description of Systems and Data
(Frontiers Media, 2021) Avinash Kumar Singh; Guillermo Sahonero-Alvarez; Mufti Mahmud; Luigi Bianchi
OPINION article Front. Neuroinform., 23 August 2021 | https://doi.org/10.3389/fninf.2021.699840