Search

This paper demostrate the calculate for calibration parameters of the Percent Oxygen Saturation estimation equation by means of a multiple linear regression type supervised machine learning algorithm with the objective of being able to use a smartphone as an oximeter, for this a training and test data set composed of predictor variables representing the characteristics of the smartphones used in this development is used, in addition to the statistical parameters extracted from two thousand videos, predicting values of with an error of less than with respect to a standard oximeter.

Optical cardiac mapping is an experimental method developed to record the electrical behavior of the heart, through the analysis of films filmed at high speed. Due to the conditions of the experiment along with the signal, a great amount of noise from different sources is stored. In this article, the comparison of the IIR type filters and the FIR filters is proposed, where the order of the filters, the phase difference and the application on the film have been compared. From this analysis it is determined that a 9th order IIR filter behaves in the same way as a 256 order FIR filter. Therefore, it can be determined that a 9th order IIR filter can be used for filtering this type of signal, reducing the computational costs in its application.

The development of smart agriculture has presented extensive development in recent years, that is why countless proposals have been presented around the world. This high variability of technologies used in the implementation of this type of solutions has generated certain users depending on what types of equipment or communication protocols to use depending on the application case. In this article, the different jobs and technologies used in IoT applied to agriculture are analyzed, comparing their technical characteristics through documentary analysis, simulations of case studies, among others. After this study, the results obtained from the bibliographic and documentary review are described by means of tables, in addition sensor nodes are reproduced with specific technical characteristics such as their communication protocol, energy consumption, degrees of protection of the devices, security of the implemented networks, among others in the Cooja software for the simulation of the case studies. This study provides a methodology for selecting the technology that best suits each type of crop.

This article proposes the design of a low-cost IoT architecture based on Wireless Sensor Network technology for agricultural monitoring which is deployable in different types of crops, in this particular case cacao crops have been chosen. The architecture will allow small and medium agricultural producers, through a multi-platform application (web, mobile, etc.), to monitor and store information of various climatic and soil factors that influence the optimal growth and production of cacao. The data collected by the sensor network will be visualized through interactive maps, tables and statistical graphs. Furthermore, the system will notify or emit alerts to the farmer through emails or the application’s own graphical interface about a specific event that has occurred, in order to support optimal and opportune decision-making. The proposal of this architecture corresponds to a inclusive tool of the agro-technological field for family cacao farmers through the collection, storage, management and visualization of agricultural variables data. The information acquired is fundamental for the sustainable management of the crop through the correct administration of resources, facilitating the quality control of the product and the generation of preventive plans for protection against pests and diseases.

In recent years, attention has been paid to wireless sensor networks (WSNs) applied to precision agriculture. However, few studies have compared the technologies of different communication standards in terms of topology and energy efficiency. This paper presents the design and implementation of the hardware and software of three WSNs with different technologies and topologies of wireless communication for tomato greenhouses in the Andean region of Ecuador, as well as the comparative study of the performance of each of them. Two companion papers describe the study of the dynamics of the energy consumption and of the monitored variables. Three WSNs were deployed, two of them with the IEEE 802.15.4 standard with star and mesh topologies (ZigBee and DigiMesh, respectively), and a third with the IEEE 802.11 standard with access point topology (WiFi). The measured variables were selected after investigation of the climatic conditions required for efficient tomato growth. The measurements for each variable could be displayed in real time using either a laboratory virtual instrument engineering workbench (LabVIEWTM) interface or an Android mobile application. The comparative study of the three networks made evident that the configuration of the DigiMesh network is the most complex for adding new nodes, due to its mesh topology. However, DigiMesh maintains the bit rate and prevents data loss by the location of the nodes as a function of crop height. It has been also shown that the WiFi network has better stability with larger precision in its measurements.

The intracardiac electrical activation maps are commonly used as a guide in the ablation of cardiac arrhythmias. The use of catheters with force sensors has been proposed in order to know if the electrode is in contact with the tissue during the registration of intracardiac electrograms (EGM). Although threshold criteria on force signals are often used to determine the catheter contact, this may be a limited criterion due to the complexity of the heart dynamics and cardiac vorticity. The present paper is devoted to determining the criteria and force signal profiles that guarantee the contact of the electrode with the tissue. In this study, we analyzed 1391 force signals and their associated EGM recorded during 2 and 8 s, respectively, in 17 patients (82 ± 60 points per patient). We aimed to establish a contact pattern by first visually examining and classifying the signals, according to their likely-contact joint profile and following the suggestions from experts in the doubtful cases. First, we used Principal Component Analysis to scrutinize the force signal dynamics by analyzing the main eigen-directions, first globally and then grouped according to the certainty of their tissue-catheter contact. Second, we used two different linear classifiers (Fisher discriminant and support vector machines) to identify the most relevant components of the previous signal models. We obtained three main types of eigenvectors, namely, pulsatile relevant, non-pulsatile relevant, and irrelevant components. The classifiers reached a moderate to sufficient discrimination capacity (areas under the curve between 0.84 and 0.95 depending on the contact certainty and on the classifier), which allowed us to analyze the relevant properties in the force signals. We conclude that the catheter-tissue contact profiles in force recordings are complex and do not depend only on the signal intensity being above a threshold at a single time instant, but also on time pulsatility and trends. These findings pave the way towards a subsystem which can be included in current intracardiac navigation systems assisted by force contact sensors, and it can provide the clinician with an estimate of the reliability on the tissue-catheter contact in the point-by-point EGM acquisition procedure.

This paper presents a virtual reality app for pulmonary diseases treatment in children through VR game, which consists of visual and auditory stimulation thus the therapy won’t be annoying to the patient. The procedure consists of a previous stage of respiratory training which the patient is asked for a deep inhalation followed by an exhalation, both within a period of 3 to 6 s and requested 3 times. The app will offer the patient different activities in a virtual environment depending on the inhalation and exhalation exercise required by the stages of their therapy, using HTC VIVE virtual reality glasses. Recognition of inhalation and exhalation exercises is performed using a DTW classifier running in real time in MATLAB and with a direct, two-way connection to Unity. Therefore, the app encourages the patient to perform the exercises therapy in an accurate and fun way and as a result respiratory signal graphs are shown for evaluation by the therapist.

The present work aims to develop a non-invasive interactive system by using an eye sensor known as Tobii Eye Tracking to evaluate students in environments such as reading or visual appreciation. Finally, the results obtained are shown graphically showing the trajectories of what the person observes and a statistical weighting close to the normal standard.

Parallel robots, which are faster and more robust than serial robots, use servomotors for movement generation on each of their joints, which are independently controlled. This control is usually addressed by wired connections, which increases the fail probability and has an effect on the actuation speed. In this work, we propose to implement a wireless control system for parallel robots, based on RS-232 interface. We used Robotic Operation System (ROS) for controlling the joint actuators, and a Python developed algorithm supported by OpenCV libraries. Experiments in a drawing application with bidimensional plots showed that the network implementation and the control algorithm provide us with increased robustness, response velocity and reliability (lower fail probability), thanks to the reduction of connection points. Los robots paralelos, son más rápidos y más robusto que los robots tipo serie, se utilizan nervomotores para la generación de movimiento en cada una de sus articulaciones, que son controlados de forma independiente. El control y conexión de los actuadores se lo realiza mediante buses de comunicación con la finalidad de reducir las probabilidades de fallos. En este trabajo, se propone implementar un sistema de control para robots paralelos, basado en la interfaz RS-232. Se utilizó el Sistema Operativo Robótico (ROS) para controlar los conjuntos de actuadores, y un algoritmo desarrollado Python apoyado por las bibliotecas OpenCV. Los experimentos en una aplicación dibujo con gráficos bidimensionales mostraron que la implementación de la red de actuadores y el algoritmo de control proporcionan robustez, velocidad de respuesta y fiabilidad (inferior fallan probabilidad), gracias a la reducción de los puntos de conexión.

Wind turbine generators represent a valid and sustainable alternative for a significant energy provision, which is increasingly demanded by the planet, and a number of generator models have been proposed for supporting their design. However, equatorial regions have very special conditions for their gravity and wind behavior. Therefore, we present here a new wind turbine-generator model suitable for equatorial environments. Our simulation system is based on computational fluid dynamics and the Navier-Stokes equation, accounting both for structural and energy efficiency considerations. The most relevant simulation parameters were shown to be the Shovel number, the rotor diameter, the generated power, and the working frequency. Simulation results were consistent with different gravity conditions affecting to the fluid viscosity and the blades weight, as well as with differences in uniform and turbulent wind flow behavior. The proposed model allows us to make decisions about the structure and optimal requirements suitable for equatorial regions.