USC Repository :: Browsing by Author "Castillo García, Javier Ferney"

Browsing by Author "Castillo García, Javier Ferney"

Now showing 1 - 15 of 15

Algorithms for the Management of Electrical Demand Using a Domotic System with Classification of Electrical Charges
(Springer, 2020-03-03) Suaza Cano, Kevin Andrés; Castillo García, Javier Ferney
Electricity demand management is the process of making appropriate use of energy resources. This process is carried out with the aim of achieving a reduction in electricity consumption. The electrical demand management algorithms are implemented in a domotic system that has the capacity to identify electrical loads using artificial neural networks. An analysis was carried out on the most important physical variables in the home, which have a direct relationship with energy consumption, and strategies were proposed on how to carry out a correct control over these, in search of generating energy savings without affecting comfort levels in the home. It was obtained, as a result that it is possible to generate an energy saving of 63% in comparison to a traditional house, this without affecting to a great extent the comfort of the user and allowing a great level of automation in the home.
Characterization of people with type ii diabetes using electrical bioimpedance
(Springer, 2020-08-11) Rodríguez Timaná, Luis Carlos; Castillo García, Javier Ferney
Diabetes is a disease that causes the death of a person every seven seconds around the world and is also expensive. In 2014, it invested 600 billion dollars to be treated worldwide, that is why the need arises develop technological projects that allow the analysis of specific patterns in people suffering from this disease, in order to detect the pathology in a non-invasive manner and reduce costs, for which an electrical bioelectrical impedance analyzer was developed for the analysis of diabetes. The integrated AD5933 was used as a bioimpedance signal acquisition device and a beaglebone black development platform to process said data. Bioelectrical impedance data were taken from 5 healthy people and 3 people with the pathology. The data were processed by mathematical methods such as linearization with least squares and correlation, which allowed us to find parameters to differentiate between the signals of people with diabetes and people without diabetes. It was determined that people with diabetes have a curve that relates their bioimpedance in a range of frequencies from 10 kHz to 80 kHz, a curve that presented a high correlation to a power function of the form aXb. It was observed that the people who presented values of coefficients (a) greater than 38000 and exponents (b) less than −0.659 were people with diabetes, this in turn allowed to find the equation of a line that separates the two populations W0 + 1W * a + W2 * b = 0.
Determination of Electrical Bioimpedance Characteristics for the Study of People with Type II Diabetes
(Springer, 2020-03-03) Rodríguez Timaná, Luis Carlos; Castillo García, Javier Ferney
Diabetes is a disease that causes the death of one person every seven seconds worldwide and is also costly, in 2014 was invested 600 billion dollars to be treated worldwide, that is why there is a need to develop technological projects to analyze patterns determined in people who suffer from this disease, in order to detect the pathology in a non-invasive way and reduce costs. That is why an electrical bioimpedance analyzer was developed for the analysis of diabetes. For this purpose, the integrated AD5933 was used as an acquisition device for bioimpedance signals and a beaglebone black development platform to process such data. Electrical bioimpedance data were taken from healthy people and people with the pathology. The data were processed using mathematical methods that allowed parameters to be found to differentiate between the signals of people who have diabetes and people who do not. These methods and the performance measures of the device were evaluated through the Confusion Matrix which determined that the best ratio to decree people with and without diabetes was the quotient between the magnitude of bioimpedance at frequencies of 10 kHz with the magnitude of bioimpedance at frequencies of 100 kHz.
Embedded system for electrical load characterization based on artificial neuronal networks in the management of electrical demand in a domotic system
(Springer, 2020-08-11) Suaza Cano, Kevin Andrés; Angulo Gamboa, Ángel Stiven; Castillo García, Javier Ferney
A load characterization system was developed in an embedded platform, in order to identify electrical devices used in the home. For the characterization process, the most representative electrical parameters of the different loads were defined, which were used in the training of an artificial neural network implemented in an embedded platform with a network topology with the best performance in terms of computational resources, time of execution and percentage of error. The network topologic had two hidden layers each one with 10 neurons. With the characterization of electrical charges, an intelligent home automation system could be created which can generate savings of up to 23% compared to traditional home automation systems or 69% savings compared to a home without any automation or system control. The proposed demand management system can actively manage the loads due to the knowledge of the elements connected to the network, identifying periods of low consumption which can be related to charging processes completed in mobile phones, laptops or standby mode for televisions. The identification of charges facilitates the implementation of management schemes and control of electric charges.
Estimation of Electrical Conductivity from Radiofrequency Hyperthermia Therapy for Cancer Treatment by Levenberg Marquardt Method
(Springer, 2020-03-03) López Perez, Jorge Iván; Serna Maldonado, Rafael Daniel; Bermeo Varón, Leonardo A.; Castillo García, Javier Ferney
Introduction: The radiofrequency hyperthermia is a technique that by induction of the electromagnetic waves produces the heating in the biological tissues. The increase in body temperature in a range of 40 °C to 46 °C causing heat-induced necrosis, protein inactivity, and inhibition of DNA recovery mechanisms in the cancer cell. The application of this therapy depends on parameters like the frequency and power and physical properties of the tissue, which vary from person to person. One of the important properties is the electrical conductivity of the tissue, which varies depending on the tissue and frequency. In this paper, the electrical conductivity estimation is performed in hyperthermia therapy with different frequencies. Methodology: The estimation process of electrical conductivity is carried out through the Levenberg Marquardt method. The process is performed on simulated experimental data and mathematical model of the system with different frequencies. The geometry used is a copper coil that induces radiofrequency to a domain located in the center of the coil. Results: The estimation of electrical conductivity is obtained to different frequencies from radiofrequency hyperthermia therapy for cancer treatment by the Levenberg Marquardt method. Also, these results allow that by identifying the electrical conductivity of each patient. Conclusions: The estimation of physical properties in the application of cancer treatment is important, in this case with radiofrequency hyperthermia therapy, because it is possible to plan appropriate treatment, due to a better knowledge of the system.
Estimation of Non-physiological Parameter for Electric Power Generation Using a Conventional Bicycle
(Springer, 2020-03-03) Salazar Muñoz, Daniel; Millán Castro, Aura María; Castillo García, Javier Ferney
The need to find new alternative energy sources brings with it the use of unconventional power generation sources such as bicycles and the question arises as to how safe these sources are from the user’s perspective. The present work consists in the estimation of a parameter of easy evaluation, for the safe use of a conventional bicycle in the generation of electrical energy. The generation of energy is achieved by coupling a bicycle to an electric alternator and this to an inverter. The load used was a 100 W lamp. The measurement of non-physiological parameters such as vibration, ambient temperature and pedaling speed as well as certain physiological parameters such as heart rate (HR) and body temperature, were used to determine both physiological and electrical signals when the user is overexerting. A protocol oriented to two routines was defined to evaluate the use of the bicycle in conditions of maximum effort and conditions of safe operation. Eight people between the ages of 22 and 32, body weights from 56 kg to 80 kg and heights from 1.59 m to 1.84 m participated. Voltage and current readings were taken to estimate the power and energy generated by the participants. In the process of user-bike interaction it was found that when the participant over-exerted, he/she resorted to compensatory postural movements to maintain the pedaling speed. These compensatory movements made it possible to observe a relationship between the first derivative of vibration and HR.
Modelo de seguridad biométrico para el Estadio Olímpico Pascual Guerrero basado en dispositivo inalámbrico para la captura de imágenes
(Universidad Santiago de Cali, 2019) Cuero Ponce, Elmer Steven; Castillo García, Javier Ferney
The bad behavior of some soccer fans in Colombia generates insecurity in the stadiums, this article presents the proposal to support the security system in the Olympic stadium Pascual Guerrero located in the city of Cali - Colombia, for the development of this proposal begins with the consultation of the state of the art of the different systems that support the security system nationally and internationally and thus know how it works, the elements and human resource involved in the process, with this information begins the research process of the proposal for the development of the prototype of an electronic device that supports by means of images the biometric system of facial recognition that the governmental entities have for the identification of people who participate in vandalism actions and serves as evidence to apply the corresponding sanctions. The result of this investigation generated a prototype of the device with a cost of 1% with respect to the value that has as budget for the system of biometric cameras of the stadium, using the same human resource that currently supports logistics of the event, having as the only additional action the pressing of a button for the taking of images of the exact moment that the event is happening, this proposal makes that less time is required to make analysis to the evidences, since the images will be only of situations that present facts of bad behavior of the fans. This type of tools is part of the persuasive technologies that contribute to the strategies of change on the part of the fan towards a good behavior, to achieve that these scenarios are safe and become a culture for future generations.
Platform for Adaptation of Myoelectric Prostheses in People with Upper Limb Amputation
(Springer, 2020-03-03) Arcos Hurtado, Edgar Francisco; Ortegón Sanchez, Andrés Felipe; Rentería, Juberth; Castillo García, Javier Ferney; Millán Castro, Maria Del Mar
This paper describes a platform for adaptation of myoelectric prostheses in people with upper limb amputation. The design of the platform is based on the anthropometry and biomechanics of human upper limb, servomotors are used to drive each degree of freedom, except in the articulation of the elbow, in which a gear motor is used. The myoelectric signal acquisition system includes Myoware myoelectric signal sensors from the company Advancer Technologies, an embedded system based on Arduino and a graphic interface to visualize myoelectric signals in real time. The implementation platform allows to replicate flexion/extension movements for the elbow, wrist, and each finger of the hand, pronation/supination of the wrist, and adduction/abduction of the thumb. The data acquisition system allows to visualize in real time, muscular activity concerning for 4 muscles, and was tested in people with upper limb amputation registering significant values for different movement intentions. The platform presented provides a feedback that could improve the adaptation of a superior limb amputee to a myoelectric prosthesis. The characterization of myoelectric signals generated by the residual limb of a person with upper limb amputation, allows to generate control signals according to a movement intention that would be replicated in the platform.
Proposal for the Implementation of MLP Neural Networks on Arduino Platform
(Springer, 2020-03-03) Suaza Cano, Kevin Andrés; Moofarry, Jhon Freddy; Castillo García, Javier Ferney
This paper presents implementation MLP artificial neural networks on embedded low-cost microcontrollers that can be dynamically configured on the run. The methodology starts with the training process, goes through the codification of the neural network into the microcontroller format, and finishes with the execution process of the embedded NNs. It is presented how to compute deterministically the memory space require for a certain topology, as well as the required fields to execute the neural network. The training and verification was done with Matlab and programming with a IDE Arduino compiler. The results show statistical and graphical analysis for several topologies, average execution times for various transfer function, and accuracy.
Robohip: Robotic Platform for Hippotherapy in Children with Disabilities
(Springer, 2020-03-03) Murillo Penagos, Luis Carlos; Millán Castro, Aura María; Castillo García, Javier Ferney
The problems inherent to the intervention of animals in therapies are associated with risks that imply this interaction and the low capacity to carry out a quantitative assessment. This document aims to offer patients with motor, sensory and cognitive disabilities a different and safe treatment option. The approach to this problem uses a robotic platform divided into three systems, integrating elements for motor, cognitive and sensory rehabilitation: The first emulating the head and neck of the animal; the second emulating movements of rotation and translation of the horse’s back in the three axes (base); the third to calculate the force vector relating the distribution of the child’s weight, performing emulation of temperature ranging from 38 ºC to 42 ºC depending on the speed of work (seat), recording articular angles of the cervical region, thoracic cage, lumbar and hip; The patient is evaluated posturally, in-corporating a set of lights that make it easier to observe to which side the resulting force vector is directed, allowing him to modify his posture and improve his proprioception. The system comprises interaction of commands for the user so that he can develop new psychomotor skills and abilities. The data obtained can serve as indicators for the differential evaluation of each patient, as well as the possibility of monitoring variables such as Temperature, joint angles, and weight.
Selection of Mental Tasks for Brain-Computer Interfaces Using NASA-TLX Index
(Springer, 2020-03-03) Moofarry, Jhon Freddy; Suaza Cano, Kevin Andrés; Saavedra Lozano, Diego Fernando; Castillo García, Javier Ferney
The brain-computer interfaces - BCIs allow people with disabilities to interact with the outside world using different communication channels than conventional ones. This article deals with the selection of tasks in the protocols for the development of BCI based on the paradigm of mental tasks. It is proposed to use the NASA-TLX index to evaluate the effect of the mental load of each of the tasks and contrast the performance of the interface task by task. In the implementation of BCI, the OPENBCI hardware was used for signal acquisition and the MATLAB software for processing. Five mental tasks were defined that activated different regions of the cerebral cortex. The acquisition protocol consisted of defining the rest time, execution and recovery for the tasks. The extraction methods used temporal, frequency and time-frequency combination characteristics. The classifiers used were neural networks, nearby neighbors and support vector machines. The evaluation of the TLX index seeks to quantify the appreciation of the effort, frustration and complexity of the task, therefore after the acquisition of signals for each task, the participant proceeded to evaluate the mental overload using the NASA-TLX index. The results obtained show that those tasks that require greater complexity to be performed presented a greater repeatability and higher success rate.
Software to Determine the Readability of Written Documents by Implementing a Variation of the Gunning Fog Index Using the Google Linguistic Corpus
(Springer, 2020-03-03) Rodríguez Timaná, Luis Carlos; Saavedra Lozano, Diego Fernando; Castillo García, Javier Ferney
In English linguistics the Gunning Fog Index is used to determine the readability of texts. This methodology isn’t as effective in the Spanish language because the complexity of words isn’t determined by the number of syllables, unlike what happens in English. Therefore, a software was developed that allows us to estimate the readability of an academic text written in Spanish in a quantitative way. This software allows to compare the traditional methodology of the Gunning fog index and a modification to it, using the corpus linguistics for the Spanish language, based on thousands of texts digitized by Google, where the frequency of use of certain words is related. Texts produced by students from first to last semester were evaluated. Each text was subjected to the Gunning fog index assessment methodology and the corpus methodology, changing the percentage of complex words to the percentage of unknown words. In the evaluation of first semester texts it was found that the average fog index was 29.25, and an average of 37.9 complex words, for these same texts was found a modified fog index of 18.62 and 5.1 unknown words. On the other hand, for the evaluation of the texts produced in the last semester, the average fog index was 27.55 and an average of 51.4 complex words, with the modified fog index was an average of 15.08 and 7.1 unknown words. With this study, aspects related to the best use of punctuation marks and the increase of vocabulary related to the profession can be identified in a quantitative way.
System for analysis of human gait using inertial sensors
(Springer, 2020-08-11) Saavedra Lozano, Diego Fernando; Castillo García, Javier Ferney
Gait laboratories using image processing are the standardized method to analyze human gait, but these are expensive, require restrictive workspaces, and post-processing times. On the other hand, inertial sensors are cheaper and reach high performance with lower computational cost in its implementation. In this work, a wireless system was implemented for the analysis of human gait using inertial sensors. The inertial sensor was chosen according to its specifications, cost, and pursuant to the characteristics of the human gait. In total, seven inertial sensors were used, arranged on the pelvis, thighs, legs and feet. A calibration algorithm was implemented to adjust the sensor angles with those of their respective body segment based on a known posture. The data capture system was verified comparing the angle of flexion-extension of the knee with the angle obtained by the artificial vision system from the sagittal plane and comparing it with bands of normality. As a result, it was possible to implement a low-cost inertial motion capture system for the analysis of human gait, with its respective graphical interface to visualize the orientation, flexion-extension angles for each segment and joint of the lower limbs. It is concluded that is possible to develop a complete tool for the kinematic analysis of human gait with the information of the artificial vision system or an anthropometric model.
Technical Feasibility for the Mobile Measurement of Noise Pollution by Remotely Piloted Aircraft System
(Springer, 2020-03-03) Rodríguez Timaná, Luis Carlos; Saavedra Lozano, Diego Fernando; Díaz Velásquez, María Fernanda; Castillo García, Javier Ferney
Excessive noise causes gradual hearing loss and interferes with sleep, reading and concentration. It can even cause physiological disturbances in the cardiovascular system. Noise quantification is usually performed using multiple static measurements with sound level meters. This article implements the technical feasibility analysis to perform mobile noise measurements using a Remotely Piloted Aircraft System-Drone. Initially the acoustic power emitted by a Drone Matrice 100 was estimated, for which a parallelepiped is defined taking as indications the ISO3744 standard and by means of an audio capture system. For the measurement a semi-anechoic chamber was established in a football field and the measurements were made in the early hours of the morning. The acoustic power of this type of drone was 84.6 dB, which determined that the signal-to-noise ratio had a very high value. An intervention in the design of the drone propellants is suggested to reduce the noise of the drones, so that previously the technical viability for applications of measurement of acoustic pollution is discarded.
Toward Automatic and Remote Monitoring of the Pain Experience: An Internet of Things (IoT) Approach
(Springer, 2020-03-03) Rodríguez Rodríguez, Juan José; Castillo García, Javier Ferney; Argüello Prada, Erick Javier
Automatic and remote monitoring of patients with pain may decrease treatment costs and improve the quality of care. In this sense, the Internet of Things (IoT) emerges as a suitable candidate for developing solutions enabling continuous and remote assessment of pain experience. However, only a few efforts have been devoted to adopting IoT-based solutions for pain assessment. In the present work, an IoT-based system for pain monitoring is proposed on the basis of a performance assessment of several communication protocols for IoT: TCP/IPv4, TCP/IPv6, UDP, MQTT, and HTTP. The peripheral blood flow and the skin’s ability to conduct electricity were chosen as the physiological parameters through which it is possible to measure pain. The capabilities of the aforementioned IoT communication protocols for transmitting the physiological data stream to a cloud server were evaluated by implementing each of those protocols and using the Wireshark protocol analyzer to compute the mean byte rate, the mean packet rate, the mean error value, and the network reliability for 1 h. Results show that the TCP/IPv4 and TCP/IPv6 protocols showed the highest packet transmission rate as well as the highest network reliability. Moreover, given the characteristics of the chosen physiological parameters, the proposed solution does not require a high transmission data rate, so there would be no limitation regarding the wireless communication protocol that could be used for implementing it. Nevertheless, a wider range of parameters needs to be considered in order to carry out a more rigorous performance assessment.

Browsing by Author "Castillo García, Javier Ferney"

Results Per Page

Sort Options