Browsing by Author "Saavedra Lozano, Diego Fernando"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item 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 FerneyThe 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.Item Sistema para el análisis de la marcha humana usando sensores inerciales(Universidad Santiago de Cali, 2019) Saavedra Lozano, Diego Fernando; Castillo Garcia, Javier FerneyThe human gait analysis in specialized laboratories is not available in Colombia for applications such as rehabilitation or sports. Therefore, a capture system is designed using inexpensive inertial sensors to analyze the kinematics of the lower limbs. In this article, initially the characteristics and parameters of the human gait are studied, then it was chosen the inertial sensor that would be used according to its specifications and cost, then the prototype of the inertial capture system was made, and finally, the capture system data was verified by comparing the angle of flexion 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 and extension angles for each segment and joint of the lower limbs. As a conclusion of this work, it was found that with the information of the artificial vision system, from the sagittal plane, it was possible to identify the gait phases and temporal and spatial parameters such as cadence, step length, stride length, speed of stride, as well as the length of the segments, likewise the inertial system can obtain this information with a system of artificial vision or an anthropometric model, to develop a complete tool for the kinematic analysis of human gaitItem 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 FerneyIn 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.Item System for analysis of human gait using inertial sensors(Springer, 2020-08-11) Saavedra Lozano, Diego Fernando; Castillo García, Javier FerneyGait 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.Item 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 FerneyExcessive 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.