Browsing by Author "Sarria Paja, Milton Orlando"
Now showing 1 - 5 of 5
Results Per Page
Sort Options
Item Gestión de infraestructura tecnológicas en entidades públicas(Universidad Santiago de Cali, 2019) Amaya Moreno, Diego Fernando; Sarria Paja, Milton OrlandoThe management of the technological infrastructure is vital for the functioning of the State; Colombia has regulations that fall short of the international context, as well as the availability of technological resources with a high social impact. However, the technological infrastructure in relation to the provision of services and the presence of technology by the State is inefficient in some areas of the country. This paper analyzes these problems and proposes an action plan that optimizes the management of technological infrastructure in public entities, following a Top-Down technical design model.Item Movements classification system for transhumeral amputees using myoelectric signals(Elsevier Ltd, 2024) Arcos Hurtado, Edgar Francisco; Bermeo Varón, Leonardo Antonio; Sarria Paja, Milton Orlando; Azcarate Carmona, Jaime Andrés; Sarria Durán, Juan Camilo; Villarejo Mayor, John JairoThe extent of loss of functionality in people with transhumeral amputation or elbow disarticulation is considered highly compromised. The person with this impairment loses the primary muscle involved in the movement of the hand and fingers, and the elbow flexion/extension. In this sense, the development of myoelectric prostheses must include mechanisms that replicate these movements. Moreover, the control system for controlling a prosthesis must be robust and intuitive, where pattern recognition and artificial intelligence techniques represent an important and increasingly explored alternative. This study aims to develop a movement intention classification system based on myoelectric signals (MES) obtained from an elbow disarticulation amputee. Different features were extracted from the MES as the Mean absolute value (MAV), zero crossings (ZC), slope sign changes (SSC), waveform length (WL), and autoregressive (AR) coefficients. Machine learning classifiers (Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), Random Forests (RF), and Multilayer Perceptron (MLP)) were used to predict seven gestures: elbow flexion (EF), elbow extension (EE), forearm pronation (FP), forearm supination (FS), hand opening (HO), hand closing (HC), and rest (R). The results obtained with LDA, QDA, KNN, MLP, SVM, and RF were 60.84%, 71.05%, 77.10%, 78.06%, 78.57%, and 79.72% of accuracy, respectively. These results are promising and will allow the development of a myoelectric prosthesis control system for people with transhumeral amputation or elbow disarticulation.Item Polisomnografía con redes de sensores inalámbricas en el estudio y diagnóstico de la apnea del sueño(Universidad Santiago de Cali, 2019) Obregón Garcés, Fawssy Evans; Sarria Paja, Milton OrlandoIn Colombia, obstructive sleep apnea syndrome (OSAS) is a little known or diagnosed disease, the real number of people affected being uncertain, due to the difficult access to the necessary equipment for diagnosis, lack of qualified personnel and deficits in The health system in general. The objective of this study is to synthesize the research or implementation of wireless sensors in the diagnosis and control of OSAS. To this end, it is possible to highlight methodologies and devices for the orientation of future studies or developments of this type sensors, oriented mainly to SAOS. Thus facilitating the execution of studies at national level that allow to know the real state of health of people affected by SAOS in the country. The review focused mainly on two diagnostic methodologies based on vector support machine and artificial neural networks, reaching values higher than 80% in the classification and detection of OSAS events, and mention is made of two complementary technologies such as data collection Contactless polysomnographic and the development of a wireless sensor for integrated circuits. The implementation of these devices in future projects, will allow the diagnosis and remote monitoring of this disease and the miniaturization integration to smart watchesItem Reconocimiento técnico de componentes para el procesamiento de imágenes en vehículos autónomos terrestres(Universidad Santiago de Cali, 2019) Unigarro Díaz, Julio Cesar; Sarria Paja, Milton OrlandoAutonomous vehicles today have become the standard innovation for the new driving methods demanded by the world's societies. Its objectives on environmental care, accidents and autonomy are unique pillars that have led certain vehicle manufacturers to make the next leap in the independent mobile revolution. In this way, the objective of this study is to make a fundamental tour that analyzes what are autonomous land vehicles, their technical, algorithmic components, image processing, the use of radar, the advantages and disadvantages of the implementation of a new transport system, which, it is speculated that for the next decade, would be in the market of the main cities of the world. Thus, it was found that these systems to process images require improvements, while driving Autonomous Vehicles (AV) which essentially implies, modernization with high-tech electronic equipment, this has greatly increased costs, that is why that prototypes are still being designed particularly, but not mass productionItem Sistema de interlocución audiovisual de necesidades básicas para niños con lenguaje y motricidad reducida debido a parálisis cerebral infantil (PCI)(Universidad Santiago de Cali, 2019) Velásquez Mina, Wiston; Barona Sánchez, Johnson Camilo; Sarria Paja, Milton OrlandoLa parálisis cerebral infantil (PCI) es un daño que se presenta en el cerebro durante sus etapas tempranas; por una infección materna que afecta al desarrollo fetal (varicela, herpes, sífilis, zika, entre otras) en la etapa prenatal; falta de oxígeno al nacer, parto de nalgas y bajo de peso al nacer en la etapa perinatal; fiebre, convulsiones y desnutrición en la etapa postnatal. Esto compromete una gran heterogeneidad de manifestaciones clínicas: motoras, sensitivas, cognitivas, del lenguaje, perceptivas y conductuales. La incidencia mundial ha permanecido estable durante los últimos años presentándose alrededor de dos casos en países desarrollados y 2.5 en países en vía de desarrollo, por cada 1,000 niños nacidos vivos. Específicamente, en Colombia se presentan de uno a dos casos por mil nacidos vivos existiendo en total 300.000 pacientes y más del 70% viven en la pobreza. Por lo anterior, surge este proyecto que implementa una solución tecnológica para la comunicación de necesidades básicas primarias y algunas actividades a pacientes con parálisis cerebral infantil (PCI). Y así, generar en cierta medida independencia del paciente en su entorno familiar y reducir costos asociados a su cuidado. Se utilizó lenguaje de programación llamado “Python” como principal fuente para desarrollar una interfaz audio-visual, de fácil comprensión para el paciente y/o cuidadores. La librería “OpenCV” para desarrollar un programa que con la cámara web reconozca al usuario, este realice movimientos y estos a su vez sean interpretados como movimientos del cursor. Un sintetizador de texto a voz, que permitirá comunicar los deseos del paciente. . La aplicación puede ser usada por pacientes con cuadriplejia debido a parálisis cerebral infantil (PCI). De acuerdo con las pruebas realizadas en un paciente con la anterior condición, la herramienta es funcional y logrará que el paciente con parálisis cerebral infantil (PCI) pueda comunicar lo que desea en el momento a sus cuidadores.