Ingeniería Electrónica
URI permanente para esta colecciónhttp://hdl.handle.net/11349/2043
Examinar
Envíos recientes
Ítem Sistema de monitoreo y generación de alertas de prevención contra inundaciones con IOTSánchez Vargas, Sebastián; Ramirez Bernal, Jose Gabriel; Plazas Nossa, LeonardoThe document presents the design and development of a flood monitoring and early warning system, a recurring issue due to geographical and climatic conditions, as well as the impact of climate change. The proposal includes low-cost sensors such as the HC-SR04 to measure water levels, an ESP32 for data processing and communication, and a mobile application to disseminate real-time alerts. Additionally, the system is powered by solar panels, ensuring autonomy in remote areas. This approach aims to mitigate the impact of floods through accessible technology that enables constant monitoring, effective alerts, and swift action in vulnerable communities.Ítem Desarrollo de plataforma iot para monitoreo inteligente de potencia eléctrica utilizando esp32Cortés Sánchez, Wilson; Ropero Mosquera, Manuel Alejandro; Guacaneme Moreno, Javier AntonioIn this project, a power meter is made using the ESP32 microcontroller programmed in Arduino IDE and a SCT-013 current sensor. A conditioning circuit for reading voltage and current and a phase lock circuit (PLL) are developed. The two cores of the ESP32 are used, one for capturing and processing input signals and the other for data transmission. A Wi-Fi connection is implemented to send Power data to a server. To do this, the HTTP protocol is used and the data is sent in JSON format, which with an IoT (Internet of Things) application allows the sending and receiving of data, facilitating communication with other devices and cloud servers; where a web page is designed that receives the processed information from the server, storing it in a database. The resulting instrument is easy to install and low cost and indicates reliable power measurements. This project is carried out with the support of the LIFAE research group of the Francisco José de Caldas District University.Ítem Estudio comparativo de clasificadores convolucionales implementados sobre la TPU coral dev boardCasas Solarte, Laura Marcela; Aranguren Díaz, Gabriel Felipe; Gaona Barrera, Andrés EduardoIn this work, criteria are proposed for selecting image databases and convolutional architectures, as well as an integrated model for classifications in software and hardware. A functional classifier prototype was implemented on the Coral Dev Board TPU. The results show that MobileNet has the shortest inference time and mixed accuracy results. No differences in power consumption were found between architectures or when using a webcam. Rates of up to 320 FPS were achieved, making real-time implementation feasibleÍtem Modelo de telecomunicaciones para telemedicina en zonas ruralesLeon Rodriguez, Jhoan Nicolas; Ovalle Calderon, Sebastian Camilo; Aparicio Pico, Lilia EdithThe document aims to provide a tool to support the implementation of telemedicine projects. The proposed model analyzes and adapts various telecommunication technologies such as mobile networks, WiMAX, fiber optics, radio links, and satellites to meet the requirements of remote medical services, such as teleimaging, teleoperation, telemonitoring, etc. Furthermore, it details how these technologies can support different telemedicine modalities, focusing on technical criteria such as bandwidth, latency, and transmission capacity to ensure efficient implementation in diverse contexts. The study also reviews the current regulatory framework and best practices in telemedicine to ensure that the proposed solutions are viable and scalable at a general level, not just in rural areas.Ítem Evaluación de la propagación y transporte de portadoras en bandas milimétricas sobre enlaces ópticosCarvajal Jara, Santiago; Puerto Leguizamón, Gustavo Adolfo; Puerto Leguizamón, Gustavo Adolfo [0000-0002-6420-9693]The field of telecommunications is experiencing constant evolution, characterized by the implementation of successive generations of mobile technology. The recent introduction of fifth-generation (5G) mobile networks has highlighted the importance of millimeter waves, which, despite their notable benefits, present significant challenges in their implementation. In this context, this thesis focuses on evaluating the propagation and transport of carriers in millimeter-wave bands over optical links, a crucial aspect for the development and optimization of future wireless communication networks. This study analyzes the characteristics of transmission in millimeter-wave bands, as well as the effects of dispersion, attenuation, and other phenomena in optical fiber. Through simulations conducted with "Optisystem" software, the behavior of millimeter waves is examined by varying parameters such as transmission frequency, transmission rate, and fiber length. This approach allows for a detailed comparative analysis of the obtained results. Additionally, various application scenarios for these technologies in advanced communication systems are identified and evaluated.Ítem Diseño de un modulo para la autenticación usando datos biometricos en un entorno descentralizadoBarrios Ruiz, Estefania; Garzon Bejarano, Diego Alejandro; Pava Diaz, Roberto Albeiro; Pava Diaz,Roberto Albeiro [0000-0003-0440-892X]Context: Traditional username and password-based authentication systems are insecure and prone to unauthorized access, especially when users reuse passwords across accounts. While biometric authentication offers a more secure alternative, it introduces risks if biometric data is stolen, requiring stronger security measures. Objective: The research aims to design an authentication system that integrates blockchain technology, biometric authentication, and distributed storage to address the security flaws of traditional methods and mitigate the risks of credential compromise. Method: The study developed a facial recognition-based biometric authentication system, using a React interface and OpenCV for face detection. The system integrates blockchain via Ganache, with smart contracts managed through Truffle, and connects to IPFS and MongoDB for distributed storage. The model was tested for efficiency, authentication and accuracy. Results: The integrated system showed promising results in efficiency, authentication rates, and resistance to identity theft, highlighting its potential to enhance security in access systems. Conclusion: Despite some challenges, the project provides a strong foundation for future enhancements, demonstrating the effectiveness of combining blockchain, biometric authentication, and distributed storage to improve access security.Ítem Actualización y mejoras de la capa de seguridad de la plataforma Web ZENITH(Universidad Francisco Jose de Caldas) Rojas Lozano, Carlos David; Plazas Nossa, LeonardoThe report "Update and Improvements to the Security Layer of the ZENITH Web Platform" addresses the implementation of cybersecurity measures to protect the confidentiality, integrity, and availability of information systems against increasing cyber threats. Justified by the need to avoid severe financial and legal consequences, the project focuses on identifying and mitigating vulnerabilities, enhancing two-factor authentication, updating password policies and technological components, and adding security filters. The results show a significant reduction in vulnerabilities and emphasize the importance of comprehensive security that combines technology, policies, and user awareness to create a secure and resilient digital environment.Ítem Prototipo para gestion y control de aguas lluvias en uso domestico de bajo costo con IOTAriza Tirado, Sebastián; Caviedes García, Alejandra; Plaza-Nossa, Leonardo; Plaza-Nossa, Leonardo [0000-0002-2223-9886]This project focuses on the development of a system for filtering and monitoring rainwater quality using IoT technology. Within this system, critical physicochemical variables such as turbidity, dissolved solids, electrical conductivity and temperature, which affect water quality, are identified and evaluated. This process, by implementing specific sensors, seeks to obtain real-time data that allow a more efficient and effective management of water resources in domestic environments. In addition, the design and construction of a prototype for the collection and treatment of rainwater, with a focus for use in urban homes, is presented. This prototype integrates monitoring technologies that allow the detection of anomalies in water quality, facilitating decision making for the treatment and use of the collected water. The project also addresses the importance of recalibration of the system's sensors to ensure measurement accuracy and system reliability. Finally, the results obtained demonstrate the effectiveness of the proposed system in improving water management, contributing to environmental sustainability and responsible use of water resources. The implementation of an application for remote control and data visualization allows users to monitor water quality from any location, promoting greater awareness of the importance of water management in the current context of climate change and resource scarcity.Ítem Modelamiento e identificación de parámetros para el helicóptero 2DOF quanser aeroGonzález Camberos, Juan Nicolás; Álzate Monroy, Marco Aurelio; Álzate Monroy, Marco Aurelio [0000-0001-6488-6013]The following project addresses the identification of a non-linear dynamic model that adequately represents the behavior of the QUANSER AERO system in its configuration as a two-degree-of-freedom (2DOF) helicopter. This project focuses on the area of unmanned aerial vehicles (UAVs), which is gaining relevance in various applications such as search and rescue, disaster prevention, traffic control and event recording, among others. This trend is due to the reduction of costs and its ability to operate at low altitudes. However, most of the research on this topic has focused on the design and implementation of control techniques, generally independent of the model, and even though modeling is mentioned, it is not further explored nor is the model validated. In order to obtain the systems (linear and non linear) models, the system is first modeled using the Euler-Lagrange method, considering the interactions between movements and inputs. Then, experimental system data is taken under different operating conditions, followed by the identification of the model parameters for validation; this being a crucial process for capturing the dynamics. Parameter estimation is then performed for the linear model, from which values are subsequently extracted for the non-linear model. Finally, the models are adjusted and the results are validated. The research seeks to overcome the limitations of previous models, which did not faithfully represent the behavior of the system; not only by providing a particular model, but also an adequate method for modeling similar systems.Ítem Clasificación de señales caóticas sintetizadas en imágenes por medio de técnicas de aprendizaje automático científicoTamayo Quiroga, Jimmy Jaiber; Olarte Romero, Juan Camilo; Melgarejo Rey, Miguel AlbertoIn this work we propose a method of image synthesis from signals, based on the phase space reconstruction method proposed by Takens, which fits with the objective of Scientific machine learning by integrating a neural network for the detection of chaos in signals, so that it can facilitate the identification of unknown dynamic systems. Understanding that chaos can be detected in phase space, we synthesize images that have information about the reconstruction of this space. A chaotic signal classifier model is tuned with 94.3% precision and 94.1% accuracy, trained with the transfer learning method. This model supports the proposal of integrating machine learning algorithms in questions from the area of science, associating these two areas of knowledge.Ítem Diseño de red de transporte convergente para redes de sensores inalámbricos y fotónicos(Universidad Distrital Francisco José de Caldas) Quevedo Beltrán, Cristian Camilo; Puerto Leguizamón, Gustavo AdolfoThis paper presents the design of a convergent optical transport architecture for wireless and photonic sensor networks, based on the existing optical transport network deployed in the city of Bogotá, Colombia. The proposed architecture is evaluated through the transport of services using subcarrier multiplexing, enabling the definition of different operating frequencies for RF, initially at 2.4 GHz, and support services such as WiFi, Bluetooth, Zigbee, SigFox, among others. The proposed design demonstrates high scalability given the distribution of the pre-existing network, allowing for its modification to incorporate both types of sensors: photonic (FBG) and wireless (RoF), in locations that will serve the multi-coverage area with significant historical, economic, cultural, and social relevance. The system exhibits optimal performance in terms of bit error rate (BER) and signal power within the multi-coverage area, considering various interference parameters such as SS-RSRP, SS-RSRQ, DL-SINR, and Throughput-DL.Ítem Sistema de planificación de recursos para fábrica de confecciones mediante aplicación móvil androidDíaz Peña, Johan Nicolás; Aguilar Bosiga, Juan Carlos; Plazas-Nossa, Leonardo; Plazas-Nossa, Leonardo [0000-0002-2223-9886]The project aims to develop a customized Android mobile application for implementing a resource planning system tailored for a garment manufacturing company. Currently facing challenges in communication and coordination among its production areas, the lack of a centralized information system leads to errors, delays, and inefficiencies. Therefore, the project's main objective is to enhance production efficiency by automating repetitive tasks, centralizing information, and monitoring production processes. By leveraging mobile technology, specifically through an Android application, the project seeks to address the company's needs for improved communication, coordination, and resource planning. With the increasing importance of rapid decision-making and strategic competitiveness in today's business environment, implementing a Material Requirements Planning (MRP) system, facilitated by the proposed mobile application, aligns with industry trends and offers significant potential for enhancing the company's competitiveness and operational efficiency.Ítem Diseño de automatización de mapas de backbone sobre un sistema de monitoreo de redes(Universidad Distrital Francisco José de Caldás) Garzón Agudelo , Sergio; Piñeros Duarte, David; Plazas Nossa, Leonardo; Plazas Nossa, Leonardo [0000-0002-2223-9886]This project focuses on the implementation of an automated network monitoring system through the design of Backbone maps. The objective is to enhance the management of complex networks by providing a clear and real-time visualization of the network topology, allowing for rapid fault detection and more efficient response, while also automating the generation of these visualizations to streamline the creation of network maps. By leveraging monitoring protocols such as SNMP and ICMP, the project aims to improve continuous monitoring of the organization's network links and deliver agile and effective solutions to ensure the operability and security of the network infrastructure.Ítem Diseño e implementación de dron para registro de códigos seriales para inventarios en bodegasArdila Paiba, Laura Natalia; Jutinico Alarcón, Andrés Leonardo; Jutinico Alarcón, Andrés Leonardo [0000-0001-9146-9637]In this degree project in internship mode, the knowledge acquired in the electronic engineering career at the Universidad Distrital Francisco José de Caldas is used to design and implement a drone to record serial codes for warehouse inventories. Several areas of knowledge such as embedded systems, industrial instrumentation and motor management are involved in this project. For the realization of this project we consulted about the essential elements for the construction of the drone, then they were chosen according to their characteristics and the weight they represented in the structure, establishing two versions, the first based on Arduino elements, and the second with the Pixhawk flight controller. Subsequently, the systems are designed and implemented, and then the corresponding tests are performed.Ítem Método de síntesis de funciones de prueba para optimizadores basado en autocodificadores variacionales y regresión simbólicaLópez Guevara, Juan Pablo; Melgarejo Rey, Miguel Alberto; López Guevara, Juan Pablo [0009-0000-4427-356X]Part of the future work proposed in the degree work Method for the synthesis of two-dimensional optimization landscapes by Mariana Medina is addressed. The process of generating optimizer test problems through the implementation of a VAE is addressed, also proposing the process of characterization of the problems generated through the use of symbolic regressors. The experimental design is carried out on the variations in the number of dimensions that compose the latent space, the symbolic regressor PySR is considered the winner, and finally, the generated and generated databases are compared through the use of a self-organizing map (SOM) trained by means of the use of the ELA characteristics of the generated optimization problems. High-dimensional generation and controlled generation are proposed as future work. The work performed contributes to the development of the paper Optimization test function synthesis with generative adversarial networks and adaptive neuro-fuzzy systems.Ítem Técnicas de Deep Learning enfocadas a la estimación adaptativa de canales en redes de quinta generación(Universidad Distrital Francisco José de Caldas) Chacón Alonso , Andrés Felipe; Fuentes Ramírez, Miguel Angél; Suárez Fajardo , Carlos Arturo; Suárez Fajardo, Carlos Arturo [0000-0002-1460-5831]In mobile communications, the channel estimation process is one of the main keys to optimize the communication between the transmitter and the receiver. Knowing the channel response is a challenge because there are multiple phenomena like attenuation, multi-path loss, noise, and delays that affect the transmitted signals. Methods based on pilot insertion such as Least Squares (LS) and Minimal Mean Squared Error (MMSE) are commonly used to estimate the channel. Nevertheless, they have issues related with their performance and complexity in varying scenarios. In this document, it is proposed that different Deep Learning (DL) techniques assist a pilot-based channel estimation for a 5G communication system affected by Doppler shift due to the level of mobility. Through simulation modeling including Line-of-Sight (LoS) and Non-Line-of-Sight (NLoS) environments in a Tapped Delay Line (TDL) model, it is measured the performance based on the Bit Error Rate (BER), Error Vector Magnitude (EVM), estimation time, and Mean Squared Error (MSE). The results prove that the DL models outperform linear interpolation and practical estimators in a Signal-to-Noise Ratio between 0 dB and 20 dB. Furthermore, the proposed estimation techniques have adaptability to different channel conditions.Ítem Planeación, diseño e implementación de una expansión de red telco cloud Huawei para un operador móvil en ColombiaDurán Pulido, Héctor Julio; Plazas Nossa, LeonardoThis project involved the expansion of a cloud telecommunications network on an existing infrastructure that integrated various technologies and protocols. The project development was carried out in several key stages: first, a detailed analysis of the client's requirements was conducted; then, the solution was planned and designed, which included the incorporation of hardware such as boards, sub-boards, and interfaces, as well as the management of necessary licenses to ensure the optimal operation of the devices. After the solution design, it was implemented during scheduled maintenance windows, minimizing the impact on network operations. Finally, switching tests of the new interfaces and technologies were conducted to ensure proper functionality, resulting in the successful delivery to the client and the completion of the project.Ítem Análisis del blanqueamiento coralino en fotografías subacuáticas con redes neuronales artificialesFernández Rodríguez, Carol Zuleimy; López Sánchez, Wilson Ricardo; López Sánchez, Wilson Ricardo [0009-0004-2836-4794]Coral bleaching, a phenomenon that affects coral reefs around the world, is a crucial indicator of the health of marine ecosystems. The ability to accurately monitor and evaluate bleaching is critical to understanding its impact and taking effective conservation measures. The present work addresses the challenge of coral bleaching by developing a methodology based on artificial neural networks to analyze underwater photographs and quantify the degree of coral bleaching. The methodology consists of three phases: detection of corals for which the Grounding DINO model was used, segmentation of corals with the Segment Anything model and quantification of bleaching with the K-means algorithm. To validate it, an image bank was used and the results were compared with manual segmentation carried out with the help of a coral expert. High efficiency was demostrated in the detection and segmentation of corals, as well as in the identification of areas affected by bleaching in most cases. However, challenges related to color quantization were identified, especially under lighting conditions and specific coral characteristics. This study represents a significant advance in the development of automated tools for monitoring coral bleaching, offering new perspectives for the research and conservation of marine ecosystems.Ítem HTZ: Diseño, simulación y optimización de radioenlaces satelitales(Universidad Distrital Francisco José de Caldas) Corredor Cortés , Juan David; Vaca Paiba, Jersson Andrés; Poveda Zafra , José Noé; Poveda Zafra, José Noé [0000-0002-4099-894X]This project examines the use of HTZ Communications software in the planning, design, and simulation of satellite links, essential for reliable connectivity. It provides a practical guide detailing the process from data importation to link simulation, highlighting the software's ability to optimize key parameters and ensure signal quality. The simulation of a link between Bogotá and Leticia, using the Intelsat 901 satellite, demonstrated the software's effectiveness, underscoring its utility in improving connectivity in remote areas of Colombia.Ítem Diseño de un prototipo de asistencia para invidentes mediante el uso de redes neuronales convolucionalesHernández Jurado, Fabián Camilo; Rivera Henao, Johan Sneider; Gaona Barrera, Andrés Eduardo; Gaona Barrera, Andrés Eduardo [0000-0002-3966-5646]This document presents the development of a functional prototype to assist urban mobility for visually impaired individuals, primarily based on artificial vision using convolutional neural networks. Additionally, it explores different alternatives for training the object detection and classification model, which is derived from a personalized database created specifically for the stated objectives.