Ingeniería en Electrónica y Telecomunicaciones

Permanent URI for this communityhttps://dspace-test.ucuenca.edu.ec/handle/123456789/32

Browse

Now showing 1 - 20 of 175

Algoritmos de aprendizaje no supervisado para la estimación de la resistencia a la insulina y el síndrome metabólico en el adulto mayor de la ciudad de Cuenca
(2017) Vintimilla García, Christian Xavier; Wong de Balzan, Sara; Astudillo Salinas, Darwin Fabián
In this degree work, Insulin Resistance (IR) and Metabolic Syndrome (MS) are explored in the Cuenca‘s elderly population, from the point of view of unsupervised classification methods. In the case of IR, five estimation methods were analyzed using a K-means classification on a population of 119 people older than 65 years old who underwent a two-point Oral Glucose Tolerance Test (OGTT). The K-means algorithm with K = 2 and K = 3 was applied in onedimensional experiments for the Homa-IR, Quicki, Avignon, and Matsuda methods. The results obtained allowed the development of a platform to aid in the diagnosis of IR. These findings were object of two publications (IV Congress of Information and Communication Technologies TIC-EC 2017, and IEEE ETCM 2017: 2nd IEEE Ecuador Technical Chapters Meeting). For the study of MS using Kohonen’s SOM, two types of normalization (binary and by rank) were analyzed for the inputs of the neural network using a population of 387 elderly people. The results, using a pre-processing by ranges allow a better classification of the population in all cases. This study allowed to select the type of pre-processing for the diagnosis of MS in the elderly population of the city of Cuenca using SOM and was the object of a publication in the V Congress REDU 2017 and the II Congress I+D+Ingeniería. The future work is oriented to validate the results obtained in other elderly populations.
Análisis comparativo de algoritmos de posicionamiento para un sistema de localización basado en tecnología LoRa
(2019-04-29) Arpi Saquipay, Braulio Vinicio; Sánchez Venenaula, Christian Paúl; Vázquez Rodas, Andrés Marcelo; Astudillo Salinas, Darwin Fabián
Along the last years, we have seen a growing demand of services and systems that depend on the specific location of both people and different kinds of gadgets. For this reason, there is an interest on the development and evolution of Positioning Systems (PS) that use the Wireless Sensor Networks (WSN) to complex location services. The main aim of these PS is to estimate the relative position related to other known positions inside of a coordinate system. Currently, the Global Positioning System (GPS) offers good accuracy on location services around the world. Although it does not work effectively on applications with a high amount of small, cheap and low power requirements devices. Therefore, current researchers prefer to work on new low-cost wireless technologies; for example, WiFi, Zigbee, or LoRa. In this context, it is very important to know some fundamental aspects before of start to design a PS. For example; the architecture of the PS, sources of error; common positioning algorithms, such as ToA, TDoA, AoA, and RSSI; and common location algorithms, such as multilateration, triangulation, and trilateration. Besides, it is important to know the needs and limitations of both positioning and localization algorithms about RF features. The main purpose is to verify the feasibility of determined devices available to design and implement the PS. To conclude, this thesis project has the main aim to design and implement a low-cost PS based on RSSI positioning algorithm and trilateration location algorithm. To analyze the behavior and feasibility of both FiPy and LoPy devices with LoRa technology in location applications. Besides, the thesis evaluates a set of tests to find irregular behaviors and to mitigate these problems. As a final result provide a PS working correctly; and a comparative analysis about the accuracy error among different scenarios and similar studies.
Análisis comparativo entre sistemas de clasificación basados en técnicas de Machine Learning para catalogar tipos de empuje de un patinador de velocidad
(Universidad de Cuenca, 2023-08-23) Albornoz Tépan, Ximena Lorena; Ulloa Montaleza, Bryan Sebastián; Astudillo Salinas, Darwin Fabián
Speed skating is a highly regarded sport that requires technical skills and an optimal physical condition; nevertheless, there is a need for a tool that complements the training of athletes in training. Thus, the use of artificial vision and Machine Learning (ML) systems is proposed. For the former, the OpenPose system is used to obtain data about the skater’s joins and keypoints; the latter, to identify and classify the type of push when skaters use the inline technique. In the research, 2 main focuses are explored. The first one consists of image classification through a Convolutional Neural Network (CNN), using the Visual Geometry Group (VGG)19 architecture, achieving an accuracy of 90.72 %. The second approach uses feature vectors through a biomechanical analysis with a Support Vector Machine (SVM) system and a Random Forest (RF) algorithm, obtaining an accuracy of 94 % y 92 %, respectively. Different evaluation metrics are presented, such as accuracy, precision, sensitivity, and F1-score, along with a confusion matrix and Receiver Operating Characteristic (ROC) curves. Moreover, features of the prior-mentioned approaches are discussed, for instance, the use of data augmentation to combat overfitting. Furthermore, the study includes result tables of biomechanical variables and pictures of distinctive angles during the execution of for- ward pushing techniques. Overall, the CNN and SVM exhibit promising results in the classification of data for the different types of pushes in speed skating inline technique.
Análisis comparativo entre tecnologías dedicadas y soluciones de bajo costo para la implementación de sistemas domóticos
(Unversidad de Cuenca, 2023-02-01) Astudillo Vallejo, Victor Daniel; Reinoso Delgado, Joel Francisco; Minchala Ávila, Luis Ismael
This work presents details about the design and implementation of two home automation systems, in order to compare the efficiency, reliability, security and scalability between a technology dedicated to home automation and another low cost and easy integration (DIY - Do It Yourself). In this context, Local Control Network (LCN) technology is compared, on the one hand, and devices that can be integrated with Amazon's voice assistant, Alexa, on the other. Each network is planned with the intention of automating the luminaires, as well as their intensity, the automatic disconnection of equipment that consumes energy unnecessarily, and a surveillance system. The two houses present similar consumption habits, which allows them to be compared and to determine to what extent the low-cost solutions have efficient performance compared to dedicated technologies. Additionally, to improve the performance of home automation systems, architectural modifications of each technology are proposed, such as the implementation of a visualization system through a free software platform, Home Assistant; likewise, the sectioning of the low-cost network. This implementation made it possible to define the main advantages of dedicated technologies that use bus lines, highlighting scalability, low latency and security over low-cost technologies; On the other hand, its cost is very high and it has many benefits for application in home automation.
Análisis de algoritmos de aprendizaje máquina aplicados a la asignación de recursos en la red de acceso para redes 5G con segmentación
(Universidad de Cuenca, 2023-09-26) Carabajo Avila, Sthefany Paola; Chimbo Vega, Michelle Giovanna; Astudillo Salinas, Darwin Fabián; Tello Oquendo, Luis Patricio
This degree project focuses on the study and improvement of the random access method in 5G networks, applying two approaches for the dynamic management of preambles. In this context, users request uplink resources by transmitting preambles, which are characterized by being orthogonal signatures. However, one problem that arises is the possible congestion and network collapse when multiple identical signa- tures are transmitted in a short period of time. The first method consists of the use of supervised learning by training a neural network using a set of data that contains in- formation about the preambles that have previously benefited the system during tests carried out. The neural network processes this information and generates outputs that indicate which preambles are best suited to avoid crashes and improve the probability of successful access to uplink resources. The second proposed method involves the use of reinforcement learning, which implements a policy for preamble management based on Q-learning. In this approach, a function called Q is used that evaluates ac- tions taken in specific states of the system. The system continually feeds itself back, reinforcing those choices that benefit the system’s performance and punishing those that harm it. In this way, the random access system can learn to allocate preambles more intelligently and effectively, adapting to network conditions and optimizing the utilization of available resources.
Análisis de amenazas de seguridad basado en la detección de anomalías en el tráfico de red de la infraestructura tecnológica de instituciones de educación superior mediante el uso de técnicas de machine learning
(Universidad de Cuenca, 2021-10-18) Vásquez Bravo, María José; Astudillo Salinas, Darwin Fabián
Communications networks have undergone unprecedented developments, mainly due to a significant increase in data traffic. This makes the issue of the security of technological infrastructures an important point to be addressed within the scope of Higher Education Institutions. These types of institutions handle large amounts of data, which imply an increase in network traffic; therefore, the anomalies or vulnerabilities number’s have been progressively increasing. These security attacks involve threats to the confidentiality, integrity and/or availability of the data handled. However, there are tools such as ML algorithms, which allow pre-detection of such events. The present experimental work carries out the framework’s implementation that allows anomalies’ detection in the Higher Education Institutions network’s traffic applying ML techniques, specifically in the UNACH case. To do this, a collection of events corresponding to a time lapse was analyzed through the ELK stack; subjected to data’s preprocessing stages, storage and visualization for the analysis. Through the application of the K-Means algorithm, developed through Python’s Scikit-Learn library and Weka software, a total of three experiments were performed on the collected events. This allowed the detection of potential threats or anomalies, which will be presented and corroborated using dashboards developed in Kibana. Through the implementation of this framework, the clusterization algorithms’ utility was verified as an optimal tool for the anomalies’ detection within a university network. Obtaining anomalous behaviors within the network such as interference, channel overlaps, authentication of unidentified users or identification of unauthorized AP.
Análisis de factibilidad del uso de unidades de procesamiento gráfico en algoritmos de optimización meta-heurísticos
(Universidad de Cuenca, 2020-10-16) Guiracocha Yuquilima, Manuel Mesias; Astudillo Salinas, Darwin Fabián; Torres Contreras, Santiago Patricio
Currently, several real-world optimization problems have been mathematically modeled. The modeling process takes into account as much information as possible so that the model obtained is as close to reality. However, as information increases, complexity also increases. Consequently, larger computational capacity is needed to solve complex and scalable problems. Exact or mathematical optimization methods are considered exhaustive, which for multi-dimensional problems is not practical. As a result, meta-heuristic algorithms have been developed to solve complex optimization problems. These algorithms are commonly used for problems of two or more dimensions, involving vector and matrix operations. Therefore, to solve this type of problem, it is useful to carry out parallel processes that reduce the runtime. Currently, there are multi-core CPU that can easily solve small problems with parallel calculations. However, the GPU offers the potential to improve performance by incorporating a larger number of cores than the CPU, which is very useful for problems with multiple processes in parallel. A classic problem in the electrical power systems research community is the Transmission Expansion Planning (TEP). In the Department of Electrical, Electronics, and Telecommunications Engineering, in the project “Use of the AC model for multi-stage integrated planning of transmission / sub-transmission line expansion and reactive power sources in electric power systems”, It is tried to improve the performance of the TEP problem. The project seeks to reduce the calculation time by improving the meta-heuristic algorithms. In this final d egree p roject, a s a c omplement t o the aforementioned project, the feasibility of reducing the execution time was analyzed, implementing the meta-heuristic algorithms using a GPU. For which, prior to the implementation of the TEP problem, the use of the GPU in parallelizable problems and the implementation of a meta-heuristic algorithm in a two-dimensional problem were analyzed, in which favorable results have been obtained to motivate the use of the GPU
Análisis de la aplicación de auto codificadores en sistemas de comunicaciones para minimizar el efecto del ruido
(Universidad de Cuenca, 2024-08-30) Otavalo Alvarado, David Andrés; Zaruma Morocho, Samantha Fernanda; Solano Quinde, Lizandro Damián
Conventional communication systems use processing blocks to perform specific tasks, such as encoding or modulating input signals. Recently, Deep Learning (DL) theory has inspired programmers and researchers in the area of digital communications to apply it to these traditional systems with the aim of making them adaptable to different environments, reducing the complexity in the design of blocks that perform specific tasks. In this context, the main objective of this work is to develop an Autoencoder (AE), which is the application of an unsupervised learning artificial neural network, with an encoding-decoding structure similar to that of a conventional communication system. The model presented in Chapters 4 and 5 is developed using the TensorFlow libraries and functional API. The implemented encoding was based on the following modulation schemes: BPSK, QPSK, 8-PSK, 16-PSK, 32-PSK, 4-QAM, 16-QAM, 32-QAM, 64-QAM, and 128-QAM. Through training, the model aims to efficiently reduce the error between the original information and the reconstructed information after passing through a noisy AWGN channel. To optimize the training, the early stopping technique is incorporated, which halts the training when the loss function values stop improving. To verify the functionality of the AE, constellation diagrams, Block Error Rate (BLER) and Bit Error Rate (BER) plots were obtained for each modulation scheme. These graphs were analy- zed and compared with the typical curves of the aforementioned digital modulations. The results of the autoencoder indicate greater precision and efficiency in reconstructing the transmitted data, consequently leading to a significant improvement in information transmission.
Análisis de la calidad de servicio de SMA en la ciudad de Cuenca mediante el diseño e implementación de un sistema de control de calidad usando los datos obtenidos del sistema autónomo de control de redes móviles (SAMM)
(2017) Fernández Landívar, Jimmy Xavier; Reino Abad, Paola Gabriela; Ochoa Figueroa, Edgar Efraín
The telecommunications regulation and control agency (ARCOTEL) controls the service offered by the mobile operators of Ecuador, monitoring and checking their networks, with the principal objective of guaranteeing the compliance of the established normative and the contractual parameters. The Autonomous System of Mobile Networks (SAMM) is a tool that allows making measurements of the quality parameters in Advanced Mobile Service (SMA) and placing them into a database for a subsequent process and analysis. The principal purpose of this project is the performance of a comparative analysis of the quality in Advanced Mobile Service offered by the mobile operators in Cuenca city. For this reason, an algorithm was design and implemented that optimizes the time employed to process data obtained from SAMM server, allowing a more efficient control on the quality of SMA. An investigation was developed about Advanced Mobile Service, the current normative and resolutions in Ecuador, and a study of SAMM, its functional diagram, architecture and system components. Then, it was implemented a tool that allows the download and process of the information saved into SAMM server. Finally, the developed tool obtained data, within July 2015 and June 2016, related to calls, shorts messages, quality of conversation and coverage level, the last one mentioned provided by ARCOTEL. With the information obtained, a comparative analysis was made between the three mobile operators offering services in Ecuador. Through the analysis of the acquired data, a perspective of mobile service was given concerning to the center zone of Cuenca city, determining the operator with the highest Quality of Service index for each parameter.
Análisis de la calidad de servicio de telefonía fija inalámbrica CDMA 450 de la Corporación Nacional de Telecomunicaciones (CNT. EP.) en la provincia del Cañar
(2013) Bravo Farfán, Jorge Luis; Mendoza Neira, Mirian Susana; Arévalo Maldonado, Sofía Priscila
This graduation project performs a study about the CDMA 450 wireless fixed telephone service evolution and actual state in the Cañar province, through the evaluation of some technical system parameters. In order to get the main goal it develops coverage diagrams of every node in the province, it makesmeasurement of received power in the user terminal in different places, it realizes comparison between software coverage diagrams and real coverage, it makes a node traffic monitoring and test calls where it evaluates theestablishing time and drop calls in the system. Also it identifies the causes of the service degradation and the geographical zones where it is affected. Finally this document presents a set of solutions in order to enhance service quality; these solutions are based in the test outcome analysis developed during this project.
Análisis de la factibilidad de mejorar la disponibilidad del sistema SCADA durante los procesos de mantenimiento de los equipos de la micro-red de la Universidad de Cuenca
(Universidad de Cuenca, 2024-09-06) Gutiérrez Otavalo, Lourdes Verónica; Padilla Guamán, Claudia Estefanía; Astudillo Salinas, Darwin Fabián; Villa Ávila, Edisson Andrés
This report focuses on the challenges associated with increasing the availability of Supervi- sory Control and Data Acquisition (SCADA) systems in the industrial sector, specifically in the Micro-Grid Laboratory of the University of Cuenca. This system monitors and controls various equipment through a wired Operational Technologies (OT) network. The primary problem addressed lies in the interruptions caused in the communication and control of the SCADA system during device maintenance procedures, which affects the sys- tem’s functionality. Disconnecting the power supply for maintenance results in a temporary loss of device detection and control by the SCADA, thus causing a forced system shutdown. To address this issue, three potential hypotheses are proposed. Firstly, the management of network redundancy through Weidmüller switches is explored, using protocols such as Spanning Tree Protocol (STP), Rapid Spanning Tree Protocol (RSTP), Spanning Tree, and Turbo-Ring. Secondly, the installation of a physical bypass in the network to prevent interruptions is suggested by reconfiguring the fiber optic infrastructure. Lastly, the SCADA implementation is analyzed, focusing on the algorithm implemented in Laboratory Virtual Instrument Engineering Workbech (LabVIEW) and correcting the detected flaws. Each hypothesis was validated through the research methods utilized. The implementation of the selected solutions has achieved continuity in the control and communication of the SCADA system during maintenance processes. Finally, the thesis work concluded with the fulfillment of all the objectives set and a considerable improvement in the system’s initialization time, achieved through all the experiments conducted, mainly by modifying the LabVIEW programming.
Análisis del rendimiento y eficiencia de un sistema Radio-over-Fiber sobre una red PON mediante Optisystem
(Universidad de Cuenca, 2021-09-30) Cabrera Cochancela, Iván Fernando; Zambrano Jaramillo, José Andrés; Araujo Pacheco, Alcides Fabián
In the present work radio over fiber systems RoF aimed at the application of mobile networks or more specifically for the development of 5G cellular technology, were studied. The insertion of RoF technology on a GPON-FTTH network was estudied, using it as a fronthaul for the mobile service. Contribution obtained is consistent with the new Fi-Wi technology standards that are being developed and gives a new perspective at the time of its implementation, taking it as a reference. Thus, the following questions were raised: What would be the performance and efficiency of a FTTH network when inserting RoF technology for the mobile service? Will the performance and efficiency be maintained or will it have any disturbance? The answers to the previous questions correspond to the justification of this work, aimed at expanding the field of services applied to fiber optics without representing a greater investment to the interested parties. For the aforementioned, the OptiSystem software was used to analyze the FTTH-RoF system for the mobile service. Initially, a GPON-FTTH network was characterized considering both download link and upload link. Similarly, the RoF system was designed in its two versions: A-RoF and D-RoF, considering them as two case studies. Both study cases were based on OFDM system with QAM modulation: 4-QAM, 16-QAM and 64-QAM. For the case of the FTTH network, a bit rate of 2.5 Gbps for download link and 1.25 Gbps for upload link was considered; while for mobile system, a bit rate of 5 Gbps was simulated for both links. Subsequently, the system was multiplexed, achieving a convergence of services that made it possible to evaluate its performance. The performance and efficiency evaluation of GPON-FTTH system was performed based on OPM parameters, among which is considered to the following: attenuation, chromatic dispersion, signal-to-noise ratio OSNR, BER, quality factor Q , eye diagram and constellation diagram
Análisis digital forense de los sensores de un teléfono inteligente para la detección y recreación de actividad motriz inusual en una localización determinada
(2016) Espinoza Farfán, David Antonio; Yánez Rodas, Juan Martín; Campos Argudo, Karina Pamela
The objective of this research is to develop a new methodology in order to detect and recreate unusual motor activity from a possible victim in a determined location. This work is framed within the field of digital forensic analysis, branch of criminology which is in charge of obtaining potential digital evidence from electronic devices with criminal purposes by applying a set of adequate techniques and procedures. This work has as its base the use of information obtained from a smartphone, so in first instance an application for the Android operative system is developed with the purpose of extracting and registering measurements from some sensors of the device. Once the information is stored it is processed and analyzed in MATLAB, from which the identification of abrupt movements is achieved regardless of the type of activity performed by the victim at the time of the incident. Finally, a desktop application is developed in the same platform, it contains a graphical interface in which is presented the digitalized reconstruction in three dimensions of the trajectory followed by the victim, as well as the geographic location of the exact site where the incident occurred. In the desktop application is also presented other information relevant to the forensic research like the resultant acceleration before and after the occurrence of unusual activity, the date and hour, number of steps taken by the victim and the total distance of displacement.
Análisis e implementación en NS3 de un modelo de propagación difusivo para comunicaciones moleculares
(Universidad de Cuenca, 2021-04-27) Calderón Calderón, José Paúl; Zúñiga Gómez, Eddy Andrés; Astudillo Salinas, Darwin Fabián; Tello Oquendo, Luis Patricio
In this research, analysis and implementation of a MPD for MCs are performed in NS-3. The work is based on the IEEE 1906.1-2015 standard recommendation, which seeks to create a reference framework for MCs. The standard provides a simulation module in NS-3, which contains only the general structure components of MC and their interaction. The components mentioned are Message Carrier, Motion, Field, Perturbation and Specifity. The research is focused on four aspects: Modulation, Molecules movement, Inter Symbol Interference, and Demodulation. For modulation, the Perturbation component is modified, and the CSK modulation is implemented, which releases a certain number of molecules depending on the transmitted bit. Concerning the molecules movement, the Brownian mathematical model is implemented within the motion component. Also, two types of BM are considered: simple and drifting. The former refers to a free molecular motion, and the latter refers to a motion influenced by the direction of the fluid in which it moves. On the other hand, the fundamental element in the simulation is the medium, which manages the components motion and field. Within the medium the ISI is implemented. This interference considers molecules that remain moving in the medium and arrive at the receiver out of time. Finally, for the demodulation, the receiver has been modified to use the amplitude-based molecule detection technique. This technique demodulates the information depending on the number of molecules that have arrived at a determined time. Free BM, BM with drift, free BM bounded by the medium, and BM with drift bounded by the medium are considered. In addition to the modifications made, a data collection model was implemented to analyze the results, where the movement of the molecules is captured and, if they reach the receptor, the time is recorded. As a result, the pulse train of the concentration of molecules as a function of time at the receiver is obtained. Also, the delay time, the amplitude of the number of molecules, the pulse width, and the channel capacity as a function of distance at the receiver are evaluated. Besides, the obtained results are validated with an investigation performed in N3Sim. Finally, it is corroborated that the receiver’s concentration using the MPD implemented complies with the mathematical model established by Fick’s second law
Aplicación de MANET’s como sistema de comunicación en la movilidad sostenible
(Universidad de Cuenca, 2023-09-15) Eras Eras, Nancy Maribel; Otavalo Quito, José Andrés; González Martínez, Santiago Renán
Sustainable mobility is crucial in today’s society, which seeks to reduce greenhouse gas emis- sions and promote the use of cleaner and more efficient means of transportation. The bicy- cle has become essential as it offers affordability, efficiency, health, safety and environmental friendliness. Thus, different cities have promoted bicycles from both the public and private spheres, implementing technologies that improve their operation and safety. The Mobile Ad- Hoc Network (MANET) have emerged as an innovative solution to improve communication in sustainable mobility. This research work proposes an experimental methodology to implement a communication system between electric bicycles as nodes of a MANET and the evaluation of the same using the proactive routing protocols Optimized Link State Routing (OLSR) and Bet- ter Approach to Mobile Ad-Hoc Networking (B.A.T.M.A.N.). The network configuration is set up systematically, considering the 2.4 GHz wireless channel conditions, maximum transmission range and bandwidth at one and three hops. In addition, an application layer solution is provi- ded in order to simulate the transmission of text messages and audio traffic in the network. In order to compare the functionality of the communication system using each protocol, different test scenarios with fixed and moving nodes are established. In terms of the network metrics evaluated, the Delay, Packet Reception Ratio (PRR) and Throughput were used.
Arquitectura de control centralizado usando un enfoque cuasi óptimo para la regulación de la marcha bípeda de un exoesqueleto de extremidades inferiores
(Universidad de Cuenca, 2021-04-07) Córdova Cuenca, Andrés Fabricio; Morales Guamán, Hernán Augusto; Minchala Ávila, Luis Ismael
Robotic devices have reached an important role in modern society, where their presence is increasingly common in the industry and personal use. Specifically to the rehabilitation field, it is entirely beneficial to have robotic devices that help specific pathologies’ recovery processes. This project introduces the design and implementation of a quasi-optimal control architecture to manage distributed controllers of a single lower limb robotic exoskeleton. To achieve this, a control and communication topology of the exoskeleton is established based on a master node and three slave nodes. The communication system employs CAN protocol with Process Data Objects (PDO), which reduces communication times by not using acknowledgement (ACK). Comparing it with SDO, there is a significant improvement, so it demonstrates the potential of PDO to take full advantage of the CAN bus. This system is implemented in the central node utilizing CAN reading and writing functions for frame management. The control system is also implemented in this node, which sends the necessary orders to each of the EPOS4 distributed controllers with an internal speed and position controller for the application of gait trajectory. Furthermore, it includes a heuristic-based optimizer that analyzes the error to determine when a correction of the control signal is necessary to apply to minimize the trajectory tracking error. The result is a functional single lower limb exoskeleton with three joints: hip, knee, and ankle. Control and communication algorithms showed an improvement over previous versions regarding the time of sending and receiving data through CAN bus, as well as its processing in the central node. In consequence, this allows planning an extension of the algorithms for an additional limb. This project makes it possible to clarify the capabilities of distributed nodes to establish solid bases for future research with the prototype. In this way, the subsequent studies could focus on improving the control system and a possible paradigm change. This would imply performing several tests with the prototype in the rehabilitation area to eventually improve people’s health status and their quality of life.
Clasificación automática de señales para comunicaciones inalámbricas basada en técnicas de inteligencia artificial
(Universidad de Cuenca, 2025-09-24) Pardo Castro, Carlos Andrés; Pérez Vargas, Juan Pablo; Solano Quinde, Lizandro Damián; Palacio Baus, Kenneth Samuel
This work addresses the identification of digital modulation schemes under realistic chan- nel conditions—multipath fading, additive white Gaussian noise (AWGN), and carrier phase offset—across six formats: BPSK, QPSK, 16-QAM, cross-32-QAM, 64-QAM, and cross-128- QAM; a complementary analysis with 256-QAM is also included to assess performance under higher constellation orders. To capture channel variability, scenarios with different signal-to- noise ratio (SNR) levels, numbers of propagation paths, and phase-offset values were gene- rated using the TorchSig toolkit; the resulting baseband in-phase/quadrature (I–Q) signals fed three neural-network architectures trained and evaluated in supervised classification tasks. Finally, a voting-based ensemble that combines the top k models from each network is pro- posed, yielding consistent gains in correct classification probability (PCC) across all evaluated scenarios.
Comparación de modelos de seguimiento solar y análisis económico-eléctrico de un sistema solar fijo
(Universidad de Cuenca, 2021-08-11) Carpio Vintimilla, Javier Fernando; Gonzalez Morales, Luis Gerardo
The environmental damage caused by the use of fossil fuels has increased substantially on the planet, this drives initiatives that promote the use of new non-conventional renewable energy sources, in this case photovoltaic solar energy. This is a clean energy because it does not produce environmental pollution and sustainable because the solar resource is present all the time on our planet. The present work seeks to analyze the generation of electricity through photovoltaic solar energy, comparing three different systems. For this purpose, three small-scale prototypes of solar energy collection are analyzed through simulations and measurements, which are: the conventional fixed system with a panel taking data in a single geographical position all the time, secondly, a solar tracker of one axis (from east to west) and finally a tracker of all cardinal points (two axes) is added, to analyze through results the best solar photovoltaic system. Complementarily, an electrical and economic analysis of the photovoltaic system of the Balzay Campus of the University of Cuenca is carried out to determine the feasibility of executing studies of solar photovoltaic micro generation projects considering the regulations of the public service of electric energy in force in Ecuador, both for companies and conventional houses in the city of Cuenca. In addition, a small survey is conducted to determine what economic value people would be willing to pay for a clean electricity service
Construcción de un ventilador manual invasivo de asistencia mecánica para respiración asistida
(Universidad de Cuenca, 2021-11-05) Carrión Portilla, Paúl Gustavo; Montalván Astudillo, David Andrés; Minchala Ávila, Luis Ismael; Astudillo Salinas, Darwin Fabián
In mid-December 2019, in the city of Wuhan, China, the first cases of the infectious respiratory virus COVID-19 were reported. COVID-19, according to the World Health Organization (WHO), is an infectious respiratory disease caused by a virus belonging to the large CoV family (Coronavirus). The symptoms vary in intensity for each human being, from a mild clinical picture that does not require specific care, to severe symptoms that could lead to a series of serious diseases that require intensive respiratory treatment or in the worst cases, death. This situation forces the medical staff to decide if patients are suitable to access the different life support treatments according to the "severity and intensity of the resources", including the use of mechanical ventilators. However, the creation of new medical devices to alleviate this saturation is possible, which is why the construction of low-cost portable ventilators is presented as an important and feasible solution. This document shows the process followed in order to build an assisted mechanical ventilator model. The model was developed based on the research collected during the pandemic by Italian physicians and MIT. This ventilator allows patients with less severe Covid-19 symptoms to be cared for by less experienced healthcare specialists. All this helps while the rest of the resources are used in patients with severe clinical case. In the implementation, a satisfactory operation of the device was obtained in addition to having reduced costs in its construction. Compression of the manual resuscitation bag was achieved by varying the tidal volume, which is designed to vary in a range between 100 and 800 ml. Likewise, the assisted mode has greater precision for tidal volume values between 400 and 500 ml and a RR of 1.2 Brpm
Construcción e implementación de un modelo para diagnosticar el nivel de la ciberseguridad en una micro-red. Caso de Estudio: micro-red de la Universidad de Cuenca
(Univerisdad de Cuenca, 2023-05-25) Jiménez Mendieta, Daniela Dolores; Sumba Naula, Julio Andres; Astudillo Salinas, Darwin Fabián
A cyberattack on a critical infrastructure can cause a crash or interruption in its operation. The direct consequences in the environment where the impact occurs are very high, causing serious economic losses, in addition to endangering human lives or affecting the environment. A micro- grid is within this type of structure, so a cybersecurity maturity model is important for them. In the present work, the construction of a cybersecurity maturity model was made, which allows measuring the level of cybersecurity maturity in a micro-grid, this model is based on the series ISO 27000, NIST 800 and the C2M2 model. The model is made up of ten domains, which have a series of attributes with different assigned scores, and four levels of maturity indicators NIM, which have a range of scores and color indicators to establish the level of maturity in which is a micro- grid. A web application was developed, which allows the evaluation of cybersecurity using the model created through a questionnaire, allowing to establish and show the level of maturity in which a micro-grid according to the results. As a case study, the evaluation of the microgrid of the University of Cuenca was carried out. The results obtained are detailed, and based on them, recommendations were made to increase the level of maturity of the same.