Ciencias Exactas y Ciencias de la Salud
Permanent URI for this collectionhttps://hdl.handle.net/11285/551039
Pertenecen a esta colección Tesis y Trabajos de grado de las Maestrías correspondientes a las Escuelas de Ingeniería y Ciencias así como a Medicina y Ciencias de la Salud.
Browse
Search Results
- A comparison between Machine Learning models for OSA detection based on ECG signal(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-12-04) Espinosa Varela, Miguel Angel; Ponce Cruz, Pedro; emimmayorquin; Ponce, Pedro; Rojas, Mario; Borja, Vicente; Mata, Omar; Molina, Arturo; School of Engineering and Sciences; Campus Ciudad de México; Rojas Hernández, MarioOSA is a one of the most common sleep disorders nowadays, which is diagnosed by a Polysomnography (PSG) study. Even though this is the golden standard to diagnose OSA, it is time consuming, very expensive and there are not many specialized centers to conduct it, this implies that fewer patients are diagnosed. The development of new solutions at a lower cost and in less time would allow more patients to be diagnosed and treated promptly. There are solutions that enable the diagnosis of OSA through monitoring signals from the human body, including an auto-diagnosis. However, these solutions do not aim to perform screening on the most significant parameters along with the best model for making predictions. The main objective of this tesis is to make a comparison between 27 Machine Learning (ML) models in order to find the best model to diagnose OSA. It also aims to find which are the most representative parameters in OSA detection. By doing a frequency-domain, time-domain and non-linear domain analysis to extract them from the RR intervals, and with a wilcoxon test and correlation matrix, select the most useful ones. The results showed that the best model was Support Vector Machine (SVM) with an accuracy, balanced accuracy, ROC AUC and F1 Score of 0.97. The most significant parameters found were: RR tri index, LF/HF ratio, alpha 2, HF\%, SDNN and RMSSD. This solution can be integrated into current clinical cases for a quick OSA diagnosis. Proposal does not aim to replace PSG for a complete and accurate diagnosis, but to be a pre diagnosis accessible to a larger number of patients. Health providers can implement this solution and reduce the number of patients in the waiting list. Also, this proposal would make research in OSA diagnosis more accessible and provide a framework that can be the starting point to other researchs.
- A comparison between fuzzy logic, and PID controllers to guidance their application in a DC-DC boost converter system with PV source(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-12-01) Aguirre Damián, Bernabé; Ponce Cruz, Pedro; emiggomez, emipsanchez; Molina Gutiérrez, Arturo; School of Engineering and Sciences; Campus Ciudad de México; Sánchez García, José ManuelThere is a need to integrate alternative sources of energy due to the expected lack of conventional sources, in addition to this energy consumption is expected to grow. Solar photovoltaic (PV) energy has emerged as a highly abundant source, and its use has increased in recent years, but it is important to consider that, as this source produces direct DC power, the voltage regulation is a crucial part in PV systems. To achieve this task PID control is a widely used control technique, however intelligent control strategies have been developed in recent years, among these strategies, Fuzzy Logic Control (FLC) use has been increasing, as it aims to be a simpler control technique. PID and FLC have both been used to control the voltage in PV systems, each of these techniques being capable of regulating the output voltage in DC-DC converters, but both controllers behave differently, and each have their own tuning mechanism, so, in order to prove the performance of both control methodologies, a comparison to differentiate the main features that these controllers can bring in PV systems is required. In this work it is developed a DC-DC boost converter model in MATLAB/SIMULINK, and with the application of optimization algorithms, such as particleswarm, patternsearch, simulannealbnd and genetic algorithms it is tuned the PID gains, and it is developed a PID controller tuned by each algorithm and are compared with fuzzy controllers whose membership functions are tuned with the information obtained by the PID controllers performance. In total 8 different controllers are compared, even though the PID controllers presented lower error values, the FLC’s presented advantages in rise time and settling time reduction, overshoot minimization and ripple limitation in the response. In addition, a robustness analysis of both controller methodologies is carried out, changing the temperature and irradiance from the PV source, and a sensitivity analysis of the controllers changing the voltage reference.
- Multi-criteria decision-making fuzzy TOPSIS for the integration of solar energy systems in small and medium-sized mexican manufacturing companies based on the S4 framework(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-06-14) Pérez Briceño, Citlaly; Ponce Cruz, Pedro; puemcuervo, emipsanchez; Méndez Garduño, Juana Isabel; Maldonado Romo, Javier; Rojas Hernández, Mario; School of Engineering and Sciences; Campus Ciudad de México; Molina Gutiérrez, ArturoOver the past few years, there has been a significant increase in the demand for electrical energy due to a rise in population and industrial automation. However, most of the electricity worldwide is currently generated from fossil fuels, leading to detrimental environmental and human health effects. To address this issue, using solar energy as a source of electricity has gained popularity. Solar energy not only diversifies energy sources but also offers cost savings and reduces dependence on fossil fuels. Consequently, it leads to a decrease in CO2 emissions and minimizes the overall environmental impact. In Mexico, there needs to be more awareness and knowledge regarding the benefits and potential of solar photovoltaic (PV) systems. As a result, the adoption rate of these systems is slower, particularly among small and medium-sized manufacturing companies. Choosing the appropriate technology and elements for solar PV systems is complex, and the available resources to guide decision-making are limited. Existing frameworks and guidelines for solar PV systems primarily focus on the technical aspects of the installation stage, neglecting other crucial elements and stages in the lifecycle of these systems. Moreover, most of these frameworks are tailored to European, Asian, or North American contexts, with minimal consideration for the Latin American context. Selecting a solar panel company for PV system installation becomes challenging due to a lack of information and multiple factors with varying levels of importance, including technical, economic, environmental, and social aspects. Therefore, decision-makers require a suitable tool and methodology to analyze available choices and select the best option. The main objective of this thesis is to adapt the S4 Framework proposed in the literature. The aim is to determine the representative features that need to be considered within the S4 Framework to adopt PV systems. This adaptation involves employing a multi-criteria decision-making method and integrating sensing, smart, sustainable, and social features. The framework intends to provide guidance and support for decision-makers installing, operating, and disposing of PV systems. To validate the effectiveness and practical applicability of the framework, a case study is conducted in a Mexican machinery and equipment manufacturing company located in Baja, California. The results of the case study demonstrate the practicality and effectiveness of the framework, highlighting its potential to assist decision-makers in the PV system adoption process.
- Design and implementation of a sensing platform to assess and forecast environmental conditions(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-05-25) Rivera Corona, Antonio Carlos; Ponce Cruz, Pedro; puemcuervo, emipsanchez; Mata Juárez, Omar; School of Engineering and Sciences; Campus Ciudad de México; Molina Gutiérrez, ArturoLocal environments are altered due to natural phenomena caused by climate change. Some nature changes are, for instance, heat waves, floods, wildfires, and air pollution, among others. Monitoring these alterations is compulsory for users who require a better understanding of their surroundings, such as farmers, transportation companies, and climate researchers. There are already solutions implemented to address this, such as fixed weather stations, satellite images, or drone mapping; However, the limitation of these approaches is that they are unaffordable for small users due to high-cost sensors and the trained personnel needed for operation and maintenance. Also, they have limited coverage and do not share information with the public. Therefore, this paper shows the design, development, and evaluation ofan open-source automatic weather station (OSWS) based on low-cost sensors that monitor environmental variables, including temperature, relative humidity, atmospheric pressure, CO2 concentration, and particulate matter (PM1, PM2.5, and PM10). This station provides a fast solution for in-site measurements for different users; it can monitor the variables remotely and forecast values within a short-time period based on the historical data captured using the ARIMA model.
- Virtual architecture of the automation pyramid based on the digital twin(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-05-30) Martinez Galicia, Edwin Mauricio; PONCE CRUZ, PEDRO; 31857; Ponce Cruz, Pedro; emipsanchez; López Caudana, Édgar Omar; Soriano Avendaño, Luis Arturo; Escuela de Ingeniería y Ciencias; Campus Ciudad de México; Molina Gutiérrez, ArturoIndustry 4.0 has been empowered by new emerging technologies to improve the competitiveness in companies. One of these technologies is the digital twin (DT) which is an advanced virtual model that enables to predict, detect and classify normal and abnormal operating conditions in a factory or a particular production process to improve the features of a physical system. On the other hand, the manufacturing processes generally follow standards to segment and distribute their processes, information, and implementation areas. Among the most widely recognized standards in the manufacturing industry is the ISA-95 standard that incorporates the business functions and control systems performed in a company with the objective to enhance the implementation of interfaces between business and control systems. Some architectures, as the Automation Pyramid (AP), hierarchically place the elements that take part in a manufacturing process, from the basic elements such as sensors and actuators, to the decision-making systems, whose functions and shared information are defined in the ISA-95 standard. In industry, one of the main functions of decision-making systems, such as the Manufacturing Execution System (MES), is to provide critical data in real-time at the operational level to increase productivity and process capability of the manufacturing process. However, these systems usually do not have capabilities to offer a prompt/autonomous/learning-based response to face unpredicted changes in the course of operating resources. Therefore, when a fault condition occurs, not only quick responses are required but also predictive information to prevent future failure scenarios. Thus, this work proposes to provide responsiveness to decision-making levels in the face of unforeseen scenarios, through the incorporation of intelligent algorithms. The main objectives of this thesis are presented below: To propose a complete Virtual Architecture of the Automation Pyramid based on the Digital Twin: This enables the simulation of scenarios with elements from the shop-floor to the management levels, considering the advantages that the DT provides. To align the proposal with international standards: The model is driven by the ISA-95 standard incorporating the functions and information flow defined in it for decision-making levels. %Thus, the decision-making process is into an automation dynamic loop. To provide learning capabilities to the decision-making systems through artificial neural networks, incorporated in a model based on the DT concept: Since neural networks are able to learn and generalize knowledge, they can learn specific conditions for helping the decision-making process. Evaluate a manufacturing system for educational purposes through the proposed model: The parts of the virtual model of the AP will be identified in a manufacturing cell system used for education at Tec de Monterrey. Its components will be evaluated within the framework of the proposed architecture and the elements to complete the virtual model of the AP will be identified. As a result, this work proposes the complete virtual model of the Automation Pyramid based on the concept of the Digital Twin, where it is proposed to add autonomy capabilities to the decision-making levels through neural networks. The proposed model is aligned with the international standard ISA-95 as an alternative to be applied directly to a process or factory that can be based on the standard.
- Deep learning for clothing classification, case study:thermal comfort(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-11-23) Medina Rosales, Adán; Ponce Cruz, Pedro; puemcuervo; López Caudana, Edgar Omar; Rojas Hernández, Mario; Soriano Avendaño, Luis Arturo; School of Engineering and Sciences; Campus Ciudad de México; Molina Gutiérrez, ArturoImage classification algorithm has being in quick development over the last 10 years with a new algorithm appearing every year, this new algorithms aim to be faster and more accurate than its predecessors, so real time implementations for object classifiers are more frequent. However the solutions for problems are going to more complex problems leaving things such as clothing ensemble classification on the side. There are some proposed solutions on the recognition of clothing garments but all aim to a specific solution in the fashion industry for customer categorization or shopping proposals, however a more general approach which recognizes multiple clothing garments is missing, and a real time clothing ensemble detection could be implemented in several problems. One of such problems is the case study for this project were a CNN implementation is used in video testing to propose the solution for clothing insulation determination using the real time clothing ensemble detector and therefore have a more accurate thermal comfort value. The results proved that the implementation of the chosen CNN architecture could be used as a clothing ensemble detector in a real time implementation, however since a minimized version of the needed dataset was used to verify the viability of this proposal a more complete dataset needs to be created in order to improve the models performance. In general this proposal shows the comparison between come CNN architectures and the datasets available for the propose objectives, as well as the creation of a new dataset that can be successfully used to train the chosen CNN model and produce a real time clothing ensemble detector.
- DFT-based phasor estimator using a MAF with a phase-lead compensator(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-09-15) Escudero Armillas, Rafael; Ponce Cruz, Pedro; puelquio/tolmquevedo; Guillén Aparicio, Daniel; Soriano Avendaño, Luis Arturo; Gómez Hernández, José Alberto; Escuela de Ingeniería y Ciencias; Campus Ciudad de México; Ibarra Moyers, Luis MiguelDue to the advancing complexity of the electrical power system, phasor estimators are becoming essential for measuring its dynamics. Many estimators are now needed to effectively monitor some grid, specially for the wireless sensor networks development. However, the smart sensors comprising such networks are low-cost devices and they are only capable of running low computationally loaded algorithms. In consequence, complex algorithms, like the ones based on Kalman filters and the wavelet transform, cannot be applied and a simpler approach is needed. The Fourier filter emerges as a solution since it has a low computational load and it incorporates a moving average filter, whose main advantage is that it can eliminate harmonics. Nevertheless, the moving average filter causes a significant phase delay that is undesirable in fast-response applications. Therefore, in this thesis it is proposed to add a phase-lead compensator to the moving average filter to solve its phase delay problem, while preserving its harmonic rejection ability and the algorithm’s simplicity. This estimator was compared with the conventional Fourier filter and the cosine filter in IEEE C37.118.1 standardized tests to analyze its performance under harmonic contamination, amplitude, and phase angle step changes. After tuning the compensator, the proposal did meet all the standard requirements and showed a slightly faster response than its non-compensated version, yet increasing the algorithm’s execution time. Also, the proposal was tested over the IEEE 13 node test feeder, showing a faster response than the Fourier filter and the cosine filter.
- Aplicación móvil para la detección del uso del teléfono celular al conducir un vehículo(Tecnologico de Monterrey) Acosta Meza, Juan Ángel; Juan Ángel Acosta Meza; Ponce Cruz, Pedro; Pedro Ponce Cruz
- Automatización de un invernadero de jitomates basada en lógica difusa(Tecnologico de Monterrey) Parra Martí, Pedro; Pedro Parra Martí; Aguirre Ríos, Salvador Felipe; Reyes Pérez, Mariana; Ponce Cruz, Pedro