Tesis
Permanent URI for this communityhttps://hdl.handle.net/11285/345119
Colección de Tesis y Trabajos de grado (informe final del proyecto de investigación, tesina, u otro trabajo académico diferente a Tesis, sujeto a la revisión y aceptación de una comisión dictaminadora) presentados por alumnos para obtener un grado académico del Tecnológico de Monterrey.
Para enviar tu trabajo académico al RITEC, puedes consultar este Infográfico con los pasos generales para que tu tesis sea depositada en el RITEC.
Browse
Search Results
- Machine Learning-Based Methodology for Intelligent Energy Management Strategy in Heavy-Duty Fuel Cell Hybrid Electric Vehicles with Pantograph(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-07) Julio Rodríguez, Jose del Carmen; Ramírez Mendoza, Ricardo Ambrocio; emimmayorquin; School of Engineering and Sciences; Campus Monterrey; Santana Díaz, AlfredoThis work presents the proposal and validation of a novel methodology for enhancing energy management strategies in heavy-duty FCHEVs with overhead current collector (pantograph) by means of ML-based predictions for the characterization of the driver-vehicle system from a holistic approach, correlating its energy and power profiles with characteristics of the route where it transits, specifically the speed profile and the height profile for the complete route. The base concept is the possibility of characterizing the vehicle’s energy use from an approach that also considers the driver behavior and road characteristic. This data-driven characterization using historic and real-time data stream from the vehicle allowed for a ML-model to be trained to make predictions using limited information from the upcoming route. The predictions created with the described method included energy demand, power base-values and optimal SoC profiles. These predictions were then used in an energy management strategy by means of a heuristic controller that received and used the optimal SoC profile and the power demand base-value of the complete route, thus allowing the controller to perform in accordance to current and upcoming vehicle energy demand. The methodology begins with the clusterization of vehicle and road data to define zonetypes for assigning labels to individual samples by means of unsupervised machine learning. Next, the labeled data is used to train a supervised machine learning classification algorithm which is then used to make predictions about the upcoming route. The clusterization and zone type predictions are then used for discretizing the complete route in a step called zonification, where the route is divided into sections with their own characteristics, providing a base on which the energy management strategy can be adjusted and executed accordingly. The data used for these tasks included vehicle dynamics data and energy demand profiles, as well as road information. The information used regarding the road was the expected speed profile and the elevation profile of the route. Both of these features can be obtained from external sources like vehicle to X communication or third-party navigation services and cartography. The ML-enhanced EMS controller was then validated through simulation using real data from 5 different routes in Germany and its performance was compared to that of other 3 controllers which made use of different approaches for the actuation and control of the onboard energy systems. The results were consistent in demonstrating the superior performance of the controller making use of the ML predictions, obtaining the best scores in FC degradation and H2 mass consumption indexes, with 25% and 27% less than the next best performer on each index respectively.
- Introducing Sequence-based Hyper-heuristics with Multiple Points of Interpretation(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-06) Garrafa Pacheco, Leonardo Francisco; Ortiz Bayliss, José Carlos; emimmayorquin; School of Engineering and Sciences; Campus Estado de MéxicoHyper-heuristics are a type of search methods used for solving optimization problems. This field is relatively new and has caught the attention of researchers because it employs existing heuristics to construct solutions for specific problems. In other words, instead of inventing new technics, they combine already available technics to tackle optimization problems. There are two kinds of hyper-heuristic models in the literature: "rule-based", which rely on a set of rules that guide the solver to decide what heuristic to perform next, and "sequence-based", which rely on a sequence of heuristics to apply. One remarkable characteristic of sequence-based models is that they do not need to identify features that map the problem state but represent the actions to make at each decision step. Furthermore, current works have shown that the sequence length does not need to equal the number of required decisions to find a good solution. Instead, the sequence can be small and repeated under a looping schema to fulfill the required number of decisions. Although employing looping schemas seems to provide suitable solutions, they may be somewhat restrictive due to their fixed nature and other limitations. For instance, the current looping schemas require repeating all the elements in the sequence of actions, which could be very disruptive during the learning stage of the hyper-heuristic because any change of the sequence is a change in each of their repetitions. In this sense, a relaxation of the looping schemas could improve the performance of the models. To that end, this work presents two models that learn their looping schemas by interpreting their sequence of actions from different positions and approaches: the Bidirectional Point Of Interpretation (BPOI) model and the Partial Bidirectional Point Of Interpretation (PPOI) model. We found that the PPOI not only can produce reasonable solutions to solve problems but also keeps the length of the sequence small. Furthermore, we introduced the notion of a length penalization to keep the sequence small, which from experiments, also seems to improve the models' performances.
- On Mass Estimation of fruits with modern Computer Vision: a Deep Learning approach(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-06-01) Ruíz Hernandéz, Pablo César; Hernández Grees, Neil; emimmayorquin; González Mendoza, Miguel; Hervert Escobar, Laura; Castro Espinoza, Félix Agustín; School of Engineering and Sciences; Campus MonterreyThis work presents a comparison between a selection of Deep Learning models against a selection of Machine Learning models studying how these perform estimating the mass of a selection of fruits using Computer Vision techniques to extract features for this purpose. The selected models for Deep Learning include a Fully Connected Neural Network, a Fully Connected Neural Network with a dropout factor between hidden layers, a proposed model with a similar architecture, a simple CNN model, MobileNet, and DenseNet; while the Machine Learning selection includes SVR and Linear Regression. All these were implemented using TensorFlow and Scikit-Learn libraries in Python 3.9. YOLOv8, Detectron2, and the manually annotated segmentations were used to separate the fruits from the background of the image to extract features and compare their results. This work also presents the creation of three datasets of the selection of fruits, in this case, blueberries, raspberries, and strawberries. Two datasets were created for each fruit, one relating high-definition images of the fruits with high-precision readings of their mass, and another one including only images of the fruits. The general aim of this work is to find out, how to build datasets of fruits with high-definition images and high-precision readings of their mass, which method is better to extract features of the fruits of the images by segmenting the image between YOLOv8 and Detec- tron2, and how the selection of Deep Learning models performs against the selection of Machine Learning models estimating the mass of the selection of fruits. Currently, the best results estimating the mass of fruits and similar structures have been obtained by analyzing simple features with Machine Learning models, which is why a comparison with Deep Learning is of special interest. After the creation of the datasets, both YOLOv8 and Detectron2 models were compared showing high accuracy in segmenting the fruits from the images. It was found that the best correlation feature with mass is the area of the fruit, which is proportional to the real area. After extracting features, these were divided into classes which were contrasted in the results of all models against all classes and with different training epochs when possible; resulting in 288 different experiments. The experiments resulted in Machine Learning outperforming Deep Learning, however, Deep Learning presents the potential improvement under different conditions such as more training epochs or larger datasets. The results obtained from the creation of the datasets, the segmentation of the fruits, and the comparison of models estimating the mass of fruits, are of interest to research lines aiming to create datasets relating images and physical properties of objects, perform segmentation of non-regular polygon structures in 2D images, and estimate the mass of fruits or similar structures.
- Metodología para la gestión de proyectos de diseño de herramentales(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2021-07-14) Trejo Berrones, Alexander; Hernandez Luna, Alberto Abelardo; puemcuervo, emipsanchez; Saldaña Lopez, Azael; Escuela de Ingeniería y Ciencias; Campus Monterrey; Luciana Pascual, PaulaEl presente proyecto de titulación expone la creación de metodología para la gestión de proyectos de diseño de herramental (Tool Fixture Design) . Donde actualmente el departamento carece de una metodología a seguir durante todo el proceso, desde inicio a fin, para el diseño de herramientas. Esto es debido a que en la actualidad el departamento es de reciente creación, es decir un año, y no cuenta con alguna metodología que pueda seguir durante el proceso de diseño de herramientas. así mismo esta metodología servirá para crear una plataforma digital, donde los diseñadores del departamento puedan tener un fácil acceso a información de relevancia, como manuales, repositorio de ejemplos, biblioteca de información los cuales les será de gran ayudara a reducir el tiempo invertido durante los proyectos y así ofrecer trabajos y entregables de mayor calidad a los clientes. Esta metodología de gestión fue desarrollada bajo la estructura DIMAC y metodología LEAN, la cual permite analizar detalladamente desde inicio a fin como se encuentra el proceso que se sigue actualmente y poder hacer el desarrollo, implementación y control de esta nueva metodología de manera eficiente. Mostrando como resultado una plataforma virtual que apoyara en el manejo y gestión de proyectos de diseño de herramientas.
- Modelling, designing and PEST analysis implementation of a porcine products supply chain: a metaheuristics approached solved case study(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022) Elizalde Camacho, Álvaro Ronaldo; Smith Cornejo, Neale Ricardo; puelquio, emimayorquin; Leal Coronado, Mariel Adriana; Escuela de Ingeniería y Ciencias; Campus Monterrey; Hajiaghaei Keshteli, MostafaThere is evidence that supply chain design plays a critical role in the development of competitiveness among companies and industries. Furthermore, the new trends and purchasing behavior exhibited by customers call for the improvement of the supply chain’s performance and mitigation of negative environmental impacts, resulting in the design of varied supply chains, including closed-loop supply chains as they comprise forward and backward flow of products, information, and finance. In this paper, a porcine closed-loop supply chain design for pig and porcine products is proposed due to pig meat and pork products importance thanks to their nutritional value among other agri-food products. Hereby, a multi-period, multi-product linear mathematical model is developed to explain the behavior and minimize the net present value as well as the total cost of the proposed network. To give solution to the model, a set of metaheuristics is used, comprising single-solution, population-based and hybrid algorithms. In addition, a set of 15 trial cases is formed to validate the model. Furthermore, a case study is built for the determination of the parameters to feed the model. The study’s results are compared through the mean relative percentage deviation and convergence curves. According to the results, all used metaheuristics can provide solutions to the proposed model and network, but the metaheuristic H_KASA outperforms all the others in terms of objective function quality values and number of iterations. Finally, managerial insights regarding transportation cost, inventory cost, production capacity and demand are developed.
- Autorregulación para mejora de la motivación autónoma y el bienestar psicológico según la teoría de la autodeterminación en estudiantes de medicina de sexto semestre(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-05-19) Villalvazo López, Mireya; Jasso Peña, Felipe de Jesús; emipsanchez; Torres Delgado, Gabriela; Escuela de Humanidades y Educación; Campus Guadalajara; De la Fuente Alcázar, Juana MaríaSe llevó a cabo un seminario de estrategias de autorregulación con el objetivo de mejorar la motivación autónoma y el bienestar psicológico de estudiantes de medicina en la Universidad de Guadalajara, campus de la costa en Puerto Vallarta, Jalisco, México. Tras un diagnóstico inicial, se identificó la falta de formación en autorregulación del aprendizaje y los bajos niveles de motivación autónoma y autodeterminación en los rubros de competencia y autonomía. El seminario se implementó a 48 estudiantes de medicina, quienes completaron cuestionarios previos: el learning self-regulation questionnaire (SRQ-l), la escala de autorregulación del aprendizaje (SRLPS) y la escala de satisfacción y frustración de las tres necesidades psicológicas básicas (BPNSFS), con 41 respuestas. Durante cuatro semanas, se ofrecieron clases y actividades con énfasis en psicología cognitiva, aplicación práctica de la teoría del procesamiento de la información y revisión de estrategias de aprendizaje, junto con revisión y reforzamiento del componente motivacional. Posteriormente, se aplicaron los mismos cuestionarios (36 respuestas) y se evidenció una mejora en los niveles de motivación autónoma, percepción de autorregulación y bienestar psicológico según la teoría de la autodeterminación. Reconocer y adquirir conciencia metacognitiva y de autorregulación del aprendizaje puede mejorar la autodeterminación de los estudiantes de medicina, que se relaciona con bienestar psicológico, el nivel de motivación autónoma, lo que se relaciona con aprendizaje significativo. Estos resultados respaldan la importancia de implementar intervenciones similares en el currículo educativo para promover un enfoque motivacional autónomo con resultados satisfactorios para el aprendizaje.
- High-density coaxial emitter device for electrospray: pushing the limits of additively manufactured microfluidic devices by SLA/DLP(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022-06) Lozano Sura, Roberto Carlos; Olvera Trejo, Daniel; emimmayorquin; Escuela de Ingeniería y Ciencias; Campus MonterreyPhotopolymerization-based 3D printing technologies like SLA and DLP offer efficient fabrication of diverse structures, eliminating the requirement for molds or machining. These techniques allow fast fabrication of intricate designs such as microfluidics devices at low cost, however, the accuracy and resolution of microchannels are still challenging to control for very intricate microfluidics. This study focuses on understanding the influence of manufacturing parameters on the quality of microchannels and miniaturization limits by developing a mathematical model to predict mechanical properties depending on the curing times. Also, we study the limits of this technology in terms of the accuracy of microchannels for the fabrication of multiplexed coaxial electrospray sources. We demonstrate the effectiveness of the mathematical model to improve the quality of these devices with diameters of 360 um with 41 unclogged coaxial nozzles in 1 cm2. The contribution of this work also demonstrated incorporating purge channels was essential to clean uncured resin and the proposed procedure to ensure proper cleaning of the device. The devices were electrically characterized via electrospray processes observing uniform array operation depending on the nozzle size.
- Improved Kidney Stone Recognition Through Attention and Feature Fusion Strategies(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-05) Villalvazo Avila, Elias Alejandro; Ochoa Ruiz, Gilberto; emimmayorquin; Gonzalez Mendoza, Miguel; Hinojosa Cervantes, Miguel Salvador; Daul, Christian; Campus Estado de MéxicoUrolithiasis is the second most common kidney disease and is expected to increase its incidence rate in upcoming years. This disease refers to the formation of crystalline accretions from minerals dissolved in urine in the urinary tract (kidneys, ureters, and bladder) that cannot be expelled. Identifying the kidney stone type is considered crucial by many practitioners because it allows them to prescribe a proper treatment to eliminate kidney stones and most importantly, to avoid future relapses. For diagnostic purposes, the morpho-consitutional analysis (MCA) is the reference for ex-vivo stone characterisation. This analsysis consists of two complementary analyses. First, the visual examination under the microscope of the stone to obtain a description of the crystalline structure at different regions of the stone. Second, a FTIR that provides the biochemical composition of the kidney stone. The current clinical practices for removing kidney stones make increasing use of laser techniques for fragmenting the stone, such as ”dusting”, that reduces intervention time and the trauma for the patient, at the expense of losing important information about the morphology of the stone, which could lead to an incomplete or incorrect diagnosis. To overcome this issue, few experts visually identify the stone type on screen during the procedure. This visual kidney stone recognition by urologists is operator dependent and a great deal of experience is required due to the high similarities between classes. Therefore, AI techniques assessing endoscopic images could lead to automated and operator-independent in-vivo recognition. It has been proved that on ex-vivo data, with very controlled scenes and image acquisition conditions, kidney stones classification is indeed feasible. In the literature it has also been shown that classification on-the-vivo is also feasible using deep-learning architectures. This thesis presents a deep learning method for the extraction and fusion of information relating to kidney stone fragments acquired from different viewpoints of the endoscope. Surface and section fragment images are jointly used during the training of the classifier to improve the discrimination power of the features by adding attention layers at the end of each convolutional block. This approach is specifically designed to mimic the morpho-constitutional analysis performed in ex-vivo by biologists to visually identify kidney stones by inspecting both views. The addition of attention mechanisms to the backbone improved the results of single-view extraction backbones by 4% on average. Moreover, in comparison to the state-of the-art, the fusion of the deep features improved the overall results by up to 11% in terms of kidney stone classification accuracy.
- Análisis de viabilidad de una nueva división de negocios para Laboratorios Becar.(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2022) Jacobo Genel, Juan Carlos; Garza Nuñez, Dagoberto; emimmayorquin; Vargas Marquez, Benjamin; Escuela de Ingeniería y Ciencias; Campus Monterrey; Castañares Marquez, EduardoPara el crecimiento de una empresa se requieren inversiones en proyectos que permitan diferenciarse, atrapar más clientes y acaparar un mayor mercado, reducir costos y poder generar mayores ingresos. Es primordial saber a cuáles proyectos dedicarles recursos económicos, de personal y de tiempo. Se debe de hacer un análisis de viabilidad de los proyectos presentados para tratar de predecir la mejor opción de inversión de los recursos. En el presente escrito se realiza un análisis de viabilidad de una nueva división para un laboratorio de servicios de análisis de alimentos. Se presenta un estudio de la legislativa actual, un estudio de mercado, el análisis técnico y financiero del montaje de la nueva división de Laboratorios Becar. La nueva división integra un área de laboratorio donde se ofrezcan análisis de control de calidad, microbiológicos, toxicológicos, de potencia y fisicoquímicos de los productos derivados de la familia del cannabis como son la marihuana y el cáñamo.
- Desarrollo de modelo de negocios para empresa mexicana enfocada a R & D de productos de agroinsumos(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2023-03-21) Oliva Nieto, Carlos Arturo; Alemán Flores, Martha Eugenia; emipsanchez; Escuela de Negocios; Campus Estado de MéxicoLa industria de protección de cultivos tiene distintas variables que impactan en su crecimiento, siendo una de las más importantes los costos de mantenimiento de un cultivo. Esto dio paso a este trabajo de investigación. El objetivo de este trabajo es desarrollar un modelo de negocios sustentable, que permita al campo mexicano fortalecer la calidad y cantidad de sus cosechas por medio de agroinsumos desarrollados por científicos mexicanos dentro del territorio nacional, focalizado en la zona florícola mexiquense y hortícola morelense. Para esta investigación se empleó un enfoque cualitativo, por medio de entrevistas a agricultores, e involucramiento directo a zona de estudio. Como resultado de estas entrevistas se concluye que existe un área de oportunidad para la introducción de una empresa de desarrollo de agroinsumos basados en investigación y desarrollo, específicamente a través de análisis de laboratorio de suelo y planta. Es por esto, que a través de la información recolectada se ha diseñado un modelo de negocios aplicable a la realidad de la zona de estudio.
