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
- A prompt assisted image enhancement model using BERT classifier and modified LMSPEC and STTN techniques for endoscopic images(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12) Cerriteño Magaña, Javier; Ochoa Ruiz, Gilberto; emipsanchez; Sánchez Ante, Gildardo; Alfaro Ponce, Mariel; School of Engineering and Sciences; Campus MonterreyThis document presents a research thesis for the Master in Computer Science (MCCi) degree at Tecnologico de Monterrey. The field of medical imaging, particularly in endoscopy, has seen significant advancements in image enhancement techniques aimed at improving the clarity and interpretability of captured images. Numerous models and methodologies have been developed to enhance medical images, ranging from traditional algorithms to complex deep learning frameworks. However, the effective implementation of these techniques often requires substantial expertise in computer science and image processing, which may pose a barrier for medical professionals who primarily focus on clinical practice. This thesis presents a novel prompt-assisted image enhancement model that integrates the LMSPEC and STTN techniques, augmented by BERT models equipped with added attention blocks. This innovative approach enables medical practitioners to specify desired image enhancements through natural language prompts, significantly simplifying the enhancement process. By interpreting and acting upon user-defined requests, the proposed model not only empowers clinicians with limited technical backgrounds to effectively enhance endoscopic images but also streamlines diagnostic workflows. To the best of our knowledge, this is the first dedicated prompt-assisted image enhancement model specifically tailored for medical imaging applications. Moreover, the architecture of the proposed model is designed with flexibility in mind, allowing for the seamless incorporation of future image enhancement models and techniques as they emerge. This adaptability ensures that the model remains relevant and effective as the field of medical imaging continues to evolve. The results of this research contribute to the ongoing effort to make advanced image processing technologies more accessible to medical professionals, thereby enhancing the quality of care provided to patients through improved diagnostic capabilities.
- Synthesis and Characterization of FAPbI3 Perovskite and its Incorporation into a Photovoltaic Heterostructure(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-10) Miró Zárate, Jorge Luis; Elias Espinosa, Miilton Carlos; emimmayorquin; Rosas Meléndez, Samuel Antonio; Melo Máximo, Dulce Viridiana; Flores Ruíz, Francisco Javier; School of Engineering and Sciences; Campus Ciudad de México; Diliegros Godines, Carolina JananiConsidering the importance of having the α-FAPbI3 as it is the photoactive and functional phase for the use of this perovskite in a solar cell and understanding the growth process by incorporating an additive. In this work, it is presented a methodology that combine a method for deposition called sequential deposition with the incorporation of a pseudo halogen additive NH4SCN at various concentration of moles into the PbI2 solution, in order to have α-FAPbI3 perovskite deposited at open atmosphere. This research focuses on the mechanisms of growth of the FAPbI3 perovskite films over glass with the NH4SCN additive. Subsequently, the incorporation of the FAPbI3 perovskite into a heterostructure is presented. The architecture FAPbI3/ETL/ITO/Glass is presented, where the ETLs used are TiO2 and SnO2. The incorporation of FAPbI3 into a heterostructure allows us to evaluate the perovskite's properties for its photovoltaic application. Based on the outstanding electrical properties, WS2 was incorporated into the heterostructure through interface engineering, forming the heterostructure FAPbI3/WS2/ETL/ITO/Glass. Both architectures are compared in terms of their optoelectronic and morphological properties to determine the best FAPbI3-based heterostructure for improved photovoltaic application.
- Mentimeter como herramienta estratégica para la mejora de la evaluación formativa(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-10-13) Ocampo Pastrana, Lorena; Hernández Raygoza, Javier; emimmayorquin; Escuela de Humanidades y Educación; Universidad Virtual en Línea; González Peña, CarolinaEl proyecto de intervención tuvo como objetivo mejorar el sistema de evaluación del departamento de computación, a nivel secundaria, por medio de la aplicación de estrategias de evaluación formativa con la herramienta Mentimeter. La intervención se realizó en una escuela privada en la zona sur de la Ciudad de México, en la delegación Tlalpan, con la participación de maestras del departamento de computación. La estrategia se centró en capacitarlas para aplicar la evaluación formativa con el uso de Mentimeter a través de un taller, a fin de desarrollar las competencias necesarias para una implementación efectiva. Los resultados evidenciaron un incremento considerable en los exámenes de conocimientos en evaluación formativa y en el uso de Mentimeter aplicados antes y después del taller. La evaluación de habilidades con una rúbrica demostró que las maestras mejoraron su desempeño en la mayoría de los criterios. La autoevaluación reveló una mejora en la autopercepción y confianza en el tema. En conclusión, la capacitación resultó exitosa, permitiendo a las maestras desarrollar competencias para implementar eficazmente la evaluación formativa con Mentimeter. Estos hallazgos sugieren que la integración de Mentimeter puede transformar la práctica evaluativa, fomentando un aprendizaje más dinámico, reflexivo y significativo. Se sugiere llevar a cabo investigaciones a largo plazo para analizar su efecto en el desempeño académico del alumnado.
- Instant deliveries in Mexico City: a socio-economic analysis and profit maximization framework for couriers(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11-27) Galindo Muro, Ana Bricia; Mora Vargas, Jaime; emipsanchez; Dablanc, Laetitia; Ugalde Monzalvo, Marisol; De Unanue Tiscareno, Adolfo Javier; School of Engineering and Sciences; Campus Ciudad de México; Cedillo Campos, Miguel GastónThis thesis introduces an engineering approach to understanding instant delivery operations within the platform economy. During the first step, through two surveys, the study highlighted couriers’ significant risks and challenges, shedding light on their precarious working conditions and financial pressures. The results emphasize the glaring disparity between the platform economy’s promise of flexibility and independence and the harsh reality experienced by most couriers. Furthermore, the study presents an assignment model to support technological advancements, which can lead to more effective decision-making, benefiting all actors involved in the urban instant delivery platform. By incorporating a fee algorithm and operational cost calculations, the quantitative model developed in this study demonstrates that a 20% increase in couriers’ income compared to traditional assignment models is advantageous for all parties. This approach seeks to raise awareness about the socioeconomic implications of emerging technologies such as Instant Deliveries and their regulation, particularly in rapidly developing urban areas. It offers valuable insights to build a more socially responsible and environmentally sustainable optimization approach in engineering.
- Circular economy: Tequila vinasse treatment for upcycling and downcycling(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12-04) Ramos Reyes, María Fernanda; Gradilla Hernández, Misael Sebastián; Tuesta Popolizio, Diego A.; García Garcia, Christian Enrique; School of Engineering and Sciences; Campus Monterrey; González López, Martin EstebanTequila is one of Mexico's most iconic distilled beverages, with a steadily growing industry that also embodies a significant cultural legacy. However, most tequila producers in the country face challenges in managing the waste generated during production due to the high costs of treatment and the low economic returns from by-products. This thesis begins by exploring the intricate relationships between tequila production and various industrial, environmental, and governmental sectors through a comprehensive mapping process. The second section examines the production of distillates, including bioethanol, tequila, and other alcoholic beverages, focusing on the treatment of substantial liquid waste known as vinasse, which is produced at a rate of 10-15 liters per liter of distilled product. This waste presents critical environmental challenges, such as eutrophication, soil pollution, and toxicity. A systematic review conducted in this thesis evaluates various pathways for valorizing distillery vinasse. The review includes 72 treatments involving ethanol industry vinasse, tequila vinasse, and their combinations with agro-industrial residues, categorized into three main valorization strategies: waste-to-energy, waste-to-food, and waste-to-product. Biotechnological treatments, such as two-stage anaerobic digestion and fungal anaerobic fermentation, achieved the highest yields and product diversity. Moreover, bacterial processes demonstrated significant potential for producing high-value products like polymers, enzymes, and proteins. The third part of this thesis is about an aerobic treatment in co-cultures and monocultures using strains like C. utilis, R. mucilaginosa, K. marxianus, A. niger, A. oryzae, and R. oligosporus were explored for contaminant removal and high-protein biomass production. The C. utilis and A. oryzae co-culture generated the best results at the tube scale, showing remotion up to 63.52% TN removal, 86.87% P removal, and 46.21% COD removal over 72 hours in the benchtop scale. A kinetic study modeled biomass growth using a biphasic Zwietering-modified Gompertz model, achieving a maximum protein of 47.27 g kg⁻¹. The thesis also explores other high-value products using this substrate, such as phenols, and the importance of these remotions.
- Cursos cortos de programación: una alternativa para aumentar la participación de la mujer en la tecnología en Colombia.(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11-13) Galán Vargas, Mónica Carolina; Tejeda Torres, Santa Esmeralda; emimmayorquin; No tiene campusLa brecha de género en el sector de tecnología sigue siendo un desafío global, y Colombia no es la excepción. El presente trabajo de grado estudia cómo los cursos cortos de programación, conocidos como bootcamps, pueden servir como una alternativa viable para aumentar la participación de las mujeres en la tecnología. A través de una investigación cualitativa realizada con cinco escuelas de codificación en Colombia, este estudio analiza las acciones e iniciativas que han contribuido a mejorar la inclusión de género en estos programas. Los resultados destacan factores claves que motivan a las mujeres a optar por cursos cortos, como su flexibilidad y enfoque práctico, así como su impacto positivo en la empleabilidad femenina. Sin embargo, también se identificaron desafíos significativos, como barreras culturales y estructurales que limitan el acceso y la retención de mujeres en estas iniciativas. El estudio concluye que, si bien los bootcamps ofrecen una vía alternativa efectiva para reducir la brecha de género en el sector, es necesario fortalecer las políticas de inclusión y diseñar estrategias más integrales para asegurar su sostenibilidad a largo plazo.
- From classical to quantum machine learning for analyzing and predicting alumni outcomes(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12) Ramos Pulido, Sofía; Hernández Gress, Neil; Torres Delgado, Gabriela; Hervert Escobar, Laura; Garza Villarreal, Sara Elena; Méndez Hinojosa, Luz Marina; School of Engineering and Sciences; Campus Monterrey; Ceballos Cancino, Héctor G.This thesis is submitted to the graduate program at the School of Engineering and Sciences as part of the requirements for obtaining the degree of Doctor of Philosophy in Computer Science. This study aims to generate models using both classical and quantum machine learning (ML) methodologies to accurately predict three key outcomes for alumni: job level, career satisfaction, and first employment. The data analyzed comes from Tec de Monterrey university alumni surveys. The study’s objectives also include the identification of important and actionable features for alumni outcome predictions. Among the challenges in finding models to predict and explain alumni outcomes, we encountered issues such as handling imbalanced classification, hyperparameter tuning, model prediction interpretation, and long training times. To address the latter, we proposed a method that reduces execution time when working with large datasets, particularly in methodologies like support vector machines. This proposal effectively resolves time and memory limitations in high-dimensional classification problems without compromising performance accuracy. The results show that classical machine learning models accurately predicted alumni outcomes. For instance, gradient boosting was most accurate in predicting job level and career satisfaction, while support vector machines outperformed in employment prediction. Significant features identified included current salary and number of people supervised for job level, with higher salaries and more supervisory responsibilities correlating with higher job positions. For career satisfaction, life and income satisfaction were important indicators, as higher satisfaction levels in these areas predicted greater career satisfaction. In the case of employment, networking support resulted as the most important feature, with stronger professional connections significantly increasing the likelihood of securing employment shortly after graduation. Additionally, the research identified actionable features that can impact both educational institutions and students. For job level, soft skills, particularly communication and teamwork, were found to be crucial in advancing to higher positions. Institutions can focus on enhancing these skills through their programs, while students are encouraged to develop them actively. For career satisfaction, the effective use of skills and technological tools acquired during education was a strong predictor, indicating the importance of aligning academic training with the demands of the job market. Facilitating robust professional networks proved essential for employment, emphasizing the need for institutions to create networking opportunities and for students to build social connections proactively. Many more interesting trends and findings related to alumni outcomes are highlighted in the thesis. Regarding quantum machine learning (QML) models, this research demonstrates the v feasibility of predicting alumni outcomes. A hybrid quantum-classical approach was particularly effective in predicting the three alumni outcomes in reduced datasets without substantially affecting accuracy. For example, quantum support vector classifiers (QSVC) showed comparable performance to classical support vector classifiers (SVC) while utilizing a reduced dataset versus SVC with complete datasets. Although QML is still in its early stages, this research suggests that QML could become a viable alternative in educational data mining as the field expands.
- Influence of human error and situational awareness in decision-making in complex tasks. Case of study: forklifts operators(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11-19) Arias Portela, Claudia Yohana; Mora Vargas, Jaime; emipsanchez; Castillo Martínez, Juan Alberto; González Mendoza, Miguel; Thierry Aguilera, Ricardo; School of Engineering and Sciences; Campus Ciudad de México; Caro Gutiérrez, Martha PatriciaThis dissertation investigates situational awareness (SA) and human errors in logistics operations, using a multiphase and multifactorial approach as an innovative approach. The research responds the question of how SA errors can be assessed, along with their influence on decision-making in complex tasks, by considering a comprehensive HFE approach to various triggering factors. Characterization of the process with ethnography and process mapping, analysis of visual attention with Eye-tracking and retrospective think-aloud (RTA), an Error taxonomy and the bases of a data science approach were used to study the diverse cognitive, behavioral, and operational aspects affecting SA. Analyzing 566 events across 18 tasks, the research highlights eye-tracking's potential by offering real-time insights into operator behavior, and RTA as a method for cross-checking the causal factors underlying errors. Critical tasks, like positioning forklifts and lowering pallets, significantly impact incident occurrence, while high cognitive demand tasks such as hoisting and identifying pedestrians/obstacles, reduce SA and increase errors. Driving tasks are particularly vulnerable and are the most affected by operator risk generators (ORG), representing 42% of events with a risk of incident. The study identifies driving, hoisting and lowering loads as the tasks most influenced by system factors. Limitations include the task difficulty levels, managing physical risk, and training. Future research is suggested in autonomous industrial vehicles and advanced driver assistance systems (ADAS). This study provides valuable insights for improving safety in logistics operations by proposing a multiphase and multifactorial approach to uncover patterns of attention, perception and cognitive errors, and their impact on decision-making in the logistic field
- lmproved Diagnosis of Breast Cancer via NLP Analysis of Radiological Reports(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11) Sosa Silva, Patricia Angelli; Tamez Peña, José Gerardo; emimmayorquin; Martínez Ledezma, Emmanuel; Avendaño Davalos, Betzabeth; School of Engineering and Sciences; Campus Monterrey; Santos Díaz, AlejandroToe main objective of this thesis was to evaluate the use of natural language processing (NLP) techniques and machine learning models to improve the specificity of breast cancer diagnosis and reduce false-positive rates using a dataset of radiological reports from Mexican hospitals. Toe methodology involved text preprocessing, feature extraction using NLP techniques and classification using machine learning models for the radiological reports. The preprocessing consisted of lemmatization, stop-word removal, and tokenization. Various NLP techniques were then applied, including bag-of-words, TF-IDF, Word2Vec embeddings, and ClinicalBERT embeddings. These were used as input features for classical machine learning models (Logistic Regression, Random Forest, Extreme Grading Boosting, Naive Bayes, k-Nearest Neighbors, Support Vector Machine and their ensemble) as well as a deep learning LSTM model. The models were trained, calibrated, and evaluated using metrics: AUC, accuracy, precision, recall, specificity and Fl-score. The key findings showed that the ensemble model with Bag-of-words and SVM using TF-IDF vectorized reports achieved the best performance, with an AUC of 0.79, specificity of 0.27 and AUC of 0.80 and specificity of 0.26, respectively. Thess model was able to identify all true positive cases while reducing the number of unnecessary biopsies by 19.49% and 15.08%, respectively. Feature importance analysis revealed that terms like "speculated", "irregular", and "4a category" were critica! for breast cancer classification. In contrast, the deep learning LSTM model performed poorly, with an AUC of only 0.52 and specificity of O. These results demonstrate the potential of NLP and machine learning techniques to enhance the reliability of breast cancer diagnosis and management, reducing the burden of unnecessary medica! procedures on patients and the healthcare system. The theoretical implications include the importance of effective feature engineering and the limitations of deep learning models for this specific task.
- Interactive recipe suggestions for diet and allergen management: utilizing llaMA with HEI and DQI for healthier eating(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11-15) Estrada Beltrán, Diego; González Mendoza, Miguel; emipsanchez; Gutiérrez Uribe, Janet Alejandra; Domínguez Uscanga, Astrid; Hinojosa Cervantes, Salvador Miguel; School of Engineering and Sciences; Campus MonterreyChoosing daily meals can be a complex and overwhelming task, especially when considering nutritional requirements, ingredient availability, preparation time, cooking complexity, dietary restrictions, and allergens. Inadequate nutrition is linked to a variety of health problems, including cardiovascular diseases, obesity, and psychological disorders, highlighting the need for effective dietary management solutions. Existing machine learning approaches, such as food recommender systems, recipe generators, and recipe completion models, often focus on suggesting ingredients or generating recipes based on training data and with some ingredients to start from, but they typically do not address the challenge of creating complete daily meal plans that meet personalized nutritional needs. The advent of Large Language Models (LLMs), including Meta’s LLaMA, OpenAI’s ChatGPT, and Google’s Gemini, offers a promising new avenue for enhancing personalized meal recommendations due to their accessibility and interactive capabilities. This thesis introduces a novel system that leverages LLaMA 3.1 combined with Retrieval-Augmented Generation (RAG) to provide daily meal suggestions tailored to individual users’ nutritional profiles, dietary preferences, and allergen restrictions. Our system evaluates meal recommendations against established nutritional metrics such as the Healthy Eating Index (HEI) and Diet Quality Index (DQI) to ensure they align with dietary guidelines and promote healthy eating. Through the integration of LLaMA’s advanced language understanding and RAG’s contextual retrieval capabilities, the system delivers precise, personalized, and accessible meal recommendations, offering a practical tool for improving dietary management and supporting healthier eating habits. The results demonstrate the effectiveness of this approach in addressing the complexities of meal planning, making it a valuable resource for individuals seeking to optimize their dietary choices through informed and interactive guidance.
