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 robust and interpretable machine learning framework for vanadium oxide supercapacitors(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025-06-13) Ortiz Aldana, Emmanuel Alexei; Kumar, Rudra; emimmayorquin; Mallar, Ray; Sánchez Ante, Gildardo; Kumar, Kishant; School of Engineering and Sciences; Campus Monterrey; Ebrahimibagha, DariushAs global energy demands intensify, the development of efficient, scalable and reliable energy storage systems becomes increasingly urgent. While lithium-ion batteries dominate the current market, their low power density makes them unsuitable for current fluctuations degrading their life expectancy. Supercapacitors (SCs) with pseudocapacitance materials such as vanadium oxide offer an attractive option, with high power density, long life cycle and fast charge-discharge rate. However, their low energy density remains a major bottleneck limiting broader adoption. Current supercapacitor research is focused on improving the specific capacitance and thus expanding their energy density, nevertheless this is mostly done on traditional trial and error experiments, making it time-consuming, slow and expensive. Materials Informatics offers a paradigm shift by implementing machine learning (ML) techniques to uncover patterns in existing data and accelerate the design of novel materials. Despite promising results, many current materials ML studies suffer from limitations such as small data range, improper data preprocessing, target leakage, and lack of reproducibility due to unshared code and datasets. In this work a robust machine learning framework was developed for vanadium oxide SCs, designed to extract interpretable insights from manually gathered literature data. A rigorous cross-validation (CV) pipeline was implemented to ensure reliable model evaluation, avoiding common pitfalls such as overfitting and data leakage. Among the evaluated models, a Voting Regressor combining Ridge Regression, Extreme Gradient Boosting (XGBoost), and Categorical Boosting (CatBoost) achieved the best performance with a mean absolute error (MAE), root mean squared error (RMSE), and 𝑅2 of 81 𝐹 𝑔 ⁄ , 104 𝐹 𝑔 ⁄ and 0.61, respectively. To extract insights from the models, interpretability algorithms, including permutation importance (PI) and SHapley Additive exPlanations (SHAP) values were employed. Binder-free electrodes, wider potential windows, and a low current density are consistently associated with higher specific capacitance predictions. These findings highlight the potential of interpretable methods to uncover the ML models behavior and lead guided design of SCs.
- Data-driven modeling and bayesian optimization of cooling towers for the reduction of water consumption(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2025) Alatorre Cuéllar, Karla Valeria; Montesinos Castellanos, Alejandro; emipsanchez; Hernández Romero, Ilse María; López Guajardo, Enrique Alfonso; School of Engineering and Sciences; Campus MonterreyThis study presents a data-driven framework that integrates Machine Learning and Bayesian Optimization to minimize water consumption in industrial cooling towers while preserving cooling efficiency. Using historical operational and environmental data from a power generation facility, several regression models (Linear Regression, Random Forest, XGBoost, and Neural Networks) were developed to predict makeup water flow. Random Forest and XGBoost achieved the highest accuracy, with R2 scores of 0.982 and 0.972, respectively. Bayesian Optimization was employed to efficiently tune hyperparameters, yielding substantial improvements in predictive performance such as reducing RMSE by up to 18.6%. The methodology also incorporated feature importance analysis, which identified critical operational drivers such as blowdown flow and inlet water temperature. Overall, Random Forest was preferred due to its superior predictive accuracy, ease of interpretation, and practical integration into operational dashboards. By combining predictive modeling, optimization, and interpretability, the study offers a powerful methodology for a data-driven tool to support decision-making and identify opportunities for minimizing makeup water use in cooling tower operation.
- Tool Condition Monitoring System for Competitive Aluminum Milling(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12-02) Navarro Macías, Horacio Armando; Morales Menendez, Ruben; emimmayorquin; Guedea Elizalde, Federico; School of Engineering and Sciences; Campus Monterrey; Vallejo Guevara, Antonio Jr.In recent years, the auto parts industry has experienced a significant transformation, transitioning from gasoline-powered vehicles to electric vehicles, influenced by the Connected, Autonomous, Shared, and Electric (CASE) technologies trends. This shift is increasing the demand for advanced components like sensors and ECUs, requiring enhanced manufacturing techniques such as die casting and machining. However, North American manufacturers face a risk in competitiveness due to must of this mechanical parts are supplied by Asian suppliers, posing risks to increase manufacturing cost related to tariffs and logistics. To stay competitive and embrace these trends, North America needs to establish a CASE manufacturing hub to localize production. Denso is a Japanese mobility supplier that has provided advanced automobile technologies, components, and systems to major manufacturers since 1949, operating in 38 countries Denso (1 10). Established in 1996, Denso México (DNMX) has grown significantly, with four plants—two in northern Mexico, one in Silao, and a recent addition in Irapuato. As of March 2023, DNMX employs over 7,000 people, making it one of the largest facilities within Denso North America and playing a key role in the North American market for CASE products (Connected, Autonomous, Shared, and Electric vehicles). To improve competitiveness in the auto-parts and support the localization of parts the strategy of DNMX is to focus on enhancing the Monozukuri spirit1. The approach involves establishing a manufacturing foundation thru integration of advance industry 4.0 strategies, including IoT, automation, and data analytics, to optimize processes and improve efficiency and quality. In the context of CASE, the emphasis is on producing essential components like aluminum-machined cases for electric parts and inverter motors. To gain a competitive advantage, there is a significant investment in advanced technologies for machining processes, aiming to ensure cost efficiency, enhance productivity, maintain quality, and extend tool life. The real-time autonomous Tool Condition Monitoring System (TCMS) is a key element of this strategy, enhanced by Artificial Intelligence (AI), which leverages machine learning to analyze real-time data, predict tool wear, and prevent potential failures. The development and deployment of the AI-driven TCMS follow the Cross-Industry Standard Process for Data Mining (CRISP-DM) methodology, a robust framework widely adopted for data analytics projects. CRISP-DM ensures a structured approach through six phases: business understanding, where goals and objectives align with organizational strategy; data understanding, involving detailed exploration of machining and tool condition data; data preparation, including cleaning and structuring data for analysis; modeling, where machine learning algo-rithms predict tool wear and failure; evaluation, assessing model accuracy and alignment with objectives; and deployment, integrating the AI system into manufacturing processes. This methodology enhances the iterative refinement of predictive capabilities, ensuring alignment with strategic objectives and operational realities. By adopting CRISP-DM, DNMX ensures the systematic development of its AI-integrated TCMS, enhancing machining accuracy and reliability, optimizing maintenance schedules, and reducing downtime. This structured approach continuously improves the system, reinforcing DNMX’s leadership in the North American auto-parts industry and contributing to the transformation towards electric vehicles.
- Enhancing BGP security with MAD anomaly detection system and machine learning techniques(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-12) Romo Chavero, María Andrea; Cantoral Ceballos, José Antonio; emipsanchez; Botero Vega, Juan Felipe; Navarro Barrón, Francisco Javier; School of Engineering and Sciences; Campus Monterrey; Pérez Díaz, Jesús ArturoAnomalies in the Border Gateway Protocol (BGP) represent a signicant vulnerability in the Internet’s infrastructure, as they can cause widespread disruptions, trafc misdirection, and even security breaches. Proactive detection of these anomalies is vital to preserving network stability and preventing potential cyberattacks. In response to this challenge, we present the Median Absolute Deviation (MAD) anomaly detection system, which combines traditional statistical methods with advanced machine learning (ML) techniques for more precise and dynamic detection. Our approach introduces a novel adaptive threshold mechanism, allowing the system to adjust based on the changing conditions of network trafc. This dynamic thresholding signif- icantly improves the accuracy, precision, and F1-score of anomaly detection compared to the previous xed-threshold version. Additionally, we integrate the MAD system with a diverse ML classiers, including Random Forest, XGBoost, LightGBM, CatBoost, and ExtraTrees to enhance the system’s ability to identify complex patterns that indicate unusual BGP behavior.We evaluate our detection system on well-documented BGP anomaly events, such as the Slammer worm, Nimda, Code Red 1 v2, the Moscow blackout, and the Telekom Malaysia misconguration. The results show that our system when combined with ML models achieves an overall accuracy and F1-score of 0.99, demonstrating its effectiveness across various anomaly types. By using both statistical and ML models, the system is able to capture irregularities that could signal security threats, offering a more comprehensive detection solution.This research highlights the importance of combining statistical anomaly detection with ML to obtain a balance between accuracy and computational efciency. The system’s low resource requirements and minimal pre-processing make it highly scalable, allowing it to be potentially deployed in real-time on large-scale networks.
- Multimodal data fusion algorithm for image classification(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11) Beder Sabag, Taleb; Vargas Rosales, César; emipsanchez; Pérez García, Benjamín de Jesús; School of Engineering and Sciences; Campus MonterreyIImage classification algorithms are a tool that can be implemented on a variety of research sectors, some of these researches need an extensive amount of data for the model to obtain appropriate results. A work around this problem is to implement a multimodal data fusion algorithm, a model that utilizes data from different acquisition frameworks to complement for the missing data. In this paper, we discuss about the generation of a CNN model for image classification using transfer learning from three types of architectures in order to compare their results and use the best model, we also implement a Spatial Pyramid Pooling layer to be able to use images with varying dimensions. The model is then tested on three uni-modal data-sets to analyze its performance and tune the hyperparameters of the model according to the results. Then we use the optimized architecture and hyperparameters to train a model on a multimodal data-set. The aim of this thesis is to generate a multimodal image classification model that can be used by researchers and people that need to analyze images for their own cause, avoiding the need to implement a model for a specific study.
- Machine translation for suicide detection: validating spanish datasetsusing machine and deep learning models(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-11) Arenas Enciso, Francisco Ariel; Zareel, Mahdi; emipsanchez; García Ceja, Enrique Alejandro; Roshan Biswal, Rajesh; School of Engineering and Sciences; Sede EGADE MonterreySuicide is a complex health concern that affects not only individuals but society as a whole. The application of traditional strategies to prevent, assess, and treat this condition has proven inefficient in a modern world in which interactions are mainly made online. Thus, in recent years, multidisciplinary efforts have explored how computational techniques could be applied to automatically detect individuals who desire to end their lives on textual input. Such methodologies rely on two main technical approaches: text-based classification and deep learning. Further, these methods rely on datasets labeled with relevant information, often sourced from clinically-curated social media posts or healthcare records, and more recently, public social media data has proven especially valuable for this purpose. Nonetheless, research focused on the application of computational algorithms for detecting suicide or its ideation is still an emerging field of study. In particular, investigations on this topic have recently considered specific factors, like language or socio-cultural contexts, that affect the causality, rationality, and intentionality of an individual’s manifestation, to improve the assessment made on textual data. Consequently, problems like the lack of data in non-Anglo-Saxon contexts capable of exploiting computational techniques for detecting suicidal ideation are still a pending endeavor. Thus, this thesis addresses the limited availability of suicide ideation datasets in non-Anglo-Saxon contexts, particularly for Spanish, despite its global significance as a widely spoken language. The research hypothesizes that Machine- Translated Spanish datasets can yield comparable results (within a ±5% performance range) to English datasets when training machine learning and deep learning models for suicide ideation detection. To test this, multiple machine translation models were evaluated, and the two most optimal models were selected to translate an English dataset of social media posts into Spanish. The English and translated Spanish datasets were then processed through a binary classification task using SVM, Logistic Regression, CNN, and LSTM models. Results demonstrated that the translated Spanish datasets achieved scores in performance metrics close to the original English set across all classifiers, with limited variations in accuracy, precision, recall, F1-score, ROC AUC, and MCC metrics remaining within the hypothesized ±5% range. For example, the SVM classifier on the translated Spanish sets achieved an accuracy of 90%, closely matching the 91% achieved on the original English set. These findings confirm that machine-translated datasets can serve as effective resources for training ML and DL models for suicide ideation detection in Spanish, thereby supporting the viability of extending suicide detection models to non-English-speaking populations. This contribution provides a methodological foundation for expanding suicide prevention tools to diverse linguistic and cultural contexts, potentially benefiting health organizations and academic institutions interested in psychological computation.
- Identificación de señales críticas en scan dumps para la depuración de microprocesadores(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-05-17) Del Valle Valenzuela, Jorge Xicotencatl; Falcon Morales, Luis Eduardo; emimmayorquin; Padilla Zarate, Gerardo; Mendoza Montoya, Omar; Falcon Morales, Luis Eduardno; School of Engineering and Sciences; Falcon Morales, Luis EduardoEl proceso de depuración de micro procesadores ha ido aumentando de complejidad en relación con los diferentes bloques que se integran dentro del mismo empaquetado. Los métodos clásicos que se utilizan para depuración, se han vuelto insuficientes por la cantidad vasta de datos a analizar. Los diseñadores de estos chips, integran metodologías y herramientas dentro del chip para que en la etapa de Post Silicio puedan ser utilizadas para acelerar la depuración, una de estas metdologies es el uso de Scan Dumps. Los Scan Dumps se pueden describir como el proceso de tomar un snapshot de las señales internas del procesador en un punto de tiempo específico. Este método es muy útil para el proceso de depuración, pues proporciona visibilidad interna del chip, sin embargo, la cantidad de datos a analizar son millones y en ciertos casos, cientos de millones por lo que se vuelve un reto el intentar analizar esta cantidad de información. Los ingenieros de validación, desarrollan reportes con el fin de seleccionar las señales principales que proporcionen la mayor cantidad de información, sin embargo, el método de seleccionar dichas señales es totalmente manual y basado en la experiencia del depurador. El presente trabajo proporciona una metodología para la selección de dichas señales por medio del uso de Selección de Características. Se presentan los pasos y los resultados de dicho proceso.
- Harnessing machine learning for short-to-long range weather forecasting: a Monterrey case study(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024-05) Machado Guillén, Gustavo de Jesús; Cruz Duarte, Jorge Mario; mtyahinojosa, emimmayorquin; Filus, Katarzyna; Falcón, Jesús Guillermo; Ibarra, Gerardo; Departamento de Ciencias Computacionales; Campus Monterrey; Conant, Santiago EnriqueWeather forecasting is crucial in adapting and integrating renewable energy sources, particularly in regions with complex climatic conditions like Monterrey. This study aims to provide reliable weather prediction methodologies by evaluating the performance of various traditional Machine Learning models, including Random Forest Regressor (RFR), Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), and Recurrent Neural Networks (RNN) such as SimpleRNN, Gated Recurrent Unit (GRU), Long Short-Term Memory (LSTM), Cascade LSTM, Bidirectional RNNs, and a novel Convolutional LSTM/LSTM architecture that handles spatial and temporal data. The research employs a dataset of historical weather data from Automatic Weather Stations and Advanced Baseline Imager Level 2 GOES-16 products, including key weather features like air temperature, solar radiation, wind speed, relative humidity, and precipitation. The models were trained and evaluated across different predictive ranges by combining distinct sampling and model output sizes. This study’s findings underscore the effectiveness of the Cascade LSTM models, achieving a Mean Absolute Error of 1.6 °C for 72-hour air temperature predictions and 85.79 W/m2 for solar radiation forecasts. The ConvLSTM/LSTM model also significantly improves short-term predictions, particularly for solar radiation and humidity. The main contribution of this work is a comprehensive methodology that can be generalized to other regions and datasets, supporting the nationwide implementation of localized machine-learning forecasting models. This methodology includes steps for data collection, preprocessing, creation of lagged features, and model implementation, as well as applying distinct approaches to forecasting by using autoregressive and fixed window models. This framework enables the development of accurate, region-specific forecasting models, facilitating better weather prediction and planning nationwide.
- Estimating occupancy level in indoor spaces using infrared values and environmental variables(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024) Ovando Franco, Angelo Jean Carlo; Ceballos Cancino, Héctor Gibrán; mtyahinojosa, emimmayorquin; Dávila Delgado, Juan Manuel; Minero Re, Erik Molino; School of engineering and Sciences; Campus Monterrey; Alvarado Uribe, JoannaImproving energy efficiency in indoor spaces is critical to reduce harmful effects of excessive energy consumption worldwide. For this reason, estimating occupancy level of people in indoor spaces has been identified as a significant contributor to improve energy efficiency and space utilization. In this thesis, in order to contribute to the solution of this problem, it is proposed to estimate occupancy level of people in enclosed spaces through an indirect approach based on environmental and infrared data, using Machine Learning (ML) techniques. The selected environmental variables are temperature, relative humidity, and atmospheric pressure. In the process, the values of five different workstations from a collaborative work area at Tecnologico de Monterrey were collected to determine the occupancy level of each workstation. To estimate occupancy, supervised ML algorithms were used, obtaining an average accuracy for each workstation of 93%, by using both environmental and infrared data, compared to ground truth counts during occupied hours. Our results show that infrared data plus environmental variables are more accurate than infrared-only sensors for estimating indoor occupancy. At the same way, Random Forest (RF) was the algorithm that reached the highest accuracy among Support Vector Machine (SVM), K-Nearest Neighbors (KNN).
- Deep Learning Approach for Alzheimer’s Disease Classification: Integrating Multimodal MRI and FDG- PET Imaging Through Dual Feature Extractors and Shared Neural Network Processing(Instituto Tecnológico y de Estudios Superiores de Monterrey, 2024) Vega Guzmán, Sergio Eduardo; Alfaro Ponce, Mariel; emimmayorquin; Ochoa Ruíz, Gilberto; Chairez Oria, Jorge Isaac; Hernandez Sanchez, Alejandra; School of Engineering and Sciences; Campus Monterrey; Ramírez Nava, Gerardo JuliánAlzheimer’s disease (AD) is a progressive neurodegenerative disorder whose incidence is expected to grow in the coming years. Traditional diagnostic methods, such as MRI and FDG-PET, each provide valuable but limited insights into the disease’s pathology. This thesis researches the potential of a multimodal deep learning classifier to improve the diagnostic accuracy of AD by integrating MRI and FDG-PET imaging data in comparison to single modality implementations. The study proposes a lightweight neural architecture that uses the strengths of both imaging modalities, aiming to reduce computational costs while maintaining state-of-the-art diagnostic performance. The proposed model utilizes two pre-trained feature extractors, one for each imaging modality, fine-tuned to capture the relevant features from the dataset. The outputs of these extractors are fused into a single vector to form an enriched feature map that better describes the brain. Experimental results demonstrate that the multimodal classifier outperforms single modality classifiers, achieving an overall accuracy of 90% on the test dataset. The VGG19 model was the best feature extractor for both MRI and PET data since it showed superior performance when compared to the other experimental models, with an accuracy of 71.9% for MRI and 80.3% for PET images. The multimodal implementation also exhibited higher precision, recall, and F1 scores than the single-modality implementations. For instance, it achieved a precision of 0.90, recall of 0.94, and F1-score of 0.92 for the AD class and a precision of 0.89, recall of 0.82, and F1-score of 0.86 for the CN class. Furthermore, explainable AI techniques provided insights into the model’s decisionmaking process, revealing that it effectively utilizes both structural and metabolic information to distinguish between AD and cognitively normal (CN) subjects. This research adds supporting evidence into the potential of multimodal imaging and machine learning to enhance early detection and diagnosis of Alzheimer’s disease, offering a cost-effective solution suitable for widespread clinical applications.