https://hdl.handle.net/20.500.12724/20561 Wed, 13 May 2026 08:36:54 GMT 2026-05-13T08:36:54Z https://hdl.handle.net/20.500.12724/24464 Predictive machine learning models for match outcomes in taekwondo based on competitive history Velásquez Chávez, Daphne Solange; Utani Bendezú, Ximena Nataly; Escobedo Cárdenas, Edwin Jonathan Taekwondo is an Olympic combat sport where performance depends on speed, strength, and tactical precision. Although data-driven methods are advancing in sports science, predictive modeling in taekwondo remains limited. Most existing studies focus on physical metrics or more popular disciplines, leaving a gap in outcome prediction based on competitive history. In this study, we analyze the contribution of technical and contextual features to match outcomes, aiming to identify the most relevant predictors of success. We also propose a dual-structured dataset: one version models individual match sequences, and the other captures pairwise confrontations. This design allows evaluation under both temporal and head-to-head prediction frameworks. Using official data from the Peruvian Taekwondo Sports Federation, we trained and compared eight machine learning models. LightGBM achieved the highest F1-score (84.00%) in the sequence-based format, while XGBoost performed best (75.00%) in the pairwise version. Feature importance analysis revealed second-round actions—clean points and penalties—as key predictors. Our findings demonstrate that machine learning can effectively identify technical and contextual variables that influence match outcomes, offering valuable support for performance improvement, training optimization, and strategic planning in high-performance taekwondo. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.12724/24464 2025-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/24467 Facial Expressions Recognition in Sign Language Based on a Two-Stream Swin Transformer Model Integrating RGB and Texture Map Images Ramirez Cerna, Lourdes; Rodriguez Melquiades, Jose; Escobedo Cárdenas, Edwin Jhonatan; Cámara Chávez, Guillermo; Garcia Miranda, Dayse The study of facial expressions in sign language has become a significant research area, as these expressions not only convey personal states, but also enhance the meaning of signs within specific contexts. The absence of facial expressions during communication can lead to misinterpretations, underscoring the need for datasets that include facial expressions in sign language. To address this, we present the Facial-BSL dataset, which consists of videos capturing eight distinct facial expressions used in Brazilian Sign Language. Additionally, we propose a two-stream model designed to classify facial expressions in a sign language context. This model utilizes RGB images to capture local facial information and texture map images to record facial movements. We assessed the performance of several deep learning architectures within this two-stream framework, including Convolutional Neural Networks (CNNs) and Vision Transformers. In addition, experiments were conducted using public datasets such as CK+, KDEF-dyn, and LIBRAS. The two-stream architecture based on the Swin Transformer model demonstrated superior performance on the KDEF-dyn and LIBRAS datasets and achieved a second-place ranking on the CK+ dataset, with an accuracy of 97% and an F1-score of 95%. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.12724/24467 2025-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/24465 Optimizing Credit Risk Prediction in the Financial Sector Using Boosting Algorithms: A Comparative Study with Financial Datasets Villanueva Mora, Renzo Orlando; Escobedo Cárdenas, Edwin Jhonatan Credit risk is a significant concern for financial institutions. Despite advances in predictive models, there is still room for improvement in accurately assessing credit risk. This study focuses on developing a methodological process to predict credit risk in the financial sector using algorithms based on boosting techniques, such as XGBoost, LightGBM and Boosted Random Forest. We found that datasets with good accessibility and an appropriate variable distribution are contained in the UCI Machine Learning Repository. These datasets are potential to outperform results with different metrics, such as the F-Score and the Area Under the Curve. The datasets used include Statlog German Credit Data, Statlog Australian Credit Approval, Bank Marketing, Credit Approval, and South German Credit Data. The approach involves feature engineering, exploratory data analysis, and hyperparameter tuning. Furthermore, we propose a new strategy that involves adding a column based on an unsupervised algorithm such as Kmeans. Our results indicate that XGBoost has better performance than LightGBM and Boosted Random Forest in different scenarios. Finally, the performance of these boosting-based models is superior to that of Boosted Decision Trees and Factorization Machine models from previous studies. These findings are important for financial institutions seeking an effective methodology to improve credit risk prediction rate. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.12724/24465 2025-01-01T00:00:00Z https://hdl.handle.net/20.500.12724/24430 PeruFoodNet: A unique dataset of traditional peruvian food for image recognition systems and allergenic ingredient inference Arzola Gutierrez, María Franchesca; Canchari Muñoz,Edgar Alexander; Escobedo Cárdena,s Edwin Jonathan Peruvian cuisine has won numerous international awards, attracting tourists from around the world to Peru to experience its diverse culinary offerings. However, some dishes contain ingredients that can trigger allergic reactions, posing a potential health risk for visitors. To address this, we created PeruFoodNet, a dataset featuring 4,000 images of traditional Peruvian dishes. The dataset includes 40 of the most popular dishes, such as Ceviche and Anticuchos, with 100 images of each dish. The images of the dishes have been captured from various angles, settings, lighting conditions, dimensions and backgrounds. To gather these images, we prepared the dishes ourselves, purchased some from restaurants, and received contributions from external users over a two-month period. However, most of the images were captured by the authors of the dataset. The dataset is publicly available and can be valuable for research in image recognition and classification using Computer Science techniques, such as Deep Learning. Additionally, it can aid in identifying allergenic ingredients in dishes by linking the dish’s image to a list of ingredients through a technological platform, such as a chatbot or an app. Wed, 01 Jan 2025 00:00:00 GMT https://hdl.handle.net/20.500.12724/24430 2025-01-01T00:00:00Z