Conference Agenda

This quantitative, applied, and experimental study was carried out in 2024. The present study aimed to implement total quality management to reduce non-conforming products in a footwear SME in Trujillo. A quantitative research was carried out, with an applicative level, explanatory scope, and pre-experimental design. The population consisted of all the SME's products, selecting a sample of the non-conforming products. Data collection was carried out through continuous visits, direct observation, and documentary collection, using an observation guide and a data collection sheet. Initially, activity and flow diagrams were used to identify the main activities and determine the percentage of non-conforming products, which was 12.25%. Total quality management tools such as Ishikawa and Pareto diagrams, brainstorming, statistical process control, PDCA, and Hoshin Kanri were applied to reduce non-conformity. The results showed a decrease in non-conforming products from 12.25% to 4.09% in 22 days, representing a reduction of 8.16%. The research concludes that the hypothesis is true, demonstrating the relationship between total quality management and the reduction of non-conforming products.

Fatigue detection using facial analysis with computer vision and machine learning in embedded systems is a non-invasive solution, but it faces challenges in evaluating the computational resources used on hardware devices like a Raspberry Pi. Previous studies have investigated fatigue and drowsiness detection using facial features related to mouth and eye opening and computer vision-based classification models, without considering the computational performance of these solutions. This research aims to evaluate the performance of machine learning models that use facial point features for fatigue detection implemented on a Raspberry Pi, considering metrics such as CPU usage, memory, inference time, and processing speed. To this end, support vector machine, random forest, and decision tree models are evaluated to assess their computational performance. The results show that no single model is superior in all aspects, as decision trees demonstrate better detection of events like yawning (YAWN), while the SLEEP class proves to be the most complex for all models. Furthermore, the decision tree stands out for its lower latency and greater adaptation to real-time applications, so the selection of the model is based on a relationship between accuracy, latency and consumption of processing resources

Nowadays, the advance of digitalization and the growing need to optimize processes have driven companies to look for innovative solutions to improve their operational efficiency. In this context, the following study aimed to implement an intelligent system based on Deep Learning to automate data processes within the company, focusing on improving efficiency, accuracy and optimization of operational tasks. The research used a pre-experimental design, with quantitative approach and applied character, analyzing a population of 1,400 records of human management data, such as attendance, task and customers. Data collection was carried out through direct observation and documentary analysis, while the system development was based on the Crystal-Clear agile methodology, allowing specific adaptations to the company's operational needs. The results showed significant improvements: information access time was reduced from 29.90 seconds to 15.77 seconds, accuracy in identifying sensitive data increased from 58.70% to 91.43%, and automation efficiency increased from 28.67% to 95.67%. Statistical tests confirmed the relevance of these results. The system optimized processes and reduced manual intervention and highlighted the importance of customized intelligent solutions to improve organizational performance. These findings highlight the potential of Deep Learning-based systems to transform data-sensitive sectors such as private security.

Student dropout is a significant problem in public universities, with academic, economic, and social repercussions. This study aims to develop a predictive model based on machine learning techniques for the early identification of students at risk of dropping out. This will enable the implementation of measures to reduce dropout rates through intervention strategies such as personalized tutoring and socioeconomic support. The data used consists of academic, socioeconomic, and behavioral records from 2015 to 2024. The methodology employed is quantitative and predictive, utilizing algorithms linked to supervised learning techniques such as Logistic Regression, Decision Trees, Random Forest, and AdaBoost. The data were pretreated through cleaning, Z-score normalization, balancing using the SMOTE technique, and subdivision using the holdout technique into training (70%), validation (15%), and test (15%) subsets. k-fold cross-validation (k = 5) was applied during the training phase.

The performance metrics considered to evaluate the proposed models were accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC). The results obtained for each model indicated that the AdaBoost model performed best, achieving an accuracy of approximately 89% and an AUC of 0.957. Random Forest had an AUC of 0.902, and Logistic Regression had an AUC of 0.948. Therefore, it is concluded that the proposed model could be considered a suitable tool for the early detection of students at risk of dropping out.