http://hdl.handle.net/10757/621164 Sección que corresponde a la producción científica registrada en bases de datos internacionales y que corresponden a los miembros de la universidad. 2026-04-12T00:35:11Z http://hdl.handle.net/10757/689051 Exploring the Seismic Performance of Confined Brick Masonry Walls via Diverse Toothing Connections: A Numerical Investigation Shandilya, A. N.; Haldar, A.; Yacila, Jhair; Mandal, S. Confined brick masonry (CBM) combines masonry walls with reinforced concrete ties for enhanced structural integrity. The wall-to-tie connection is essential for effective load transfer, preventing out-of-plane failure, and enhancing ductility. Introducing tie-columns into masonry walls through various toothing connections is crucial. However, previous research and guidelines do not provide clear insights into their specific contributions, making it difficult to accurately assess their impact. Addressing this gap, our study employed a robust numerical approach, utilizing an integrated finite element macromodel that treated wall and tie members as a single entity, thereby improving computational efficiency. Additionally, the study applied the concrete damage plasticity model to predict damage progression in CBM walls and performed pushover analysis to evaluate the seismic performance of various toothing schemes in CBM walls. An extensive parametric study was conducted to compare various toothing schemes, evaluate the optimal horizontal and vertical projections of tooth, assess the impact of height-to-thickness ratio on toothing schemes, and investigate the effect of openings on the performance of toothing schemes in CBM walls. This research also assessed the severity of damage encountered by CBM walls, providing insights into crack propagation and distribution and emphasizing the significance of its design. This study highlights the critical role of toothing schemes in the seismic performance of CBM walls, with the machine-made toothing schemes demonstrating superior results. These schemes significantly enhanced ultimate strength, stiffness, and energy absorption compared to handmade, horizontal reinforcement, and no-tooth options. The research also quantified the positive correlation between increased wall thickness and improved structural resilience, particularly when paired with machine-made toothing. Furthermore, the study identified the adverse effects of wall openings on seismic performance, emphasizing the importance of precise tooth size and arrangement. Notably, a 100-mm vertical projection was shown to offer the most effective seismic performance, providing valuable, data-driven guidelines for the design of earthquake-resistant CBM structures. 2026-02-01T00:00:00Z http://hdl.handle.net/10757/689050 Enhancing Minimarket Customer Experience Through YOLOv8-Powered Checkout Systems Arana-Del-Carpio, Sebastian; Becerra-Bisso, Luis; Ugarte, Willy In Lima, Peru, minimarkets are vital, providing essential goods to a growing population. However, slow payment processes lead to long lines and frustrated customers, impacting satisfaction and profitability. The main issue is the slow, error-prone manual item scanning at the checkout. Addressing this inefficiency can enhance economic impact, customer satisfaction, and operational efficiency. Despite the benefits, implementing object detection technology faces challenges such as technological complexity, integration issues, diverse product ranges, and high costs. Previous solutions failed due to inadequate technology, high costs, poor integration, and user resistance. This paper proposes using YOLOv8, a state-of-the-art object detection model, for its precision, real-time processing, cost-effectiveness, and easy integration. This work includes custom hardware, an integration layer, and a user interface, with the aim of reducing checkout times, achieving over 94% product recognition accuracy, and improving customer satisfaction. Initial tests show promising results in speed, accuracy, and customer feedback. 2026-01-01T00:00:00Z http://hdl.handle.net/10757/689049 IoT System Based on Deep Learning for the Identification and Feedback of Work Postures When Using a Computer Caballero-Lara, Eduardo; Camargo-Ramirez, Enzo; Ugarte, Willy It is common for office workers, mostly dedicated to IT, to present musculoskeletal pain in the back, neck and shoulders due to poor posture practices they adopt while doing their work in front of the computer for long periods, this is known as forced postures. Our main work seeks to implement an IoT system with force sensors, model RP-S40-ST, based on the use of classification algorithms and deep learning techniques for the identification and correction of postures through feedback. Ten classification algorithms were used for training and validation of the model, with the Logistic Regression algorithm achieving the highest accuracy rate being .8794 and .9052 respectively. 2026-01-01T00:00:00Z http://hdl.handle.net/10757/689048 Mitigating Information Leakage in Tech-Sector SMEs: Implementing ISO 27001:2022 for Comprehensive Security Quispe, Gabriel O.; Zuloaga, Cesar K.; Castañeda, Pedro S. This paper presents a model for implementing an Information Security Management System (ISMS) based on ISO 27001:2022 tailored to the needs of small and medium-sized enterprises (SMEs) in the technology sector in Lima Metropolitana. The model focuses on mitigating data leakage, a critical issue exacerbated by the increasing digitization of business operations. The proposed framework integrates controls from ISO 27001 aligned with NIST SP 800-53 to enhance information security practices. Results from applying the model to two technology SMEs indicate that one company (Company A) achieved a 94.44% Critical Control Implementation Index (IICC), a 70% Critical Vulnerability Resolution Rate (TRVC), and an 85% Policy Compliance Rate (TCPS), while the second company (Company B) achieved significantly lower rates of 50%, 40%, and 60%, respectively. These findings highlight both strengths in technological controls and weaknesses in organizational security management. This research contributes to the field by providing a practical, scalable approach for SMEs to enhance their information security posture, addressing both human and technological factors. 2026-01-01T00:00:00Z http://hdl.handle.net/10757/689047 Unveiling Injustice: Analyzing Child Mortality Inequality across decades in Peru (1981–2017) Huaroto, César; Francke, Pedro; Vivas, Claudia Peru is a developing country that has significantly improved the average of almost all health indicators. Specifically, in the past four decades, child mortality decreased tenfold. However, the same is not necessarily true of equality, which remains a challenge. Using microdata from Peru's population censuses in 1981, 1993, 2007, and 2017, we estimate the inequality in child mortality across different social groups. We estimate differences between ethnic groups, education levels, wealth quintiles, regions, and urban–rural groups and find that although inequality has decreased, it remains significantly high. The data show that inequality in child mortality increased between 1981 and 1993, declined between 1993 and 2007, and then increased between 2007 and 2017. Differences in education are the most crucial factor, associated with 45 % of the inequality in 1981 and 58 % in 2017. Differences between Lima and rural areas account for 27 % to 30 % of the inequality, while ethnicity contributes only 6 % in 1981 and 10 % in 2017. 2026-01-01T00:00:00Z http://hdl.handle.net/10757/689046 A Thorough Evaluation of Demand Prediction Models: Machine Learning, Deep Learning, and Statistical Techniques for Import Businesses Julca-Mejia, Wilson; Julca-Mejia, Annie Nowadays, managing demand in companies is crucial to avoid storage overcosts, stockouts and to improve the service level of companies. To address this scenario, demand predictions through models and algorithms emerge. Therefore, this research aims to evaluate the performance of seven prediction techniques applying machine learning, deep learning, and statistical methods. To validate our experiments, we used Dickey–Fuller, Shapiro–Wilk, Friedman, and Wilcoxon post-hoc statistical tests on the predictions of the models using demand records from a Peruvian import company. The results indicated that deep learning and statistical models have significantly better predictions than machine learning models. In particular, the LSTM, CNN, ARIMA, and Holt-Winters models significantly improve accuracy compared to the Ridge Regression, Random Forest Regressor, and Decision Tree Regressor models. Compared to machine learning models, statistical and deep learning models improve accuracy in a range from 66.01 to 86.10%. These results highlight the statistical advantage of deep learning and statistical models in demand prediction, with the LSTM model showing the lowest error. 2026-01-01T00:00:00Z