Conference Agenda

The present research focused on the development of artificial intelligence (AI) tools within the mining sector, specifically through predictive regression models, with an emphasis on the copper industry. This study adopted a quantitative and exploratory approach, enabling the development of models using various features of artificial neural networks (ANN) through Machine Learning algorithms, based on historical data in both cases. The main objective of this study was to develop predictive regression models in the copper mining industry using artificial neural networks (ANN). In this context, forecasts were made for the future price of copper and the capital cost of open-pit copper mines. The results indicate that it was possible to estimate, with an acceptable degree of accuracy, both the future price of copper and the mining capital cost for open-pit copper mines. In the first case, a model was developed using the TensorFlow-based Deep Learning ANN technique for the "REDPC_17" test. A 7-day forecast was achieved with an acceptable margin for the three networks—LSTM, GRU, and CNN—resulting in an MSE of 2.6621e-04, 5.8286e-04, and 3.0642e-04, respectively. This led to an average percentage error of 7.9342% for the CNN network, which proved to be the best performer in the test. In the second case, a model was developed using the Scikit-Learn MLPRegressor ANN technique for the "REDES_20" test. This model achieved the best performance in estimating CAPEX, with a determination coefficient (R²) of 0.00960 and an MSE of 0.8674.

This study evaluates in the ten Peruvian airports with the highest movement between 2015 and 2025, to what extent the discrepancy between the TAF aeronautical forecast and the METAR observation is associated with preventive cancellations, operationalized through a monthly proxy based on commercial operations and observed meteorological severity. Historical TAF/METAR series downloaded from OGIMET and commercial operations by airport-month were integrated from CORPAC's National Airport General Movement report. The proxy label was defined as the conjunction between a strange drop in operations and observed adverse weather determined by global percentiles of METAR variables (FG/TS phenomena, visibility, wind and ceiling). A base model with METAR variables was compared with models incorporating TAF-METAR discrepancies, using temporal validation (train ≤2022; test ≥2023). The results show incremental improvement by including robust discrepancies in phenomena such as fog and storm. In addition, airports with a higher frequency of falls without adverse weather observed were identified, providing evidence to focus operational audits and future studies with flight-level data.

This study evaluates the effectiveness of computational models in improving nutritional diagnosis and food recognition through the analysis of image-based and numerical data. The research focuses on the performance of Deep Learning (DL), Machine Learning (ML), and hybrid DL + ML approaches, highlighting their role in nutritional evaluation, quality classification, and food identification. Results show that CNN – Based DL models achieve the highest accuracy when processing large and complex datasets, outperforming others architectures in tasks such as nutrient estimation, food quality assessment, and disease detection in crops and food products. Hybrid Ensemble – CNN models demonstrate superior robustness, offering more stable results and enhanced diagnostic performance across multiple applications.

Energy consumption in educational buildings is a growing concern due to environmental and economic implications. Many academic institutions lack effective tools for monitoring and controlling energy use, hindering data-driven decision-making for sustainability. This paper presents a mobile application that enables monitoring and analysis of electrical consumption in the FCMF-UG building, addressing the need for accessible real-time data and historical insights. The system was developed using the Scrum framework, with requirements gathered through surveys and stakeholder interviews. Key features of the app include CSV uploads of sensor readings, interactive visualization of consumption statistics, anomaly-detection alerts, and a user-friendly interface for non-technical staff. A modular architecture was implemented using a cross-platform mobile framework and a Python-based backend, ensuring scalability and offline functionality. The application was validated through functional testing and user evaluations, which indicated improved accessibility to energy data and better interpretation of consumption patterns. Results show that users can identify usage anomalies and compare trends over time, facilitating more informed energy management. The proposed solution demonstrates significant potential to optimize energy usage in academic buildings and foster sustainable practices. Its adaptable design can be extended to similar institutional contexts.

Abstract– Today, public digital platforms increasingly process personal and sensitive data through complex and interconnected information systems. This necessitates analyzing different engineering approaches that integrate privacy requirements from the earliest stages of system design. While Privacy by Design (PbD) has been studied from a regulatory and conceptual perspective, its implementation on public digital platforms remains a significant engineering challenge.

This paper proposes an engineering framework for designing and evaluating Privacy by Design on public digital platforms. The proposed framework applies PbD principles to concrete engineering artifacts by structuring privacy integration in three dimensions: a) design requirements, b) technical safeguards, and c) evaluation indicators. These approaches support both decision-making during the design phase and post-implementation evaluation, enabling systematic assessment throughout the platform's lifecycle.

To validate the proposed framework, a case-based evaluation was conducted on a set of public digital platforms in the Argentine public sector. An automated prototype was developed to evaluate Privacy by Design (PbD) benchmark indicators, including secure communication mechanisms, transparency features, and observable data minimization practices in user-accessible components. The results reveal recurring engineering deficiencies, including default security configurations, limited visibility into privacy policies, and inadequate handling of sensitive data.

This proposal provides a replicable approach that supports engineering practices in the public sector, enabling developers and designers to implement Privacy by Design beyond mere regulatory compliance. This contribution promotes privacy-respecting engineering practices and supports the development of more reliable public digital systems in terms of privacy.

This article aimed to determine the impact of a mobile application on optimizing citizen reporting of urban security incidents in Trujillo, Peru. Citizen insecurity represented a critical problem in the La Libertad region, where traditional reporting channels suffered from accessibility and trust limitations, resulting in a 75% underreporting rate. To address this issue, Harkai, a mobile application implemented with Flutter, Firebase, and a chatbot assistant called Harkbot, was developed. The methodology was applied, with a pre-experimental pre-test/post-test design using a single group. Two hundred participants were evaluated over six months using indicators such as the number of citizen reports, the number of criminal incidents, the level of perceived accessibility, and the level of citizen trust. The results, validated using Student's t-test (α=0.05), showed a 251.21% increase in citizen reports, a 17.96% reduction in crime incidents, a 92.49% improvement in perceived accessibility, and a 118.27% increase in citizen trust. It was concluded that Harkai significantly optimized citizen reporting of urban security incidents in Trujillo.