Conference Agenda

People spend approximately more than 90% of their time indoors, which exposes them to airborne gaseous and chemical pollutants that can affect their health and well-being. Recent studies have shown that up to 63% of healthcare personnel present at least one health issue associated with poor indoor air quality. Consequently, this study evaluated various existing technologies aimed at improving indoor air quality. Based on the collected information, a synergistic multi-band prototype was developed, harnessing the germicidal efficacy of UV-C light and the photocatalytic effect generated by exposing titanium dioxide to UV-A light. Several tests were conducted under three different experimental scenarios: no intervention, UV-C intervention, and UV-C + photocatalysis intervention. The prototype achieved reductions of 86.19%, 81.68%, and 69.87% in volatile organic compounds, and 100% elimination of aerobic bacteria and yeasts when applied in various hospital environments. The data obtained was subjected to rigorous statistical analysis, demonstrating significant differences (p<0.0001) among each of the experimental scenarios.

This study explores the application of a Platsil Gel-10 silicone coating to a polylactic acid (PLA) hand prosthesis fabricated through fused deposition modeling (FDM). The objective was to evaluate both thermal behavior and aesthetic performance of the coated structure under practical stress conditions. Thermal characterization was conducted on individual prosthetic fingers using K-type thermocouples during controlled and high-intensity heat exposure. Temperature progression followed a largely linear trend across trials, suggesting predictable heat transfer behavior and no immediate signs of material instability. Beyond thermal response, the surface and visual qualities of the silicone layer were examined. Color matching was assessed against a reference skin tone, and surface morphology was inspected using microphotography. The coating demonstrated detailed reproduction of dermal features, including fine ridges and pores, while adhesion testing showed no early delamination under cyclic loading. Tactile evaluation indicated a compliant surface texture comparable to soft tissue. Although initial performance was encouraging, limitations were observed in color retention and in the projected durability of the coating under prolonged mechanical wear. These findings highlight areas for material formulation refinement. Overall, the results indicate that silicone-coated PLA structures may provide a cost-accessible pathway for improving the cosmetic realism of upper-limb prostheses, particularly in settings where manufacturing resources are constrained.

Risk inspection and mitigation in underground mining pose critical challenges due to unstructured environments, limited visibility, and geomechanical instabilities. This paper presents an autonomous quadruped robotic architecture based on multimodal 3D perception fusion for safe navigation and early hazard detection in complex mining scenarios. The system integrates LiDAR, computer vision, and inertial data through probabilistic fusion to generate consistent three-dimensional maps using real-time SLAM.
A risk-aware predictive planning framework is formulated as an optimization problem with dynamic weighting of critical zones and safe trajectory generation under kinematic and dynamic constraints. A robust dynamic controller ensures stability and adaptability over irregular terrain and external disturbances.
The architecture is validated through high-fidelity ROS~2 simulations and laboratory experiments emulating underground gallery conditions. Results confirm real-time computational feasibility and demonstrate improved obstacle avoidance robustness and superior chassis stabilization compared to reactive navigation strategies. The proposed integration of multimodal perception, predictive planning, and risk-oriented dynamic control establishes a scalable framework for safe automation in underground mining.

This paper presents a comprehensive intelligent artificial vision system designed to automate risk prevention in industrial and construction environments by supporting occupational health and safety supervisors (SSOMA). The proposed solution integrates real-time camera-based monitoring with trained deep learning models capable of detecting unsafe behaviors such as improper use of personal protective equipment (PPE), incorrect manual load handling postures, and other hazardous actions. The system processes video streams locally using optimized computer vision algorithms and neural network models trained on labeled datasets to ensure reliable detection under varying environmental conditions.

Upon identifying a safety violation, the system automatically generates visual alerts, stores photographic evidence, and logs the event in a structured database. All information is centralized in a local server developed using Flask, which provides an interactive web-based interface for real-time supervision, historical incident review, and risk analytics. The architecture prioritizes data privacy through on-premise deployment, low latency response, and scalability for multi-camera industrial scenarios. Experimental validation demonstrates high detection accuracy, rapid response times, and operational robustness, highlighting its potential as a practical, cost-effective, and scalable Industry 4.0 solution for proactive workplace risk management.

The Internet of Things (IoT) has transformed modern industry through real-time monitoring and automation, but it has also increased cyber risk in edge implementation with limited resources. The article presents the implementation and web deployment of a lightweight anomaly detection system for IoT environments, structure using the cross-Industry Standard Process for Machine Learning with Quality models (Isolation Forest, Single Class SVM and K-Means), the BoT-Iot dataset was used, and operational behavior was validated with real-time packet capture. The models are evaluated with internal clustering metrics (Silhouette, Calinski-Harabasz, Davies-Bouldin) and attack-driven behavior, and the selected artifacts are implemented through a Streamlit interface for interactive inference and monitoring. The results show that the proposed pipeline is feasible and reproducible for small-scale IoT deployments, while providing accessible, user-oriented security analytics.

Open government data have significantly increased the availability of information about procurement processes. However, despite the growing use of network analysis to study economic and institutional interactions, structural dependency between suppliers and health institutions has rarely been operationalized as a measurable property of procurement networks. This limitation is particularly relevant in medical equipment markets, where supplier concentration may affect the resilience and continuity of healthcare services.

This study models Chile’s medical equipment procurement system as a weighted bipartite network constructed from awarded purchase orders published on the national e-procurement platform (www.mercadopublico.cl) between January 2022 and April 2025. The resulting network connects 204 healthcare institutions with 249 suppliers through 1,420 procurement transactions. Community detection based on modularity optimization reveals eleven structural groups characterized by dense internal connectivity and sparse inter-group links.

The results indicate a structural organization of the market. High-value procurement relationships are concentrated in specific technological segments, particularly imaging and surgical equipment, where a small number of multinational suppliers dominate much of the transaction volume. In contrast, other communities display diversified procurement patterns involving multiple suppliers and mid-range purchase values.

These findings provide a structural characterization of Chile’s medical equipment procurement ecosystem and suggest that network-based approaches can support the identification of supplier dependency risks in healthcare markets. By translating large volumes of procurement data into interpretable network structures, the framework contributes to the development of tools that can support evidence-based procurement planning and risk monitoring in health technology management.

While traditional game design methods focus on creating immersive experiences, artificial intelligence (AI) has ushered in a new era where developers can design games that adapt to a player’s behavior and preferences, offering a more personalized experience. Classic board games like chess focus on strategic movement but lack realistic battlefield dynamics. Players seeking a deeper tactical experience often turn into complex strategy games, which can be overwhelming. This project focuses on creating a novel, browser-based strategy game designed to bridge the gap between classic board games and complex tactical simulations. Dominion: Fields of Honor, a web API, chess-like strategy game, combines the mechanics of the “Dominion” deck-building card game with a “Fields of Honor” concept. It integrates war tactics, unit variety, and terrain-based combat while remaining simple to learn and play online. A key innovation is the integration of a simplified, rule-based AI module designed to adapt to gameplay challenges and generate dynamic in-game events, offering a more personalized experience than traditional static games. The final product is a fully functional web-based game featuring units with unique stats and randomized terrain, along with a scalable architectural blueprint that demonstrates the potential of AI in enhancing simple interactive applications.

This paper describes the design and realization of a mobile platform for autonomous vehicles to participate in robotics design competitions, such as the Intelligent Ground Vehicle
Competition (IGVC). The goal of constructing this platform is to develop future designs of similar platforms and to provide modular software and hardware structures for re-use and adaptability. The software system is loaded onto a Jetson Orin Nano Super and utilizes
the Humble distribution of Robot Operating System 2 (ROS 2). It separates each core processing task into a threaded node where data topics are published and/or subscribed to as variable arguments for processing. New nodes can be integrated into the system by linking them to published data topics. In this implementation, sensor integration, data processing, and waypoint planning are all separated into discrete nodes. The mechanical and hardware systems of the robot include a flexible power distribution system
using adjustable voltage regulators to support a wide family of use cases. Additionally, an emergency-stop system is built into the frame of the robot and includes a button interface on the robot and a remote transmitter to stop the system at a distance. This frame is
an aluminum construction that sits atop a motorized wheelchair base and is connected via a mast that is inserted into a pole in that wheelchair base. This allows for quick changes to the fundamental design structure to be made. A dual-motor differential drive provides the robot with the ability to rotate in place and the ability to perform routine maneuvers necessary to complete navigation tasks.

This study evaluates the impact of incorporating bamboo fibers into the mechanical and rheological performance of concrete, analyzing the influence of their geometry, dosage, and surface treatments. In the fresh state, the addition of this type of fiber significantly reduces workability (slump) due to internal friction and high water absorption. However, in the hardened state, they transform the brittle failure of concrete into ductile behavior through the bridging effect. The findings determine that the use of optimal doses (1.0% to 1.5%) with moderate lengths (20 mm to 40 mm) maximizes flexural strength, tensile strength, and toughness. Although compressive strength tends to decrease due to increased porosity, alkaline treatments (such as magnesium or calcium hydroxide) mitigate this loss. Quantitatively, the review shows increases in tensile strength ranging from 17% to 101%, reaching flexural values of up to 14.4 MPa, while compressive strength remains mostly within a structurally viable range of 20 to 50 MPa. These treatments clean impurities, improve interfacial adhesion, and ensure high durability against moisture-dry cycles. Therefore, modified bamboo fiber is established as a sustainable and structurally viable reinforcement alternative.

This study evaluates the stability and mobility of pedestrians during tsunami-induced flooding in Puerto Rico. The research was divided into two main phases: the development of an analytical stability model (Phase 1) and an experimental fatigue study (Phase 2). In Phase 1, pedestrians were represented as rectangular prism and cylindrical monoliths to determine the impact of water depth and velocity on their sliding and overturning stability. Drag, buoyancy, friction, and body weight forces were considered. Anthropometric data from Puerto Rican adults and 6-year-old Colombian children were used to evaluate the analytical model. The results demonstrated that instability could occur at low water levels and moderate velocities, that sliding is the predominant cause of instability, and that the footwear-to-ground friction coefficient is the critical parameter. It was also observed that children and women are the most vulnerable populations. In Phase 2, a gait study was conducted using two concentric pools simulating an endless evacuation walk, monitoring heart rate and oxygen consumption with a portable spirometer at different flood levels (ankle, knee, and hip). Contrary to the initial hypothesis, the greatest physiological effort (measured by oxygen consumption) occurred at intermediate levels (ankle and knee). At the hip level, buoyancy reduced muscle load but drastically decreased walking speed. These findings demonstrate that horizontal evacuation routes should be designed with pavements that provide a high coefficient of friction, and that extended evacuation under flooded conditions may be infeasible, highlighting the need to integrate vertical evacuation options in high-risk coastal areas.

This research analyzed the acceptance of e-commerce on the website of a Costa Rican SME through a mixed-method design that triangulated conscious survey data with unconscious neuromarketing metrics (Eye-Tracking, Face Reader) in a sample of 67 women. Multiple regression confirmed Perceived Utility and Usefulness as the only significant predictors of conscious acceptance. However, biometric analysis revealed a critical discrepancy: the "Refund Policy" captured 61% of the total visual time, demonstrating that risk mitigation is the dominant unconscious barrier. This finding, along with a 65% purchase abandonment rate due to usability failures, concludes that perceived risk—while consciously insignificant—generates a "Neutral" emotional experience and is the primary driver of abandonment at the unconscious behavioral level.