Facultad de Ingenierías

Parent Organisation

Universidad Indoamérica

Now showing 1 - 10 of 224

Some of the metrics are blocked by your
consent settings
Artificial intelligence for resilient transportation infrastructure: the first Ecuadorian pavement damage dataset and an assessment of domain transfer across international road networks
(Frontiers Media SA, 2026-08-26)
Zambrano-Salazar, Leonardo
;
López, Enma Gamboa
;
Pinto Almeida, Carlos
Background Pavement-condition monitoring is a cornerstone of resilient and sustainable transportation infrastructure, yet existing public datasets for automatic damage detection are dominated by data from high-income countries. Deep-learning models trained on those data often transfer poorly to Latin American road networks, where deterioration patterns, materials, and maintenance regimes differ. No publicly available pavement damage dataset for Ecuador has been reported to date, to the best of our knowledge. Methods We present the Ecuadorian Pavement Distress Dataset (EcuPDD), 1,295 images annotated under ASTM D6433 into six damage classes (4,559 annotated instances), collected across seven cities in the three geographic regions of Ecuador (Sierra, Coast, and Amazon). The dataset is released under CC BY 4.0 on Zenodo (DOI: 10.5281/zenodo.20454801 ). On this base we trained five YOLOv8n variants progressively fused with three open international datasets—RDD2022 Japan, RDD2022 China_MotorBike, and McMaster Pavement Crack Detection—for a total corpus of up to 15,941 images (of which roughly 80% were used for training and 20% for validation, following the splits described in Section 3). Each version was trained five times with independent random seeds (25 runs in total), and results are reported as mean ± standard deviation. We evaluated each version on its mixed validation set and, separately, on a fixed 259-image Ecuadorian held-out subset. We complemented the standard mAP50/ mAP50-95 metrics with Wilson 95% confidence intervals on per-class detection rates, a Gini coefficient for class imbalance, and a Domain Gap Index (DGI) that we define as 1 − (mAP50Ecuador/ mAP50general), summarising the divergence between the general and local performance of each model. Results Adding international data lifted the mixed-validation mAP50 from 14.65% (V1, Ecuador only) to 57.66% (V5, Ecuador + McMaster + China_MotorBike), an absolute gain of 43.01 percentage points. However, when evaluated only on the 259 Ecuadorian held-out images, mAP50 stayed between 14.65% and 15.90% across all five versions—a swing of 1.25 pp despite the inclusion of up to 14,646 additional images. The Wilson 95% confidence intervals on those Ecuadorian-only mAP50 values overlap heavily for all versions, indicating substantial overlap and no clear evidence of separation among versions at this sample size. The Domain Gap Index reaches 0.733 for V5 and 0.713 for V2, while remaining ∼0 for V1 and V3. Patching, despite contributing only 2.3% of the instances, reached a Wilson-CI-supported detection rate of 0.78 [0.73, 0.82] thanks to its strong visual distinctiveness when paired with the McMaster dataset. Conclusion International datasets improve a YOLOv8n detector globally but do not, by themselves, close the domain gap to Ecuadorian roads. The bottleneck is the volume and representativeness of local annotated data. EcuPDD provides the first openly licensed Ecuadorian benchmark for this task and an empirical calibration point that researchers in Latin America and other under-represented regions can use to plan dataset-construction and model-development efforts aligned with the resilience and sustainability goals of the AI-for-infrastructure agenda.
Some of the metrics are blocked by your
consent settings
Comparative Analysis of the Technical Performance of a Centralized Photovoltaic Power Plant and Distributed Micro-Solar Power Plants
(IEEE, 2026-07)
Quiñaliza, Daniel
;
Masache Almeida , Paul Andres
This article presents a comparative analysis of the technical and energy performance of centralized and distributed photovoltaic (PV) generation configurations applied to a rural radial feeder. The analyzed feeder exhibits peak demand during nighttime hours, revealing a structural misalignment between the solar generation profile and the consumption profile. Five scenarios were evaluated using hourly simulations with representative demand and generation profiles. The analysis considered daily energy losses (kWh), power flow direction, power factor behavior per phase at the delivery point, and feeder operating conditions. The results demonstrate that the reduction in losses is not proportional to the installed capacity. The centralized configuration generated sustained reverse flows during peak irradiance hours. In contrast, the configurations sized based on average daytime demand exhibited more balanced energy performance, achieving reductions of up to 2.41% in total losses through phase-adjusted single-phase distributed generation. It is concluded that the optimal integration of photovoltaic generation in rural networks with a predominantly nighttime load profile depends primarily on the temporal alignment between generation and local demand, rather than on matching the system's peak demand. The study provides a methodological framework based on hourly energy analysis and phase-by-phase evaluation, geared towards the optimal planning of photovoltaic penetration in rural distribution systems. © 2026 IEEE.
Some of the metrics are blocked by your
consent settings
AI-ready hydraulic risk prioritization of deteriorated Andean concrete channels
(Frontiers Media SA, 2026-09-01)
Núñez, Mayra Alejandra
;
Núñez, Samanda Monserrath
;
Guevara, Arlette Dayana
;
Pinto Almeida, Carlos
Introduction Open concrete channels in Andean watersheds convey irrigation water and urban stormwater, and their deterioration raises Manning’s roughness coefficient (n), alters specific energy (E) and consumes freeboard. Managers know that a channel is degraded but lack a reproducible procedure for turning that observation into a defensible intervention priority. Methods We characterise ten consecutive reaches (219 m) of a rectangular cyclopean-concrete channel in Ambato, Ecuador (b = 0.645 m; Q = 0.21 m 3 /s; s 0 ≈ 0.03). Each reach was scored on a 1–5 Structural Damage Index and mapped to a Manning coefficient through an additive decomposition reported reach by reach. The coefficients were propagated through the Manning–Strickler equation, solved simultaneously with continuity, to obtain normal depth, velocity, Froude number, specific energy and freeboard. Because these quantities are deterministic functions of the assigned n, they are reported as transfer curves rather than as statistical relationships; analysis is confined to the observations themselves and to the propagation of observer uncertainty. Results Assigned coefficients ranged from 0.016 to 0.034, that is 23%–162% above the design value of 0.013. Departure of specific energy from the design condition ranged from 14.5% to 30.9%, and freeboard fell from 0.277 m to 0.160 m in the most degraded reach, a loss of 42% of the original margin. The transfer curve is not monotonic: the departure peaks near n ≈ 0.030 and declines beyond it, because specific energy passes through its minimum at the critical regime, reached here at n ≈ 0.0304. A one-class error in visual scoring displaces the departure by 8.6 percentage points on average and would change the intervention tier of six of the ten reaches; the two requiring immediate intervention are not among them. Conclusion Structured visual assessment combined with transparent hydraulic propagation yields a traceable intervention hierarchy reproducible with a camera, a total station and an open-source solver. The hydraulic values are model-derived estimates conditional on the assigned coefficients, not measurements; calibration against in situ measurement remains necessary and generalisation beyond this channel is not demonstrated. The protocol, imagery and scripts are released as an openly licensed dataset intended as ground truth for future classifiers.
Some of the metrics are blocked by your
consent settings
Effect of replacing mixing water with milk on the compressive strength of concrete at different curing ages
(Frontiers Media SA, 2026-07-17)
Pinto Almeida, Carlos
;
Zambrano, Leonardo
;
Apraez, Jose
;
Gómez, Juan
;
Zurita, Marco
Introduction – The chemical composition of mixing water directly affects cement hydration and the strength development of concrete. Although alternative mixing liquids—such as treated wastewater, leachates, and wash water—have shown moderate strength reductions compatible with structural use, the behavior of concrete exposed to complex organic liquids remains largely uncharacterized. Methods – This study investigates how replacing mixing water with whole bovine milk, a medium rich in lactose, casein, and fat, affects cement hydration and compressive strength in conventional Portland concrete. Three mixtures with increasing replacement levels were produced: 0% (M0, control), 50% (M50), and 100% (M100). Twenty-seven cylindrical specimens (3 mixtures × 3 ages × 3 replicates) were tested under axial compression following ASTM C39/C39M at 15, 28, and 45 days. Peak strength, stress–strain curves, within-condition dispersion, and failure modes were recorded. Results – The control developed strengths of 14.39 ± 0.64, 16.47 ± 0.73, and 20.91 ± 0.81 MPa at 15, 28, and 45 days, whereas M50 and M100 remained below 1 MPa at all ages (M50: 0.61 ± 0.03, 0.67 ± 0.03, 0.90 ± 0.06 MPa; M100: 0.38 ± 0.02, 0.55 ± 0.02, 0.60 ± 0.03 MPa), a strength loss greater than 95% relative to the control. Coefficients of variation ranged from 3.9% to 6.1%, below the 10% threshold of ACI 214R. The modified mixtures also lost the ascending branch of the stress–strain curves and exhibited diffuse failure modes, without the longitudinal cracking typical of sound concrete. Conclusion – The magnitude of the strength loss (>95%) places milk in a category distinct from previously reported alternative mixing liquids. Rather than producing a degraded variant of conventional concrete, it generates a system in which the cementitious reaction is practically inhibited. This behavior, attributable to the combined action of lactose, casein, and fats on C3S hydration, redefines the operational limits of chemical compatibility between organic fluids and cementitious systems and provides a reference calibration point for predictive models of organic inhibition. Copyright © 2026 Pinto, Zambrano, Apraez, Gómez, Zurita and Buele.
Some of the metrics are blocked by your
consent settings
Rain-Triggered Mass Movement Hazard Assessment of the 2025 Tejar Chimbo Landslide in Andean Ecuador
(Highlights of Science, S.L., 2026-06-16)
Banegas, Fredy
;
Salinas, Isela
;
Toulkeridis, Theofilos
;
Ordoñez-Fernandez, Jose
;
Chunga, Kervin
The rainfall-triggered landslide that occurred at the Tejar site in Andean Ecuador on 27 April 2025 (12:35 p.m., local time), provides a representative case for understanding the interaction between extreme precipitation and volcanic geomaterials in slope instability processes. This study aims to characterize the geological and geotechnical conditions controlling the failure and to evaluate the mechanisms associated with rainfall-induced saturation in the Andean foothills of San José de Chimbo. Geological reconnaissance identified three main lithological units: cohesive laharic deposits, massive lapilli tuffs, and andesitic to ignimbritic volcanic rocks. Structural analysis revealed well-defined discontinuity planes, including joint systems and shear fractures with normal components, which extend several meters within the rock mass and act as preferential sliding surfaces. The methodology integrates field mapping, kinematic analysis, aerial photogrammetry, laboratory direct shear testing, and deterministic slope stability modeling using limit equilibrium methods. Additionally, historical precipitation records since 2010 were analyzed and correlated with intense rainfall associated with La Niña Modoki conditions. Results indicate that slope instability is primarily controlled by structurally guided planar failure mechanisms, significantly influenced by rock mass saturation and water infiltration along discontinuity planes. Back-analysis demonstrates that the factor of safety (FS) decreases from stable conditions (FS > 1.2) to values close to failure (FS ≈ 1.0) under fully saturated conditions, consistent with observed field behavior. The landslide evolved into debris flows with runout distances of up to 200 m and variable thicknesses. Based on these findings, mitigation measures including reinforced earth walls (e.g., Terramesh systems), slope regrading with berms, and deep anchoring elements were proposed, resulting in a significant increase in slope stability under both static and pseudo-static conditions. The proposed methodology provides a practical and transferable framework for rapid landslide assessment and mitigation in volcanic terrains, particularly in mountainous urban areas of the Andes and other regions with similar geological and climatic conditions. © 2026 Banegas et al.
Some of the metrics are blocked by your
consent settings
Decision-Making and Operational Research Methods: A Theoretical-Cognitive Approach Personal Experience
(Springer Nature Switzerland, 2026)
Álvarez Sánchez, Ana
;
Suárez del Villar, Alexis
;
Guerrero-Aldana, Andy Nicolás
This article examines the relationship between decision-making and operations research methods, focusing on their evolution and application in complex environments. The main objective is to analyze how tools such as linear programming, simulation, and queue theory optimize resources and improve efficiency through the incorporation of advanced technologies like artificial intelligence and predictive analytics. These methods have been essential in solving problems across various sectors such as manufacturing, transportation, and services. Interviews with 50 participants, including academics and students, were used to assess the effectiveness of various operational methods in decision-making. The primary criterion was efficiency and improvement in the results obtained, while secondary results included the perception of flexibility and practical applicability of the methods. Simulation emerged as the most efficient approach, with a 22% improvement over other methods. Simulation methods proved to be the most effective, improving results by 22% compared to other approaches like integer and nonlinear programming. Participants highly valued practical and flexible methods, such as simulation, due to their ability to adapt to different contexts and situations. Additionally, the ease of implementation and time savings in decision-making were key factors in their preference. The study confirms that simulation is a key tool in decision-making in complex operational environments, providing superior results in efficiency. This suggests that, for future research, further exploration of the integration of practical and flexible methods like simulation, along with the exploration of their potential in combination with emerging technologies, is needed to optimize real-time decision-making processes. It is also recommended to evaluate their implementation in other sectors beyond those analyzed in this study, such as healthcare and public management. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
Some of the metrics are blocked by your
consent settings
Improving Electrical Efficiency at La Roca S.A. Construction Company
(Springer Nature Switzerland, 2026)
Arellano Vargas, Patricio Rodrigo
;
Sisalema-Cisneros, Allanis Angelina
;
Segura, Juan
The present research conducted at Constructora La Roca S.A. focuses on improving electrical energy efficiency due to the lack of adequate history in energy management within the organization. The methodology includes a diagnosis of the current situation, identifying opportunities for energy savings in electrical equipment, and implementing three energy efficiency indicators. A load survey was carried out for the two transformer services, revealing a 32.16% overload in service one and the lack of a transformer bank for 380 V equipment. Additionally, the lighting network did not meet UNE and NEC standards, leading to the proposal of a new 400 kVA transformer and a 45 kVA dry transformer, as well as changing fluorescent lamps to LEDs in the production area, reducing installed power from 12 kW to 3.2 kW and achieving an energy efficiency of 87.51%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
Some of the metrics are blocked by your
consent settings
User Experience in Virtual Reality (VR) Applications for Elderly People with Cognitive Impairment and Dementia: A Scoping Review
(2024)
Buele, Jorge
;
Avilés-Castillo, Fátima
;
Guillermo Palacios-Navarro
Background: In recent years, Virtual Reality (VR) has emerged as a promising tool to improve the well-being and functional capabilities of older adults. Although VR applications have shown positive results, their impact on user experience and therapeutic outcomes still needs to be evaluated. Objective: This scoping review aims to analyze existing studies on VR use in older adults with neurodegenerative disorders, focusing on the factors that influence usability, satisfaction, and immersion, as well as the effects on emotional and cognitive well-being. Materials and Methods: Empirical studies in English were included on VR applications applied to older adults with cognitive impairment without study design restrictions. The search was conducted in IEEE Xplore, PubMed, Scopus, and Web of Science, identifying a total of 650 initial results. After screening, 14 studies met the inclusion criteria. Results: Immersive VR tends to generate a greater sense of presence, which contributes to improving emotional well-being and reducing neuropsychiatric symptoms, such as apathy and depression. However, its impact on cognitive functions, including memory and executive skills, varied depending on the level of immersion and participant characteristics. Despite these positive findings, significant heterogeneity was evident in study designs, measurement instruments, and user experience indicators. Conclusion: Virtual environments have great potential as a therapeutic tool for older adults, but their success depends on the personalization of applications and the adaptation of technology to the specific needs of this population. Future research should focus on developing standardized protocols, incorporating adaptive technologies such as artificial intelligence, and evaluating the long-term effects of VR to maximize its benefits and minimize its risks. This review was registered in Open Science Framework (OSF). Registration Number: 10.17605/OSF.IO/PNU36
35
Some of the metrics are blocked by your
consent settings
Academic Performance and Inequality: Can Generative AI Widen the Digital Divide in Higher Education?
(2026)
Castro Chuquiana , Ricardo David
Higher educationHigher education has undergone a rapid transformation driven by digitalization and the rise of generative artificial intelligenceGenerative artificial intelligence tools, such as Chat Generative Pre-trained Transformer and Copilot. While these technologies offer significant opportunities to support learning processes, they also risk deepening existing inequalities if not implemented under equitable conditions. Many students, particularly those in rural areas or with limited resources, continue to face barriers related to device availability, Internet connectivity, and digital training, which restricts the effective use of generative AIArtificial intelligence and negatively affects academic performance. To analyze this gap and identify possible solutions, a critical narrative review of eighteen academic and technical sources published between 2022 and 2024 was conducted. The review focused on five key areas: access, digital literacy, academic impact, structural inequality, and inclusive strategies. The findings reveal sharp disparities: only 27% of rural students have access to devices compatible with generative AI, compared to 70% in urban settings, and students with strong digital competencies obtain up to 60% greater academic benefit from these tools. These results underscore the urgent need for targeted interventions to avoid exacerbating the digital divide. In response, the study proposes five strategies: ensuring equitable institutional access, strengthening critical digital literacyCritical digital literacy, adopting hybrid pedagogical models, designing inclusive curricula, and promoting dedicated research lines on public policy. The conclusion is that although generative artificial intelligenceGenerative artificial intelligence holds considerable educational potential, its benefits will only be realized if embedded in inclusive ecosystems that guarantee equal conditions, teacher support, and the ethical development of learning. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
8
Some of the metrics are blocked by your
consent settings
Enhancing Simulation Accuracy in Radioactive Decay Models: Comparative Analysis of Euler and RK2 Methods for Interactive Systems
(2026)
Yánez Arcos, Dayanara Lissette
The modeling of radioactive decay processes has long been essential in fields such as nuclear physics, embedded systems, and educational simulations. Traditionally, the Euler method has been used to numerically solve the differential equations governing these phenomena. However, Euler’s method exhibits significant limitations in terms of accuracyAccuracy and stability, particularly in coupled systems or stiff mathematical configurations. To address this issue, this study presents a detailed comparison between the Euler method and the second-order Runge-Kutta method (RK2), aiming to evaluate their performance in terms of error accumulation, temporal fidelity, and the ability to preserve system dynamics. The goal is to determine which method is more suitable for simulations that demand high precision and computational efficiency. Numerical simulations were conducted for dual decay, cyclic decay, and thermistor cooling models using normalized time steps (Δt = 0.01 and 0.05). The results were compared against analytical solutions and analyzed through logarithmic error plots. RK2 consistently outperformed the Euler method, reducing absolute error by up to 80%. For instance, in the dual decay model, Euler’s error reached 3.41 units, while RK2 kept it below 0.62. Moreover, RK2 preserved the oscillatory dynamics in cyclic models and accurately predicted thermal thresholds in thermistor simulations. RK2 proves to be significantly more suitable for dynamic simulations where numerical precision and stability are critical. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
15

Facultad de Ingenierías

Filters

Settings

Sort By

Results per page