Jose Gornall
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jose Gornall has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- José García
Escuela de Ingeniería de Construcción y Transporte, Pontifícia Universidad Católica de Valparaíso, Valparaíso 2362804, Chile
6 shared publications - Hernan Pinto
Escuela de Ingeniería de Construcción y Transporte, Pontifícia Universidad Católica de Valparaíso, Valparaíso 2362804, Chile
3 shared publications - Jorge Rojas Vivanco
Escuela de Ingeniería de Construcción y Transporte, Pontificia Universidad Católica de Valparaíso, Valparaíso, Chile
3 shared publications - Alvaro Peña
Escuela de Ingeniería de Construcción y Transporte, Pontificia Universidad Católica de Valparaíso, Avenida Brasil 2147, Valparaíso 2362804, Chile
2 shared publications - Paola Moraga
Escuela de Ingeniería de Construcción y Transporte, Pontifícia Universidad Católica de Valparaíso, Valparaíso 2362804, Chile
2 shared publications - Vinicius Minatogawa
Pontificia Universidad Católica de Valparaíso
2 shared publications
Latest Publications
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (19) , 28215-28239
Physics-Guided Machine Learning for Path Loss Prediction: A Review
- 1 October 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (19) , 28215-28239
Physics-Guided Machine Learning for Path Loss Prediction: A Review
- 8 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
An adaptive fuzzy-penalty swarm metaheuristic for the multi-demand multidimensional Knapsack problem
- 8 July 2026
- Published by Elsevier in Applied Soft Computing
- Vol. 202
An adaptive fuzzy-penalty swarm metaheuristic for the multi-demand multidimensional Knapsack problem
- Open Access
- 20 June 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (12) , 2217
Multi-Criteria Financial Screening Under Data Uncertainty: An LLM-Extraction and Min–Max TOPSIS Approach for SMEs
Small and medium enterprises routinely face a paradox in financial monitoring: their accounting documents exist, but the cost of converting heterogeneous PDFs into timely financial signals is prohibitive without dedicated analytical staff or specialized software. This paper presents a two-layer artifact, designed under Design Science Research, that bridges this gap using only public-web large language models (LLMs) and a parsimonious multi-criteria decision routine. Layer 1 implements a structured LLM-driven workflow that extracts account–value pairs from annual tax balance sheets without code, APIs, or fine-tuning. Layer 2 reconstructs auditable accounting aggregates and ranks yearly financial condition through TOPSIS with min–max normalization—a deliberate replacement for classical vector normalization, which fails when profitability indicators are negative, as routinely occurs in distress years. To avoid size effects and algebraic redundancy, the decision matrix uses only three criteria spanning liquidity, profitability, and solvency. The artifact is demonstrated in a four-year case study of an anonymized construction SME (2021–2024), with accountant-verified document-level match rates of 0.810, 0.998, 0.950, and 0.909. Equal weighting is the only weighting configuration used; a supplementary entropy-based dispersion diagnostic yields the same ordinal ranking—2024 > 2023 > 2021 > 2022—and 10,000 Monte Carlo replications, with uncertainty injected at the reconstructed-aggregate level, confirm that the extreme ranks are invariant across all runs. The contribution is methodological and practical: a transparent, low-infrastructure pipeline that brings first-pass financial screening within reach of SMEs operating under severe data and budget constraints.
- 20 June 2026
- Published by MDPI AG in Mathematics
- Vol. 14 (12) , 2217
Open AccessMulti-Criteria Financial Screening Under Data Uncertainty: An LLM-Extraction and Min–Max TOPSIS Approach for SMEs
Small and medium enterprises routinely face a paradox in financial monitoring: their accounting documents exist, but the cost of converting heterogeneous PDFs into timely financial signals is prohibitive without dedicated analytical staff or specialized software. This paper presents a two-layer artifact, designed under Design Science Research, that bridges this gap using only public-web large language models (LLMs) and a parsimonious multi-criteria decision routine. Layer 1 implements a structured LLM-driven workflow that extracts account–value pairs from annual tax balance sheets without code, APIs, or fine-tuning. Layer 2 reconstructs auditable accounting aggregates and ranks yearly financial condition through TOPSIS with min–max normalization—a deliberate replacement for classical vector normalization, which fails when profitability indicators are negative, as routinely occurs in distress years. To avoid size effects and algebraic redundancy, the decision matrix uses only three criteria spanning liquidity, profitability, and solvency. The artifact is demonstrated in a four-year case study of an anonymized construction SME (2021–2024), with accountant-verified document-level match rates of 0.810, 0.998, 0.950, and 0.909. Equal weighting is the only weighting configuration used; a supplementary entropy-based dispersion diagnostic yields the same ordinal ranking—2024 > 2023 > 2021 > 2022—and 10,000 Monte Carlo replications, with uncertainty injected at the reconstructed-aggregate level, confirm that the extreme ranks are invariant across all runs. The contribution is methodological and practical: a transparent, low-infrastructure pipeline that brings first-pass financial screening within reach of SMEs operating under severe data and budget constraints.
- Open Access
- 19 December 2025
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 9
Extended Realityin Construction 4.0: A Systematic Review of Applications, Implementation Barriers, and Research Trends
Extended reality (XR) is increasingly used to address productivity, communication, and safety challenges in the construction industry, but large-scale adoption within Construction 4.0 remains limited. The existing reviews rarely provide an integrated perspective that jointly examines XR applications, underlying technology stacks, and the barriers that constrain implementation. This study fills that gap by combining a PRISMA-compliant systematic review with a bibliometric analysis of 76 journal articles published between 2019 and 2024. The review maps XR usage in construction, which XR modes, devices, and graphics engines are most prevalent, and which barriers hinder deployment in real projects. Design visualization and coordination, immersive training, and remote assistance or inspection emerge as the dominant application areas. Augmented reality (AR) and virtual reality (VR) lead the technology landscape, with Microsoft HoloLens and Meta Quest as the most frequently reported head-mounted displays and Unity as the main graphics engine. Implementation barriers are categorized into five groups—technological, organizational, economic, infrastructural, and methodological—with interoperability issues, hardware performance limitations, and the lack of standardized BIM-to-XR workflows being particularly recurrent. The review contributes to the Construction 4.0 agenda by providing a consolidated map of XR applications, technologies, and barriers, and by highlighting enablers such as open data schemas and competency-based training programs. Future research should validate AI-assisted, bidirectional BIM–XR workflows in real projects, report cost–benefit metrics, and advance interoperability standards that integrate XR into broader Construction 4.0 strategies.
- 19 December 2025
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 9
Open AccessExtended Realityin Construction 4.0: A Systematic Review of Applications, Implementation Barriers, and Research Trends
Extended reality (XR) is increasingly used to address productivity, communication, and safety challenges in the construction industry, but large-scale adoption within Construction 4.0 remains limited. The existing reviews rarely provide an integrated perspective that jointly examines XR applications, underlying technology stacks, and the barriers that constrain implementation. This study fills that gap by combining a PRISMA-compliant systematic review with a bibliometric analysis of 76 journal articles published between 2019 and 2024. The review maps XR usage in construction, which XR modes, devices, and graphics engines are most prevalent, and which barriers hinder deployment in real projects. Design visualization and coordination, immersive training, and remote assistance or inspection emerge as the dominant application areas. Augmented reality (AR) and virtual reality (VR) lead the technology landscape, with Microsoft HoloLens and Meta Quest as the most frequently reported head-mounted displays and Unity as the main graphics engine. Implementation barriers are categorized into five groups—technological, organizational, economic, infrastructural, and methodological—with interoperability issues, hardware performance limitations, and the lack of standardized BIM-to-XR workflows being particularly recurrent. The review contributes to the Construction 4.0 agenda by providing a consolidated map of XR applications, technologies, and barriers, and by highlighting enablers such as open data schemas and competency-based training programs. Future research should validate AI-assisted, bidirectional BIM–XR workflows in real projects, report cost–benefit metrics, and advance interoperability standards that integrate XR into broader Construction 4.0 strategies.
- Open Access
- 22 October 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (21) , 3359
Artificial Intelligence Applied to Soil Compaction Control for the Light Dynamic Penetrometer Method
Compaction quality control in earthworks and pavements still relies mainly on density-based acceptance referenced to laboratory Proctor tests, which are costly, time-consuming, and spatially sparse. Lightweight dynamic cone penetrometer (LDCP) provides rapid indices, such as and , yet acceptance thresholds commonly depend on ad hoc, site-specific calibrations. This study develops and validates a supervised machine learning framework that estimates , , and directly from readily available soil descriptors (gradation, plasticity/activity, moisture/state variables, and GTR class) using a multi-campaign dataset of observations. While the framework does not remove the need for the standard soil characterization performed during design (e.g., W, , and ), it reduces reliance on additional LDCP calibration campaigns to obtain device-specific reference curves. Models compared under a unified pipeline include regularized linear baselines, support vector regression, Random Forest, XGBoost, and a compact multilayer perceptron (MLP). The evaluation used a fixed 80/20 train–test split with 5-fold cross-validation on the training set and multiple error metrics (, RMSE, MAE, and MAPE). Interpretability combined SHAP with permutation importance, 1D partial dependence (PDP), and accumulated local effects (ALE); calibration diagnostics and split-conformal prediction intervals connected the predictions to QA/QC decisions. A naïve GTR-average baseline was added for reference. Computation was lightweight. On the test set, the MLP attained the best accuracy for (, RMSE ), with XGBoost close behind (, RMSE ). Paired bootstrap contrasts with Holm correction indicated that the MLP–XGBoost difference was not statistically significant. Explanations consistently highlighted density- and moisture-related variables (, , and W) as dominant, with gradation/plasticity contributing second-order adjustments; these attributions are model-based and associational rather than causal. The results support interpretable, computationally efficient surrogates of LDCP indices that can complement density-based acceptance and enable risk-aware QA/QC via conformal prediction intervals.- 22 October 2025
- Published by MDPI AG in Mathematics
- Vol. 13 (21) , 3359
Open AccessArtificial Intelligence Applied to Soil Compaction Control for the Light Dynamic Penetrometer Method
Compaction quality control in earthworks and pavements still relies mainly on density-based acceptance referenced to laboratory Proctor tests, which are costly, time-consuming, and spatially sparse. Lightweight dynamic cone penetrometer (LDCP) provides rapid indices, such as and , yet acceptance thresholds commonly depend on ad hoc, site-specific calibrations. This study develops and validates a supervised machine learning framework that estimates , , and directly from readily available soil descriptors (gradation, plasticity/activity, moisture/state variables, and GTR class) using a multi-campaign dataset of observations. While the framework does not remove the need for the standard soil characterization performed during design (e.g., W, , and ), it reduces reliance on additional LDCP calibration campaigns to obtain device-specific reference curves. Models compared under a unified pipeline include regularized linear baselines, support vector regression, Random Forest, XGBoost, and a compact multilayer perceptron (MLP). The evaluation used a fixed 80/20 train–test split with 5-fold cross-validation on the training set and multiple error metrics (, RMSE, MAE, and MAPE). Interpretability combined SHAP with permutation importance, 1D partial dependence (PDP), and accumulated local effects (ALE); calibration diagnostics and split-conformal prediction intervals connected the predictions to QA/QC decisions. A naïve GTR-average baseline was added for reference. Computation was lightweight. On the test set, the MLP attained the best accuracy for (, RMSE ), with XGBoost close behind (, RMSE ). Paired bootstrap contrasts with Holm correction indicated that the MLP–XGBoost difference was not statistically significant. Explanations consistently highlighted density- and moisture-related variables (, , and W) as dominant, with gradation/plasticity contributing second-order adjustments; these attributions are model-based and associational rather than causal. The results support interpretable, computationally efficient surrogates of LDCP indices that can complement density-based acceptance and enable risk-aware QA/QC via conformal prediction intervals. - Open Access
- 22 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8527
Mesostructural Model for the Fatigue Analysis of Open-Cell Metal Foams
Metallic foams exhibit unique properties that make them suitable for diverse engineering applications. Accurate mechanical characterization is essential for assessing their performance under both monotonic and cyclic loading conditions. However, despite the advancements, the understanding of cyclic load responses in metallic foams has been limited. This study aims to propose a mesostructural model to assess the fatigue behavior of open-cell metal foams subjected to cyclic loading conditions. The proposed model considers the previous load history and is based on the analogy of progressive collapse, integrating a finite element model, a fatigue analysis model, an equivalent number of cycles model, and a failure criterion model. Validation against experimental data shows that the proposed model can reliably predict the fatigue life of the metallic foams for specific strain amplitudes.
- 22 September 2024
- Published by MDPI AG in Applied Sciences
- Vol. 14 (18) , 8527
Open AccessMesostructural Model for the Fatigue Analysis of Open-Cell Metal Foams
Metallic foams exhibit unique properties that make them suitable for diverse engineering applications. Accurate mechanical characterization is essential for assessing their performance under both monotonic and cyclic loading conditions. However, despite the advancements, the understanding of cyclic load responses in metallic foams has been limited. This study aims to propose a mesostructural model to assess the fatigue behavior of open-cell metal foams subjected to cyclic loading conditions. The proposed model considers the previous load history and is based on the analogy of progressive collapse, integrating a finite element model, a fatigue analysis model, an equivalent number of cycles model, and a failure criterion model. Validation against experimental data shows that the proposed model can reliably predict the fatigue life of the metallic foams for specific strain amplitudes.