http://hdl.handle.net/10453/35217 2026-06-10T15:12:08Z http://hdl.handle.net/10453/195278 Title: Advancing 3D-printed fiber-reinforced concrete for sustainable construction: A comparative optimization based study of hybrid machine intelligence models for predicting mechanical strength and CO₂ emissions Authors: Liu, S; Liu, T; Alqurashi, M; Abdou Elabbasy, AA; Alanazi, N; Shakor, P Abstract: With the increasing demand for sustainable and resilient marine infrastructure in marine environments, 3D printing technologies offer a promising solution for fabricating customized, durable components under challenging conditions. 3D-printed fiber-reinforced concrete (3DPFRC) presents significant potential for rapid, waste-reducing construction of complex geometries, making it suitable for marine structures such as sea walls, breakwaters, underwater pipelines, and floating platforms. However, optimizing 3DPFRC for mechanical performance and environmental sustainability remains a complex challenge. This study proposes advanced machine learning (ML) models to simultaneously predict compressive strength and CO₂ emissions of 3DPFRC, enabling both mechanical and environmental performance evaluation. A user-friendly graphical user interface (GUI) was also developed to facilitate practical deployment by engineers without programming expertise. Four hybrid ML models were evaluated: CNN-LSTM, RA-PSO, XGBoost-PSO, and SVM-PSO. RA-PSO outperformed others with an R² of 0.9819 (training) and 0.9674 (testing) for compressive strength and 0.97 (training) and 0.94 (testing) for CO₂ emissions, alongside the lowest MSE (48.24 MPa²) and highest F1-score (0.9519). This superior performance is primarily due to RA-PSO's adaptive parameter tuning and randomized search, which maintain population diversity and prevent premature convergence, enabling the model to capture complex nonlinear interactions in 3DPFRC mix parameters. Sensitivity analysis revealed that water content (34 %), silica fume (30 %), and the water-to-binder ratio (23 %) were the most influential parameters on compressive strength. These findings confirm RA-PSO as a highly reliable tool for optimizing 3DPFRC mix designs while minimizing environmental impact, particularly in Sustainable Marine and Civil Infrastructure Applications. 2025-12-01T00:00:00Z http://hdl.handle.net/10453/195277 Title: Advances in Enhancing Earthquake Resilience of Concrete Infrastructure: A State-of-the-Art Review Authors: Qader, DN; Khudhur, HM; Shakor, P; Jumaa, GB; Hasan, S; Chandra, SS Abstract: This study presents a comprehensive review of state-of-the-art seismic retrofitting techniques for reinforced concrete (RC) structures, focusing on structural resilience, economic feasibility, and sustainability. By systematically analyzing over 100 experimental, numerical, and case studies, this work benchmarks conventional methods—such as concrete and steel jacketing—against advanced solutions, including fiber-reinforced polymers (FRP), shape memory alloys (SMA), and base isolation systems. The findings indicate that FRP retrofitting increases lateral load capacity by up to 40%, shear strength by 30-80%, and ductility by 100-200%, while reducing overall structural weight by 50-75% compared to steel jacketing. SMA components exhibit up to 8% strain recovery, a 30-40% improvement in energy dissipation, and a 70% reduction in post-earthquake residual deformations, effectively enhancing self-centering capabilities. Base isolation systems reduce inter-story drift by 50-75%, floor accelerations by 65-85%, and overall structural damage by 40-60%, though their high initial cost (20-50% of total project costs) limits widespread adoption. Hybrid systems, such as SMA-FRP combinations, achieve 50-60% increased energy absorption and 90% recovery of deformation, further optimizing seismic resilience. Sustainability assessments show that FRP and SMA retrofitting reduce embodied carbon emissions by 20-40% and lifecycle maintenance costs by 30-50% compared to traditional methods. To address challenges such as cost, durability concerns, and standardization gaps, this review introduces a performance-based framework integrating lifecycle cost analysis, seismic risk assessment, and material efficiency to optimize retrofitting strategies for diverse structural applications, from heritage conservation to critical infrastructure. 2025-06-01T00:00:00Z http://hdl.handle.net/10453/195274 Title: A comprehensive literature review on risk identification and assessment in green building construction projects Authors: Yussif, AM; Taiwo, R; Shakor, P; Han, T; Mohandes, SR; Antwi-Afari, MF; Qazi, K; Singh, AK; Christo, MS; Shah, MA Abstract: Building green for sustainability cannot be over-emphasised, considering the current environmental crises. Green buildings minimise environmental degradation and reduce consumption of depletable resources while providing maximum occupancy satisfaction. Despite the numerous studies of risk assessment in Green Building Construction Projects (GBCPs), limited attention has been given to methodologies that enable risk evaluation from the projects' inception to the end of their service life. Secondly, the existing methods do not consider the accumulated knowledge and experience obtained from previous risk assessment models. Finally, existing studies fail to provide a detailed description of each risk, as they only list them, leading to ambiguity in the practical sense. A scientometric analysis was performed to reveal the current research trend of risk identification in GBCPs. This study systematically reviewed relevant literature from the last two decades until the end of 2024 to collate the most influential risks associated with GBCPs. From the systematic literature review, a total of forty-two (42) risks were identified and defined clearly before further grouping them into nine (9) mutually exclusive categories to ease targeted assessments. The knowledge-based approach was proposed for identifying and evaluating the risks due to its unique nature of enabling long-term analysis by tapping into the accumulated knowledge and experience from previous evaluation models. The knowledge-based approach emphasises establishing a strong foundation involving risk scope definition, identification, analysis, response planning, execution, and monitoring and control as a feedback system supporting risk evaluation throughout the service life of the project. After the analysis, it was found that the risk evaluation studies in GBCPs need to create assessment models that consider the post-construction variables and the accumulated knowledge of previous evaluations. Secondly, a clear description of each risk eases its categorisation for tailor-targeted assessment. The current limitations include limited collaboration between developing and developed countries and a scarcity of empirical research in developing nations. The study proposes future research opportunities in green building risk studies to promote research growth, highlights the need for holistic risk management frameworks, and fosters sustainable construction practices globally. 2025-12-01T00:00:00Z http://hdl.handle.net/10453/195269 Title: Artificial Intelligence-Powered prediction and optimization of compressive strength in lightweight hemp-based blocks for sustainable construction Authors: Tahera,; Babu, BJP; Chandra, SS; Patil, S; Doddamani, ND; Shakor, P Abstract: The study presents a machine learning-driven methodology for projecting the compressive strength of lightweight hemp-based blocks, framing as an ecologically sound replacement for standard construction resources. These blocks are formulated using hemp hurd, lime, cement, glass powder, and water. Five advanced models, Random Forest, Gradient Boosting, Extreme Gradient Boosting, Categorical Boosting (CatBoost), and Artificial Neural Networks (ANNs), were rigorously developed and evaluated, using a well-structured data set. Critical preprocessing protocols encompassed normalization, feature selection, and exploratory data analysis. The model performance was evaluated using the metrics R², RMSE, MAE, WMAPE, and Nash–Sutcliffe Efficiency. Visual tools such as regression plots, 3-dimensional surface plots, Taylor diagrams, and Regression Error Characteristic curves were also employed. The results indicated that CatBoost outperformed ANN and other combined methods in generating accurate predictions. The amount of cement and the curing time were more influential than the amounts of lime and glass powder in the mixes. The results revealed that ensemble machine learning models uncovered nonlinear relationships, facilitating the prediction of biocomposite material performance. The approach supports sustainable construction by offering mix designers a scalable, data-driven alternative to the trial-and-error method. This technology reduces testing costs and enhances the accuracy of mix design optimization, thereby accelerating the adoption of hemp-based blocks in green building projects. 2025-01-01T00:00:00Z