Abu Bakar Nabilah

To address the limitations of traditional models in capturing complex features for concrete strength prediction, this study proposes a hybrid deep learning approach that integrates multiple attention mechanisms with gated recurrent units (GRU). The methodology employs a multi-scale validation framework, conducting three-dimensional validation across three datasets: the Kaggle standard dataset, the lightweight foam concrete dataset, and the self-compacting concrete dataset. Six attention mechanisms (SE attention, dot-product attention, self-attention, etc.) are comprehensively compared to optimise the GRU network structure. A Newton–Raphson-based optimiser (NRBO) enables hyperparameter adaptive tuning. Experimental results show significant improvements over the baseline GRU model: mean R² increased by 6.99%, while RMSE and MAE decreased by 38.5% and 37.5%, respectively. SHAP interpretability analysis confirms that attention mechanisms effectively capture key parameters like SP and VMA in the self-compacting concrete dataset. Based on the findings, this study recommends using self-attention for datasets smaller than 200 samples and selecting the higher-accuracy model between self-attention and stacked attention mechanisms for larger datasets.

In reference to the alumino-silicious binder materials, it is observed that almost all studies composed of binary and ternary geopolymer systems have focused on fly ash (FA) and ground granulated blast-furnace slag (GGBS) as primary source materials. Despite their technical benefits, this scenario is attributable to the high availability of the binder globally and its low cost. Various research had been done on the elimination of heat curing on the application of FA-based geopolymer composites. However, most studies have put a focus on Class-C FA, which has a high calcium content. As such, this research is exploring the enhancement of Class-F FA (low calcium content) and the potential of palm oil fuel ash (POFA) as the source of binder in FA-based geopolymer systems. POFA has similar characteristics to FA but POFA possesses slightly higher calcium content compared to Class-F FA. A systematic evaluation was carried out on an FA-based geopolymer mixture with the incorporation of GGBS. POFA was included as a secondary compound and for the tertiary compound at a range of 10%–30%. Meanwhile, 10% metakaolin (MK) was used as a tertiary compound in the FA/POFA geopolymer system. Alkaline activators of combination between sodium silicate and sodium hydroxide with a ratio of 2.5, 12 M sodium hydroxide and a liquid-to-binder ratio of 0.43 were used for the study. The geopolymerisation reactivity, setting time, flowability, and strength were the properties evaluated. Additionally, statistical analysis and sustainable assessment were done to highlight the environmental advantages. This approach offers a pathway to reduce reliance on Portland cement, contributing to environmentally friendly construction practices. Overall, the findings revealed that high FA content results in high early strength with the incorporation of GGBS. POFA demonstrates its viability for use in both FA/GGBS and FA/POFA geopolymer systems. Nonetheless, the usage of POFA should not exceed 20% when the FA content is high. FA-based geopolymer reduced carbon emissions around 68% compared to conventional cement. Ultimately, the strength achieved by the FA-based geopolymer system shows its potential as an alternative construction material for industry.

Net-zero energy building (NZEB), an initiative to address energy conservation and emission reduction, has received widespread attention worldwide. This study aims to systematically explore recent challenges in NZEB retrofit research through a mixed-method approach and provide recommendations and future directions. A review of 106 documents (2020–2024) retrieved from the Web of Science and Scopus databases found that the globalization of NZEB retrofit research is unstoppable. Assessment methods are diverse, ranging from modeling energy efficiency (using different software such as DesignBuilder 7.0, PVsyst 7.4, EnergyPlus 24.1.0, etc.) to multi-attribute decision-making methods (e.g., DEMATEL-AHP/ANP-VIKOR) and comparative analysis. Current assessment metrics are dominated by economic benefits (e.g., net present value, dynamic payback period, and total operating cost) and energy consumption (e.g., electricity consumption and generation), with less consideration of environmental impacts (e.g., carbon reduction), as well as comfort (e.g., thermal comfort and indoor comfort). The study found that current challenges mainly include “Low economic feasibility of retrofitting”, “Building retrofit energy code irrationality”, and “Insufficient understanding, communication, and trust between stakeholders”. To overcome these challenges, the study also proposes a framework of strategies to address them, including (1) maximizing natural space, (2) introducing a tenant equity system, (3) upgrading waste management, (4) strengthening energy monitoring, (5) establishing complete life cycle mechanisms, (6) providing systemic solutions; (7) promoting the use of low-carbon building materials, and (8) increasing policy support.

The utilization of blended concrete in reinforced concrete (RC) design could significantly reduce the CO2 emission in construction. However, its usage imposes higher material costs which hampers its utilization in the design. This research develops a multi-objective optimization (MOO) algorithm that minimizes the cost and CO2 emission of RC beam design. Apart from the usual design parameters, this algorithm considers the strength and mix design of blended concrete containing fly ash and GGBS. The Pareto solutions were analysed and the optimal design was obtained using the TOPSIS method. It was found that the MOO algorithm could optimize the design of the RC beam by favouring the 70% GGBS concrete having lower strength between 20 to 32 MPa. The optimal solution was highly dependent on the weightage used between cost and CO2 emission. The MOO is very effective and should be used in the design to produce sustainable concrete at an optimal cost.