Johnny Kwok Wai Wong

Few early-stage building studies combine systematic design-space exploration with concurrent assessment of embodied carbon intensity (ECI) and installed material cost intensity (MCI). Evidence therefore remains limited on how design choices jointly affect these indicators and when carbon and cost priorities converge or conflict. This study addresses this gap across an Australian commercial-office design space comprising 892 quality-screened Carbon Designer 3D scenarios. The scenarios were restricted to rectangular plans and six predominantly concrete-based structural systems, with variations in recorded gross floor area (GFA), storey count and three aspect ratios. Matched comparisons examined the effects of vertical development, plan proportion and structural system on A1–A3 product-stage ECI and MCI. Both indicators increased with storey count, although proportional increases declined with increasing recorded GFA; the size of the ECI increases may partly reflect the platform’s area-normalisation convention. Aspect-ratio effects depended on structural system. The same structural system minimised ECI and MCI in 89 of 108 matched configurations (82.4%), whereas 19 exhibited cost–carbon trade-offs. Six regression algorithms were evaluated as design-space-specific surrogates using 713 training scenarios and 179 held-out scenarios. Support vector regression produced the lowest five-fold cross-validated mean absolute error and was retained as the in-domain surrogate for both targets. The principal contribution is the joint analysis of ECI and MCI across a controlled commercial-office design space; the surrogate models provide a computational basis for rapid screening and subsequent multi-objective optimisation within that same design space.

Building cracks are among the critical building defects, as they can compromise structural integrity, occupant safety and building sustainability. Traditional laborious building inspection methods are cumbersome and erroneous. Computer vision-based crack detection relies on image recognition and does not analyse the underlying causes or suggest rectification strategies. This study explores the potential and limitations of multimodal AI models, that integrate image and text modalities for building crack analysis. As a proof-of-concept, the vision–language model, CracksGPT was built upon a fine-tuned MiniGPT-v2. It was trained on custom crack images with text descriptions detailing visual features, possible causes, and rectification options. It was tested on crack images from a building site in Sydney. When provided with an image of a wall crack, CracksGPT can classify crack patterns of vertical, horizontal, diagonal, and stair-step and interpret possible underlying causes with potential rectification strategies. The ROUGE metric was used for language generation quality evaluation followed by a performance evaluation by building inspection experts. The model’s performance is sensitive to input image quality and training data limitations, specifically in complex scenarios, reaffirming the value of expert overseeing. The findings highlight the potential and limitations of multimodal AI for integrating vision–language reasoning into building inspections.

Purpose: Early-stage building design optimisation research often addresses environmental impact and cost separately, despite their interdependence. Many studies apply optimisation algorithms or machine learning models to minimise either carbon emissions or material cost – but rarely both within a unified framework. This fragmented approach risks suboptimal trade-offs, where cost-efficient designs may overlook carbon impacts and vice versa. To address this gap, this study conducts a systematic literature review to examine patterns, differences and shared practices in current research. It then proposes an integrative framework for building performance optimisation that accommodates diverse cost and environmental objectives, offering clear guidance for future studies. Design/methodology/approach: About 18 peer-reviewed articles (2013–2023) were identified through Scopus and Web of Science and screened using PRISMA. A dialectical systems thinking lens guided analysis across concept, methodology and value dimensions. Nine key variables were extracted in content analysis, informing the development of a step-by-step integrative framework for life cycle performance optimisation that aligns design choices with cost and environmental objectives. Findings: Most studies rely on NSGA-II, MOPSO and occasionally ANN, GPR and ELM to co-optimise life-cycle cost and carbon, often excluding other performance metrics. Tools like jEPlus + EA and MOBO lack BIM integration. This study introduces a nine-step framework linking methods, standards and tools to guide future optimisation research and practice. Originality/value: This study offers a novel nine-step framework that synthesises fragmented optimisation practices in early-stage building design, linking concepts, methods and values. It provides a reproducible roadmap for balancing cost and carbon, guiding future research and supporting informed design decisions.

Transformer-based models have accelerated EEG motor imagery (MI) decoding by using self-attention to capture long-range temporal structures while complementing spatial inductive biases. This systematic survey of Scopus-indexed works from 2020 to 2025 indicates that reported advances are concentrated in offline, protocol-heterogeneous settings; inconsistent preprocessing, non-standard data splits, and sparse efficiency frequently reporting cloud claims of generalization and real-time suitability. Under session- and subject-aware evaluation on the BCIC IV 2a/2b dataset, typical performance clusters are in the high-80% range for binary MI and the mid-70% range for multi-class tasks with gains of roughly 5–10 percentage points achieved by strong hybrids (CNN/TCN–Transformer; hierarchical attention) rather than by extreme figures often driven by leakage-prone protocols. In parallel, transformer-driven denoising—particularly diffusion–transformer hybrids—yields strong signal-level metrics but remains weakly linked to task benefit; denoise → decode validation is rarely standardized despite being the most relevant proxy when artifact-free ground truth is unavailable. Three priorities emerge for translation: protocol discipline (fixed train/test partitions, transparent preprocessing, mandatory reporting of parameters, FLOPs, per-trial latency, and acquisition-to-feedback delay); task relevance (shared denoise → decode benchmarks for MI and related paradigms); and adaptivity at scale (self-supervised pretraining on heterogeneous EEG corpora and resource-aware co-optimization of preprocessing and hybrid transformer topologies). Evidence from subject-adjusting evolutionary pipelines that jointly tune preprocessing, attention depth, and CNN–Transformer fusion demonstrates reproducible inter-subject gains over established baselines under controlled protocols. Implementing these practices positions transformer-driven BCIs to move beyond inflated offline estimates toward reliable, real-time neurointerfaces with concrete clinical and assistive relevance.

Efficiency and comfort in buildings rely on on well-functioning HVAC systems. However, system faults can compromise performance. Modern data-driven fault detection methods, considering diverse techniques, encounter challenges in understanding intricate interactions and adapting to dynamic conditions present in HVAC systems during occupancy periods. Implementing fault detection during active operation, which aligns with real-world scenarios and captures dynamic interactions and environmental changes, is considered highly valuable. To address this, utilizing the dynamic simulation system HVAC SIMulation PLUS (HVACSIM+), an HVAC fault model was developed using 194 sensor signals from each HVAC component within a single-story, four-room building. The advanced HVAC fault detection framework, leveraging simulated HVAC operational scenarios with the Gramian angular field (GAF) and two-dimensional convolutional neural networks (GAF-2DCNNs), offers a robust and proactive solution. By utilizing the GAF capacity to convert time-series sensor data into informative 2D images, integrated with 2DCNN for automated feature extraction, hidden temporal relationships within 1D signals are captured. After training on nine significant HVAC faults and normal conditions during occupancy, the effectiveness of the proposed GAF-2DCNN is evaluated through comparisons with support vector machine (SVM), random forest (RF), and hybrid RF-SVM, one-dimensional convolutional neural networks (1D-CNNs). The results demonstrates an impressive overall accuracy of 97%, accompanied by precision, recall, and F1 scores that surpass 90% for individual HVAC faults. Through the introduction of the unified approach that integrates HVACSIM+ simulated data and GAF-2DCNN, a notable enhancement in robustness and reliability for handling substantial HVAC faults is achieved.

The malfunctioning of the heating, ventilating, and air conditioning (HVAC) system is considered to be one of the main challenges in modern buildings. Due to the complexity of the building management system (BMS) with operational data input from a large number of sensors used in HVAC system, the faults can be very difficult to detect in the early stage. While numerous fault detection and diagnosis (FDD) methods with the use of statistical modeling and machine learning have revealed prominent results in recent years, early detection remains a challenging task since many current approaches are unfeasible for diagnosing some HVAC faults and have accuracy performance issues. In view of this, this study presents a novel hybrid FDD approach by combining random forest (RF) and support vector machine (SVM) classifiers for the application of FDD for the HVAC system. Experimental results demonstrate that our proposed hybrid random forest–support vector machine (HRF–SVM) outperforms other methods with higher prediction accuracy (98%), despite that the fault symptoms were insignificant. Furthermore, the proposed framework can reduce the significant number of sensors required and work well with the small number of faulty training data samples available in real-world applications.

Purpose: Sensing- and warning-based technologies are widely used in the construction industry for occupational health and safety (OHS) monitoring and management. A comprehensive understanding of the different types and specific research topics related to the application of sensing- and warning-based technologies is essential to improve OHS in the construction industry. The purpose of this paper is to examine the current trends, different types and research topics related to the applications of sensing- and warning-based technology for improving OHS through the analysis of articles published between 1996 and 2017 (years inclusive). Design/methodology/approach: A standardized three-step screening and data extraction method was used. A total of 87 articles met the inclusion criteria. Findings: The annual publication trends and relative contributions of individual journals were discussed. Additionally, this review discusses the current trends of different types of sensing- and warning-based technology applications for improving OHS in the industry, six relevant research topics, four major research gaps and future research directions. Originality/value: Overall, this review may serve as a spur for researchers and practitioners to extend sensing- and warning-based technology applications to improve OHS in the construction industry.