TTTeik Toe Teoh

Teik Toe Teoh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Teik Toe Teoh has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Decision-Level Uncertainty Calibration for Fire-Tenability Surrogates: Effects on ASET and Evacuation Failure Probability

    by Samson Tan, Teik Toe Teoh, Paul Joseph, Khalid Moinuddin

    Fire-tenability surrogate errors matter when they change an evacuation decision. This study links sampled available safe egress time (ASET), missed unsafe classifications and finite-horizon failure probability. It combines an 18-case Fire Dynamics Simulator (FDS) library, 5000 surrogate scenarios, matched statistical experiments and 48 additional fires evaluated with a frozen predictor. A common-horizon formulation keeps missed-failure loss observable despite censored ASET. In the retrospective calculation, shifting censored endpoints explained 6.24 of a 6.38-percentage-point increase in flags after a 20 s deduction. Visibility governed all 32 observed breaches in the additional-fire batch; 25 predictions were late, with mean absolute error 7.97 s across breached cases. A 20 s deduction removed 0.0057 percentage points of joint misses under full-descent timing and 0.2009 points under corridor-segment timing, while adding 6.1551 and 1.1948 points of false-unsafe classifications, respectively. Under equal door weights, the corridor changes became 0.3947 and 1.8542 points. These are classification changes, not reductions in physical fire risk. The contribution is an auditable assessment of censoring, scenario support and decision cost. Numerical findings remain conditional on one geometry, prescribed fires and assumed evacuation laws; no universal deduction is established.

  • Open Access

    Probabilistic Risk Assessment of Grid-Scale Lithium-Ion Battery Energy Storage System Fire Hazards: Hydrogen Fluoride (HF) Toxicity, Suppression Effectiveness, and Comparative Compartment Design Analysis

    by Samson Tan, Teik Toe Teoh, Paul Joseph, Khalid Moinuddin

    Battery Energy Storage Systems (BESS), utilising chemistries based on Nickel Manganese Cobalt (NMC) containing lithium-ion devices, often present fire safety hazards that existing qualitative risk frameworks, including NFPA 855’s 5 × 5 consequence-likelihood matrix, are insufficiently granular to quantify. This paper presents an original probabilistic risk assessment (PRA) of fire hazards associated with BESS for a 485.52 kWh NMC installation at the Equinix SG4-4A data centre in Singapore, using Monte Carlo simulation (N = 10,000 iterations) to characterise uncertainty in hydrogen fluoride (HF) gas dose, time to Immediately Dangerous to Life or Health (IDLH) concentration, cabinet-to-cabinet propagation probability, and suppression effectiveness. The HF yield is modelled as a triangular distribution (0.3–0.8 g/kWh, mode 0.5 g/kWh), ventilation activation delay as log-normal (median 90 s), and suppression effectiveness as a piecewise function of water application delay. The results demonstrated that HF dose exceeded the National Institute for Occupational Safety and Health (NIOSH) IDLH of 25 mg/m3 in 100% of simulated scenarios for both single- and two-compartment designs, thus confirming that threshold HF toxicity was essentially unavoidable for any occupant present during a full thermal runaway event, and that ventilation alone cannot achieve adequate risk reduction. The single-stage suppression effectiveness was found to be only 37.9% (mean), providing quantitative confirmation that two-stage (clean agent + water) suppression is warranted for NMC chemistry. The two-compartment design was found to reduce the peak HF dose by 50%, and also reduced the mean IDLH clearance time from 599 to 301 min, thus shifting residual risk from As Low As Reasonably Practicable (ALARP)-tolerable to broadly acceptable under UK Health and Safety Executive (HSE) criteria. The paper proposes a quantitative PRA framework as a complement to NFPA 855 Chapter 5’s qualitative Hazard Mitigation Analysis, enabling more informed engineering decisions for BESS fire safety. To the best of our knowledge, this is the first study to apply Monte Carlo simulation to HF dose modelling in a tropical data-centre BESS context and thereby address a documented gap in the literature.


  • Open Access

    Explainable Artificial Intelligence (XAI)-Enabled Probabilistic Fire Risk Prediction for High-Rise Residential Buildings: SHAP Attribution of Human and Organisational Risks

    by Samson Tan, Teoh Teik Toe, Paul Joseph, Khalid Moinuddin

    Fire safety in high-rise residential buildings depends on active fire protection systems subject to technical, human, and organisational risks. Prior probabilistic models incorporating human and organisational errors (HOEs) raise expected risk-to-life by 20 to 37%, yet remain inaccessible to the owners, managers, qualified persons, and regulators who must act on them. This paper applies SHAP (SHapley Additive exPlanations) to a reconstructed Bayesian network fire risk model with Markov Chain Monte Carlo uncertainty propagation, extending the T-H-O-Risk methodology across sixteen system configurations and seven buildings in five jurisdictions (Singapore, Australia, Hong Kong, New Zealand, the UK) plus a generic reference case. Global SHAP analysis attributes 89.8% of total HOE attribution to maintenance-related factors (H7, insufficient technical handover; H8, insufficient safety check; H9, inadequate periodic inspection), reframing the primary intervention from behavioural to structural. The reconstruction reproduces 112 published ERL values with a mean absolute percentage error of 1.8% on total ERL (13.7% on the HOE increment, the layer carrying the paper’s claims) and 96% interval coverage. Attribution outputs are translated into graded, risk-informed maintenance conditions for SCDF waiver assessment. To the authors’ knowledge, this is the first Shapley values attribution of HOE factors in a building system-level Bayesian network fire risk model.

  • Open Access

    Probabilistic Risk Assessment of Grid-Scale Lithium-Ion Battery Energy Storage System Fire Hazards: Hydrogen Fluoride (HF) Toxicity, Suppression Effectiveness, and Comparative Compartment Design Analysis

    by Samson Tan, Teoh Teik Toe, Paul Joseph, Khalid Moinuddin

    Battery Energy Storage Systems (BESS), utilizing chemistries based on Nickel Manganese Cobalt (NMC) containing lithium-ion devices, often present fire safety hazards that existing qualitative risk frameworks, including NFPA 855's 5×5 consequence-likelihood matrix, are insufficiently granular to quantify. This paper presents an original probabilistic risk assessment (PRA) of fire hazards associated with BESS for a 485.52 kWh NMC installation at the Equinix SG4-4A data centre in Singapore, using Monte Carlo simulation (N = 10,000 iterations) to characterise uncertainty in hydrogen fluoride (HF) gas dose, time to Immediately Dangerous to Life or Health (IDLH) concentration, cabinet-to-cabinet propagation probability, and suppression effectiveness. The HF yield is modelled as a triangular distribution (0.3–0.8 g/kWh, mode 0.5 g/kWh), ventilation activation delay as log-normal (median 90 s), and suppression effectiveness as a piecewise function of water application delay. HF dose exceeded the National Institute for Occupational Safety and Health (NIOSH) IDLH of 25 mg/m³ in 100% of simulated scenarios for both single- and two-compartment designs, confirming that HF toxicity is essentially present for any occupant during a full thermal runaway event and that ventilation alone cannot achieve adequate risk reduction. Single-stage suppression effectiveness was only 37.9% (mean), confirming that two-stage (clean agent + water) suppression is warranted for NMC chemistry. The two-compartment design reduced peak HF dose by 50% and reduced mean IDLH clearance time from 599 to 301 minutes, shifting residual risk from As Low As Reasonably Practicable (ALARP)-tolerable to broadly acceptable under UK Health and Safety Executive (HSE) criteria. The paper proposes a quantitative PRA framework as a complement to NFPA 855 Chapter 5's qualitative Hazard Mitigation Analysis. To the best of our knowledge, this is the first study to apply Monte Carlo simulation to HF dose modelling in a tropical data-centre BESS context, addressing a documented gap in the literature.

  • Open Access

    Explainable Artificial Intelligence (XAI)-Enabled Probabilistic Fire Risk Prediction for High-Rise Residential Buildings: SHAP Attribution of Human and Organizational Risks

    by Samson Tan, Teoh Teik Toe, Paul Joseph, Khalid Moinuddin

    Fire safety in high-rise residential buildings depends on the reliable performance of active fire protection systems subject to technical, human, and organizational risks. Probabilistic risk assessment frameworks incorporating human and organizational errors (HOEs) show that HOEs raise expected risk-to-life by 20 to 37%, yet such models remain inaccessible to the building owners, facility managers, qualified persons, and regulators who must act on their outputs. This paper applies Explainable Artificial Intelligence, specifically SHAP (SHapley Additive exPlanations), to a Bayesian network probabilistic fire risk model integrated with Markov Chain Monte Carlo posterior uncertainty quantification, extending the validated T-H-O-Risk methodology across sixteen active fire safety system configurations and seven case studies in Singapore, Australia, Hong Kong, New Zealand, and the United Kingdom. Global SHAP analysis shows that maintenance-related HOEs (H8, insufficient safety check; H9, inadequate periodic inspection) account for 83.1% of total HOE attribution, outranking compliance and training variables and reframing the primary intervention from behavioural to structural. Validation against published results yields Pearson r = 0.927 across 112 building-design combinations. This is the first application of SHAP attribution to a Bayesian network fire risk model, giving regulators and qualified persons a transparent, uncertainty-aware tool for inspection-regime calibration and ALARP demonstration.

  • Open Access

    Machine Learning for Building Code Waiver Assessment: A Predictive Analytics Framework from 197 Singapore BCA Cases (2021–2023)

    by Samson Tan, Teik Toe Teoh

    Building code waiver assessments in Singapore remain largely discretionary, relying on case officers’ subjective judgement with limited decision-support tooling. This study presents the first machine learning framework for predicting building code waiver outcomes, trained on 197 historically decided cases from the Building and Construction Authority (BCA) across five waiver categories: barrier-free accessibility (n = 45), ventilation (n = 61), staircase design (n = 37), safety provisions (n = 30), and structural modifications (n = 24), spanning 2021 to 2023. Fourteen engineered features, including documentation completeness, technical justification quality, and compliance history, were extracted through domain-expert annotation. Four models were evaluated: L2-regularised logistic regression, random forest, gradient boosting (XGBoost 2.0.1), and a weighted ensemble. The ensemble achieved the highest predictive accuracy of 83.7% (95% CI: 79.2–88.1%) with an area under the receiver operating characteristic curve (AUC) of 0.891 (95% CI: 0.854–0.928), significantly outperforming all individual models (McNemar’s test, p < 0.05). SHAP analysis revealed that documentation completeness and technical justification quality collectively account for 55% of prediction variance. A companion five-by-five risk assessment matrix, combining predicted rejection probability with consequence severity, stratified cases into actionable risk tiers correlating with observed approval rates ranging from 90.3% (very low risk) to 10.0% (very high risk; Spearman rho = −0.71, p < 0.001). Performance varied across waiver categories: ventilation waivers achieved the highest balanced accuracy (87.1%) while safety waivers proved most challenging (balanced accuracy 64.3%, sensitivity 40.0%). The framework offers a transparent, data-driven decision-support complement to regulatory judgement, learning patterns from historically decided applications within the 2021–2023 BCA context, and demonstrates feasibility for integration into Singapore’s Corenet X digital building submission platform. These five waiver categories serve as domain stratification variables. The machine learning target variable is the binary regulatory outcome: Approved (46.2% of cases) or Rejected (53.8%).

  • Open Access

    Machine Learning for Building Code Waiver Assessment: A Predictive Analytics Framework from 197 Singapore BCA Cases (2021-2023)

    by Samson Tan, Teik Toe Teoh

    Building code waiver assessments in Singapore remain largely discretionary, relying on case officers' subjective judgment with limited decision-support tooling. This study presents the first machine learning framework for predicting building code waiver outcomes, trained on 197 historically decided cases from the Building and Construction Authority (BCA) across five waiver categories: barrier-free accessibility (n = 45), ventilation (n = 61), staircase design (n = 37), safety provisions (n = 30), and structural modifications (n = 24), spanning 2021 to 2023. Fourteen engineered features, including documentation completeness, technical justification quality, and compliance history, were extracted through domain-expert annotation. Four models were evaluated: L2-regularised logistic regression, random forest, gradient boosting (XGBoost), and a weighted ensemble. The ensemble achieved the highest predictive accuracy of 83.7% (95% CI: 79.2-88.1%) with an area under the receiver operating characteristic curve (AUC) of 0.891 (95% CI: 0.854-0.928), significantly outperforming all individual models (McNemar's test, p < 0.05). SHAP analysis revealed that documentation completeness and technical justification quality collectively account for 55% of prediction variance. A companion five-by-five risk assessment matrix, combining predicted rejection probability with consequence severity, stratified cases into actionable risk tiers correlating with observed approval rates from 90.3% (very low risk) to 10.0% (very high risk; Spearman rho = -0.71, p < 0.001). The framework offers a transparent, data-driven complement to regulatory judgment and demonstrates feasibility for integration into Singapore's Corenet X digital building submission platform.

  • Open Access

    AI-Driven Optimization of Sanitary Facilities in Office Buildings: A Machine Learning Approach Using LSTM Neural Networks

    by Samson Tan, Teik Toe Teoh

    This study introduces an artificial intelligence-based approach to planning sanitary facilities in buildings, with a focus on long short-term memory neural networks. By examining factors like occupancy patterns, daily fluctuations, and building-specific characteristics, the model delivers data-driven guidance for fixture allocation. Validation was carried out using empirical data from a Singaporean office building, resulting in strong predictive performance and improved operational efficiency. The long short-term memory model surpassed traditional methods, with a 39.26% boost in mean absolute percentage error over queueing theory. In a real-world scenario, its predictions were within 2.63–4.76% of actual needs, whereas prescriptive codes deviated by 12.07–19.05%. Sensitivity analysis showed that total occupancy, time of day, and gender ratio exerted the greatest influence, enabling gender-specific recommendations. The findings also indicate a potential 15% cut in overall fixtures with no compromise in service quality, providing considerable cost and space savings. By uniting advanced computational modeling with real data, this research demonstrates how artificial intelligence can elevate sanitary facility planning toward evidence-based decision-making, efficient resource use, and higher user satisfaction. The results may influence policy, regulatory standards, and performance-oriented design in contemporary buildings.


  • Open Access

    AI-Driven Optimization of Sanitary Facilities in Office Buildings: A Machine Learning Approach Using LSTM Neural Networks

    by Samson Tan, Teik Toe Teoh

    This study introduces an AI-based approach to planning sanitary facilities in buildings, with a focus on Long Short-Term Memory (LSTM) neural networks. By examining factors like occupancy patterns, daily fluctuations, and building-specific characteristics, the model delivers datadriven guidance for fixture allocation. Validation was carried out using empirical data from a Singaporean office building, resulting in strong predictive performance and improved operational efficiency. The LSTM model surpassed traditional methods, with a 39.26% boost in Mean Absolute Percentage Error (MAPE) over queueing theory. In a real-world scenario, its predictions were within 2.63%–4.76% of actual needs, whereas prescriptive codes deviated by 12.07%–19.05%. Sensitivity analysis showed that total occupancy, time of day, and gender ratio exerted the greatest influence, enabling gender-specific recommendations. The findings also indicate a potential 15% cut in overall fixtures with no compromise in service quality, providing considerable cost and space savings. By uniting advanced computational modeling with real data, this research demonstrates how AI can elevate sanitary facility planning toward evidence-based decision-making, efficient resource use, and higher user satisfaction. The results may influence policy, regulatory standards, and performance oriented design in contemporary buildings.


  • Open Access

    Predicting Shot Accuracy in Badminton Using Quiet Eye Metrics and Neural Networks

    by Samson Tan, Teik Toe Teoh

    This paper presents a novel approach to predicting shot accuracy in badminton by analyzing Quiet Eye (QE) metrics such as QE duration, fixation points, and gaze dynamics. We develop a neural network model that combines visual data from eye-tracking devices with biomechanical data such as body posture and shuttlecock trajectory. Our model is designed to predict shot accuracy, providing insights into the role of QE in performance. The study involved 30 badminton players of varying skill levels from the Chinese Swimming Club in Singapore. Using a combination of eye-tracking technology and motion capture systems, we collected data on QE metrics and biomechanical factors during a series of badminton shots for a total of 750. Key results include: (1) The neural network model achieved 85% accuracy in predicting shot outcomes, demonstrating the potential of integrating QE metrics with biomechanical data. (2) QE duration and onset were identified as the most significant predictors of shot accuracy, followed by racket speed and wrist angle at impact. (3) Elite players exhibited significantly longer QE durations (M = 289.5 ms) compared to intermediate (M = 213.7 ms) and novice players (M = 168.3 ms). (4) A strong positive correlation (r = 0.72) was found between QE duration and shot accuracy across all skill levels. These findings have important implications for badminton training and performance evaluation. The study suggests that QE-based training programs could significantly enhance players’ shot accuracy. Furthermore, the predictive model developed in this study offers a framework for real-time performance analysis and personalized training regimens in badminton. By bridging cognitive neuroscience and sports performance through advanced data analytics, this research paves the way for more sophisticated, individualized training approaches in badminton and potentially other fast-paced sports. Future research directions include exploring the temporal dynamics of QE during matches and developing real-time feedback systems based on QE metrics.