Irfan Gazi

Mr. Irfan Gazi

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 May 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KKKyungki Kim
Kyungki Kim
Irfan GaziIrfan Gazi
Irfan Gazi
JWJohn Windle
John Windle
CHChristian Haas
Christian Haas
MCMelissa Christian
Melissa Christian
TDTuankhanh Dao
Tuankhanh Dao
Despite recent advances in healthcare robotics, most existing systems remain limited to single-purpose functions and lack the flexibility to collaborate dynamically with clinicians and facility systems. To address these limitations, this study presents an LLM-orchestrated framework for a multifunctional Robotic Health Attendant (RHA) that enables robot actions and environment interactions to be coordinated in healthcare environments. Within this framework, the RHA functions as a multifunctional nursing assistant capable of performing physical, communicative, and informational tasks through natural-language interaction. Tasks are expressed in natural language and decomposed into coordinated behaviors across three functional branches: physical, for navigation, object manipulation, and delivering medication; communicational, for dialog with patients and clinicians; and informational, for retrieving and summarizing clinical knowledge, such as patient education on complex heart transplant procedures. The framework integrates multiple Large Language Models (LLMs) and sensing nodes to combine facility data, patient information, and clinician commands, enabling robots and building systems to act in a context-aware manner through coordinated task execution across robotic and environmental components. Implemented in a simulated environment, the framework demonstrates the feasibility of executing representative tasks through LLM-based orchestration, serving as a proof-of-concept toward integrated robotic assistance in healthcare settings.

1 August 2026 in Scientific Reports
Verified
Journal Article
Open access
PDF file
MRMd Tanvir Rahman Rifat
Md Tanvir Rahman Rifat
SDShuvo Dip Datta
Shuvo Dip Datta
MHMd. Mehrab Hossain
Md. Mehrab Hossain
MJMd Shah Jamal
Md Shah Jamal
MMMarcel Maghiar
Marcel Maghiar
Irfan GaziIrfan Gazi
Irfan Gazi
South Asian countries, including Bangladesh, continue to experience unacceptably high rates of occupational accidents and fatalities in the construction sector, driven by rapid urbanization and infrastructure development. Traditional risk assessment methods, such as static risk matrices, frequently fail to capture the stochastic nature of these accidents, rely on point-based probability and severity estimates, and neglect the behavioral risk perceptions of decision-makers. This study develops and applies a hybrid framework that integrates Monte Carlo Simulation (MCS) with Utility Theory (UT) to prioritize occupational risks in construction projects in Bangladesh. Primary data were collected through a structured questionnaire survey of 112 construction professionals across 43 infrastructure projects in Bangladesh, who assessed the probability and severity of 30 occupational risks on a five-point scale. For each risk, triangular distributions, parameterized using minimum, mode, and maximum values derived from survey statistics and bounded within the 1–5 rating scale, were specified in @Risk. A total of 5,000 Monte Carlo iterations were executed to ensure convergence stability in the simulated risk exposure distributions. Simulated risk exposure indices were subsequently transformed into utility-based priorities using an exponential utility function that explicitly represents risk-averse, risk-neutral, and risk-seeking decision profiles. Results indicate that falls from a higher level (RI = 22.3, SRI = 14.78), shocks from overhead powerlines (RI = 19.8, SRI = 13.51), and falling on the same level (RI = 18.6, SRI = 13.36) represent the most critical occupational hazards. The utility-based analysis translates simulated risk exposure scores into behaviorally interpretable priority values under risk-averse, risk-neutral, and risk-seeking decision profiles. The primary methodological contribution of this study lies in the explicit integration of probabilistic uncertainty modeling (MCS) with behavioral risk-preference modeling (UT) for occupational safety prioritization in a developing-country construction context. The framework provides a transparent, reproducible, and adaptable tool for decision-making in construction safety. Its findings are intended to guide practitioners in resource allocation and intervention planning, though field-level validation in real-time safety management contexts remains a recommended direction for future research.