Safety Checks Research Articles

Enhancing fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones

Industrial collaborative robotics is promising for manufacturing activities where the presence of a robot alongside a human operator can improve operator’s working conditions, flexibility, and productivity. A collaborative robotic application has to guarantee not only safety of the human operator, but also fluency in the collaboration, as well as performance in terms of productivity and task time. In this paper, we present an approach to enhance fluency and productivity in human-robot collaboration through online scaling of dynamic safety zones. A supervisory controller runs online safety checks between bounding volumes enclosing robot and human to identify possible collision dangers. To optimize the sizes of safety zones enclosing the manipulator, the method minimizes the time of potential stop trajectories considering the robot dynamics and its torque constraints, and leverages the directed speed of the robot parts with respect to the human. Simulations and experimental tests on a seven-degree-of-freedom robotic arm verify the effectiveness of the proposed approach, and collaborative fluency metrics show the benefits of the method with respect to existing approaches.

Can meaning make cents? Making the meaning of work salient for US manufacturing workers.

We conducted a field experiment in a small electronics manufacturing firm in the US with the specific aim to improve minutes worked, punctuality, tardiness and safety checks. Our intervention was to put posters on the production floor on a random day, which made salient to the blue-collar employees the meaning and importance of their job, which comprised of routine repetitive tasks, in a before and after design. Overall, the intervention was a success with positive and significant effects consistently found for the outcomes both immediately after the experiment finished (+3 days) and also more than two weeks after (+15 days). Our study highlights it is possible to motivate blue collar manual workers intrinsically by drawing attention to the meaning of their work.

BIM-enabled semantic web for automated safety checks in subway construction

Rule-based construction safety checking aims to inspect safety risk factors during the construction process to ensure that risk factor states are within safety thresholds. However, integrating multisource safety risk factors and text-based rules remains a challenge. This study proposes a semantic approach to integrate heterogeneous data under a building information modeling (BIM) environment and enable automated safety checking through SPARQL-based reasoning. In this framework, four interconnected ontologies are developed to provide a semantic schema for subway construction safety checking. Safety risk factors data are extracted from BIM and sensor data and then converted into integrated ontology instances. Text-based rules are automatically transformed into SPARQL-based checking rules. The proposed framework can improve knowledge sharing and promote real-time and automated safety checking. A case is illustrated to show how the framework can be applied, confirming the feasibility and effectiveness of the proposed framework.

Neural Network Detection of Pacemakers for MRI Safety

Flagging the presence of cardiac devices such as pacemakers before an MRI scan is essential to allow appropriate safety checks. We assess the accuracy with which a machine learning model can classify the presence or absence of a pacemaker on pre-existing chest radiographs. A total of 7973 chest radiographs were collected, 3996 with pacemakers visible and 3977 without. Images were identified from information available on the radiology information system (RIS) and correlated with report text. Manual review of images by two board certified radiologists was performed to ensure correct labeling. The data set was divided into training, validation, and a hold-back test set. The data were used to retrain a pre-trained image classification neural network. Final model performance was assessed on the test set. Accuracy of 99.67% on the test set was achieved. Re-testing the final model on the full training and validation data revealed a few additional misclassified examples which are further analyzed. Neural network image classification could be used to screen for the presence of cardiac devices, in addition to current safety processes, providing notification of device presence in advance of safety questionnaires. Computational power to run the model is low. Further work on misclassified examples could improve accuracy on edge cases. The focus of many healthcare applications of computer vision techniques has been for diagnosis and guiding management. This work illustrates an application of computer vision image classification to enhance current processes and improve patient safety.

Impact of technology-assisted versus manual sterile compounding on safety and efficiency in a Canadian community hospital.

PurposeInterventions to improve the safety and efficiency of manual sterile compounding are needed. This study evaluated the impact of a technology-assisted workflow system (TAWS) on sterile compounding safety (checks, traceability, and error detection), and efficiency (task time).MethodsObservations were conducted in an oncology pharmacy transitioning from a manual to a TAWS process for sterile compounding. Process maps were generated to compare manual and TAWS checks and traceability. The numbers and types of errors detected were collected, and task times were observed directly or via TAWS data logs.ResultsAnalysis of safety outcomes showed that, depending on preparation type, 3 to 4 product checks occurred in the manual process, compared to 6 to 10 checks with TAWS use. TAWS checks (barcoding and gravimetric verification) produced better traceability (documentation). The rate of incorrect-drug errors decreased with technology-assisted compounding (from 0.4% [5 of 1,350 preparations] with the manual process to 0% [0 of 1,565 preparations] with TAWS use; P < 0.02). The TAWS increased detection of (1) errors in the amount of drug withdrawn from vials (manual vs TAWS, 0.4% [5/1,350] vs 1.2% [18/1565]; P < 0.02), and (2) errors in the amount of drug injected into the final container (manual vs TAWS, 0% [0/1,236] vs 0.9% [11/1,272]; P < 0.002). With regard to efficiency outcomes, TAWS use increased the mean mixing time (manual vs TAWS, 275 seconds vs 355 seconds; P < 0.001), had no significant impact on average visual checking time (manual vs TAWS, 21.4 seconds vs 21.6 seconds), and decreased average physical checking time (manual vs TAWS, 58.6 seconds vs 50.9 seconds; P < 0.001).ConclusionIn comparison to manual sterile compounding, use of the TAWS improved safety through more frequent and rigorous checks, improved traceability (via superior documentation), and enhanced error detection. Results related to efficiency were mixed.

Electron flash-RT program in clinical setting for human translation.

e13596 Background: A FLASH-RT program was established at Dartmouth-Hitchcock Medical Center in minimally-modified clinical setting by joint efforts of biomedical engineering, radiation oncology, radiation biology and medical physics teams. Various projects on dosimetry, chemical sensing, molecular profiling, software/hardware development, and translational studies have been conducted. The aim is to share logistical considerations and experience on running a FLASH-RT program to support institution-wide academic activities with an ultimate goal of treating human patients with FLASH-RT in 2022. Methods: A linac was converted in the clinical setting by qualified engineers to deliver an ultra-high dose rate (UHDR) electron beam. Routine safety and dosimetry checks were done by physicists for every reversible conversion. Long-term record-keeping and retrospective surveys were carried out to demonstrate the feasibility, safety, stability and accuracy of this dual-purpose (FLASH and conventional RT) approach. Comprehensive failure mode and effects analysis (FMEA) has been completed to systematically evaluate safety related considerations. A treatment planning system (TPS) has been developed in Varian Eclipse to facilitated comparative studies. The FLASH-capable linac has been utilized as shared resource to support institution-wide academic activities as well as normal clinical treatments. Results: With its safety (no accident or FLASH-related malfunction), flexibility (&gt; 100 conversions in 2 years), reliability (̃6000 hours in flash mode and ̃5x105 Gy accumulative dose delivered at isocenter) and accuracy (̃5% conversion-to-conversion variations) demonstrated by commissioning, long-term user experience and comprehensive FMEA analysis, the FLASH-RT platform has been actively utilized for researches in six major categories 1) FLASH beam dosimetry; 2) real-time beam delivery monitoring and control; 3) oximetry and chemical sensing; 4) preclinical/translational small/large animal treatment with tumor control and normal tissue complication endpoints, 5) treatment plan and delivery optimization; 6) the design of phase I/II trials. Key findings in each category will be reported. Conclusions: A FLASH-RT program in clinical setting is established at Dartmouth with joint efforts, promoting collaborative projects to advance FLASH-RT to clinical treatment. The system has been reliably utilized for over two years for mechanistic as well as translational studies and support a phase I/II trial treating cutaneous lymphoma with eFLASH-RT.

Clinical Audit of the Awareness of Safety Guidelines on Lithium Prescribing Within the Acute Hospital- James Cook University Hospital

AimsLithium is a useful drug and is of particular benefit in patients with chronic mood disorders like bipolar affective disorder and recurrent depression. Lithium requires careful monitoring and dose adjustment for safe use due to its narrow therapeutic index and high potential for toxicity. Monitoring must carry on even when mental health patients taking Lithium are admitted to acute hospital. Therefore, the main aim of this clinical audit was to evaluate the level of awareness of the lithium safety guidance amongst medical staff working within the Acute Hospital, James Cook University Hospital. Ideally 100% of staff should have the appropriate knowledge.MethodsQuestionnaire consisted of 6 items which were derived from key points within the Trust guidelines for Lithium. It was designed to highlight the key points in the document and check the level of awareness of the respondents. Respondents were drawn from James Cook University Hospital and South Tees Liaison Psychiatry team. A total of 25 respondents were included in the study.Results96% (24/25) of the respondents were aware that renal and thyroid function should be checked for patients on Lithium. 84% (21/25) were aware of the potential impact of Lithium on Kidney function (eGFR) and 68% (17/25) were aware of signs of Lithium toxicity.60% (15/25) of acute staff were aware about referring patients with deranged Lithium levels to the Liaison Psychiatry team. 40% (10/25) were aware of the drugs that could potentially increase lithium levels like Diuretics, Non-steroidal anti-inflammatory drugs, ACE (angiotensin converting enzyme) inhibitors. Only 24% (6/25) of acute trust staff were aware about checking lithium levels on admission.ConclusionIdeally, a 100% compliance and positive response rate should be achieved as these relate to completion of expected safety checks. Lithium is a potentially high-risk drug with a narrow therapeutic index. Possibility of its acute and chronic side effects, including lithium toxicity, makes it essential to follow safety guidelines on lithium prescribing and hence ensure patient safety.In view of this, the clinical audit results clearly show that there is significant room for improvement to achieve a 100% positive response rate for awareness of safety guidelines on Lithium prescribing.Overall, there were an average of 57% positive responses and 42% negative responses for awareness of various aspects of the safety guidelines for Lithium.A robust action plan which included teaching sessions on creating awareness about lithium monitoring was planned because of this audit.

Can a digital twin of the residuum improve bionic solutions for individuals suffering from limb loss?

Introduction: Understanding the influence of whole-body activity (e.g., physical training) on the biophysics at organ-, tissue-, and sub-tissue-levels is important for designing optimal physical training/rehabilitation and effective control of assistive devices. The Griffith Centre of Biomedical and Rehabilitation Engineering (GCORE) has developed mature rehabilitation and assistive device technologies underpinned by the Personalized Digital Human (PDH). Method framework: The PDH is a physics-based digital twin of the human (and devices), which includes representation of an individual’s bones, articulations, muscles, and other soft tissues. Coupled with peripheral muscle excitation (e.g., electromyograms), PDH encodes muscle activations specific to the individual (e.g., sensitive to training and disease) and task (e.g. sensitive to control task)1. Examples: To analyze human performance, PDH quantifies mechanical parameters such as net loading to the body, organ (e.g., whole bone; Fig. 2), joint, tissue (e.g., ligament; Fig. 1)2, and sub-tissue (e.g., local strain in tendon; Fig. 1)1. Within a control system3, PDH predicts muscle activations that produce target mechanics (e.g., torque on rehabilitation ergometer), compliment an assistive device (e.g., torque above motor-driven assistance), sensory afferents that augment/simulate sensory experience (e.g., haptics), and safety margins (e.g., critical stresses) (Fig. 2).Fig. 2The PDH used within a control system to interpret sensor data, model the internal states of the human, provide augmented sensory afferents, and perform safety checks on the loading of musculoskeletal tissues3.View Large Image Figure ViewerDownload Hi-res image Download (PPT) Discussion/future directions: Currently, we are developing direct fusion of PDH with prosthesis design to optimize amputee residuum health4. Further, PDH could readily be extended to become the personalized digital soldier, with extensive scope for use in monitoring training loads, improving rehabilitation efficacy, and designing equipment to better interface with humans. Acknowledgements: The PDH is the result of numerous nationally-competitive and industry grants for over 2 decades. References 1Pizzolato C, Shim VB, Lloyd DG, et al. Targeted achilles tendon training and rehabilitation using personalized and real-time multi-scale models of the neuromusculoskeletal system. Front Bioeng Biotechnol 2020; 8:878. https://doi.org/10.3389/fbioe.2020.00878 2Nasseri A, Khataee H, Bryant AL, et al. Modelling the loading mechanics of anterior cruciate ligament. Comp Meth Prog Biomed 2020; 184:105098. https://doi.org/10.1016/j.cmpb.2019.105098 3Pizzolato C, Gunduz MA, Palipana D, et al. Non-invasive approaches to functional recovery after spinal cord injury: therapeutic targets and multimodal device interventions. Exp Neurol 2021; 330:113612. https://doi.org/10.1016/j.expneurol.2021.113612 4Frossard LA, Lloyd DG. The future of bionic limbs. Res Feat 2021; 134:74-77. https://doi.org/10.26904/RF-134-7477

On the Joint Exploitation of Satellite DInSAR Measurements and DBSCAN-Based Techniques for Preliminary Identification and Ranking of Critical Constructions in a Built Environment

The need for widespread structural safety checks represents a stimulus for the research of advanced techniques for structural monitoring at the scale of single constructions or wide areas. In this work, a strategy to preliminarily identify and rank possible critical constructions in a built environment is presented, based on the joint exploitation of satellite radar remote sensing measurements and artificial intelligence (AI) techniques. The satellite measurements are represented by the displacement time series obtained through the Differential Synthetic Aperture Radar Interferometry (DInSAR) technique known as full resolution Small BAseline Subset (SBAS) approach, while the exploited AI technique is represented by the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) methodology. The DBSCAN technique is applied to the SBAS-DInSAR products relevant to the achieved Persistent Scatterers (PSs), to identify clusters of pixels corresponding to buildings within the investigated area. The analysis of the deformation evolution of each building cluster is performed in terms of velocity rates and statistics on the DInSAR measurements. Synthetic deformation maps of the areas are then retrieved to identify critical buildings. The proposed methodology is applied to three areas within the city of Rome (Italy), imaged by the COSMO-SkyMed SAR satellite constellation from ascending and descending orbits (in the time interval 2011–2019). Starting from the DInSAR measurements, the DBSCAN algorithm provides the automatic clustering of buildings within the three selected areas. Exploiting the derived deformation maps of each study area, a preliminary identification and ranking of critical buildings is achieved, thus confirming the validity of the proposed approach.

Multipath-Assisted Radio Sensing and State Detection for the Connected Aircraft Cabin.

Efficiency and reliable turnaround time are core features of modern aircraft transportation and key to its future sustainability. Given the connected aircraft cabin, the deployment of digitized and interconnected sensors, devices and passengers provides comprehensive state detection within the cabin. More specifically, passenger localization and occupancy detection can be monitored using location-aware communication systems, also known as wireless sensor networks. These multi-purpose communication systems serve a variety of capabilities, ranging from passenger convenience communication services, over crew member devices, to maintenance planning. In addition, radio-based sensing enables an efficient sensory basis for state monitoring; e.g., passive seat occupancy detection. Within the scope of the connected aircraft cabin, this article presents a multipath-assisted radio sensing (MARS) approach using the propagation information of transmitted signals, which are provided by the channel impulse response (CIR) of the wireless communication channel. By performing a geometrical mapping of the CIR, reflection sources are revealed, and the occupancy state can be derived. For this task, both probabilistic filtering and k-nearest neighbor classification are discussed. In order to evaluate the proposed methods, passenger occupancy detection and state detection for the future automation of passenger safety announcements and checks are addressed. Therefore, experimental measurements are performed using commercially available wideband communication devices, both in close to ideal conditions in an RF anechoic chamber and a cabin seat mockup. In both environments, a reliable radio sensing state detection was achieved. In conclusion, this paper provides a basis for the future integration of energy and spectrally efficient joint communication and sensing radio systems within the connected aircraft cabin.

Firearm Injury and Mortality Prevention in Pediatric Health-care Settings.

Firearm Injury and Mortality Prevention in Pediatric Health-care Settings.

Large outbreak of Jimsonweed (Datura stramonium) poisoning due to consumption of contaminated humanitarian relief food: Uganda, March\u2013April 2019

BackgroundJimsonweed (Datura stramonium) contains toxic alkaloids that cause gastrointestinal and central nervous system symptoms when ingested. This can be lethal at high doses. The plant may grow together with leguminous crops, mixing with them during harvesting. On 13 March 2019, more than 200 case-patients were admitted to multiple health centres for acute gastrointestinal and neurologic symptoms. We investigated to determine the cause and magnitude of the outbreak and recommended evidence-based control and prevention measures.MethodsWe defined a suspected case as sudden onset of confusion, dizziness, convulsions, hallucinations, diarrhoea, or vomiting with no other medically plausible explanations in a resident of Napak or Amudat District from 1 March—30 April 2019. We reviewed medical records and canvassed all villages of the eight affected subcounties to identify cases. In a retrospective cohort study conducted in 17 villages that reported the earliest cases, we interviewed 211 residents about dietary history during 11–15 March. We used modified Poisson regression to assess suspected food exposures. Food samples underwent chemical (heavy metals, chemical contaminants, and toxins), proteomic, DNA, and microbiological testing in one national and three international laboratories.ResultsWe identified 293 suspected cases; five (1.7%) died. Symptoms included confusion (62%), dizziness (38%), diarrhoea (22%), nausea/vomiting (18%), convulsions (12%), and hallucinations (8%). The outbreak started on 12 March, 2–12 h after Batch X of fortified corn-soy blend (CSB +) was distributed. In the retrospective cohort study, 66% of 134 persons who ate CSB + , compared with 2.2% of 75 who did not developed illness (RRadj = 22, 95% CI = 6.0–81). Samples of Batch X distributed 11–15 March contained 14 tropane alkaloids, including atropine (25-50 ppm) and scopolamine (1-10 ppm). Proteins of Solanaceae seeds and Jimsonweed DNA were identified. No other significant laboratory findings were observed.ConclusionThis was the largest documented outbreak caused by food contamination with tropane alkaloids. Implicated food was immediately withdrawn. Routine food safety and quality checks could prevent future outbreaks.

Mortality Reduction After a Preincision Safety Check Before Cardiac Surgery: Is It the Aorta?

The introduction and use of a preincision safety check were associated with lower mortality after mixed adult cardiac surgery; however, an explanatory mechanism is lacking. Stroke, one of the most severe complications after cardiac surgery, with high mortality, may be reduced by adapting the surgical handling of the ascending aorta. This study assessed the prevalence and predictors of this adaptation after a preincision safety check and the subsequent effect on outcome. A prospective, single-center, observational study comparing adaptation with no-adaptation. The primary outcome measure was 30-day mortality. Multivariate analyses were performed to determine independent predictors of adaptation. To study the effect of adaptation on outcome, a propensity score-matched cohort was constructed in a 1:3 intervention:control ratio. At Isala Zwolle (NL), a large, nonacademic teaching hospital. All consecutive cardiac surgery procedures from 2012 until 2015, including 4,752 surgeries. The adaptation of surgical handling of the ascending aorta. In 283 cardiac surgeries (5.9%), adaptation was indicated. The most important independent predictors for adaptation were extracardiac atherosclerosis, current smoking, and increasing age. In the propensity score-matched cohort consisting of 1,069 procedures, there were no significant differences in outcome. After correction for propensity score, the hazard ratio of adaptation for 30-day mortality was 1.8 (0.85-3.79). The adaptation of aortic surgical handling after a preincision safety check was necessary for 5.9% of cardiac surgeries, with extracardiac atherosclerosis as the strongest predictor. Outcome was not significantly different between patients with and without adaptation. Although promising, it remains unclear whether adaptation may fully explain mortality reduction after the use of a preincision safety check.

Unlisted

Unlisted

Performance of a historical cantilever reinforced concrete bridge with half-joint degradation

The lack of maintenance of roadway concrete bridges built from the Second World War until the 70 s of the 20th century has led in recent years to an ever-increasing request for safety assessments. When bridge performance in terms of Serviceability Limit State (SLS) and Ultimate Limit State (ULS) has to be evaluated, in-situ visual inspections and load tests for safety and maintenance assessment have to be coupled with structural analysis. In order to identify a sound bridge structural model and to assess the actual conservation state, more refined models than those usually considered for section and reinforcement design should be used to reproduce the results of load tests and perform global and local safety checks in the structural elements. These needs are exemplified here through an assessment of the performance at SLS and ULS of a three-span cantilever reinforced bridge designed by Riccardo Morandi in Southern Italy. The central beam between the cantilevers is prestressed with bonded tendons while the side spans are made of ordinary reinforced concrete. Critical aspects of the bridge behaviour together with deficiencies due to deterioration and lack of maintenance over time, in service life, are investigated. The results of a structural assessment performed with Finite Element models are presented, through a comparison between different approaches and grades of structural analysis and through validation with in-situ investigations. Safety assessment of the half-joint is focused comparing the results obtained from strut-and-tie models supplied by Eurocodes and specifically developed for the case-study, considering the actual arrangement of the Gerber saddle. The results of this study show that a safety assessment of half-joints based on the literature and code models can lead to unreliable evaluations and that only global and local FE models validated through in-situ investigations allow the engineer to perform a reliable evaluation of safety in existing bridges.

Bidirectional Quantum Secure Direct Communication Using Dense Coding of Four Qubit Cluster States

We are introducing an efficient bidirectional quantum secure direct communication protocol that employs the four qubit cluster states, creating a novel quantum channel based on dense coding between the transmitter and receiver. By dense coding, after a conventional announcement, two legitimate users can simultaneously exchange their messages. Two safety checking measures are taken to ensure safe transmission. Information leaking is not an issue in this protocol, and it is secure against some well-known eavesdropping assaults. It is also accessible with cutting-edge technology.

Fire Risk Analysis for Construction Sites

In construction, fire safety refers to preventing fires from igniting as well as assuring workers’ safety when it occurs. Industry players devote less emphasis to the prevention of fires at building sites than they do to other forms of construction mishaps. The after effects of construction site fires are very severe even though they are not very frequent to occur they often result in injury and death of workers, project time delay and project cost overrun. This study aims to address and analyse the fire hazards in construction sites concluding with an expansive list of factors that contribute to fire hazards in construction sites. Since not all factors have a substantial likelihood of occurrence or severity of impact it’s important to eliminate those factors that have a tolerable or trivial level of risk. The factors were shortlisted using a risk matrix by using the inputs of likelihood of occurrence and severity of impact of various risk factors present in case studies. A list of 7 risk groups and 18 risk factors were finalised for further analysis in this study. The likelihood of occurrence and severity of impact of those 18 factors were obtained through questionnaire surveys. After which Fuzzy synthetic evaluation was used to calculate the risk index at 3 levels, the risk factor level, risk group and finally an overall risk index for construction sites. It was analysed that construction sites had a risk index of 3.97 out of a maximum score of 5 which indicated that construction sites were at a substantial risk to fire. Finally, a risk assessment matrix was developed which could be then used at various construction sites to keep track of the level of fire risk present in the site at any point in time. This risk assessment matrix developed in this study could be made a part of the safety checks that happen at site regularly.

Gravity dam analysis using particle swarm optimization method

Structural stability analysis is the key aspect of a gravity dam. The safety of a dam relies on its capabilities to handle all external static and dynamic forces acting on it. This study includes stability analysis of a non-overflow section of gravity dam using the Particle Swarm Optimization (PSO) method. PSO method is applied for stability analysis of gravity dam as it has very few parameters to adjust during analysis. Structural stability analysis is performed on a 23.375 m high non-overflow section of the gravity. The analysis of the dam was carried out having a height to width ratio of 1.171, which comes under seismic zone II. The safety checks results obtained graphically presented for the accuracy using PSO satisfy structural safety evaluation limits as per specified in IS 6512. In other preferred conventional methods is difficult and time-consuming to find an error and fix it compared to PSO. PSO provided an efficient and accurate solution and presented as a point or be extended to n-dimensional space. The structural stability safety checks results are graphically presented for the accuracy of manual calculations.

A LOCKED-POSITION MONITOR FOR IMPROVING SAFETY OF RELEASE HOOKS IN ENCLOSED LIFEBOATS

Repeated casualties caused by inadvertent release of lifeboat release hooks during drills and inspections have attracted the attention of the International Maritime Organization, which correspondingly amends the Life-Saving Appliance (LSA) Code in the international convention for the Safety of Life at Sea. This study proposes novel installations of locked-position monitors on release hooks for monitoring and safety checks. With the installation of locked-position monitors near unsealed pull rod, upon lifting the lifeboat from the water, the sensors can initiatively detect whether the release hooks are in a locked position. If the release hooks are not in the locked position for any reason, audible alarms are activated, warning lifeboat operators to cease operations and wait for further inspection. The example provided in this research indicates that locked-position monitors can be implemented on lifeboats to reduce accidents resulting from malfunctioning lifeboat release hooks, thereby promoting a safer working environment for all seamen at sea.

Automation Tool for Home Fire Safety Check

AbstractFire simulation tools have been developed for the inspection of environmental safety. However, they have not been extensively exploited for home use. One critical reason for this is that building the environmental model relies highly on manual operations. In this study, image sensors are adopted to automatically build an environmental model and reduce the labor burden of exploiting fire simulation tools for a fire safety check. To increase the accuracy of an environmental model, our automation extracts the essential features affecting fires from images using recognition models and the proposed approaches. Our automation converts the environmental data into an FDS6 syntax. The experimental results reveal the feasibility of our automation. Compared to a manual operation, our approach not only reduces the labor burden, but also the inconsistent environmental model owing to a manual operation.