Hazard Identification Research Articles

High-resolution aerial monitoring using DL for identifying abnormal activity based on visual patterns in drone videos

Unmanned aerial vehicles (UAVs) and sophisticated deep learning (DL) models have made the application of artificial intelligence (AI) more popular. This has resulted in an increase in the number of attempts to improve high-resolution aerial monitoring using DL for identifying abnormal activity based on visual patterns in drone videos. The study introduces a one-class support vector machine (OC-SVM) oddity locator for low-altitude, limited-scope UAVs used for ethereal video surveillance. The primary goal is to improve UAV-based observation capabilities by identifying areas or things of interest without prior knowledge, hence improving tasks like queue control, vehicle following, and hazardous product identification. The framework makes use of OC-SVM because of its quick and lightweight setup, making it suitable for continuous operation on low-computational UAVs. It empowers the identification of several peculiarities necessary for low-elevation reconnaissance by using textural characteristics to recognise both large-scale and tiny structures. Examine the UAV mosaicking and change location (UMCD) dataset to demonstrate the effectiveness of the framework, which achieves excellent accuracy and outperforms traditional methods by about one fifth in a variety of metrics. The suggested model compares with current methods, demonstrating superior accuracy and performance in recognition of peculiarities. Evaluation metrics include F1-score, review, exactness, and accuracy. The model demonstrates that it always encounters an oddity with a review compromise of up to seven on ten, achieving complete accuracy.

A Scoping Review on Hazard Recognition and Prevention Using Augmented and Virtual Reality

Hazard recognition and prevention techniques utilize augmented reality (AR) and virtual reality (VR) technology for immersive training and identification of potential hazards. Currently, no scoping reviews exist specifically on hazard recognition and prevention using AR and VR, which is crucial for forming evidence-based guidelines. This scoping review aimed to identify the use of AR and VR in hazard recognition and prevention, identify research gaps, and provide future recommendations. This Joanna Brings Institute (JBI) approach was used to investigate hazard recognition and prevention with AR and VR interventions. A total of six reliable databases were included: Google Scholar, IEEE Xplore, ACM Digital Library, PubMed, Scopus, and APA PsycNet, focusing on records and publications from the last five years. The review identified 5438 publications, with 22 meeting final inclusion criteria. The major findings include the use of AR and VR for teaching new skills, ensuring health and safety, enhancing realism, developing cognitive skills, improving performance, increasing engagement, and stimulating a sense of presence. Limitations identified include limited or non-diverse sample size, absence of real-world scenarios or contextual learning, inadequate game mechanics, insufficient validation of test results, lack of dynamic game behaviour, insufficient expert inclusion, technology issues, long-term impact assessment, and cost comparisons with traditional approaches. Technological issues have emerged as an additional impediment, limiting the efficacy of AR/VR applications in hazard recognition and prevention. In light of these findings, future research should focus on integrating contextual learning, expert inclusion, sample recruitment, expert validation, long-term impact assessment, and resolving technological challenges to enhance AR/VR applications’ efficacy and real-world viability.

Comprehensive Investigation of Epoxy Adhesives for Structural Applications in Saudi Arabia: Mechanical Performance, Environmental Impacts, and Analysis on Health.

Epoxy adhesives possess excellent mechanical properties, durability, and stability in harsh environments, making them suitable for producing engineering materials. This study selects four commercially available epoxy adhesives in Saudi Arabia: Epotec YD 128; Sikadur®-52 LP; Sikadur®-31 CF; and Sikadur®-42 MP Slow. Firstly, a comparison of their storage, application, and service temperatures was made, detailing the hazard identification and prevention measures established in accordance with the Occupational Safety and Health Administration (OSHA) guidelines. Subsequently, test samples of the four adhesives were produced, and tensile, compressive, and shear tests were conducted to compare their fundamental mechanical properties. Finally, a gas analyzer assessed the major harmful gases emitted by these epoxy adhesives 120 min after mixing the epoxy resins and curing agents. The results show that Sika 42 exhibits the highest tensile and compressive strengths among other types of adhesives, reaching 75.7 MPa and 133.8 MPa, respectively. It also has the longest pot life of 48 min at elevated temperatures (40 °C), making it suitable for the climatic conditions in Saudi Arabia. However, as a three-component adhesive, its application is complex and associated with the most identified hazards. Sika 31 presents a tensile modulus of up to 10.4 GPa, at least 3.8 times higher than the other adhesives, making it practical for controlling tensile deformation. Additionally, its ultimate shear strain reaches 10.7%, at least 6.6 times higher than the other samples, highlighting its suitability for constructing ductile bonds. After mixing of epoxy resins with curing agents, the presence of NO2 and SO2 were detected. However, no harmful gases were detected after 120 min, possibly due to the complete curing of the adhesives.

Beyond videoconferencing: enhancing remote home assessments with 3D modeling technology

Purpose: Occupational therapists in the Veterans Health Administration have transitioned from in-person to videoconferencing for home assessments, benefiting Veterans living in remote and rural areas. However, videoconferencing has limitations, including restricted field of view and poor video quality, affecting hazard identification accuracy. This study aims to introduce and evaluate a three-dimensional (3D) model as an alternative technology for remote home assessments. Materials and methods: We created 3D models using a 360-degree camera and mobile app. Five occupational therapists individually completed virtual training and practice sessions to familiarize themselves with using the 3D model. Each participant then conducted a remote home assessment using the 3D model and completed questionnaires, System Usability Scale (SUS), and semi-structured interviews. Results: Participants spent an average of 10 min training and practicing with the 3D model, and most reported either maintaining or gaining confidence in using it compared to before. All participants successfully completed the assessments, which took an average of 17 min. They rated the 3D model as easy to use, with an average SUS score of 78.5. Participants preferred the 3D model over videoconferencing, noting that it effectively addressed current challenges, and expressed their willingness to integrate it into clinical practice. Conclusion: This study demonstrates that 3D models offer a promising option for remote home assessments. With minimal training, occupational therapists could conduct more effective assessments. It is recommended to use 3D models for an initial understanding of the home environment before videoconferencing-based assessments to enhance the remote assessment experience for occupational therapists and clients.

Hazard, risk, reliability assessment and improvement of Darlington Tritium Removal Facility (DTRF) cryogenic refrigeration system

Tritium is a radioactive isotope of hydrogen, produced in heavy water, during CANDU reactor operations by neutron absorption. The tritium removal facility at Darlington (DTRF) is used to extract tritium from the heavy water on a continuous basis and concentrates it in preparation for immobilization and storage. There are several internal and external hazards associated with the operation of DTRF, such as fires, onsite transportation accidents, exposure to radioactive materials, explosion due to Hydrogen (H2) and the release of radioactive substances from the Tritium Immobilization System. This paper conducts a risk analysis for the DTRF Cryogenic Refrigeration System, associated with both Low and High Tritium Distillation columns. This study includes hazard identification, consequence analysis and risk estimation. Fault Tree and Event Tree Analysis conducted, system reliability, availability and human reliability was considered. Consequently, methods for risk reduction and integration with improvement to CRS design is discussed.

A Dualistic Perspective of Opportunity and Risk: The Impact of Head-Mounted Augmented Reality on Construction Onsite Hazard Identification of Workers

A Dualistic Perspective of Opportunity and Risk: The Impact of Head-Mounted Augmented Reality on Construction Onsite Hazard Identification of Workers

Risk Analysis of Railway Infrastructure Asset using Hazard Identification and FMEA Analysis on Track Asset

Risk Analysis of Railway Infrastructure Asset using Hazard Identification and FMEA Analysis on Track Asset

Knowledge Mapping of the Auxiliary Police: A Basis for Crafting a Capability Training Program

The auxiliary police force, particularly barangay tanods in the Philippines, faces significant challenges in effectively performing their roles due to limited formally training and capacity-building opportunities. This study was conducted to assess the level of knowledge among barangay tanods regarding their duties, responsibilities, roles as first responders, and patrolling and hazard identification and to develop a Capability Training Program tailored to address identified deficiencies. The need for this research arises from the observed gaps in advanced patrolling strategies and emergency response protocols, which hinder their effectiveness as community enforcers. Using a descriptive-quantitative research design, data were analyzed through regression analysis and descriptive statistics, including mean and standard deviation, using SPSS. The study employed adapted questionnaires targeting knowledge in key areas, such as duties and responsibilities, first responder actions, patrolling techniques, and hazard identification. Simple random sampling was applied, resulting in 140 barangay tanods participating as respondents. Findings revealed that although the overall knowledge of the respondents was high, specific gaps were evident in advanced emergency response and proactive patrolling strategies. These insights were instrumental in the development of a comprehensive Capability Training Program aimed at enhancing the effectiveness of police auxiliary services in critical operational areas.

A metamodel for sensitivity and uncertainty analysis in the modeling of loss of life due to dam failures

ABSTRACT Estimating the loss of life resulting from dam failures is required for devising emergency action plans and strategies for alert issuance and evacuation. However, current models for simulating fatalities are computationally expensive, forced by highly uncertain variables, and not readily interpretable, which may limit their use in engineering and research. For circumventing these problems, we utilize the polynomial chaos expansion technique (PCE) for approximating the loss of life as obtained from the agent-based model LifeSim and propagating uncertainty of inputs, namely, alerted population, mobilized population, alert issuance, and hazard identification, to the model responses. We also benefit from the PCE spectral representation for assessing the effects of each input in the loss of life associated with the dam failure in an urban area in Brazil, considering efficient and inefficient scenarios for alert and evacuation. The PCE error ranged from 10–3 to 10–2, and the mean squared error between the metamodel output and LifeSim was between two fatalities. In global sensitivity analysis, the variables alert issuance and hazard identification contributed the most to the number of fatalities. These findings provide objective guidelines for implementing more effective safety measures, potentially reducing loss of life resulting from a dam break in the study area.

Innovative geological–geotechnical zoning framework for urban planning: Wuhan’s experience

Traditional methods for understanding geological conditions, such as borehole drilling and on-site tests, are often costly and impractical for extensive urban areas like Wuhan’s Main Urban Area. This study introduces an innovative geological–geotechnical zoning framework that utilizes limited data to overcome these challenges, essential for urban planning, underground space development, and construction design. We began by dividing the study area into four primary geological units based on geomorphological characteristics, using a novel method validated at four metro stations. Our approach incorporated data from 1544 geological boreholes to compile a comprehensive database, from which six typical stratigraphic profiles for each unit were identified. These profiles facilitated the estimation of potential layers and their corresponding geotechnical parameters, and the identification of subsurface hazards. The study resulted in a detailed engineering geological zoning divided into nine secondary units. Our analysis not only demonstrates the effectiveness of the proposed criteria for geomorphological units in achieving more accurate and quantifiable outcomes but also shows the framework’s suitability for regions with complex sedimentary conditions. The resultant engineering geological zoning enhances understanding of geological risks, providing a foundation for safer and more sustainable urban development.

Stand-off hazardous materials identification based on near-infrared hyperspectral imaging combined with convolutional neural network

Near-infrared (NIR) hyperspectral imaging enables rapid, non-contact imaging of hazardous materials in a non-destructive manner, allowing for analysis based on spectral reflection information. However, using traditional methods, it is challenging to identify hazardous materials with less distinct spectral reflection features. This study utilizes a self-built NIR hyperspectral imaging system and proposes a new approach. Using a convolutional neural network (CNN), This allows for the rapid completion of high-throughput spectral screening, marking suspicious spectra at spatial points. we sophisticatedly classified six hazardous material types, generating impactful warning images. The optimized CNN demonstrated superior performance (accuracy 91.08 %, recall 91.15 %, specificity 91.62 %, precision 90.17 %, and 0.924 F1 score) compared to SVM and KNN methods. Our study included multitask validation tests, revealing a sensitive detection of 10 mg/cm2 for ammonium nitrate and trinitrotoluene, capable of identifying over 100 targets simultaneously. By simulating real-world scenarios, we successfully detected hazardous chemicals scattered on the ground and accurately identified these hazardous materials in glass and thin plastic products. Even in situations where clothing obstructed the view, we could still correctly identify hazardous chemicals and generate corresponding warning images. Our system demonstrated precise identification capabilities even amidst complex backgrounds. This method provides an accurate and rapid solution for identifying and locating hazardous chemicals, laying a strong foundation for the next steps in non-contact, long-distance quantitative determination of chemical concentrations. This study highlights the effective application of CNN in non-contact, long-distance classification, and recognition of hazardous materials, paving the way for further scientific and engineering applications.

Systematic Literature Review on Knowledge-Driven Approaches for Construction Safety Analysis and Accident Prevention

Due to its inherent complexities in the process and the dynamic interactions with external environmental factors, the construction industry is widely considered one of the most hazardous industries worldwide. With advancements in artificial intelligence (AI), construction safety management practices have increasingly used knowledge-driven approaches. Such incorporation of knowledge-based methods has led to significant improvements in various elements of construction safety management systems, including hazard identification and risk assessment, selection of risk mitigation strategies, analysis of accident information, sharing of health and safety knowledge, access to regulations, and identification of applicable safety requirements. Against this background, this paper presents a systematic literature review to provide an overview of the current state of the art in the use of knowledge-driven approaches in construction safety management. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) procedure, this study reviews how the knowledge-driven approach is utilized in the construction safety management field to automate different activities that come under it. Journal papers published from 2000 were considered for this review, and the analysis focused on the contributions of research, the evolution of knowledge-driven approaches, sources of incorporated knowledge, methods of system development, yearly publications, and publication by journals. The results provide a comparison of related studies over two decades and offer insights into trends and gaps in this research field. Notably, the trend analysis shows a dramatic increase in the number, as well as the depth, of research efforts utilizing AI techniques for analyzing unstructured data, such as construction images and texts from construction documents, and drawing data-based decisions for accident prevention.

Hazard Identification and Risk Assessment During Simultaneous Operations in Industrial Plant Maintenance Based on Job Safety Analysis

The risk of accidents during simultaneous operations (SIMOPS) in plant maintenance has been increasing. However, research on methods to prevent such accidents has been limited. This study aims to develop a novel framework, hazard identification and risk assessment of simultaneous operations (HIRAS), for identifying and evaluating potential hazards during concurrent tasks. The framework developed herein is expected to be an effective safety management tool that can help prevent accidents during these operations. To this end, the job location and hazard information in job safety analysis (JSA) were standardized into four attributes. The standardized information was then synchronized spatially and temporally to develop a HIRAS model that identifies and assesses the impact of hazards between operations. The model was tested using 40 JSA documents corresponding to maintenance operations at Company P, a South Korean steel-making company. The model was tested in two scenarios: one with planned operations and the other with unplanned operations in addition to planned operations. The performance evaluation results of the first scenario showed an F1-score of 98.33%. In this case, a recall of 97.52% means that the model identified 97.52% of the hazard-inducing factors. The second scenario was compared with the results of a review by six subject matter experts (SMEs). The comparison of the results identified by the SMEs and the model showed an accuracy of 89.3%. This study demonstrates the potential of JSA, which incorporates the domain knowledge of workers and can be used not only for individual tasks but also as a safety management tool for surrounding operations. Furthermore, by improving the plant maintenance work environment, it is expected to prevent accidents, protect workers’ lives and health, and contribute to the long-term sustainable management of companies.

Risk assessment for Na-Zn liquid metal batteries

Background Na-Zn liquid metal batteries, which operate at 600 °C, have recently been proposed as inexpensive stationary energy storage devices. As with any other electrochemical cell, their fabrication and operation involves certain risks, which need to be well understood in order to be minimised. Methods A risk assessment according to ISO 12100 is performed at the cell level for operating Na-Zn cells in the laboratory environment. Hazard identification and risk evaluation are systematically addressed, including a thorough literature review, theoretical calculations and selected experiments. Results Cell overpressure is found to be one of the main risks – and might be caused either by mistakes in battery production (humidity) or operation (over-charge/discharge). In terms of cell housing, the weakest component is clearly the feedthrough. Its failure might lead to the release of hazardous aerosols to the environment. In this context, the candidate electrolyte components LiCl and BaCl2 are especially dangerous, and should therefore be reduced or avoided if possible. Conclusions Overall, Na-Zn cells are expected to reach a very high safety level, similar to state-of-the-art ZEBRA technology, as they are not prone to thermal runaway. However, considering the still low TRL level and open questions concerning the durability of certain parts of their housing, the batteries should preferably be operated under a fume hood.

Hazard Identification of Well Test Operation in Drilling and Production Offshore Platform by HAZID

A significant portion of energy resources has been discovered in offshore sectors, leading to a continuous increase in the volume of activities and operations. Once a well is drilled and fluid extraction begins, all the reservoir parameters, start to change. well test operation is one of the most crucial tools for engineers to comprehend the behavior and parameters of hydrocarbon reservoirs. In this study, the hazards associated with the well test operations has been identified by using HAZID technique. A total of 189 risks were identified in the initial risk assessment, with 35 categorized as low risk, 88 as medium risk, and 66 as high risk and after implementing protection layers in the secondary risk assessment, the number of low risks incidents increased, while medium and high-risk incidents were reduced significantly. Most of the risks identified are associated with loading operations and sea transportation from the port to the drilling rig. Given that loading and unloading operations are among the most frequently repeated activities in well testing operations, it is determined that they play a critical role in the overall risk profile

Multi-hazard risk assessment analysis in La Palma: an approach for risk mitigation

BackgroundLa Palma, like many regions of the world, may be affected by various hazards, with different levels of susceptibility, which have a greater or lesser impact on society. In this context, a multi-risk approached model capable of estimating the total risk faced by the territory is required, considering the different hazards to which it is exposed (floods, earthquakes, volcanic eruptions and landslides) and the different conditions of vulnerability of both the population and the exposed assets.MethodsThe methodology employed in this study has been referred to as "multilayer single hazard", which consists of the aggregation or superposition of hazards located in the same space. As usual, the identification of the individual hazard of each one of them was carried out using heterogeneous methods, which is why an index is proposed to homogenize the hazards and make them comparable with each other. On the other hand, the model also integrates a prototype to evaluate vulnerability from a multiple perspective (vulnerability by hazard) and shows the aggregated information in maps at a medium representation scale (definition of 250 m).ResultsThe risk integration results show that 5% of the island is at high risk levels. Simultaneously, the south of the island is presented as the area that shows the highest risk by combining a high hazard, especially related to volcanic hazards, and a high exposure, as it is home to a significant volume of population.ConclusionsThe proposed methodology is also interesting because it can be replicated in other areas of study.

Mutagenicity and genotoxicity evaluation of 15 nitrosamine drug substance-related impurities in human TK6 cells

Nitrosamine drug substance-related impurities (NDSRIs) are a sub-category of N-nitrosamine drug impurities that share structural similarity to the corresponding active pharmaceutical ingredient. The mutagenicity of NDSRIs is poorly understood. We previously tested a series of NDSRIs using the Enhanced Ames Test (EAT). In this follow-up study, we further examined the genotoxicity and mutagenicity of 15 of these NDSRIs in human TK6 cells. Seven EAT-positive NDSRIs, including N-nitroso-nortriptyline, N-nitroso-fluoxetine, N-nitroso-desmethyl-diphenhydramine, N-nitroso-duloxetine, N-nitroso-lorcaserin, N-nitroso-varenicline, and N-nitroso-sertraline, induced concentration-dependent increases in micronuclei after bioactivation with hamster liver S9. These NDSRIs were also mutagenic in the TK and HPRT gene mutation assays, consistent with their positive EAT results. In the presence of hamster liver S9, the eight EAT-negative NDSRIs were negative in the micronucleus assay and negative for mutation induction. Using TK6 cells endogenously expressing a single human cytochrome P450 (CYP), we found that CYP2C19, CYP2B6, CYP2A6, and CYP3A4 are key enzymes activating the genotoxicity and mutagenicity of these NDSRIs. Overall, the hamster S9-mediated TK6 cell mutagenicity results agreed with those observed in the EAT, indicating consistency in the mutagenic responses produced by NDSRIs across different testing systems. These data support the use of EAT for hazard identification and safety assessment of NDSRIs.

Harnessing the power of ChatGPT to promote Construction Hazard Prevention through Design (CHPtD)

PurposeConstruction Hazard Prevention through Design (CHPtD) is recognized as a pivotal strategy for enhancing workplace safety. Despite its theoretical potential, practical implementation faces challenges, particularly regarding designers' familiarity with field-level operations and hazard recognition. This study aims to investigate whether ChatGPT can address these challenges by assisting in hazard recognition during CHPtD sessions.Design/methodology/approachThe research utilized a randomized controlled experiment to assess ChatGPT as an intervention in supporting hazard recognition during CHPtD sessions. The study involves 162 civil and construction engineering student participants, representing future professionals. Participants engaged in hazard recognition during CHPtD sessions either with or without the assistance of ChatGPT.FindingsParticipants who utilized ChatGPT during CHPtD sessions demonstrated a significant improvement in hazard recognition, identifying approximately 40% more hazards compared to those who did not use ChatGPT. These findings underscore the efficacy of ChatGPT in supporting CHPtD efforts.Practical implicationsThe results highlight the practical utility of harnessing ChatGPT in CHPtD sessions to enhance hazard recognition and ultimately promote workplace safety. By leveraging ChatGPT, designers and engineers can better anticipate and mitigate potential hazards during the design phase, thus creating a safer working environment for field workers.Originality/valueThis research contributes to addressing the challenges associated with implementing CHPtD by introducing ChatGPT as a valuable tool to support hazard recognition. By demonstrating the effectiveness of ChatGPT in enhancing hazard identification during CHPtD sessions, this study offers a novel approach to promoting the adoption of CHPtD and advancing workplace safety initiatives.

The Identification and Quantification of Hidden Hazards in Small Scale Reservoir Engineering Based on Deep Learning: Intelligent Perception for Safety of Small Reservoir Projects in Jiangxi Province

This study aims to enhance the detection and assessment of safety hazards in small-scale reservoir engineering using advanced image processing and deep learning techniques. Given the critical importance of small reservoirs in flood management, water supply, and ecological balance, the effective monitoring of their structural integrity is crucial. This paper developed a fully convolutional semantic segmentation method for hidden danger images of small reservoirs using an encoding–decoding structure, utilizing a deep learning framework of convolutional neural networks (CNNs) to process and analyze high-resolution images captured by unmanned aerial vehicles (UAVs). The method incorporated data augmentation and adaptive learning techniques to improve model accuracy under diverse environmental conditions. Finally, the quantification data of hidden dangers (length, width, area, etc.) were obtained by converting the image pixels to the actual size. Results demonstrate significant improvements in detecting structural deficiencies, such as cracks and seepage areas, with increased precision and recall rates compared to conventional methods, and the HHSN-25 network (Hidden Hazard Segmentation Network with 25 layers) proposed in this paper outperforms other methods. The main evaluation indicator, mIoU of HHSN-25, is higher than other methods, reaching 87.00%, and the Unet is 85.50%, and the Unet++ is 85.55%. The proposed model achieves reliable real-time performance, allowing for early warning and effective management of potential risks. This study contributes to the development of more efficient monitoring systems for small-scale reservoirs, enhancing their safety and operational sustainability.

Four years of landslide observation with anthropogenic loading as an additional trigger - Analysis of seasonal and annual variability of physical parameters

Determining the structure and evolution of landslides is crucial for geophysical hazard assessment. In this study, we employed an approach integrating the methodologies of multi-channel analysis of surface waves (MASW) and electrical conductivity to image temporal and spatial changes within a landslide in southern Poland. The area, located in the Outer Carpathians, experiences significant climate fluctuations, compounded by anthropogenic activities such as recreational skiing requiring artificial snow.Our combined seismic and electrical methods techniques reveal the landslide's susceptibility to environmental factors on both annual and seasonal scales. Additional analysis, including data clustering and remote sensing, identifies three distinct landslide zones with varying vulnerability to natural and anthropogenic influences.While focusing on a specific area, our approach has global applicability to similar mass movements. This research addresses a gap in understanding time-dependent geophysical observations of moisture-driven landslides, providing valuable insights for hazard identification and mitigation strategies.