Current Status and Future Directions of Deep Learning Applications for Safety Management in Construction

2021 ◽  
Vol 13 (24) ◽  
pp. 13579
Author(s):  
Hieu T. T. L. Pham ◽  
Mahdi Rafieizonooz ◽  
SangUk Han ◽  
Dong-Eun Lee
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Safety Management ◽  
High Reliability ◽  
Technical Aspect ◽  
Construction Safety ◽  
Current Status ◽  
Future Directions ◽  
Main Research ◽  
Safety Issues

The application of deep learning (DL) for solving construction safety issues has achieved remarkable results in recent years that are superior to traditional methods. However, there is limited literature examining the links between DL and safety management and highlighting the contributions of DL studies in practice. Thus, this study aims to synthesize the current status of DL studies on construction safety and outline practical challenges and future opportunities. A total of 66 influential construction safety articles were analyzed from a technical aspect, such as convolutional neural networks, recurrent neural networks, and general neural networks. In the context of safety management, three main research directions were identified: utilizing DL for behaviors, physical conditions, and management issues. Overall, applying DL can resolve important safety challenges with high reliability; therein the CNN-based method and behaviors were the most applied directions with percentages of 75% and 67%, respectively. Based on the review findings, three future opportunities aiming to address the corresponding limitations were proposed: expanding a comprehensive dataset, improving technical restrictions due to occlusions, and identifying individuals who performed unsafe behaviors. This review thus may allow the identification of key areas and future directions where further research efforts need to be made with priority.

A Review of Recent Deep Learning Models in COVID-19 Diagnosis

2021 ◽  
Vol 6 (5) ◽  
pp. 10-15
Author(s):  
Ela Bhattacharya ◽  
D. Bhattacharya
Keyword(s):  
Artificial Intelligence ◽  
Neural Networks ◽  
Deep Learning ◽  
Deep Neural Networks ◽  
Test Results ◽  
Learning Models ◽  
Future Directions ◽  
Human Contact ◽  
The World ◽  
Short Span

COVID-19 has emerged as the latest worrisome pandemic, which is reported to have its outbreak in Wuhan, China. The infection spreads by means of human contact, as a result, it has caused massive infections across 200 countries around the world. Artificial intelligence has likewise contributed to managing the COVID-19 pandemic in various aspects within a short span of time. Deep Neural Networks that are explored in this paper have contributed to the detection of COVID-19 from imaging sources. The datasets, pre-processing, segmentation, feature extraction, classification and test results which can be useful for discovering future directions in the domain of automatic diagnosis of the disease, utilizing artificial intelligence-based frameworks, have been investigated in this paper.

scholarly journals Construction Safety during Pandemics: Learning from the Xinjia Express Hotel Collapse during COVID-19 in China

2021 ◽  
Vol 18 (21) ◽  
pp. 11498
Author(s):  
Yu-Jie Huang ◽  
Jing Tao ◽  
Fu-Qiang Yang ◽  
Chao Chen
Keyword(s):  
Safety Management ◽  
Construction Safety ◽  
Causal Factors ◽  
Safety Issues ◽  
Severe Accidents ◽  
Safety Recommendations ◽  
Property Losses ◽  
Construction Accidents ◽  
The Relationship ◽  
Interactive Feedback

Many construction accidents occur in China each year, leading to a large number of deaths, injures, and property losses. Due to the outbreak of COVID-19, little attention is paid to construction safety, resulting in severe accidents. To prevent construction accidents and learn to how address safety issues in future pandemics, this study proposed an improved STAMP (Systems Theoretic Accident Modeling and Processes) model to analyze the collapse accident of the Xinjia Express Hotel used for COVID-19 quarantine in China. Through the application of the STAMP approach, the causes of the construction accident and the relationship between various causal factors are analyzed from a systematic perspective. The identified causes are divided into five categories: contractors, management of organizations, technical methods, participants, and interactive feedback. Finally, safety recommendations are drawn from this study to improve construction safety and safety management in pandemics.

scholarly journals Construction safety ontology development and alignment with industry foundation classes (IFC)

2022 ◽  
Vol 27 ◽  
pp. 94-108
Author(s):  
Karim Farghaly ◽  
Ranjith K. Soman ◽  
William Collinge ◽  
Mojgan Hadi Mosleh ◽  
Patrick Manu ◽  
...  
Keyword(s):  
Safety Management ◽  
Health And Safety ◽  
Construction Safety ◽  
Ontology Development ◽  
Conceptual Information ◽  
Safety Issues ◽  
Knowledge Based ◽  
Research Award ◽  
Safety Risks ◽  
Construction Safety Management

A pronounced gap often exists between expected and actual safety performance in the construction industry. The multifaceted causes of this performance gap are resulting from the misalignment between design assumptions and actual construction processes that take place on-site. In general, critical factors are rooted in the lack of interoperability around the building and work-environment information due to its heterogeneous nature. To overcome the interoperability challenge in safety management, this paper represents the development of an ontological model consisting of terms and relationships between these terms, creating a conceptual information model for construction safety management and linking that ontology to IfcOWL. The developed ontology, named Safety and Health Exchange (SHE), comprises eight concepts and their relationships required to identify and manage safety risks in the design and planning stages. The main concepts of the developed ontology are identified based on reviewing accident cases from 165 Reporting of Injuries, Diseases and Dangerous Occurrences Regulations (RIDDOR) and 31 Press Releases from the database of the Health and Safety Executive (HSE) in the United Kingdom. Consequently, a semantic mapping between the developed ontology and IfcOWL (the most popular ontology and schema for interoperability in the AEC sector) is proposed. Then several SPARQL queries were developed and implemented to evaluate the semantic consistency of the developed ontology and the cross-mapping. The proposed ontology and cross-mapping gained recognition for its innovation in utilising OpenBIM and won the BuildingSMART professional research award 2020. This work could facilitate developing a knowledge-based system in the BIM environment to assist designers in addressing health and safety issues during the design and planning phases in the construction sector.

scholarly journals Removing Confounding Factors Associated Weights in Deep Neural Networks Improves the Prediction Accuracy for Healthcare Applications

2018 ◽  
Author(s):  
Haohan Wang ◽  
Zhenglin Wu ◽  
Eric P. Xing
Keyword(s):  
Neural Networks ◽  
Deep Learning ◽  
Prediction Accuracy ◽  
High Reliability ◽  
Disease Status ◽  
Distinct Advantage ◽  
Confounding Factors ◽  
Healthcare Applications ◽  
Learning Methods ◽  
Brain Wave

The proliferation of healthcare data has brought the opportunities of applying data-driven approaches, such as machine learning methods, to assist diagnosis. Recently, many deep learning methods have been shown with impressive successes in predicting disease status with raw input data. However, the “black-box” nature of deep learning and the high-reliability requirement of biomedical applications have created new challenges regarding the existence of confounding factors. In this paper, with a brief argument that inappropriate handling of confounding factors will lead to models’ sub-optimal performance in real-world applications, we present an efficient method that can remove the influences of confounding factors such as age or gender to improve the across-cohort prediction accuracy of neural networks. One distinct advantage of our method is that it only requires minimal changes of the baseline model’s architecture so that it can be plugged into most of the existing neu-ral networks. We conduct experiments across CT-scan, MRA, and EEG brain wave with convolutional neural networks and LSTM to verify the efficiency of our method.

Sign in / Sign up

Export Citation Format

Share Document