4.7 Article

Determination of workers? compliance to safety regulations using a spatio-temporal graph convolution network

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Computer Science, Artificial Intelligence

Hand Gesture Recognition of Methods-Time Measurement-1 Motions in Manual Assembly Tasks Using Graph Convolutional Networks

Alexander Riedel et al.

Summary: This paper introduces a novel minimally invasive approach using graph neural networks and a camera to recognize workers' hand motions. Through a two-stage neural network, the method provides accurate classification results in real-time. The study shows that the proposed approach can generate Methods-Time Measurement analysis tables.

APPLIED ARTIFICIAL INTELLIGENCE (2022)

Article Engineering, Multidisciplinary

A CNN-SVM study based on selected deep features for grapevine leaves classification

Murat Koklu et al.

Summary: This study uses deep learning-based classification to classify images of grapevine leaves. By extracting features and using SVM kernels for classification, a classification success rate of 97.60% is achieved.

MEASUREMENT (2022)

Article Computer Science, Information Systems

Estimating Parkinsonism Severity in Natural Gait Videos of Older Adults With Dementia

Andrea Sabo et al.

Summary: This study utilizes vision-based human pose-estimation technology to analyze drug-induced parkinsonism in gait, with promising applications in elderly dementia patients.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2022)

Article Computer Science, Artificial Intelligence

SEE: A proactive strategy-centric and deep learning-based ergonomic risk assessment system for risky posture recognition

Yu -Chi Lee et al.

Summary: This study proposes a holistic posture acquisition and ergonomic risk analysis model with a proactive strategy-oriented philosophy for developing a risk assessment system for WMSDs. By combining the CPM method and rapid entire body assessment method, the smart ergonomic explorer (SEE) system can accurately analyze working posture and evaluate total REBA scores.

ADVANCED ENGINEERING INFORMATICS (2022)

Article Engineering, Industrial

Measuring effects of safety-reminding interventions against risk habituation

Bogyeong Lee et al.

Summary: Despite advancements in automation, construction worksites still face labor-intensive tasks and accidents. This study examines the impact of risk habituation on safety behaviors and proposes intervention scenarios to delay habituation. The results suggest that behavior-feedback interventions are more effective in combating risk habituation.

SAFETY SCIENCE (2022)

Proceedings Paper Computer Science, Cybernetics

Exercise and Performance Learning Assistant System for Self-Practice Dynamic Yoga by OpenPose and Fuzzy Based Design

Shih-Wei Shen et al.

Summary: In this study, a learning assistant system based on OpenPose and fuzzy technologies was developed for self-practice dynamic Yoga at home. The system effectively detects and scores the corresponding video frames between the user and the instructor.

2022 10TH INTERNATIONAL CONFERENCE ON INFORMATION AND EDUCATION TECHNOLOGY (ICIET 2022) (2022)

Article Computer Science, Interdisciplinary Applications

Machine Learning-Based Risk Analysis for Construction Worker Safety from Ubiquitous Site Photos and Videos

Shuai Tang et al.

Summary: This paper introduces a vision-based method for predicting worker severity levels, achieving high accuracy and demonstrating the potential for near real-time worker safety detection and assessment using actively captured visual data on construction sites.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2021)

Article Computer Science, Artificial Intelligence

Unsupervised deep learning approach for network intrusion detection combining convolutional autoencoder and one-class SVM

Adel Binbusayyis et al.

Summary: This paper introduces an unsupervised deep learning approach for intrusion detection, which integrates a one-dimensional convolutional autoencoder with a one-class support vector machine as a classifier to simultaneously optimize feature representation and classification, aiming to improve detection performance.

APPLIED INTELLIGENCE (2021)

Article Computer Science, Interdisciplinary Applications

Automatic far-field camera calibration for construction scene analysis

Amin Assadzadeh et al.

Summary: Over the past decade, the use of cameras for safety monitoring and progress tracking on construction sites has increased significantly. This study proposes an automatic camera calibration framework utilizing convolutional neural networks for geometrical scene analysis and object detection. Experimental results show that the proposed method achieves a minimum accuracy of 90% in estimating proximity of points on the ground.

COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING (2021)

Article Computer Science, Information Systems

Face mask detection using YOLOv3 and faster R-CNN models: COVID-19 environment

Sunil Singh et al.

Summary: Wearing a face mask is one of the most effective solutions to prevent the spread of the COVID-19 virus, leading researchers to explore face mask detection technology using deep learning. Two state-of-the-art object detection models, YOLOv3 and faster R-CNN, have been used to monitor people wearing masks in public places, with comparisons made on precision rate and inference time.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

Article Computer Science, Information Systems

An efficient facial emotion recognition system using novel deep learning neural network-regression activation classifier

Anjani Suputri D. Devi et al.

Summary: In the field of computer vision, Facial Expression Recognition (FER) plays a significant role. A novel Deep Learning-based approach for FER is proposed, which includes multiple stages of processing and feature extraction to achieve accurate recognition of facial expressions using the DR classifier.

MULTIMEDIA TOOLS AND APPLICATIONS (2021)

Article Construction & Building Technology

Fighting against COVID-19: A novel deep learning model based on YOLO-v2 with ResNet-50 for medical face mask detection

Mohamed Loey et al.

Summary: Deep learning models have shown potential in object detection, particularly in identifying medical face masks for COVID-19 protection. The proposed model in this research achieved higher accuracy and precision compared to related works, with an adam optimizer reaching 81% average precision percentage.

SUSTAINABLE CITIES AND SOCIETY (2021)

Article Construction & Building Technology

Towards on-site hazards identification of improper use of personal protective equipment using deep learning-based geometric relationships and hierarchical scene graph

Shi Chen et al.

Summary: This study proposes a novel model and method to effectively identify the hazards of improper use of Personal Protective Equipment (PPE) by construction workers, providing assistance for safety monitoring work.

AUTOMATION IN CONSTRUCTION (2021)

Article Chemistry, Analytical

Fast Personal Protective Equipment Detection for Real Construction Sites Using Deep Learning Approaches

Zijian Wang et al.

Summary: This paper introduces an approach to train and evaluate eight deep learning detectors based on the YOLO architectures, aiming to improve the performance of existing PPE detectors for real construction sites. By constructing the CHV dataset considering real background, different gestures, and multiple PPE classes, the comparison among the eight models shows that YOLO v5x has the best mAP.

SENSORS (2021)

Article Computer Science, Artificial Intelligence

A real-time approach of diagnosing rice leaf disease using deep learning-based faster R-CNN framework

Bifta Sama Bari et al.

Summary: Early diagnosis and appropriate treatment of rice leaf infections are crucial for healthy rice plant growth; machine-driven disease diagnosis systems can alleviate the limitations of traditional methods; using the Faster R-CNN algorithm for real-time detection of rice leaf diseases is effective.

PEERJ COMPUTER SCIENCE (2021)

Article Transportation

Multilevel weather detection based on images: a machine learning approach with histogram of oriented gradient and local binary pattern-based features

Md Nasim Khan et al.

Summary: The study developed a trajectory-level weather detection system using texture-based features extracted from images, trained with machine learning classifiers and evaluated through a multilevel model. Results showed that the multilevel model outperformed SVM, RF, and GB models, with the best performance achieved using LBP features in terms of overall accuracy.

JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS (2021)

Article Engineering, Electrical & Electronic

Video SAR Moving Target Detection Using Dual Faster R-CNN

Liwu Wen et al.

Summary: The proposed joint moving target detection approach for video SAR utilizes a dual Faster R-CNN to combine shadow detection in the SAR image and Doppler energy detection in the RD spectrum domain. By using diverse features in different domains, the performance of moving target detection can be significantly improved, leading to fewer false alarms and acceptable missing alarms compared to classical methods.

IEEE JOURNAL OF SELECTED TOPICS IN APPLIED EARTH OBSERVATIONS AND REMOTE SENSING (2021)

Article Computer Science, Information Systems

Comparative Analysis of Intelligent Driving and Safety Assistance Systems Using YOLO and SSD Model of Deep Learning

Nidhi Sindhwani et al.

Summary: The paper proposes a system to reduce road accidents by using technology to alert drivers of potholes and distress on roads, and to send the information to authorities for repairs.

INTERNATIONAL JOURNAL OF INFORMATION SYSTEM MODELING AND DESIGN (2021)

Article Ergonomics

Improved safety checklist analysis approach using intelligent video surveillance in the construction industry: a case study

Shengyu Guo et al.

Summary: This article proposes an improved safety checklist analysis approach using intelligent video surveillance to replace on-site inspection in the construction industry. A case study on metro tunnel construction illustrates the process, showing that problems can be automatically identified and recorded, safety assessment can be done through remote scoring mechanism, and the efficiency of the approach can be tested through comparative analysis. Results indicate the feasibility of this improved approach for evaluating safety management performance at construction sites.

INTERNATIONAL JOURNAL OF OCCUPATIONAL SAFETY AND ERGONOMICS (2021)

Review Computer Science, Artificial Intelligence

Computer vision for behaviour-based safety in construction: A review and future directions

Weili Fang et al.

ADVANCED ENGINEERING INFORMATICS (2020)

Article Computer Science, Information Systems

An attentional spatial temporal graph convolutional network with co-occurrence feature learning for action recognition

Dong Tian et al.

MULTIMEDIA TOOLS AND APPLICATIONS (2020)

Article Construction & Building Technology

Deep learning for site safety: Real-time detection of personal protective equipment

Nipun D. Nath et al.

AUTOMATION IN CONSTRUCTION (2020)

Article Green & Sustainable Science & Technology

Investigating the Relation between Walkability and the Changes in Pedestrian Policy through Wearable Sensing

Jihwan Yoon et al.

SUSTAINABILITY (2020)

Article Computer Science, Interdisciplinary Applications

Vision-Based Framework for Intelligent Monitoring of Hardhat Wearing on Construction Sites

Bahaa Eddine Mneymneh et al.

JOURNAL OF COMPUTING IN CIVIL ENGINEERING (2019)

Article Computer Science, Artificial Intelligence

Real-time Yoga recognition using deep learning

Santosh Kumar Yadav et al.

NEURAL COMPUTING & APPLICATIONS (2019)

Article Engineering, Industrial

RGB-D ergonomic assessment system of adopted working postures

Ahmed Abobakr et al.

APPLIED ERGONOMICS (2019)

Article Engineering, Industrial

Janitor ergonomics and injuries in the safe workload ergonomic exposure project (SWEEP) study

Adam Schwartz et al.

APPLIED ERGONOMICS (2019)

Article Construction & Building Technology

Automatic detection of hardhats worn by construction personnel: A deep learning approach and benchmark dataset

Jixiu Wu et al.

AUTOMATION IN CONSTRUCTION (2019)

Review Construction & Building Technology

Wearable Sensing Technology Applications in Construction Safety and Health

Changbum R. Ahn et al.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2019)

Proceedings Paper Computer Science, Cybernetics

Activity Recognition Using ST-GCN with 3D Motion Data

Xin Cao et al.

UBICOMP/ISWC'19 ADJUNCT: PROCEEDINGS OF THE 2019 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS COMPUTING AND PROCEEDINGS OF THE 2019 ACM INTERNATIONAL SYMPOSIUM ON WEARABLE COMPUTERS (2019)

Article Construction & Building Technology

Application of dynamic time warping to the recognition of mixed equipment activities in cycle time measurement

Hyunsoo Kim et al.

AUTOMATION IN CONSTRUCTION (2018)

Article Construction & Building Technology

Falls from heights: A computer vision-based approach for safety harness detection

Weili Fang et al.

AUTOMATION IN CONSTRUCTION (2018)

Article Computer Science, Interdisciplinary Applications

An intelligent vision-based approach for helmet identification for work safety

Hao Wu et al.

COMPUTERS IN INDUSTRY (2018)

Article Construction & Building Technology

Trends of Fall Accidents in the US Construction Industry

Youngcheol Kang et al.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2017)

Article Construction & Building Technology

Trends of Fall Accidents in the US Construction Industry

Youngcheol Kang et al.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2017)

Proceedings Paper Computer Science, Artificial Intelligence

Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields

Zhe Cao et al.

30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017) (2017)

Article Computer Science, Artificial Intelligence

Construction performance monitoring via still images, time-lapse photos, and video streams: Now, tomorrow, and the future

Jun Yang et al.

ADVANCED ENGINEERING INFORMATICS (2015)

Article Computer Science, Artificial Intelligence

Computer vision techniques for construction safety and health monitoring

JoonOh Seo et al.

ADVANCED ENGINEERING INFORMATICS (2015)

Article Ergonomics

Behavior-based safety on construction sites: A case study

Rafiq M. Choudhry

ACCIDENT ANALYSIS AND PREVENTION (2014)

Proceedings Paper Computer Science, Artificial Intelligence

2D Human Pose Estimation: New Benchmark and State of the Art Analysis

Mykhaylo Andriluka et al.

2014 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR) (2014)

Article Engineering, Civil

Enhancing Construction Worker Safety Performance Using Leading Indicators

Sathyanarayanan Rajendran

PRACTICE PERIODICAL ON STRUCTURAL DESIGN AND CONSTRUCTION (2013)

Article Ergonomics

Safety rules and regulations on mine sites - The problem and a solution

D Laurence

JOURNAL OF SAFETY RESEARCH (2005)

Article Construction & Building Technology

Viability of designing for construction worker safety

JA Gambatese et al.

JOURNAL OF CONSTRUCTION ENGINEERING AND MANAGEMENT (2005)