Construction equipment related accidents, such as collisions between equipment and pedestrian workers, pose a major challenge to occupational safety at construction sites. Decrement of operators' ...hazard detection ability resulting from attention failure is a leading cause of these accidents. Although mental fatigue induced by prolonged and monotonous operating tasks is known as the primary cause of this type of failure, little is revealed on how mental fatigue influences operators' ability to detect hazardous situations and associated visual attention features. To address this issue, this study uses wearable eye-tracking technology to evaluate the impact of mental fatigue on operators' ability in hazard detection and the corresponding patterns of visual attention allocation. Twelve healthy participants performed a simulated excavator operating task in a laboratory experiment. Subjective mental fatigue assessment, hazard detection task performance, and eye movement metrics were recorded and analyzed. In the experiment, mental fatigue was effectively induced and manipulated by a Time-On-Operating (TOO) procedure. Results revealed that operators' hazard detection ability decreased with the increase in subjective mental fatigue level, reflected by significant increases in reaction time for hazards and the number of misdetections. Attention allocation-related data were further analyzed to explain the specific manifestations of hazard detection failure in visual attention. The results indicated that the decrease of operators' hazard detection ability is associated with the changes of the distributions of fixation and gaze point while mental fatigue level increases. Consequently, clear observation of surrounding hazards and related details becomes difficult for operators. The findings demonstrate the effectiveness of wearable eye-tracking technology in measuring and quantifying operators' mental fatigue and hazard detection ability. More importantly, the findings offer insights into the impairing effect of mental fatigue on operators' hazard detection ability from a visual attention perspective. Such insights provide a solid basis for developing effective safety interventions and attentional guidance-based safety training methods to mitigate relevant site accidents.
•Mental fatigue induced by prolonged operating task is assessed by utilizing wearable eye tracker.•The decrement of hazard detection ability is quantified using eye movement metrics.•The impairing effect of mental fatigue on operators' ability to detect hazard was found.•Interventions and training methods have been discussed to reduce hazard detection failures.
Plastic electronic waste (E-waste) is constantly growing around the world owing to the rapid increase in industrialization, urbanization, and population. The current annual production rate of E-waste ...is 3-4% in the world and is expected to increase to 55 million tons per year by 2025. To reduce the detrimental impact on the environment and save natural resources, one of the best solutions is to incorporate waste plastic in the construction industry to produce green concrete. This study examines the use of manufactured plastic coarse aggregate (PCA) obtained from E-waste as a partial replacement of natural coarse aggregate (NCA) in concrete. Six types of concrete mix with 10%, 20%, 30%, 40%, and 50% substitution of NCA (by volume) with PCA are prepared and tested. This study investigates the effect of manufactured PCA on the fresh and hardened characteristics of concrete. The properties of recycled plastic aggregate concrete (RPAC) studied include workability, fresh density, dry density, compressive strength (CS), splitting tensile strength (STS), flexural strength (FS), sorptivity coefficient, abrasion resistance, ultrasonic pulse velocity (UPV), and alternate wetting and drying (W-D). The results indicate that the CS, STS, and FS of RPAC declined in the range of 9.9-52.7%, 7.8-47.5%, and 11-39.4%, respectively, for substitution ratios of 10-50%. However, the results also indicate that the incorporation of PCA (10-50%) improved the workability and durability characteristics of concrete. A significant decrement in the sorptivity coefficient, abrasion loss, and UPV value was observed with an increasing amount of PCA. Furthermore, RPAC containing different percentages of PCA revealed better results against alternate W-D cycles with respect to ordinary concrete.
AbstractHigh prevalence of musculoskeletal disorders among construction workers pose challenges to the productivity and occupational health of the construction industry. To mitigate the risk of ...musculoskeletal disorders, construction managers need to deepen their understanding of the physical and biomechanical demands of various construction tasks so that appropriate policies and preventive measures can be implemented. Among various construction trades, rebar workers are highly susceptible to lower-back disorders (LBDs) given the physically demanding nature of their work tasks. In particular, rebar tying is considered to be closely related to LBDs because it exposes workers to multiple ergonomic risk factors (repetitive works in prolonged static and awkward postures). The objective of the current study was to compare the differences in lumbar biomechanics during three typical rebar tying postures: stooping, one-legged kneeling, and squatting. Biomechanical variables including trunk muscle activity and trunk kinematics were measured by surface electromyography and motion sensors, respectively. Ten healthy male participants performed a simulated rebar tying task in each of the three postures in a laboratory setting. Repeated measures analysis of variance showed that while each posture has its unique trunk kinematic characteristics, all these postures involved excessive trunk inclination that exceeded the internationally recommended trunk inclination angle of 60° for static working postures. Of the three postures, stooping posture demonstrated a significant reduction in electromyographic activity of lumbar muscles (a reduction in 60–80% of muscle activity as compared to the other two postures). The reduced muscle activity may shift the loading to passive spinal structures (e.g., spinal ligaments and joint capsules), which is known to be a risk factor for LBD development. Collectively, the results from this study may help explain the high prevalence of LBDs in rebar workers. Future studies are warranted to confirm the findings at construction sites and to develop appropriate ergonomic approaches for rebar workers.
Construction workers are prone to physical and mental stress because of the characteristics of the construction industry. Researchers and practitioners agree that physical and mental stress should be ...proactively managed to mitigate their ill-effects which range from making errors to causing accidents and short term to long term illnesses. Accordingly, numerous research endeavors have pursued automated solutions for their monitoring to replace manual and subjective physical and mental stress monitoring. While these studies have been successful, they attempted to monitor either physical stress or mental stress at a time. Studies have shown that many times, construction workers are simultaneously exposed to both, physical and mental stress, necessitating automated simultaneous monitoring of physical and mental stress for more comprehensive workload evaluation. Therefore, the aim of the current study is to assess the possibility of accurately monitoring physical and mental stress simultaneously using physiological measures and machine learning algorithms. For the purpose, experiments were conducted that comprised of physical and mental stress scenarios. The results showed that using 56 features derived from heart rate, skin temperature, breathing rate and skin conductance, an accuracy of 94.7% was achieved for simultaneous physical and mental stress monitoring. Additionally, the study further investigated the impact of varying the features and physiological measures and discussed the potential future work in this direction. Overall, this study for the first time, demonstrated that it is possible to simultaneously monitor physical and mental stress with high accuracy. Moreover, it has laid the foundation for future studies to enable simultaneous physical and mental stress monitoring on actual job sites.
•Experiments were conducted to simultaneously monitor physical and mental stress•Physiological sensors were used along with machine learning algorithms•High accuracy was observed for simultaneous monitoring•Variation and selection of different features are also discussed•Implications and future research directions are also discussed
Construction equipment operations that require high levels of attention can cause mental fatigue, which can lead to inefficiencies and accidents. Previous studies classified mental fatigue using ...single-modal data with acceptable accuracy. However, mental fatigue is a multimodal problem, and no single modality is superior. Moreover, none of the previous studies in construction industry have investigated multimodal data fusion for classifying mental fatigue and whether such an approach would improve mental fatigue detection. This study proposes a novel approach using three machine learning models and multimodal data fusion to classify mental fatigue states. Electroencephalography, electrodermal activity, and video signals were acquired during an excavation operation, and the decision tree model using multimodal sensor data fusion outperformed other models with 96.2% accuracy and 96.175%–98.231% F1 scores. Multimodal sensor data fusion can aid in the development of a real-time system to classify mental fatigue and improve safety management at construction sites.
•Mental fatigue states were classified among equipment operators.•The EEG, EDA, and facial feature data of the operators were acquired during construction operations.•The performance of the three machine learning models was assessed.•High accuracy was achieved by integrating the data from all the sensors.•The decision tree classifier achieved the best performance with an accuracy of 96.2%.
A better understanding of circumstances contributing to the severity outcome of traffic crashes is an important goal of road safety studies. An in-depth crash injury severity analysis is vital for ...the proactive implementation of appropriate mitigation strategies. This study proposes an improved feed-forward neural network (FFNN) model for predicting injury severity associated with individual crashes using three years (2017-2019) of crash data collected along 15 rural highways in the Kingdom of Saudi Arabia (KSA). A total of 12,566 crashes were recorded during the study period with a binary injury severity outcome (fatal or non-fatal injury) for the variable to be predicted. FFNN architecture with back-propagation (BP) as a training algorithm, logistic as activation function, and six number of hidden neurons in the hidden layer yielded the best model performance. Results of model prediction for the test data were analyzed using different evaluation metrics such as overall accuracy, sensitivity, and specificity. Prediction results showed the adequacy and robust performance of the proposed method. A detailed sensitivity analysis of the optimized NN was also performed to show the impact and relative influence of different predictor variables on resulting crash injury severity. The sensitivity analysis results indicated that factors such as traffic volume, average travel speeds, weather conditions, on-site damage conditions, road and vehicle type, and involvement of pedestrians are the most sensitive variables. The methods applied in this study could be used in big data analysis of crash data, which can serve as a rapid-useful tool for policymakers to improve highway safety.
In the construction industry, the operator's mental fatigue is one of the most important causes of construction equipment-related accidents. Mental fatigue can easily lead to poor performance of ...construction equipment operations and accidents in the worst case scenario. Hence, it is necessary to propose an objective method that can accurately detect multiple levels of mental fatigue of construction equipment operators. To address such issue, this paper develops a novel method to identify and classify operator's multi-level mental fatigue using wearable eye-tracking technology. For the purpose, six participants were recruited to perform a simulated excavator operation experiment to obtain relevant data. First, a Toeplitz Inverse Covariance-Based Clustering (TICC) method was used to determine the number of levels of mental fatigue using relevant subjective and objective data collected during the experiments. The results revealed the number of mental fatigue levels to be 3 using TICC-based method. Second, four eye movement feature-sets suitable for different construction scenarios were extracted and supervised learning algorithms were used to classify multi-level mental fatigue of the operator. The classification performance analysis of the supervised learning algorithms showed Support Vector Machine (SVM) was the most suitable algorithm to classify mental fatigue in the face of various construction scenarios and subject bias (accuracy between 79.5% and 85.0%). Overall, this study demonstrates the feasibility of applying wearable eye-tracking technology to identify and classify the mental fatigue of construction equipment operators.
•A novel approach for detecting construction equipment operator’s mental fatigue based on eye movement data is proposed.•TICC method is adopted to identify multiple levels of mental fatigue and label relevant eye movement data.•Supervised learning algorithms are used to learn four different sets of eye movement features.•Results show that SVM and LDA yield high classification performance.•The feasibility of the proposed method for detecting multi-level mental fatigue is discussed.
Construction workers' posture-related data is closely connected with their safety, health, and productivity performance. The importance of posture-related data has drawn the attention of researchers ...in construction management and other fields. Accordingly, many data collection methods have been developed and applied to collect posture-related data. Despite the importance of workers' posture-related data, there lacks a review of previous data collection methods in the construction industry. This paper fills the research gap by reviewing previous methods to collect posture-related data for construction workers via 1) summarizing working principles and applications of posture-related data collection in construction management, which demonstrates the extensive use of motion sensors and Red-Green-Blue (RGB) cameras in posture-related data collection, 2) comparing the above methods based on data quality and feasibility on construction sites, which reveals the reason why motion sensors and RGB cameras have been prevalent in previous studies, 3) revealing research gaps of posture-related data collection tools and applications, and providing possible future research directions.
•Pose-related data collection methods in construction were compared based on data quality and applicability.•The review demonstrated the extensive use of motion sensors and RGB cameras and revealed the reasons.•Research gaps of pose-related data collection tools and applications were revealed.•Possible future research directions were suggested.
AbstractOverexertion-related construction activities are identified as a leading cause of work-related musculoskeletal disorders (WMSDs) among construction workers. However, few studies have focused ...on the automated recognition of overexertion-related construction workers’ activities as well as assessing ergonomic risk levels, which may help to minimize WMSDs. Therefore, this study examined the feasibility of using acceleration and foot plantar pressure distribution data captured by a wearable insole pressure system for automated recognition of overexertion-related construction workers’ activities and for assessing ergonomic risk levels. The proposed approach was tested by simulating overexertion-related construction activities in a laboratory setting. The classification accuracy of five types of supervised machine learning classifiers was evaluated with different window sizes to investigate classification performance and further estimate physical intensity, activity duration, and frequency information. Cross-validation results showed that the Random Forest classifier with a 2.56-s window size achieved the best classification accuracy of 98.3% and a sensitivity of more than 95.8% for each category of activities using the best features of combined data set. Furthermore, the estimation of corresponding ergonomic risk levels was within the same level of risk. The findings may help to develop a noninvasive wearable insole pressure system for the continuous monitoring and automated activity recognition, which could assist researchers and safety managers in identifying and assessing overexertion-related construction activities for minimizing the development of WMSDs’ risks among construction workers.
Among the numerous work-related risk factors, construction workers are often exposed to awkward working postures that may lead them to develop work-related musculoskeletal disorders (WMSDs). To ...mitigate WMSDs among construction workers, awkward working posture recognition is the first step in proactive WMSD prevention. Several researchers have proposed wearable sensor-based systems and machine learning classifiers for awkward posture recognition. However, these wearable sensor-based systems (e.g., surface electromyography) are either intrusive or require attaching multiple sensors on workers' bodies, which may lead to workers' discomfort and systemic instability, thus, limiting their application on construction sites. In addition, machine learning classifiers are limited to human-specific shallow features which influence model performance. To address these limitations, this study proposes a novel approach by using wearable insole pressure system and recurrent neural network (RNN) models, which automate feature extraction and are widely used for sequential data classification. Therefore, the research objective is to automatically recognize and classify different types of awkward working postures in construction by using deep learning-based networks and wearable insole sensor data. The classification performance of three RNN-based deep learning models, namely: (1) long-short term memory (LSTM), (2) bidirectional LSTM (Bi-LSTM), and (3) gated recurrent units (GRU), was evaluated using plantar pressure data captured by a wearable insole system from workers on construction sites. The experimental results show that GRU model outperforms the other RNN-based deep learning models with a high accuracy of 99.01% and F1-score between 93.19% and 99.39%. These results demonstrate that GRU models can be employed to learn sequential plantar pressure patterns captured by a wearable insole system to recognize and classify different types of awkward working postures. The findings of this study contribute to wearable sensor-based posture-related recognition and classification, thus, enhancing construction workers' health and safety.
•Awkward working postures in construction were classified from wearable insole data.•The performance of three types of RNN-based deep learning models was assessed.•GRU model achieved the best performance with an accuracy of 99.01%.•The proposed approach contributes to automated recognition of WMSDs risk factors.