Search

Commercial grain elevators are hazardous agro-manufacturing work environments where workers are prone to serious and life-threatening injuries. The aim of this study is to give insight into safety risks in grain handling facilities through information processing of workers’ compensation data on agro-manufacturing occupational incidents within commercial grain elevators in the Midwest region of the United States between 2008 and 2016. The severity of occupational incidents is determined by total dollar amount incurred on medical, indemnity, and other expenses in workers’ compensation claims. The most important factors that affect the cost escalation of occupational incidents are extracted using bootstrap partitioning method, and are applied as input for constructing two machine learning models: random forests decision trees, and naive Bayes. Both models show high accuracy (87.64% and 92.78% respectively) in predicting that a future claim is classified as either low or medium, severity. The models contribute to identifying high injury risk groups, and prevalent incident causes, allowing a more research-based focused intervention effort in grain handling workplaces. In addition, the results are applicable in forecasting cost severity of future claims, and identifying factors that contribute to the escalation of claims costs.

Creating safe work environment is significant in saving workers’ lives, improving corporates’ social responsibility and sustainable development. Pattern identification in occupational accidents is vital in elaborating efficient safety counter-measures aiming at improving prevention and mitigating outcomes of future incidents. The objective of this study is to identify patterns related to the occurrence of occupational accidents in non-farm agricultural work environments based on workers’ compensation claims data, using latent class clustering method as an un-supervised machine learning modeling approach. The result showed injury profiles and incident dynamics have low, average, and high levels of risks based on the main causes and outcomes of the injuries and the affected body part(s).

Fault diagnosis of bearings is essential in reducing failures and improving functionality and reliability of rotating machines. As vibration signals are non-linear and non-stationary, extracting features for dimension reduction and efficient fault detection is challenging. This study aims at evaluating performance of decision tree-based machine learning models in detection and classification of bearing fault data. A machine learning approach combining the tree-based classifiers with de-rived statistical features is proposed for localized fault classification. Statistical features are extracted from normal and faulty vibration signals though time do-main analysis to develop tree-based models of AdaBoost (AD), classification and regression trees (CART), LogitBoost trees (LBT), and Random Forest trees (RF). The results confirm that machine learning classifiers have satisfactory performance and strong generalization ability in fault detection, and provide practical models for classify running state of the bearing.

In California, bike fatalities increased by 8.1% from 2015 to 2016. Even though the benefits of wearing helmets in protecting cyclists against trauma in cycling crash has been determined, the use of helmets is still limited, and there is opposition against mandatory helmet use, particularly for adults. Therefore, exploring perceptions of adult cyclists regarding mandatory helmet use is a key element in understanding cyclists’ behavior, and determining the impact of mandatory helmet use on their cycling rate. The goal of this research is to identify sociodemographic characteristics and cycling behaviors that are associated with the use and non-use of bicycle helmets among adults, and to assess if the enforcement of a bicycle helmet law will result in a change in cycling rates. This research develops hybrid machine learning models to pinpoint the driving factors that explain adult cyclists’ behavior regarding helmet use laws.

Although machine learning methods have been used as an outcome prediction tool in many fields, their utilization in predicting incident outcome in occupational safety is relatively new. This study tests the performance of machine learning techniques in modeling and predicting occupational incidents severity with respect to accessible information of injured workers in agribusiness industries using workers’ compensation claims. More than 33,000 incidents within agribusiness industries in the Midwest of the United States for 2008–2016 were analyzed. The total cost of incidents was extracted and classified from workers’ compensation claims. Supervised machine learning algorithms for classification (support vector machines with linear, quadratic, and RBF kernels, Boosted Trees, and Naive Bayes) were applied. The models can predict injury severity classification based on injured body part, body group, nature of injury, nature group, cause of injury, cause group, and age and tenure of injured workers with the accuracy rate of 92–98%. The results emphasize the significance of quantitative analysis of empirical injury data in safety science, and contribute to enhanced understanding of injury patterns using predictive modeling along with safety experts’ perspectives with regulatory or managerial viewpoints. The predictive models obtained from this study can be used to augment the experience of safety professionals in agribusiness industries to improve safety intervention efforts.

Current maintenance intervals of mechanical systems are scheduled a priori based on the life of the system, resulting in expensive maintenance scheduling, and often undermining the safety of passengers. Going forward, the actual usage of a vehicle will be used to predict stresses in its structure, and therefore, to define a specific maintenance scheduling. Machine learning (ML) algorithms can be used to map a reduced set of data coming from real-time measurements of a structure into a detailed/high-fidelity finite element analysis (FEA) model of the same system. As a result, the FEA-based ML approach will directly estimate the stress distribution over the entire system during operations, thus improving the ability to define ad-hoc, safe, and efficient maintenance procedures. The paper initially presents a review of the current state-of-the-art of ML methods applied to finite elements. A surrogate finite element approach based on ML algorithms is also proposed to estimate the time-varying response of a one-dimensional beam. Several ML regression models, such as decision trees and artificial neural networks, have been developed, and their performance is compared for direct estimation of the stress distribution over a beam structure. The surrogate finite element models based on ML algorithms are able to estimate the response of the beam accurately, with artificial neural networks providing more accurate results.

Multiple studies show the benefits to biking safety of the use of helmets, but opponents to Bicycle Helmet Laws claim that a mandate on helmet usage would discourage cycling, therefore nullifying the advantages of helmet usage. It has been in fact shown that increasing the number of bicycle riders on the roads improves overall safety. At the end of 2019, however, the National Transportation Safety Board recommended the introduction of all-ages helmet laws to reduce fatalities involving cyclists. The goal of this research is to identify sociodemographic characteristics and cycling behaviors that are associated with the use and non-use of bicycle helmets among adults using statistical analysis of data collected via a survey questionnaire distributed in California, USA. The statistical analysis of data collected from adult participants in California helps to understand the relationship between adult cyclists’ sociodemographic factors and helmet-wearing behavior.

Detecting faulty condition of rolling-element bearings is significant in improving system reliability and preventing machine failure in industrial operations. In this paper, a machine learning pipeline is developed using filtered data through time domain features to train support vector machines with radial basis function, polynomial and linear kernels for multi-level fault diagnosis and classification. Overall accuracy rate and F-score values were used as figures of merit to evaluate and validate the performance of the machine learning model. SVM classifier showed significantly high overall accuracy rate of 91% to 99% and F-score of 0.81 to 0.99 with time domain statistical features due to the capability of this method in elimination of irrelevant features as well as reducing the dimensionality of the data. In addition, the high accuracy rate of SVMs in class-specific detection of localized bearing faults show the significant potential of data-driven classification modeling for fault detection in industrial and manufacturing operations.

Mining is known to be one of the most hazardous occupations in the world. Many serious accidents have occurred worldwide over the years in mining. Although there have been efforts to create a safer work environment for miners, the number of accidents occurring at the mining sites is still significant. Machine learning techniques and predictive analytics are becoming one of the leading resources to create safer work environments in the manufacturing and construction industries. These techniques are leveraged to generate actionable insights to improve decision-making. A large amount of mining safety-related data are available, and machine learning algorithms can be used to analyze the data. The use of machine learning techniques can significantly benefit the mining industry. Decision tree, random forest, and artificial neural networks were implemented to analyze the outcomes of mining accidents. These machine learning models were also used to predict days away from work. An accidents dataset provided by the Mine Safety and Health Administration was used to train the models. The models were trained separately on tabular data and narratives. The use of a synthetic data augmentation technique using word embedding was also investigated to tackle the data imbalance problem. Performance of all the models was compared with the performance of the traditional logistic regression model. The results show that models trained on narratives performed better than the models trained on structured/tabular data in predicting the outcome of the accident. The higher predictive power of the models trained on narratives led to the conclusion that the narratives have additional information relevant to the outcome of injury compared to the tabular entries. The models trained on tabular data had a lower mean squared error compared to the models trained on narratives while predicting the days away from work. The results highlight the importance of predictors, like shift start time, accident time, and mining experience in predicting the days away from work. It was found that the F1 score of all the underrepresented classes except one improved after the use of the data augmentation technique. This approach gave greater insight into the factors influencing the outcome of the accident and days away from work.

Agribusiness industries are among the most hazardous workplaces for non-fatal occupational injuries. The term &ldquo, post-incident state&rdquo, is used to describe the health status of an injured person when a non-fatal occupational injury has occurred, in the post-incident period when the worker returns to work, either immediately with zero days away from work (medical state) or after a disability period (disability state). An analysis of nearly 14,000 occupational incidents in agribusiness operations allowed for the classification of the post-incident state as medical or disability (77% and 23% of the cases, respectively). Due to substantial impacts of occupational incidents on labor-market outcomes, identifying factors that influence the severity of such incidents plays a significant role in improving workplace safety, protecting workers, and reducing costs of the post-incident state of an injury. In addition, the average costs of a disability state are significantly higher than those of a medical state. Therefore, this study aimed to identify the contributory factors to such post-incident states with logistic regression using information from workers&rsquo, compensation claims recorded between 2008 and 2016 in the Midwest region of the United States. The logistic regression equation was derived to calculate the odds of disability post-incident state. Results indicated that factors influencing the post-incident state included the injured body parts, injury nature, and worker&rsquo, s age, experience, and occupation, as well as the industry, and were statistically significant predictors of post-incident states. Specific incidents predicting disability outcomes included being caught in/between/under, fall/slip/trip injury, and strain/injury by. The methodology and estimation results provide insightful understanding of the factors influencing medical/disability injuries, in addition to beneficial references for developing effective countermeasures for prevention of occupational incidents.

Insurance practitioners rely on statistical models to predict future claims in order to provide financial protection. Proper predictive statistical modeling is more challenging when analyzing claims with lower frequency, but high costs. The paper investigated the use of predictive generalized linear models (GLMs) to address this challenge. Workers&rsquo, compensation claims with costs equal to or more than US$100,000 were analyzed in agribusiness industries in the Midwest of the USA from 2008 to 2016. Predictive GLMs were built with gamma, Weibull, and lognormal distributions using the lasso penalization method. Monte Carlo simulation models were developed to check the performance of predictive models in cost estimation. The results show that the GLM with gamma distribution has the highest predictivity power (R2 = 0.79). Injury characteristics and worker&rsquo, s occupation were predictive of large claims&rsquo, occurrence and costs. The conclusions of this study are useful in modifying and estimating insurance pricing within high-risk agribusiness industries. The approach of this study can be used as a framework to forecast workers&rsquo, compensation claims amounts with rare, high-cost events in other industries. This work is useful for insurance practitioners concerned with statistical and predictive modeling in financial risk analysis.