No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Off-road truck-related accidents in US mines
Abstract
Introduction:
Off-road trucks are one of the major sources of equipment-related accidents in the U.S. mining industries. A systematic analysis of all off-road truck-related accidents, injuries, and illnesses, which are reported and published by the Mine Safety and Health Administration (MSHA), is expected to provide practical insights for identifying the accident patterns and trends in the available raw database. Therefore, appropriate safety management measures can be administered and implemented based on these accident patterns/trends.
Methods:
A hybrid clustering-classification methodology using K-means clustering and gene expression programming (GEP) is proposed for the analysis of severe and non-severe off-road truck-related injuries at U.S. mines. Using the GEP sub-model, a small subset of the 36 recorded attributes was found to be correlated to the severity level.
Results:
Given the set of specified attributes, the clustering sub-model was able to cluster the accident records into 5 distinct groups. For instance, the first cluster contained accidents related to minerals processing mills and coal preparation plants (91%). More than two-thirds of the victims in this cluster had less than 5years of job experience. This cluster was associated with the highest percentage of severe injuries (22 severe accidents, 3.4%). Almost 50% of all accidents in this cluster occurred at stone operations. Similarly, the other four clusters were characterized to highlight important patterns that can be used to determine areas of focus for safety initiatives.
Conclusions:
The identified clusters of accidents may play a vital role in the prevention of severe injuries in mining. Further research into the cluster attributes and identified patterns will be necessary to determine how these factors can be mitigated to reduce the risk of severe injuries.
Practical application:
Analyzing injury data using data mining techniques provides some insight into attributes that are associated with high accuracies for predicting injury severity.
... Appendixes A and B contain the data extracted from each study. Throughout th analysis, it was possible to divide them into the following source data groups: nine studie used Mine Safety and Health Administration (MSHA) data [6,30,[42][43][44][45][46][47][48], two used dat from the Directorate General of Mines Safety (DGMS) [7,34], one was from the Directorat Technique and Environment of Mineral and Coal (DTEMC) [8], one was from the Shan dong Coal Mine Safety Supervision Bureau (SCMSSB) [49], and the other three were cas studies [50][51][52]. As most of the studies collected data from official sources, just one pre sented some information regarding sample [52]. ...
... Appendices A and B contain the data extracted from each study. Throughout the analysis, it was possible to divide them into the following source data groups: nine studies used Mine Safety and Health Administration (MSHA) data [6,30,[42][43][44][45][46][47][48], two used data from the Directorate General of Mines Safety (DGMS) [7,34], one was from the Directorate Technique and Environment of Mineral and Coal (DTEMC) [8], one was from the Shandong Coal Mine Safety Supervision Bureau (SCMSSB) [49], and the other three were case studies [50][51][52]. As most of the studies collected data from official sources, just one presented some information regarding sample [52]. ...
... Not mentioned Not mentioned Collision with another vehicle [42,45,47]; collision with another worker [45]; collision with pedestrian [42]; contact with public utility lines [42]; fall from vehicle [47]; rollovers [42,45] fall of ground [46]; Struck by equipment [50]; caught between [50]; got hit by equipment part [50]; slip/trip from the equipment [50]; ...
Surface and underground mining, due to its technical challenges, is considered a hazardous industry. The great majority of accidents and fatalities are frequently associated with ineffective or inappropriate training methods. Knowing that knowledge of occupational accident causes plays a significant role in safety management systems, it is important to systematise this kind of information. The primary objective of this systematic review was to find evidence of work-related accidents involving machinery and their causes and, thus, to provide relevant data available to improve the mining project (design). The Preferred Reporting of Items for Systematic Reviews and Meta-Analyses (PRISMA) Statement methodology was used to conduct the review. This paper provides the main research results based on a systematic review protocol registered in the International Prospective Register of Systematic Reviews (PROSPERO), where the research strategy, information sources, and eligibility criteria are provided. From the 3071 articles identified, 16 were considered eligible and added to the study. Results are presented in a narrative-based form, with additional data provided in descriptive tables. The data analysed showed that the equipment often related to mining accidents are conveyor belts, haul trucks, and dumpers, especially during maintenance or repair activities. Attention should be paid to powered tools. Effective monitoring and machine operation control are some of the stated measures to minimise accidents. Particular attention should be paid to less experienced and senior workers, mainly through fatigue control, workload management, and appropriate training programs.
... Dindarloo et al. [18] focused their study on truck-related accidents, using data from MSHA (2000MSHA ( -2012. From the dataset, 5,831 injuries (both severe and nonsevere) and 125 severe records that affected 140 employees were identified. ...
... Failure to wear seatbelts were also associated with several loader and truck accidents [1,12]. Not following the safe working procedure or standard operating procedures, or even unsafe or careless actions also may be the cause of accidents [3,18]. Failure to recognise adverse geological conditions, to respect the loader's working area, to maintain adequate berms, lack of warning signs and appropriate mine maps, inadequate provision for safety level and failure to adjust to poor weather conditions are all worker behaviours that pose a significant threat [12,14]. ...
... Loss-of-control of the equipment was found to be the leading source of machine-related fatalities in surface mining [4]. Mechanical failures were also pointed out [12,14,18]. In Kecojevic & Radomsky [12], other causes were stressed, such as collision with pedestrians or with another vehicle, rollovers, contact with public utility lines and slope failure. ...
The extractive industry is simultaneously one of the human civilisation pillars for the resources it provides, but also one of those with the highest accident index. The quarries exploitation, amongst all extractive industry activities, being considered a high-risk occupation in which, due to the development of their respective professional activities, the workers are exposed to risks that may impact on their health as well as in their physical integrity. This work aimed to identify risk assessment methods specifically used in the open pit mining industry. The research of information was based on the PRISMA methodology, where 12 databases with the appropriate keywords were searched. A total of 38,594 articles were obtained, and 42 were selected after the sorting process. It was verified that the risk assessment methods specifically addressed to the extractive industry were fundamentally destined for environmental and geological risks; for occupational risks, general evaluation methods were used. This scenario leaves open the necessity of developing methods specifically aimed at assessing the accident risk in the open pit mining industry.
... Dindarloo et al. [18] focused their study on truck-related accidents, using data from MSHA (2000-2012). From the dataset, 50831 injuries (both severe and non-severe) and 125 severe records that affected 140 employees were identified. ...
... Failure to wear seatbelts were also associated with several loader and truck accidents [1,12]. Not following the safe working procedure or standard operating procedures, or even unsafe or careless actions also may be the cause of accidents [3,18]. Failure to recognise adverse geological conditions, to respect the loader's working area, to maintain adequate berms, lack of warning signs and appropriate mine maps, inadequate provision for safety level and failure to adjust to poor weather conditions are all worker behaviours that pose a significant threat [12,14]. ...
... Loss-of-control of the equipment was found to be the leading source of machine-related fatalities in surface mining [4]. Mechanical failures were also pointed out [12,14,18]. In Kecojevic and Radomsky [12], other causes were stressed, such as collision with pedestrians or with another vehicle, rollovers, contact with public utility lines and slope failure. ...
The mining industry is one of the most challenging environments concerning safety issues. Although most of the hazards are well identified and studied, the impact of mining equipment on accidents is still not fully comprehended. PRISMA statement methodology was used in order to conduct proper research regarding this gap; from the 2594 identified papers, only 14 answered the main exclusion and inclusion criteria and were included in the study. The primary results show that haul truck, dumpers and conveyors are the equipment with higher impact on the accident rates and that proper training programs and other safety measures would help decrease the tendency.
... Firstly, GEE accounts for the possible serial correlation. 5 Secondly, GEE allows for dependent variable distribution specification, which results in a more accurate estimation. Thirdly, robust standard errors in unbalanced panel data can be used [22]. ...
... Going beyond univariate time series forecasting, https://towardsdatascience.com/var-and-panel-datamodels-the-powerhouse-of-multivariate-forecasting-techniques-22b8d8888141 e accessed 18 June 2020). 5 Serial correlation is the relationship between a given variable and a lagged version of itself over various time intervals. It measures the relationship between a variable's current value given its past values. ...
A retrospective study on accident analysis of the United States mines for 36 years was achieved using statistical analysis on the MSHA's accident databases between 1983 and 2018. A regression model of generalized estimation equation (GEE) was used for unbalanced panel data that provided 95,812 observations for 19,924 mine-ID-year in aggregate, coal, metal, and non-metal mines. The contributions of various parameters, including mine type, injured body part, days lost, age, and experience on the rate of accidents and injuries were investigated across the commodity types. The results showed coal miners in the East region are at a higher risk of accident. The results of regression analysis show that mine-tenured workers have a vital role in accident frequencies. Analysis of the injured body part on the injury rate indicates that the upper body injuries are the most significant among all mine types. Also, the fatality rate is significant in aggregate, and coal mines in comparison with metal and non-metal mines.
... Alla et al., 2020), accidents involving mining vehicles are reported regularly (Zhang et al., 2014). Data from the US published by Dindarloo et al. (2016) highlights that one of the three most frequent causes of haul truck-related facilities is the failure to provide adequate safety berms. A more recent worldwide study by Duarte et al. (2021) also emphasises that failure to provide and maintain adequate safety berms is a major cause of accidents on haul roads. ...
... Another criterion that influences the selection of a heavy equipment fleet is safety. Heavy construction equipment has been thoroughly studied in relation to accidents, fatalities, and injuries and is implicated in a high percentage of them [5]. Conveyor belts are another type of mining equipment used for hauling materials, but they are known to pose safety risks. ...
... Another criterion that influences the selection of a heavy equipment fleet is safety. Heavy construction equipment has been thoroughly studied in relation to accidents, fatalities, and injuries and is implicated in a high percentage of them [5]. Conveyor belts are another type of mining equipment used for hauling materials, but they are known to pose safety risks. ...
... Bellanca et al. [14] studied the MSHA database regarding haulage trucks and categorized the fatality hazards into equipment malfunction, ground failure, loss of control, loss of balance, loss of situational awareness, and others (e.g., falling materials from a suspended load). Dindarloo et al. [15] classified the potential hazards into four groups: losing control of the truck, berm/dump failure, unsafe actions, and mechanical failures. Kecojevic et al. [16] used a statistical data-driven method to identify the hazards of underground mining equipment-related fatal hazards. ...
... Numerous recorded accidents involve heavy transport machinery, such as haul trucks [44,50,51] and dumpers [52,53], with jack leg drills having the highest accident rate [54]. In general, mobile equipment [45] often poses a visibility issue for workers, which may be due to the size and design of the equipment. ...
Underground mining operations present critical safety hazards due to limited visibility and blind areas, which can lead to collisions between mobile machines and vehicles or persons, causing accidents and fatalities. This paper aims to survey the existing literature on anti-collision systems based on computer vision for pedestrian detection in underground mines, categorize them based on the types of sensors used, and evaluate their effectiveness in deep underground environments. A systematic review of the literature was conducted following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines to identify relevant research work on anti-collision systems for underground mining. The selected studies were analyzed and categorized based on the types of sensors used and their advantages and limitations in deep underground environments. This study provides an overview of the anti-collision systems used in underground mining, including cameras and lidar sensors, and their effectiveness in detecting pedestrians in deep underground environments. Anti-collision systems based on computer vision are effective in reducing accidents and fatalities in underground mining operations. However, their performance is influenced by factors, such as lighting conditions, sensor placement, and sensor range. The findings of this study have significant implications for the mining industry and could help improve safety in underground mining operations. This review and analysis of existing anti-collision systems can guide mining companies in selecting the most suitable system for their specific needs, ultimately reducing the risk of accidents and fatalities.
... Losing control of equipment has been reported as the leading cause of machine-related fatalities in surface mining [45]. Based on some studies, occupational groups having the highest percentage of all accidents in mines were maintenance personnel and mechanic repairmen [26,46,47]. Groves et al [48] showed that a significant portion (54%) of accidents in the mining industry was due to material handling, machinery (12%), hand tools (11%), roof falls (10%), and powered haulage (8%). ...
... e data objects can be clustered into K categories based on Equation (1). For the dataset, the mean value of all data in the relative class is initially selected as the class center, which needs iterating until the class center changes slowly or stops changing (the squared error between the empirical mean of a cluster and the points in the cluster is minimized [45]). e class center can be defined as follows: ...
Investigating the relationship between the months and traffic crashes is a foremost task for the safety improvement of mountainous freeways. Taking a mountainous freeway located in China as an example, this paper proposed a combined modeling framework to identify the relationships between months and different crash types. K-means and Apriori were initially used to extract the monthly distribution patterns of different types of crashes. A graphical approach and a risk calculation equation were developed to assess the output of K-means and Apriori. Then, using the assessment results as the input, a logistic regression model was constructed to quantify the effects of each month on crashes. The results indicate that the monthly distribution patterns of different crash types are inconsistent, i.e., for a specific month, the high risk of a certain crash type may be covered up if experts only focus on the total number of crashes. Moreover, when identified as high-risk months by K-means and Apriori, the crash-proneness will significantly increase several times than months identified as high-risk by only one of K-means and Apriori, thereby illustrating the superior performance of the mix-method. The conclusions can assist local relevant organizations in formulating strategies for preventing different types of traffic crashes in different months (e.g., the risk of rear-end crashes in August, the risk of fixed-object hitting crashes in February, and the risk of overturning crashes in October) and provide a methodological reference for relevant studies in other regions.
... We have developed a conceptual model to demonstrate our hypotheses on how various factors may increase the risk of injury at work ( Fig. 1-a). The individual and organizational factors include but not are limited to: age, work experience, work activity, type of mine, and hearing protection device (HPD) use, and have been extensively studied in the mining industry (Dindarloo et al., 2016;Sammarco et al., 2016;Cui et al., 2015;Mitchell et al., 1998). However, there is increasing evidence that occupational noise may be a significant predictor of work-related injuries (Dzhambov and Dimitrova, 2017;Girard et al., 2015;Amjad-Sardrudi et al., 2012;Picard et al., 2008). ...
This study examined associations between metrics of noise exposure and mental workload. In this cross-sectional study, five occupational noise metrics computed from full-shift dosimetry were evaluated among surface mine workers in the US Midwest. Mental workload was evaluated using a modified, raw NASA-TLX and clustered with a k-means clustering algorithm. Mixed effects logistic regression and Bayesian Kernel Machine Regression (BKMR) was utilized for analysis. Average noise exposure, the difference between peak and mean noise exposure, and the number of peaks >135 dB were each strongly associated with mental workload, while the kurtosis and standard deviation of noise throughout a shift were not. An exposure-response relationship between average noise exposure and mental workload may exist, with elevated risk of high mental workload beginning at 80 dBA. These results suggest that high noise exposure may be an independent risk factor of high mental workload, and impulse events and the difference between the peak and mean noise exposure may have interactive effects with average noise exposure.
... Detailed literature reviews suggest no application of DNN in accident prediction so far. GEP has also been used successfully in various fields [39][40][41][42]. The advantages of GEP over other nonparametric algorithms include providing a list of best explanatory features used to create the model as well as a relation between the output and explanatory variables. ...
This work proposes to use deep neural networks (DNN) model for prediction of road accidents. DNN consists of two or more hidden layers with large number of nodes. Accident data of non-urban sections of eight highways were collected from official records, and dataset consists of a total of 2680 accidents. The data of 16 explanatory variables related to road geometry, traffic and road environment were collected from official records as well as through field studies. Out of a total of 222 data points of accident frequency, 148 were used for training and remaining 74 to test the models. To compare the performance of DNN-based modeling approach, gene expression programming (GEP) and random effect negative binomial (RENB) models were used. A correlation coefficient value of 0.945 (root mean square error = 5.908) was achieved by DNN in comparison with 0.914 (RMSE = 7.474) by GEP, and 0.891 (RMSE = 8.862) by RENB with the test dataset, indicating an improved performance by DNN in prediction of road accidents. In comparison with DNN, though lower value of correlation coefficient was achieved by GEP model, it quantified the effects of various variables on accident frequency and provided a ranked list of variables based upon their importance.
... Moreover, existing fee policies related to truck lane restrictions were analyzed and characterized the state of the practice in permit fees for trucks on public freeways, evaluating these practices at the economic level [19]. Other aspects of related research include emissions, safety, fuel consumption, pavement performance, and characteristics of truck drivers [20][21][22][23][24]. Readers can refer to the above-mentioned literature for more details. ...
To support the rapid growth of demand in passengers and freight, separating trucks and passenger-cars is a potential solution to improve traffic efficiency and safety. The primary purpose of this paper is to comprehensively assess the multilane separate freeway at Huludao Toll Station in Liaoning Province, China. Based on the configuration and segmentation of the freeway near a toll station, a six-step guidance strategy is designed to adapt to the separate organization mode. Five conventional traffic scenarios are designed in the Vissim platform for comparative analysis between different guidance strategies. To investigate the vehicle-to-infrastructure (V2I) environment, a microscopic testbed is established with cooperative car-following and lane-changing models using the MATLAB platform. The numerical simulation results show that the guidance strategy significantly improves efficiency and safety, and also reduces emissions and fuel consumption. Meanwhile, pre-guidance before toll channels outperforms the scenario only applied with guidance measures after toll plaza. Compared to conventional conditions, the assessment of pollutant emissions and fuel consumption also embodies the superiority of the other five scenarios, especially in the sections of toll plaza and channels with the lowest efficiency and safety level. Generally, all indexes indicate that the cooperative V2I technology is the best alternative for multilane separate freeways.
... Drury et al. (2012) introduced the haul truck accidents in a pattern via data analysis in order to predict the accident model. Dindarloo et al. (2016) evaluated the severity of injuries caused by mine haul trucks through hybrid clustering classification. They made a cluster definition for different types of accidents, including location, the experience of the victim and severity. ...
In any mining project, which numerous activities and various equipment are running, the safety issue is one of the most challenging matters. Accordingly, it is favorable for planners to use the safest processes and equipment in daily works. In spite of many statistical and data analysis research regarding the safety, the number of papers that consider multi-variable criteria based on a dynamic behavior are few. In this paper, common transportation equipment in mines, which are trucks and conveyor belts, are evaluated in different types of transportation systems i.e. Truck-Shovel, Fixed In-Pit Crushing and Conveying (FIPCC), Semi-Fixed In-Pit Crushing and Conveying (SFIPCC), Semi-Mobile In-Pit Crushing and Conveying (SMIPCC) and Fully Mobile In-Pit Crushing and Conveying (FMIPCC) systems. The safety and social indexes, which are the indicators of safety and social levels, are introduced and compared in different transportation systems. System dynamics modeling, as a powerful tool for simulating the behavior of a system through the time, is used to model the transportation system of an open pit mine. For this, different variables and their connections in the system, which determine the level of safety and social index, are described. It was shown that these transportation systems differently behave in case of safety and social indexes such that FMIPCC stood in the first rank in safety point of view while the Truck-Shovel system was ranked the fifth. In contrast, and in the social index, the Truck-Shovel system was titled the first and FMIPCC the last. However, for determining the best transportation system in the both safety and social indexes, weighing and normalization processes were performed. System dynamics modeling can be utilized in the making decision process, which the planners want to evaluate the behavior of the system in different scenarios. This method is capable to give an insight into the current and future state of the system for any alternative.
Background:
The first hour of a shift in a mine is characterized by a large movement of miners from incoming and outgoing shifts, in addition to safety and maintenance checks of mining equipment. These activities rely on communication to ensure a safe transition between shifts. This study aims to identify risk factors for injury among miners during the first hour of a work shift and to characterize injury outcomes.
Methods:
Data from U.S. Mine Safety and Health Administration Part 50 reports, 1983-2015, were used to identify injuries occurring within the first hour of a shift. Multivariable logistic regression was used to evaluate predictors of injuries occurring during the first shift-hour and to assess the outcome of these injuries.
Results:
Out of the 545,537 cases included in the analysis, 16,446 injuries occurred during the first hour of a shift. Risk factors associated with these injuries included being female, being older, working on Sunday and Monday, having an irregular shift start, working night shifts, employed in surface mining operations, and mine operations with <200 employees, and mechanisms of injury related to falls, movement of equipment and personnel, and being struck by or caught between boxes and containers. Injurious incidents occurring during the first hour of work were associated with mass injury events involving five or more workers (aOR = 3.58; 95% CI: 2.77, 4.64).
Conclusions:
Although injury rates were substantially lower during the first hour of work compared to all other work hours, this study identified risk factors and mechanisms of injury that are highly preventable during the first hour of work.
To help develop ergonomics audit programs for mining, one source of data on both work tasks and their failures is accident reports. These are available in most industries and are often used in human factors engineering, but typically to justify and evaluate interventions rather than to provide task details and failure mechanisms. Because fatal accidents in particular contain considerable detail resulting from thorough follow-up investigations, they are thus a useful starting point for analysis. A set of 40 detailed fatal accident reports for mining haul truck accidents were analyzed to develop repeating patterns of accidents. This paper examines the accident patterns found from the initial sample, the refined pattern analysis developed from a subsequent larger sample, and the task analyses used later to help develop valid audit programs.
Purpose –:
The purpose of this paper is to identify key tasks, tools, and equipment associated with maintenance and repair injuries at US mines and to provide some mitigation strategies to reduce these types of injuries.
Design/methodology/approach –:
This study analyzed incidents resulting in injuries reported to the US Mine Safety and Health Administration from 2002 to 2011. Incident reports were limited to those occurring at mining plants, shops, yards, and aboveground locations. Incident reports were analyzed to determine which activities contributed to injuries and were due to machine maintenance and repair, non-powered hand tools, and powered hand tools. An in-depth analysis of the root causes of these injuries was then performed.
Findings –:
Maintenance and repair in mining is associated with a significant number of hand and finger injuries with a range of severities and averaging over 20 amputated fingers, 180 fractured hands and fingers, and 455 hand and finger lacerations per year. Many of these injuries are caused by hands being struck by or caught in tools and equipment. Back and shoulder strains are found to be associated with the most days lost from work and are mostly attributed to materials handling.
Practical implications –:
Occupational injuries and fatalities still occur with high incidences in the mining sector. The mission of the Office of Mine Safety and Health Research (OMSHR; part of the National Institute for Occupational Safety and Health, NIOSH) is to "eliminate mining fatalities, injuries, and illnesses through research and prevention." As part of this work, OMSHR acquires surveillance data from MSHA to quantify the types and sources of injuries at US mining facilities. The authors evaluated maintenance- and repair-related injuries at US mining sites (excluding underground coal mines). Results of this study suggest a need for improved design of machine guarding, improved hand protection through gloves and equipment design/redesign, and manual materials handling solutions.
Originality/value –:
The findings indicate that maintenance and repair in mining include occupational risks that may be managed through modifications to machines, proper usage of hand tools and hand protection, and improved manual materials handling processes.
Background:
Maintenance and repair work in mining is particularly hazardous and yet has received little focus in ergonomics research.
Purpose:
In this article, an attempt has been made to determine if patterns can be identified to categorize maintenance and repair fatalities in mining, to compare occurrence of fatalities between coal and metal/nonmetal sectors, and to use this information to identify safety deficiencies and associated proposed remedial measures.
Methods:
A classification scheme was developed to identify patterns in fatalities, including proximal causes, tasks, and contributing factors. This scheme was tested to ensure adequacy of the categories, and fatalities were categorized using the scheme. All testing and categorization were done by two of the authors to ensure reliability of the coding scheme.
Results:
Patterns were successfully identified to categorize the fatalities, and these patterns were different between coal and metal/nonmetal mines. Coal mines had a greater proportion of electrical-related fatalities, while more fatalities related to potential energy occurred at metal/nonmetal mines. Most of the fatalities were caused by the victim coming into contact with an object or machine or the victim falling from height, and they occurred most often while the victim was performing maintenance or repair on equipment, cleaning, or removing blockages. The most frequent factors contributing to these incidents were failure to properly de-energize or lock out/tag out equipment, violation of work procedures, missing or inadequate safety equipment, and failure to block equipment properly.
Conclusions:
The classification approach used was successful in identifying hazard patterns during maintenance and repair fatalities in mining. These patterns identify areas to focus attention when developing interventions to prevent the occurrence of future fatalities.
One of the principal objectives of traffic accident analyses is to identify key factors that affect the severity of an accident. However, with the presence of heterogeneity in the raw data used, the analysis of traffic accidents becomes difficult. In this paper, Latent Class Cluster (LCC) is used as a preliminary tool for segmentation of 3229 accidents on rural highways in Granada (Spain) between 2005 and 2008. Next, Bayesian Networks (BNs) are used to identify the main factors involved in accident severity for both, the entire database (EDB) and the clusters previously obtained by LCC. The results of these cluster-based analyses are compared with the results of a full-data analysis. The results show that the combined use of both techniques is very interesting as it reveals further information that would not have been obtained without prior segmentation of the data. BN inference is used to obtain the variables that best identify accidents with killed or seriously injured. Accident type and sight distance have been identify in all the cases analysed; other variables such as time, occupant involved or age are identified in EDB and only in one cluster; whereas variables vehicles involved, number of injuries, atmospheric factors, pavement markings and pavement width are identified only in one cluster.
Ground damage incidents (incidents in which airline personnel cause damage to an aircraft on the ground) occur as airline personnel are working on, or around, an aircraft on the ground, either on the ramp or at a maintenance facility. Each incident can be quite costly to the airline, with costs both tangible (repair costs and lost revenue) and intangible (passenger inconvenience, increased maintenance workload). Thus, airlines have a financial incentive to reduce the number of ground damage incidents that occur. One of the airline's most difficult tasks has been to utilize the information collected in their existing error reporting systems to determine the common latent failures which contribute to typical ground damage incidents. In this study, 130 ground damage incidents from a major airline were reviewed to determine the active and latent failures. Twelve distinct hazard patterns (representing the active failures) were identified, with three hazard patterns accounting for 81% of all ground damage incidents. Nine major latent failures were identified, and the relationships between the hazard patterns and latent failures were examined in depth. This type of analysis allows the latent failures common to different hazard patterns to be identified, and provides a means for developing focused intervention strategies to prevent future ground damage.Relevance to industryAirlines have generally had a difficult time analyzing reports of human error to make improvements in their maintenance systems. This study provides a methodology that allows reports of human error to be analyzed, and interventions developed based on the results of the analysis. The methodology would also be applicable to, and useful in, other industries.
This study describes a method for reducing the number of variables frequently considered in modeling the severity of traffic accidents. The method's efficiency is assessed by constructing Bayesian networks (BN).
It is based on a two stage selection process. Several variable selection algorithms, commonly used in data mining, are applied in order to select subsets of variables. BNs are built using the selected subsets and their performance is compared with the original BN (with all the variables) using five indicators. The BNs that improve the indicators' values are further analyzed for identifying the most significant variables (accident type, age, atmospheric factors, gender, lighting, number of injured, and occupant involved). A new BN is built using these variables, where the results of the indicators indicate, in most of the cases, a statistically significant improvement with respect to the original BN.
It is possible to reduce the number of variables used to model traffic accidents injury severity through BNs without reducing the performance of the model.
The study provides the safety analysts a methodology that could be used to minimize the number of variables used in order to determine efficiently the injury severity of traffic accidents without reducing the performance of the model.
Several different factors contribute to injury severity in traffic accidents, such as driver characteristics, highway characteristics, vehicle characteristics, accidents characteristics, and atmospheric factors. This paper shows the possibility of using Bayesian Networks (BNs) to classify traffic accidents according to their injury severity. BNs are capable of making predictions without the need for pre assumptions and are used to make graphic representations of complex systems with interrelated components. This paper presents an analysis of 1536 accidents on rural highways in Spain, where 18 variables representing the aforementioned contributing factors were used to build 3 different BNs that classified the severity of accidents into slightly injured and killed or severely injured. The variables that best identify the factors that are associated with a killed or seriously injured accident (accident type, driver age, lighting and number of injuries) were identified by inference.
At surface mining operations throughout the world, loaders and trucks are a primary means of material loading and haulage. As the size, use and technological complexity of these units have increased, so has the concern regarding loader and truck safety. The severity and number of accidents involving loaders and trucks is higher when compared to all other mining accident types. In this paper, an analysis of loader and truck-related fatalities over the last 8 years is performed, the fatality categories and causes of accidents are established and control strategies are discussed and evaluated in an effort to increase hazard awareness by emphasizing safe loading, hauling and maintenance practices, as well as the value of traditional and innovative miner training programmes.
Cluster analysis aims at identifying groups of similar objects and, therefore helps to discover distribution of patterns and interesting correlations in large data sets. It has been subject of wide research since it arises in many application domains in engineering, business and social sciences. Especially, in the last years the availability of huge transactional and experimental data sets and the arising requirements for data mining created needs for clustering algorithms that scale and can be applied in diverse domains.
Cluster analysis is the automated search for groups of related observations in a dataset. Most clustering done in practice is based largely on heuristic but intuitively reasonable procedures, and most clustering methods available in commercial software are also of this type. However, there is little systematic guidance associated with these methods for solving important practical questions that arise in cluster analysis, such as how many clusters are there, which clustering method should be used, and how should outliers be handled. We review a general methodology for model-based clustering that provides a principled statistical approach to these issues. We also show that this can be useful for other problems in multivariate analysis, such as discriminant analysis and multivariate density estimation. We give examples from medical diagnosis, minefield detection, cluster recovery from noisy data, and spatial density estimation. Finally, we mention limitations of the methodology and discuss recent developments in model-based clustering for non-Gaussian data, high-dimensional datasets, large datasets, and Bayesian estimation.
Risk management is an established loss-control methodology that has been applied successfully in many industries. Recently, interest in this structured approach has grown in the mining industry. The main objective of this research was to develop a risk-assessment process, which is a part of risk management, that can be used by the U.S. mining industry to more thoroughly characterize risks associated with haul truck-related fatalities. The assessment is based on historical data obtained from the U.S. Mine Safety and Health Administration (MSHA) investigation reports, which includes 113 fatal incidents that occurred from 1995 through 2006. The risk-assessment process used in this research involves the following basic steps: identifi cation of the risks, risk analysis and risk evaluation. The preliminary hazard assessment (PHA) method is used in identifying and quantifying risks. Risk levels are then developed using a pre-established risk
matrix that ranks them according to probability and severity. The resulting assigned risk value can then be used to prioritize control strategies. This paper is a part of a detailed study on risk assessment for equipment-related fatalities in mining sponsored by the Western U.S. Mining Safety and Health Training and Translation Center.
A sequence of 0's and 1's is observed and it is suspected that the chance that a particular trial is a 1 depends on the value of one or more independent variables. Tests and estimates for such situations are considered, dealing first with problems in which the independent variable is preassigned and then with independent variables that are functions of the sequence. There is a considerable amount of earlier work, which is reviewed.
The relationship between driver injury severity and driver, vehicle, roadway, and environment characteristics was examined. The use of two well-known neural network paradigms, the multilayer perceptron (MLP) and fuzzy adaptive resonance theory (ART) neural networks, was investigated. The use of artificial neural networks can lead to greater understanding of the relationship between the aforementioned factors and driver injury severity. Accident data for 1997 for the Central Florida area, which consists of Orange, Osceola, and Seminole Counties, were used. The analysis focuses on two-vehicle accidents that occured at signalized intersections. The MLP neural network has a better generalization performance of 65.6 and 60.4 percent for the training and testing phases, respectively. The performance of the MLP was compared with that of an ordered logit model. The ordered logit model was able to correctly classify only 58.9 and 57.1 percent for the training and testing phases, respectively. A simulation experiment was then carried out to understand the MLP neural network model. Results show that rural intersections are more dangerous in terms of driver injury severity than urban intersections. Also, female drivers are morely likely to experience a severe injury than are male drivers. Speed ratio increases the likelihood of injury severity. Drivers at fault are likely to experience severe injury than are those not at fault. Wearing a seat belt decreases the chance of sustaining severe injuries. Vehicle type plays a role in driver injury severity. Drivers in passenger cars are more likely to experience a greater injury severity level than are drivers of vans or pickup trucks. Finally, drivers exposed to impact at their side experience greater injury severity than those exposed to impact elsewhere.
In k\hbox{-}{\rm{means}} clustering, we are given a set of n data points in d\hbox{-}{\rm{dimensional}} space {\bf{R}}^d and an integer k and the problem is to determine a set of k points in {\bf{R}}^d, called centers, so as to minimize the mean squared distance from each data point to its nearest center. A popular heuristic for k\hbox{-}{\rm{means}} clustering is Lloyd's algorithm. In this paper, we present a simple and efficient implementation of Lloyd's k\hbox{-}{\rm{means}} clustering algorithm, which we call the filtering algorithm. This algorithm is easy to implement, requiring a kd-tree as the only major data structure. We establish the practical efficiency of the filtering algorithm in two ways. First, we present a data-sensitive analysis of the algorithm's running time, which shows that the algorithm runs faster as the separation between clusters increases. Second, we present a number of empirical studies both on synthetically generated data and on real data sets from applications in color quantization, data compression, and image segmentation.
Organizing data into sensible groupings is one of the most fundamental modes of understanding and learning. As an example, a common scheme of scientific classification puts organisms into a system of ranked taxa: domain, kingdom, phylum, class, etc. Cluster analysis is the formal study of methods and algorithms for grouping, or clustering, objects according to measured or perceived intrinsic characteristics or similarity. Cluster analysis does not use category labels that tag objects with prior identifiers, i.e., class labels. The absence of category information distinguishes data clustering (unsupervised learning) from classification or discriminant analysis (supervised learning). The aim of clustering is to find structure in data and is therefore exploratory in nature. Clustering has a long and rich history in a variety of scientific fields. One of the most popular and simple clustering algorithms, K-means, was first published in 1955. In spite of the fact that K-means was proposed over 50 years ago and thousands of clustering algorithms have been published since then, K-means is still widely used. This speaks to the difficulty in designing a general purpose clustering algorithm and the ill-posed problem of clustering. We provide a brief overview of clustering, summarize well known clustering methods, discuss the major challenges and key issues in designing clustering algorithms, and point out some of the emerging and useful research directions, including semi-supervised clustering, ensemble clustering, simultaneous feature selection during data clustering, and large scale data clustering.
The practice of classifying objects according to perceived similarities is the basis for much of science. Organizing data into sensible groupings is one of the most fundamental modes of understanding and learning. As an example, a common scheme of scientific classification puts organisms in to taxonomic ranks: domain, kingdom, phylum, class, etc.). Cluster analysis is the formal study of algorithms and methods for grouping objects according to measured or perceived intrinsic characteristics. Cluster analysis does not use category labels that tag objects with prior identifiers, i.e., class labels. The absence of category information distinguishes cluster analysis (unsupervised learning) from discriminant analysis (supervised learning). The objective of cluster analysis is to simply find a convenient and valid organization of the data, not to establish rules for separating future data into categories.
This study documented the burden of nonfatal construction industry work-related injuries treated in hospital emergency departments in the United States (US) from 1998 through 2005 and described injured worker demographics and injury characteristics.
Data from the National Electronic Injury Surveillance System work-related injury supplement (NEISS-Work) were used to identify and describe construction industry-related injuries. Rates were estimated using data from the Current Population Survey.
An estimated 3,216,800 (95% CI 2,241,400-4,192,200) construction industry-related injuries were seen in US emergency departments during the 8-year period; this represented an injury rate of 410/10,000 full-time equivalents and suggests that there are a greater number of construction injuries than reported through the Bureau of Labor Statistics' Survey of Occupational Injuries and Illnesses (BLS SOII). Common characteristics included diagnoses of laceration, sprain/strain, and contusion/abrasion; events of contact with an object/equipment, bodily reaction/exertion, and falls; and sources of injury of parts/materials; structures/surfaces; and tools/instruments/equipment. The upper extremities were most often affected.
These data highlight the high burden of nonfatal construction industry-related injuries. The limitations of national occupational injury data sources inherent in relying on OSHA logs highlight the utility of NEISS-Work data in occupational injury research. While data captured from emergency departments are not immune to factors that influence whether a worker or an employer reports an injury as work-related or files a workers' compensation claim, emergency department data as collected through NEISS-Work do not rely on employer involvement in order to be classified as work-related.
Researchers at the National Institute for Occupational Safety and Health studied mining accidents that involved a worker entangled in, struck by, or in contact with machinery or equipment in motion. The motivation for this study came from the large number of severe accidents, i.e. accidents resulting in a fatality or permanent disability, that are occurring despite available interventions. Accident descriptions were taken from an accident database maintained by the United States Department of Labor, Mine Safety and Health Administration, and 562 accidents that occurred during 2000-2007 fit the search criteria. Machine-related accidents accounted for 41% of all severe accidents in the mining industry during this period. Machinery most often involved in these accidents included conveyors, rock bolting machines, milling machines and haulage equipment such as trucks and loaders. The most common activities associated with these accidents were operation of the machine and maintenance and repair. The current methods to safeguard workers near machinery include mechanical guarding around moving components, lockout/tagout of machine power during maintenance and backup alarms for mobile equipment. To decrease accidents further, researchers recommend additional efforts in the development of new control technologies, training materials and dissemination of information on best practices.
The objective of this study was to evaluate the circumstances leading to fall from equipment injuries in the mining industry.
The 2006 and 2007 Mine Safety and Health Administration annual injury databases were utilized for this study whereby the injury narrative, nature of injury, body part injured, mine type, age at injury, and days lost were evaluated for each injury.
The majority of injuries occurred at surface mining facilities (approximately 60%) with fractures and sprains/strains being the most common injuries occurring to the major joints of the body. Nearly 50% of injuries occurred during ingress/egress, predominantely during egress, and approximately 25% of injuries occurred during maintenance tasks. The majority of injuries occurred in relation to large trucks, wheel loaders, dozers, and conveyors/belts. The severity of injury was independent of age and the median days lost was seven days; however, there was a large range in severity.
From the data obtained in this study, several different research areas have been identified for future work, which include balance and stability control when descending ladders and equipment design for maintenance tasks.
The morbidity, lost work time, and interference with effective work due to low back pain are markedly underestimated when only employee health service data are used. Injured subjects averaged more years of generic, orthopedic, and rehabilitation nursing experience than the non-injured group. Of the studied nurses who experienced work related low back pain within the past 6 months, 78% did not report it to management. More attention should be given to adequate staff availability for shared lifting activities, better design and use of mechanical lifting aids, and further research in how to safely perform tasks from the side of the bed.
We estimate the incidence and describe patterns of work-related injuries during 1998 to youth in retail trades and services industries. Data from the National Electronic Injury Surveillance System and the Current Population Survey were analyzed. The highest number of work-related injuries to youth younger than 18 years occurred in eating and drinking establishments and food stores. Injuries occurring in these industries accounted for 44% of all young worker injuries. Injury rates were similar during summer and school months. Youth continue to experience high numbers and rates of injuries in retail trades and services. Improvements in safety training and injury prevention in these industries, particularly eating and drinking establishments, food stores, and health services, need to be addressed for youth.
We propose a method (the \Gap statistic") for estimating the numberof clusters (groups) in a set of data. The technique uses the outputof any clustering algorithm (e.g. k-means or hierarchical), comparingthe change in within cluster dispersion to that expected under an appropriatereference null distribution. Some theory is developed forthe proposal and a simulation study that shows that the Gap statisticusually outperforms other methods that have been proposed in the literature.We also...
Cluster analysis is the automated search for groups of related observations in a data set. Most clustering done in practice is based largely on heuristic but intuitively reasonable procedures and most clustering methods available in commercial software are also of this type. However, there is little systematic guidance associated with these methods for solving important practical questions that arise in cluster analysis, such as How many clusters are there?", Which clustering method should be used?" and How should outliers be handled?". We outline a general methodology for model-based clustering that provides a principled statistical approach to these issues. We also show that this can be useful for other problems in multivariate analysis, such as discriminant analysis and multivariate density estimation. We give examples from medical diagnosis, mineeld detection, cluster recovery from noisy data, and spatial density estimation. Finally, we mention limitations of the methodology, a...
Gene expression programming, a genotype/phenotype genetic algorithm (linear and ramified), is presented here for the first time as a new technique for the creation of computer programs. Gene expression programming uses character linear chromosomes composed of genes structurally organized in a head and a tail. The chromosomes function as a genome and are subjected to modification by means of mutation, transposition, root transposition, gene transposition, gene recombination, and one- and two-point recombination. The chromosomes encode expression trees which are the object of selection. The creation of these separate entities (genome and expression tree) with distinct functions allows the algorithm to perform with high efficiency that greatly surpasses existing adaptive techniques. The suite of problems chosen to illustrate the power and versatility of gene expression programming includes symbolic regression, sequence induction with and without constant creation, block stacking, cellular automata rules for the density-classification problem, and two problems of boolean concept learning: the 11-multiplexer and the GP rule problem.
Haulage truck dump site safety: An examination of reported injuries. (DHHS (NIOSH) publication no. 2001-124, information circular 9454
- F C Turin
- W J Wiehagen
- J S Jaspal
- A G Mayton
Turin, F. C., Wiehagen, W. J., Jaspal, J. S., & Mayton, A. G. (2001). Haulage truck dump site
safety: An examination of reported injuries. (DHHS (NIOSH) publication no. 2001-124,
information circular 9454)Pittsburgh, PA: U.S. Department of Health and Human Services, Public Health Services, CDC-NIOSH.
An analysis of serious injuries to dozer operators in the U.S. Mining industry. (DHHS (NIOSH) publication no. 2001-126, information circular 9455
- W J Wiehagen
- A G Mayton
- J S Jaspal
- F C Turin
Wiehagen, W. J., Mayton, A. G., Jaspal, J. S., & Turin, F. C. (2001). An analysis of serious injuries to dozer operators in the U.S. Mining industry. (DHHS (NIOSH) publication no.
2001-126, information circular 9455)Pittsburgh, PA: U.S. Department of Health and
Health Services, Public Health Services, CDC-NIOSH.
Dindarloo has 10 years of research and professional experience. He has extensive experience in mine design, planning, and computer application. His current research interests include: mini safety and health, mining machinery, and mining equipment management
- R Saeid
- Dindarloo
- M D Ph
- B Sc
- Sc
Saeid R. Dindarloo holds Ph.D., M.Sc. and B.Sc. degrees, all in Mining Engineering, from
Missouri University of Science and Technology, USA, and Amirkabir University of Technology (Tehran Polytechnic), Iran. Dr. Dindarloo has 10 years of research and professional experience. He has extensive experience in mine design, planning, and computer
application. His current research interests include: mini safety and health, mining machinery, and mining equipment management.
An analysis of serious injuries to dozer operators in the U.S
- Wiehagen
Haulage truck dump site safety: An examination of reported injuries
- Turin