Text-clustering based deep neural network for prediction of occupational accident risk: A case study

Sarkar, Sobhan; Lodhi, Vaibhav; Maiti, J.

doi:10.1109/isai-nlp.2018.8692881

Cited by 12 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…19,22 Many studies have proven the efficiency of ML techniques in recognizing the trends and predicting risk events based on the previous data without making any assumptions about the data or variables. 9,20 Several authors have used ML to predict occupational accidents analysis in different sectors, in the aviation industry (Herrema et al 26 ; Burnett and Si 27 ), the mining industry (Rivas et al 22 ; Matias et al 28 ), construction industry (Tixier et al 4 ; Goh and Ubeynarayana 6 ; Chokor et al 29 ; Mistikoglu et al 30 ; Liao et al 31 ; Zhu et al 32 ; Choi et al 33 ), in steel and other mineral extraction industry (Sarkar et al 8,11,16,23 ; Shirali et al 34 ; Yang et al 35 ;…”

Section: Review Of Accident Data Analysis Using Machine Learning Tech...mentioning

confidence: 99%

“…Missing values is also an important issue that hampers the performance of classification models. Sarkar et al 8,11 used a random forest algorithm to impute the missing values from the dataset.…”

Section: Review Of Accident Data Analysis Using Machine Learning Tech...mentioning

confidence: 99%

“…Several fields such as construction, manufacturing, aviation, mining and so forth and other fields benefit from machine learning (ML) algorithms and other data analytics tools, but there is a need for developing predictive models for classifying accident outcomes, injury severity and consequence estimation. [7][8][9][10][11] The petrochemical companies need innovative technology and processes to gather and convert data into a strategic business while maintaining safety. 12 The rapid growth in demand for petroleum products allows companies to expand their operations and build new plants, and this industry has a significant impact on each country's GDP.…”

mentioning

confidence: 99%

“…7,15 Predicting injuries and providing actionable insights on factors associated with injuries are critical for improving workplace safety. 4,5,8,11 Also, predictive models can measure the contribution to an accident of the various causal factors. [14][15][16] Predictive models play a key role in detecting trends, and patterns in injuries and forecasting the risk of incidents at work.…”

mentioning

confidence: 99%

“…17,18 According to the study by Kakhki et al 19 industries are also concerned with workplace risk analysis and with the development of predictive safety models to reduce accident occurrence. According to Sarkar et al, 8,11,16 many organizations are unable to extract useful insights from incident data due to the lack of appropriate prediction models and unavailability of structured data. Some studies 20,21 have conducted automated risk assessments using ML algorithms and they are deployed in detecting abnormal events in the exploration of oil and gas.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Application of rough set theory and machine learning algorithms in predicting accident outcomes in the Indian petroleum industry

Gangadhari

Khanzode

Murthy

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Recent advancements in machine learning techniques are helping researchers to develop predictive models that assist decision‐makers to get a quick, unbiased overview of the processes. But studies using machine learning approaches in analyzing and classifying the injury narratives of the petroleum industries are still in their early stages due to data unavailability and lack of trust in these models. Comparatively, other industries such as construction, manufacturing, aviation and so forth are using the findings from the predictive models but the use of machine learning techniques in analyzing petroleum industry accident data is not gaining much importance. This study aims to use available accident data from the Indian petroleum industry to develop a classification model for predicting possible outcomes of an accident. The data used in this study comprises 194 accident reports with 20 information attributes collected during the 2016–20 period. Six different machine learning algorithms are used to analyze and classify the possible outcome of the accident. It has been found that the Xgboost algorithm has achieved 95% accuracy following multilayer perceptron with 94% accuracy. The rough set theory is also used to extract the indiscernibility relationship between the given attributes causing accident occurrence. The results indicate that “skill‐based error, supervisory violation, no personal protective equipment usage, and lack of standard operating procedure compliance” have contributed to the majority of the accidents. The findings of this study can be used to assist safety professionals in decision‐making, mitigating the root causes of contributing factors.

show abstract