An uncertainty-aware decision support system: Integrating text narratives and conformal prediction for trustworthy accident code classification Ashish Kumar, Amrites Senapati, Rahul Upadhyay, Snehamoy Chatterjee, Ashis Bhattacherjee, Biswajit Samanta Process Safety and Environmental Protection, 2025 It is imperative to assign accident classification codes to the Mine Safety and Health Administration (MSHA) accident data for effective data analysis and risk assessment. Although trained personnel are capable of performing this task, the manual process is both time-consuming and resource-intensive. Automating the classification process with machine learning (ML) algorithms promises to expedite code assignment. However, ML predictions typically lack uncertainty metrics. This study proposes an uncertainty-aware hierarchical classification framework that assists human experts in efficiently and accurately assigning accident codes. Several text representation techniques combined with different ML algorithms were employed within a hierarchical architecture to assign classification codes. Low-frequency codes were consolidated into a single category, with a primary classifier distinguishing between these and a secondary classifier further categorizing the grouped categories. Regularized Adaptive Prediction Sets (RAPS) was integrated to quantify uncertainty. Highly confident predictions yielding single-class sets were automatically classified, whereas multi-class sets were flagged for manual review. Primary Classifier with XGBoost with word2vec text representation achieved the best performance, with 95.12% coverage, 37.02% single-class prediction sets at 96.11% accuracy, and an average prediction set size of 2.39. Whereas the secondary classifier, a logistic regression model with TF-IDF representation, yielded 96.19% coverage, an average set size of 1.80, and 53.66% single-class prediction sets with 98.90% accuracy. Additionally, sensitivity analysis determined that a 95% coverage guarantee offers the best trade-off between prediction set size and coverage. The framework effectively integrates conformal prediction to quantify uncertainty and aid human experts in improving the decision-making process in safety management. Although the framework is broadly applicable across different sectors, it needs to be retrained on domain-specific data for effective use.
Experimentation and Statistical Prediction of Dust Emission in Iron Ore Mines using Supervised Machine Learning (Regression) Modelling Rajib Pal, Harsha Vardhan, Senapati Amrites, Swamy V. Sahas Disaster Advances, 2025 In India, the mine area and the processing plant of materials such as iron ore and coal will cause dust emissions. The fugitive dust emission creates a hazardous working environment for the workers. Dust emissions will cause pulmonary-related diseases to the workers and also to the people living in nearby areas of the mine. Environmental effects such as air pollution occur due to the dispersion of particulate matter over the permissible limit in the processing area. This study evaluates dust emission levels and air quality control measures in an iron ore mine (A), Karnataka, India. Fugitive and workplace dust sampling was conducted following DGMS and MoEF and CC guidelines, with a specific focus on PM10 and PM2.5 particulate matter. Measurements revealed that dust concentrations in several mining areas exceeded the permissible limit of 1200 μg/m³ as per the National Ambient Air Quality Standards (NAAQS, 2009). To analyze and predict these concentrations, supervised machine learning (regression) modeling including linear, polynomial (order 2) and polynomial (order 2) models, was applied. The results indicated that a third-order polynomial regression model provided the best fit for predicting dust concentrations, demonstrating lower error. The study emphasizes the necessity of more robust dust suppression measures including installing a dry fog dust suppression system, to guarantee safe working conditions and adherence to environmental regulations, even in the face of efforts to reduce dust exposure.
Investigation of Dust Emission in Limestone Mines and its Statistical Prediction using Supervised Machine Learning (Regression) Modelling Rajib Pal, Harsha Vardhan, Bharath Kumar Shanmugam, Harish Hanumanthappa, Amrites Senapati Disaster Advances, 2025 In India, the fugitive dust emissions in the processing plant and mining area of limestone mines are very high. The dust emission of (particulate matter) PM10 and PM2.5 forms an unsafe working environment for workers in processing plant areas and mining areas. The excessive emission of PM10 and PM2.5 will cause lung-related diseases to the workers and the people existing in the adjacent areas of the mine. The dust emission majorly causes air pollution to occur due to the distribution of particulate matter in the work area. This study majorly investigates the dust emission levels of PM10 and PM2.5 in the limestone mine of Kadapa, Andra Prasad, India. The investigation on the dust emission of PM10 and PM2.5 was carried out as per the guidelines of DGMS and MoEF and CC guidelines, with a specific focus on PM10 and PM2.5 particulate matter. From the study, it was clear that the dust emission levels of PM10 and PM2.5 in the mine area and some parts of the processing area were below the permissible limit of 1200 μg/m³ as per the National Ambient Air Quality Standards (NAAQS, 2009). It was also found that the dust emission levels of PM10 and PM2.5 in the crushing and screening area of the processing plant were above the permissible limit of 1200 μg/m³. Further the statistical prediction model was developed using linear, quadratic and cubic supervised machine learning (regression) modelling. The results indicated that the cubic regression model will provide the accurate prediction of fugitive dust emission with lower error and standard deviation.
Stability Assessment of Vertical Remnant Pillars In Cut and Fill Mining Method with Numerical Modelling Sumant Mohanto, Aryan Upare, Santosh Murali, Sandeep Panchal, Amrites Senapati World Congress on Civil Structural and Environmental Engineering, 2025 Cut and fill mining method involves extraction of orebody in horizontal slices in weak rock formations.The void created as a result of excavation is backfilled and vertical pillars are left at intervals if the overlying roof is weak.This method is advantageous in terms of ore recovery and safety, making it a preferred method for steeply dipping orebodies in challenging underground environments.These remnant pillars left intact plays a crucial role in supporting the overlying strata and protecting a safe environment for ore exploitation.The stability of these pillars is important since pillar failure results in catastrophic consequences including subsidence or even loss of lives.Hence, the pillar dimension is one of the important parameters which governs the stability of the overlying strata in cut and fill mining method.The present study focuses on the assessment of vertical pillar stability with 5 m 5 m dimension left intact throughout the entire depth of orebody in cut and fill post pillar mining method considering three-dimensional finite element analyses.Based on the simulation results obtained from numerical modeling, it was found that the pillar dimension of 5 m 5 m was stable enough for the considered geo-mining condition with factor of safety above unity.
A practical framework to develop and prioritize safety interventions to improve underground coal miners' safety performance Ashish Kumar, Amrites Senapati, Ashis Bhattacherjee, Apurna Ghosh, Nearkasen Chau Work, 2024 BACKGROUND: Improvement of workers’ safety performance is an integral and essential part of safety management. Relevant safety interventions to improve workers’ safety performance are generally difficult to establish when there is a wide range of occupational hazards and at-risk individuals’ features. OBJECTIVE: This study aimed at formulating a practical approach to develop and prioritize potential safety interventions based on occupational and individual risk factors perceived by workers to promote workers’ safety performance. METHODS: A simple framework developed to identify and prioritize the suitable safety interventions. This framework made use of data collected using standardized and validated questionnaire and domain experts’ opinions. Pearson correlation coefficients, exploratory factor analysis, and multiple linear regression were used to identify significant risk factors associated with workers’ safety performance. Data were collected by interviewing 202 coal mine workers with occupational injuries, and their immediate supervisors from three mines. RESULTS: Safety performance was associated with the occupational factor-domain (poor working condition, poor safety environment, poor job satisfaction, and high job stress) only (regression coefficient = 2.14, p < 0.01). The following interventions were identified and prioritized to promote workers’ safety performance: provide fair compensation to workers, job-specific and safety training, promotion policy, achievable targets, relevant perks/benefits, safety training awareness, workplace lighting, ventilation network, sensitize the management, associate safety performance to promotion, and develop team spirit. CONCLUSION: Our approach helps to identify and prioritize the most relevant interventions to promote safety at work when there are multiple risk factors.
Development of an intervention program to reduce whole-body vibration exposure based on occupational and individual determinants among dumper operators Rahul Upadhyay, Amrites Senapati, Kenora Chau, Ashis Bhattacherjee, Aditya Kumar Patra, Nearkasen Chau International Journal of Occupational Safety and Ergonomics, 2024 INTRODUCTION Studies related to a systematic approach for intervention design to reduce whole-body vibration (WBV) exposure are scarce. This study presents a systematic approach to identifying, selecting, and prioritizing safety interventions to fulfill that research gap. METHODOLOGY A total number of 130 vibration readings for dumper operators was taken from two surface iron ore mines to identify significant determinants of WBV exposure. Initially, age, weight, seat design, awkward posture, machine's age, load tonnage, dumper speed, and haul road condition were hypothesized as determinants. Data were collected through standardized questionnaires and field-based observation. A multivariate statistical approach is applied for the practical use of the intervention program. RESULTS As some of the hypothesized factors were correlated, exploratory factor analysis (EFA) followed by multiple linear regression (MLR) was used to investigate their association with WBV exposure. As per EFA results, hypothesized factors were clubbed under individual, ergonomics, and occupational factors. The occupational and ergonomics factors were found to be significantly associated with WBV exposure through MLR and were used to form safety interventions to reduce WBV exposure. CONCLUSIONS Our methodological approach is original in the occupational-health-research area and can be helpful to tailor the safety interventions for unit-level with minimum effort.
Associations between School-Behavior-Health Difficulties and Subsequent Injuries among Younger Adolescents: A Population-based Study Nearkasen Chau, Philippe Perrin, Gérome Gauchard, Ashis Bhattacherjee, Amrites Senapati, Slimane Belbraouet, Francis Guillemin, Bruno Falissard, Kénora Chau Psychiatry New York, 2023 Objective: School-behavior-health difficulties (SBHDs) may alter physical/mental capabilities and consequently increase injury risk during daily activities. This study assessed the associations of potential SBHDs and their cumulative number (SBHDcn) with various injury types among younger adolescents. Methods: The study population included 1,559 middle-school adolescents in France (10–18 years, 98% under 16,778 boys and 781 girls). They completed a questionnaire at school-year end collecting socioeconomic features (nationality, family structure, parents’ education/occupation/income), school/out-of-school injuries during the school-year (dependent variables), and SBHDs starting before the school-year (low academic performance, alcohol/tobacco/cannabis/other-illicit-drugs use, physical/verbal violence, sexual abuse, perpetrated violence, poor social support, poor general health status, sleep difficulty, depressive symptoms, and suicide attempt). Data were analyzed using logistic regression models and Kaplan–Meier estimates. Results: Injuries were frequent during school-physical/sports-training (10.9%), other-school-training (4.7%), school-free-time (7.4%), out-of-school-sports-activity (16.5%), and traffic (2.2%). Single injury (one injury all injury types combined) and ≥2 injury types affected 23.3 and 7.9% of subjects, respectively. The proportion of adolescents without SBHDs decreased with age more quickly among those with each injury type than among those without injury. Various SBHDs were associated with most injury types, single injury, and ≥2 injury types (sex-age-adjusted odds/relative-risk ratios reaching 11, p < .001). A dose–effect association was found between SBHDcn 1–2/3-5/≥6 and both single injury and ≥2 injury types (sex-age adjusted relative risk ratios reaching 12.66, p < .001, vs. SBHDcn = 0). Socioeconomic features had a moderate confounding role in these associations. Conclusions: SBHDs strongly predict injuries among adolescents. Our findings may inform healthcare providers about their prominent role in detecting/reducing SBHDs and injuries.
Understanding the role of organizational resilience, workers’ well-being, and hazard perception on workplace injuries in an aluminum smelter A Kumar, R Upadhyay, A Senapati, B Samanta, A Bhattacherjee WORK, 10519815261440894 , 2026 2026.0
Human-in-the-Loop Data Analytics for Classifying Fatal Mining Accident Causes Using Natural Language Processing and Machine Learning Techniques A Sharma, A Kumar, H Vardhan, A Mangalpady, BB Mandal, A Senapati, ... Mining, Metallurgy & Exploration 42 (6), 4155-4167 , 2025 2025.0 Citations: 1
An uncertainty-aware decision support system: Integrating text narratives and conformal prediction for trustworthy accident code classification A Kumar, A Senapati, R Upadhyay, S Chatterjee, A Bhattacherjee, ... Process Safety and Environmental Protection, 108134 , 2025 2025.0 Citations: 3
of Igneous Rocks Using Ball Mill Grinding Characteristics SV Swamy, N Channabassamma, BM Kunar, KR Chandar, A Senapati, ... Innovative and Responsible Mining for Inclusive Growth: Proceedings, 11th … , 2025 2025.0
A Hybrid Random Forest Optimized with the Dolphin Swarm Algorithm for Predicting P-Wave Velocity of Igneous Rocks Using Ball Mill Grinding Characteristics SV Swamy, N Channabassamma, BM Kunar, KR Chandar, A Senapati, ... Asian Mining Congress, 433-448 , 2025 2025.0
Stability Assessment of Crown Pillar for an Underground Mine Using K-Cross Validation Technique S Mohanto, D Deb, A Senapati International Journal of Civil Infrastructure 7 , 2024 2024.0 Citations: 1
Stability Assessment of Crown Pillar for an Underground Mine Using K-Cross Validation S Mohanto, D Deb, A Senapati 2024.0
A practical framework to develop and prioritize safety interventions to improve underground coal miners’ safety performance A Kumar, A Senapati, A Bhattacherjee, A Ghosh, N Chau Work 77 (2), 697-709 , 2024 2024.0 Citations: 9
Development of an intervention program to reduce whole-body vibration exposure based on occupational and individual determinants among dumper operators R Upadhyay, A Senapati, K Chau, A Bhattacherjee, AK Patra, N Chau International Journal of Occupational Safety and Ergonomics 30 (1), 41-55 , 2024 2024.0 Citations: 11
Associations between school-behavior-health difficulties and subsequent injuries among younger adolescents: a population-based study N Chau, P Perrin, G Gauchard, A Bhattacherjee, A Senapati, S Belbraouet, ... Psychiatry 86 (4), 344-363 , 2023 2023.0 Citations: 4
Association between screen time and cumulating school, behavior, and mental health difficulties in early adolescents: a population-based study K Chau, A Bhattacherjee, A Senapati, F Guillemin, N Chau Psychiatry research 310, 114467 , 2022 2022.0 Citations: 48
Causal relationship of some personal and impersonal variates to occupational injuries at continuous miner worksites in underground coal mines A Senapati, A Bhattacherjee, S Chatterjee Safety science 146, 105562 , 2022 2022.0 Citations: 31
A comparison of multiple machine learning algorithms to predict whole-body vibration exposure of dumper operators in iron ore mines in India R Upadhyay, A Senapati, A Bhattacherjee, AK Patra, S Chatterjee International Journal of Statistics in Medical Research 10, 169 , 2021 2021.0 Citations: 7
Associations of job-related hazards and personal factors with occupational injuries at continuous miner worksites in underground coal mines: a matched case-control study in … A Senapati, A Bhattacherjee, N Chau Industrial health 58 (4), 306-317 , 2020 2020.0 Citations: 15
Predictors of Occupational Injuries at Continuous Miner Worksite: An Epidemiological Study A Senapati, A Bhattacherjee 2018.0
Association of Some Personal and Occupational Factors with Accidents at Continuous Miner Worksite: A Case Study A Senapati, A Bhattacherjee, K Ravichandran 2017.0
Association of Occupational Risk Factors with Safety Performance of Workers and Prioritization of Interventions Using Axiomatic Principle A Kumar, A Senapati, A Bhattacherjee
Stability Assessment of Vertical Remnant Pillars In Cut and Fill Mining Method with Numerical Modelling S Mohanto, A Upare, M Santosh, S Panchal, A Senapati
IMPACT OF SOME OCCUPATIONAL HAZARDS AND INDIVIDUAL CHARACTERISTICS IN WORKERS’INJURIES AT CONTINUOUS MINER WORKSITE A Senapati, A Bhattacherjee
MOST CITED SCHOLAR PUBLICATIONS
Association between screen time and cumulating school, behavior, and mental health difficulties in early adolescents: a population-based study K Chau, A Bhattacherjee, A Senapati, F Guillemin, N Chau Psychiatry research 310, 114467 , 2022 2022.0 Citations: 48
Causal relationship of some personal and impersonal variates to occupational injuries at continuous miner worksites in underground coal mines A Senapati, A Bhattacherjee, S Chatterjee Safety science 146, 105562 , 2022 2022.0 Citations: 31
Associations of job-related hazards and personal factors with occupational injuries at continuous miner worksites in underground coal mines: a matched case-control study in … A Senapati, A Bhattacherjee, N Chau Industrial health 58 (4), 306-317 , 2020 2020.0 Citations: 15
Development of an intervention program to reduce whole-body vibration exposure based on occupational and individual determinants among dumper operators R Upadhyay, A Senapati, K Chau, A Bhattacherjee, AK Patra, N Chau International Journal of Occupational Safety and Ergonomics 30 (1), 41-55 , 2024 2024.0 Citations: 11
A practical framework to develop and prioritize safety interventions to improve underground coal miners’ safety performance A Kumar, A Senapati, A Bhattacherjee, A Ghosh, N Chau Work 77 (2), 697-709 , 2024 2024.0 Citations: 9
A comparison of multiple machine learning algorithms to predict whole-body vibration exposure of dumper operators in iron ore mines in India R Upadhyay, A Senapati, A Bhattacherjee, AK Patra, S Chatterjee International Journal of Statistics in Medical Research 10, 169 , 2021 2021.0 Citations: 7
Associations between school-behavior-health difficulties and subsequent injuries among younger adolescents: a population-based study N Chau, P Perrin, G Gauchard, A Bhattacherjee, A Senapati, S Belbraouet, ... Psychiatry 86 (4), 344-363 , 2023 2023.0 Citations: 4
An uncertainty-aware decision support system: Integrating text narratives and conformal prediction for trustworthy accident code classification A Kumar, A Senapati, R Upadhyay, S Chatterjee, A Bhattacherjee, ... Process Safety and Environmental Protection, 108134 , 2025 2025.0 Citations: 3
Human-in-the-Loop Data Analytics for Classifying Fatal Mining Accident Causes Using Natural Language Processing and Machine Learning Techniques A Sharma, A Kumar, H Vardhan, A Mangalpady, BB Mandal, A Senapati, ... Mining, Metallurgy & Exploration 42 (6), 4155-4167 , 2025 2025.0 Citations: 1
Stability Assessment of Crown Pillar for an Underground Mine Using K-Cross Validation Technique S Mohanto, D Deb, A Senapati International Journal of Civil Infrastructure 7 , 2024 2024.0 Citations: 1
Understanding the role of organizational resilience, workers’ well-being, and hazard perception on workplace injuries in an aluminum smelter A Kumar, R Upadhyay, A Senapati, B Samanta, A Bhattacherjee WORK, 10519815261440894 , 2026 2026.0
of Igneous Rocks Using Ball Mill Grinding Characteristics SV Swamy, N Channabassamma, BM Kunar, KR Chandar, A Senapati, ... Innovative and Responsible Mining for Inclusive Growth: Proceedings, 11th … , 2025 2025.0
A Hybrid Random Forest Optimized with the Dolphin Swarm Algorithm for Predicting P-Wave Velocity of Igneous Rocks Using Ball Mill Grinding Characteristics SV Swamy, N Channabassamma, BM Kunar, KR Chandar, A Senapati, ... Asian Mining Congress, 433-448 , 2025 2025.0
Stability Assessment of Crown Pillar for an Underground Mine Using K-Cross Validation S Mohanto, D Deb, A Senapati 2024.0
Predictors of Occupational Injuries at Continuous Miner Worksite: An Epidemiological Study A Senapati, A Bhattacherjee 2018.0
Association of Some Personal and Occupational Factors with Accidents at Continuous Miner Worksite: A Case Study A Senapati, A Bhattacherjee, K Ravichandran 2017.0
Association of Occupational Risk Factors with Safety Performance of Workers and Prioritization of Interventions Using Axiomatic Principle A Kumar, A Senapati, A Bhattacherjee
Stability Assessment of Vertical Remnant Pillars In Cut and Fill Mining Method with Numerical Modelling S Mohanto, A Upare, M Santosh, S Panchal, A Senapati
IMPACT OF SOME OCCUPATIONAL HAZARDS AND INDIVIDUAL CHARACTERISTICS IN WORKERS’INJURIES AT CONTINUOUS MINER WORKSITE A Senapati, A Bhattacherjee
