Dr. Ali Murtoja Shaikh: Manager at Coal India Limited (Eastern Coalfield Limited), India
Article Details
This study, published in Discover Public Health (2026), titled “Comparative evaluation of machine learning models for predicting vibration transmission across body segments in seated shuttle car operators”, investigates how whole-body vibration (WBV) travels through the human body in occupational settings.
- Authors: Ali Murtoja Shaikh, Bibhuti Bhusan Mandal
- Journal: Discover Public Health
- Study type: Experimental + machine learning modeling study
- Participants: 108 male shuttle car operators
- Data sources: Field-measured triaxial vibration signals at seat and multiple body segments
- Models tested: ANN, Gaussian Process Regression, Decision Tree, Random Forest, XGBoost, SVR
Novelty
The main novelty lies in replacing traditional biomechanical WBV models with multi-algorithm machine learning prediction of segment-wise vibration transmission.
Key novel aspects:
- Uses real occupational field data, not lab-only simulations
- Models multiple body segments simultaneously, not just whole-body response
- Incorporates human + environmental variables together (BMI, posture, clothing, vibration frequency)
- Demonstrates a clear benchmark comparison across six ML algorithms in WBV biomechanics
Overall, the novelty is moderate-to-high in applied occupational biomechanics, especially due to real-world dataset integration.
Originality
The work is fairly original in its integration of:
- Occupational vibration exposure science
- Multi-site physiological vibration measurement
- Comparative ML benchmarking for biodynamic prediction
However:
- ANN and tree-based models are already widely used in similar regression problems
- The conceptual shift (ML replacing physics-based WBV models) has been explored in related ergonomic and biomedical domains
So, originality is incremental rather than disruptive, but still meaningful in this niche.
Experimental Rigor
Strengths:
- Reasonable sample size (108 workers in real operational conditions)
- Multi-point vibration measurement improves data richness
- Inclusion of external validation on unseen data strengthens generalizability claims
- Multiple performance metrics (MAE, MSE, R²) used
Limitations:
- Only male participants → gender generalization gap
- Limited demographic diversity
- Potential overfitting risk given very high ANN performance (R² ≈ 0.98)
- No mention of cross-site validation or seasonal/temporal variability
- Feature engineering details and hyperparameter tuning transparency likely limited (common in applied ML studies)
Overall rigor: moderate to strong, but not industrial-grade validation.
Sustainability Impact
Indirect but relevant sustainability contributions:
- Improved WBV prediction can reduce long-term musculoskeletal disorders
- Better ergonomic design may reduce healthcare burden and worker absenteeism
- Can extend equipment lifespan indirectly by optimizing vibration exposure conditions
- Supports safer mining/industrial transport systems
However:
- No direct environmental sustainability (carbon, energy, emissions) contribution
- Impact is primarily occupational health sustainability
Applicability
High applicability in applied industrial and ergonomic domains:
Direct applications:
- Seat and cabin design optimization for mining/shuttle vehicles
- Occupational safety risk assessment tools
- Real-time or predictive WBV exposure monitoring systems
Potential extensions:
- Integration into wearable sensor systems for live monitoring
- Adaptation to automotive, construction, and heavy machinery sectors
- Use in regulatory compliance frameworks for vibration exposure limits
Barriers to deployment:
- Need for sensor infrastructure in real workplaces
- Model retraining required for different vehicle types and populations
- ANN interpretability limitations for safety-critical decisions
Research Portfolio
Ali Murtoja Shaikh is a Mining Engineer, researcher, and Occupational Health & Safety specialist with a PhD from IIT Kharagpur. He works in the coal mining industry with progressive experience in mine operations, strata control, and managerial responsibilities. His research focuses on occupational health risks in underground mines, particularly whole-body vibration exposure and musculoskeletal disorders, integrating machine learning and ergonomic assessment approaches.
Online Profile
He actively contributes to the mining community through digital and professional platforms, including the educational YouTube channel “Mining Knowledge,” which provides technical lectures and career guidance for mining students and professionals. He also manages a large professional network group, “Coal Indian,” where mining professionals share job updates, technical discussions, and industry knowledge, supporting continuous learning and industry engagement.
Education
He holds a PhD in Mining Engineering from IIT Kharagpur (2026) with a CGPA of 7.64, focusing on predictive modeling of vibration exposure in underground mining environments. He completed his B.E. in Mining Engineering from IIEST Shibpur in 2016 with a CGPA of 8.02, along with an Advanced Diploma in Industrial Safety (2023). His foundational education includes Higher Secondary (84.6%) and Secondary education (82.75%).
Research Focus
His research primarily addresses occupational health and safety challenges in underground coal mining, with emphasis on whole-body vibration exposure, ergonomics, and work-related musculoskeletal disorders among machinery operators. He integrates machine learning, artificial neural networks, and statistical modeling to develop predictive frameworks for risk assessment and prevention strategies in mining environments.
Experience
He has progressive industry experience in Coal India-linked mining operations, starting as a Management Trainee and advancing to Assistant Manager, Deputy Manager (Strata Control Officer), and currently serving as Manager (Pit Manager/Panel In-charge). His roles have involved shift management, strata control, operational supervision, and production safety in underground mining environments.
Research Timeline & Activities
His research journey spans from undergraduate ergonomic studies on mining workload assessment to advanced PhD-level work on vibration exposure modeling and machine learning-based prediction of musculoskeletal disorders. Over the years, he has contributed to multiple international journals, conference presentations, collaborative research projects, and training programs in AI applications, ergonomics, and sustainable mining practices.
Awards & Honors
He has received the AMUL Vidya Shree Award for outstanding academic performance (2009) and the Best Paper Award at the HWWE International Conference (2024). These recognitions highlight both his early academic excellence and his continued contributions to occupational health research in mining engineering.
Strength for an Innovative Researcher Award for Dr. Ali Murtoja Shaikh:
1. Strong Integration of Real-World Industrial Experience and Research
A key strength is the direct linkage between active coal mining operations and advanced research. The work is not theoretical or lab-isolated—it is grounded in real underground and shuttle car operating conditions. This strengthens credibility for an “Innovator Award” because it demonstrates problem-driven innovation originating from industry needs, not academic abstraction.
2. High-Impact Application of Machine Learning in Occupational Safety
The study applies advanced ML techniques (especially ANN and ensemble models) to solve a critical safety issue: whole-body vibration exposure in mining workers. The high predictive accuracy (R² ≈ 0.98) shows strong technical capability in translating AI into practical safety engineering tools, which is a hallmark of innovation with measurable impact.
3. Direct Contribution to Worker Health and Risk Prevention
The research addresses musculoskeletal disorders and long-term occupational injury risk, which are major concerns in mining. By enabling prediction of vibration transmission across body segments, the work supports:
- Early risk identification
- Improved ergonomic design
- Preventive occupational health strategies
This demonstrates human-centered innovation with tangible societal benefit, a key criterion for innovation awards.
4. Cross-Disciplinary Innovation (Mining + AI + Biomechanics)
The work uniquely integrates:
- Mining engineering
- Occupational health & ergonomics
- Machine learning and data science
- Human biodynamics
This interdisciplinary combination is a strong indicator of innovation because it moves beyond traditional mining engineering into AI-driven occupational health modeling, creating a modern hybrid research direction.
5. Leadership in Knowledge Dissemination and Industry Engagement
Beyond research, the profile shows strong innovation ecosystem contribution:
- Professional training and educational outreach (Mining Knowledge platform)
- Industry networking through Coal Indian community
- Active managerial role in Coal India operations