Dr. Hadafi Fitri bin Mohd Latip
Universiti Teknologi Malaysia, Malaysia

Dr. Hadafi Fitri bin Mohd Latip is an academic and researcher at Universiti Teknologi Malaysia (UTM), with expertise in sports performance and technology, biomechanics, sports injury, and rehabilitation. He earned his PhD from UTM in 2016. His research contributions include ankle rehabilitation, balance training, muscle activity analysis, kinesiology taping, and fall prevention.

His professional experience encompasses academic leadership, research, consultancy, and sports science education. He has delivered invited presentations on biomechanics, ergonomics, injury prevention, sports psychology, and strength and conditioning. He has also contributed to national sports science training programmes and professional committees. His work has received recognition in research, teaching, supervision, and sports, reflecting his contributions to sports science and its practical applications in health and human performance.

EDGE POSE ERGO AI APPS SLIDE PRESENTATION : 

The increasing prevalence of prolonged sitting and standing in modern workplaces has
contributed significantly to the rise of musculoskeletal disorders (MSDs), fatigue, poor
posture, and reduced occupational productivity. This study introduces EdgePose Ergo:
Real-Time AI Ergonomic Monitoring and Fatigue Prediction System for Prolonged Sitting
and Standing, an intelligent ergonomics solution that integrates edge computing,
computer vision, and artificial intelligence (AI) to monitor human posture and predict
fatigue levels in real time. The system utilizes AI-powered pose estimation algorithms to
analyze body alignment, joint angles, and movement patterns through non-invasive
camera-based monitoring. By employing edge computing architecture, posture data
processing occurs locally with minimal latency, ensuring fast response time, enhanced
privacy, and reduced dependency on cloud infrastructure.
The proposed system is capable of continuously detecting ergonomic risk factors
associated with prolonged static postures, including forward head posture, slouched
sitting, uneven weight distribution, and excessive standing duration. Machine learning
models are incorporated to predict fatigue progression based on biomechanical
indicators, posture deviations, duration of inactivity, and movement frequency. Real-time
feedback and corrective recommendations are delivered through visual and auditory
alerts to encourage healthier posture behaviours and timely micro-break interventions.
This research adopts a quantitative experimental approach involving office workers and
industrial employees exposed to extended sitting and standing tasks. Ergonomic
assessment tools such as Rapid Upper Limb Assessment (RULA), Borg Fatigue Scale,
and posture angle analysis are integrated into the validation process. The effectiveness
of the system is evaluated based on posture correction accuracy, fatigue prediction
reliability, user compliance, and reduction in ergonomic risk exposure. Preliminary
findings indicate that AI-based ergonomic monitoring significantly improves posture
awareness, reduces fatigue-related symptoms, and enhances workplace well-being and
productivity.
The innovation of EdgePose Ergo contributes to the advancement of smart occupational
health technologies aligned with Industry 4.0 and digital workplace transformation. The
system has strong potential applications in offices, manufacturing industries,
educational institutions, healthcare environments, and remote working settings.
Ultimately, this study demonstrates how real-time AI-driven ergonomic monitoring can
serve as a proactive solution in preventing workplace injuries and promoting sustainable
human performance.