AI-Powered Ergonomics: Enhancing Workplace Safety through Posture Detection

Traditional ergonomic assessments in workplaces are subjective, labor-intensive, and often inconsistent, limiting their ability to mitigate musculoskeletal disorders (MSDs). This study presents an AI-powered ergonomic framework integrating TensorFlow MoveNet for real-time posture detection and a Random Forest classifier for precise posture classification. Through a hypothesis-driven approach, we evaluate AI’s impact on workplace safety by analyzing real-world ergonomic risks and their mitigation using automated posture monitoring. Results indicate that the system achieved 100% accuracy in controlled testing and significantly improved workplace ergonomics in diverse settings. AI-driven posture correction reduced workplace injuries by 25% in manufacturing environments and office discomfort by 30%, demonstrating its effectiveness in reducing occupational health risks. Despite its potential, challenges such as data privacy, model generalization, and workplace adoption remain barriers to widespread AI-driven ergonomics adoption. This study highlights the importance of integrating AI into workplace safety standards, offering data-driven solutions to enhance employee well-being and operational efficiency.