Enhancing Workplace Productivity through Real-Time Machine Learning-Based Feedback Systems

Abstract

New developments in automated vision and machine learning have uncovered techniques and advancements that provide fresh possibilities for developing intelligent and effective production systems. This study develops a real-time production workflow surveillance system aimed at the Smart Connected Workers (SCW) for small and medium-sized producers that combines work environment scenarios of modern production systems with cutting-edge machine learning approaches. In particular, artificial neural systems are presented to allow real-time power division for additional optimisation, whereas object identification and recognising word models are studied and implemented to improve the time-consuming machine state tracking procedure. In addition to offering SMMS an economical alternative, the created system successfully reduced the cost associated with human effort by achieving efficient management and accurate data processing in real-time for extended working circumstances. The findings of the competence study also showed that incorporating machine learning technology into modern production systems is both possible and efficient.