Repository Copy of: Classifying Operator Experience from Electric Screwdriving Signals: A BiLSTM-Based Study with External Validation

Key Points

• The aim is to classify operator experience levels based on signals obtained during electric screwdriving tasks.
• Utilized bidirectional long short-term memory (BiLSTM) networks for classifying signals.
• Analyzed electric screwdriving signals to assess operator experience.
• Included an external validation step to confirm model accuracy.
• Demonstrated improved accuracy in classifying operator experience using BiLSTM.
• Achieved significant results that suggest BiLSTM is effective in processing and interpreting electric screwdriving signals.