Evaluation of the Performance of Neural and Non-Neural Methods to Classify the Severity of Work Accidents Occurring in the Footwear Industry Complex

• Published in: Applied system innovation 2024-10, Vol.7 (5), p.85
• Main Authors: da Silva, Jonhatan Magno Norte, da Silva Braz, Maria Luiza, da Silva, Joel Gomes, Bispo, Lucas Gomes Miranda, dos Santos Leite, Wilza Karla, de Araujo Vieira, Elamara Marama
• Format: Article
• Language: English
• Subjects: Accident prevention; accuracy; Algorithms; Artificial neural networks; Classification; Computational linguistics; Construction industry; Damage detection; Damage patterns; Decision making; Deep learning; Digital technology; Documents; Equipment and supplies; Footwear industry; Injuries; Language processing; Machine learning; Memory; Methods; Natural language interfaces; Neural networks; Occupational accidents; Occupational safety; Performance evaluation; Regression analysis; shoes industry; Support vector machines; Teaching; Traffic accidents & safety; Workplace accidents
• ISSN: 2571-5577; 2571-5577
• DOI: 10.3390/asi7050085

In the footwear industry, occupational risks are significant, and work accidents are frequent. Professionals in the field prepare documents and reports about these accidents, but the need for more time and resources limits learning based on past incidents. Machine learning (ML) and deep learning (DL) methods have been applied to analyze data from these documents, identifying accident patterns and classifying the damage’s severity. However, evaluating the performance of these methods in different economic sectors is crucial. This study examined neural and non-neural methods for classifying the severity of workplace accidents in the footwear industry complex. The random forest (RF) and extreme gradient boosting (XGBoost) methods were the most effective non-neural methods. The neural methods 1D convolutional neural networks (1D-CNN) and bidirectional long short-term memory (Bi-LSTM) showed superior performance, with parameters above 98% and 99%, respectively, although with a longer training time. It is concluded that using these methods is viable for classifying accidents in the footwear industry. The methods can classify new accidents and simulate scenarios, demonstrating their adaptability and reliability in different economic sectors for accident prevention.