Development of Artificial Neural Networks Model to Determine Labor Rest Period Based on Environmental Ergonomics

Food SMEs (Small and Medium Enterprises) were examples of labor-intensive industry, which involved laborers in pursuing production activities. require complex processes Support to increase work productivity reduce ergonomic risks the activities was needed. The study conducted at Tofu SMEs. determination rest period could be developed give some recovery times laborers. WBGT (Wet Bulb Globe Temperature) estimated determine period. determined by workstation environment workload labor. ANN (Artificial Neural Networks) model carried out due a nonlinear relationship. used process information from data set predict amount WBGT. trained using backpropagation. backpropagation algorithm error value change weight with forward backward propagation. result showed that dry bulb temperature, heart rate, wet gender significantly impacted A total 180 sets tofu divided into training (80%) validation (20%). optimal structure four input, hidden, two output neurons. activation function sigmoid for both layers. SSE (Sum Squared Errors) obtain best structure. R2 equal above 0.900, indicated labor based on environmental ergonomics.