Stress fusion evaluation modeling and verification based on non-invasive blood glucose biosensors for live fish waterless transportation

Non-invasive blood glucose level (BGL) evaluation technology in skin mucus is a wearable stress-detection means to indicate the health status of live fish for compensating drawbacks using traditional invasive biochemical inspection. Nevertheless, commonly used methods cannot accurately obtain BGL variations owing influence an uncertain exudation rate, ambient effects, and individualized differences. Our study proposes non-invasive multi-sensor-fusion-based method evaluate dynamic enhanced gray wolf-optimized backpropagation network (EGWO-BP) continuously acquire more accurate trends. Furthermore, K-means++ (KMPP) algorithm utilized further improve accuracy acquisition by clustering with full consideration its size features. In verification test, turbot (Scophthalmus Maximus) was selected as experimental subject perform continuous monitoring waterless keep-alive transportation acquiring comprehensive biomarker information from different parts mucus, such fins, body, tails. The comparison results indicates that KMPP-EGWO-BP can effectively variation than (GWO-BP), particle swarm-optimized (PSO-BP), (BP), support vector regression (SVR) mean absolute percentage error (MAPE), root square (RMSE), coefficient determination ( R 2 ). Finally, proposed fusion model precisely fish's physiological stress states substantially reduce potential mortality circulation industry.