Application of medical supply inventory model based on deep learning and big data

The existing management structure of medical supply inventory (MSI) is not sufficiently effective, and it incompetent to solve the problems stock control in public security emergencies. Therefore, deep learning big data technology are employed this work optimize enhance efficiency, so that optimized can play an excellent role material After browsing copious literature, economic ordering models with infinite/limited rate without shortage innovatively constructed realize efficient emergency supplies inventory. Besides, fixed-point quantitative method safety construct MSI for scarce time-sensitive supplies, respectively. Then, earthquake-related taken as a case source evaluate solution results model. Moreover, stacked auto-encoders (SAE) algorithm used build demand prediction model MSI. Finally, simulation experiment compares SAE-based back propagation neural network (BPNN) radial basis function (RBFN) verify model’s performance. experimental demonstrate after 150 times training, error between predicted value actual each within 30, accuracy significantly improved. 170 mean absolute (MAE) values BPNN RBFN 31.98 73.73, In contrast, MAE 21.32, which superior other two models. Evidently, by dividing into three critical supplies. research outcome provide essential logistical support dealing