Blood Group Interpretation Algorithm Based on Improved AlexNet

Traditional blood group interpretation technology has poor detection efficiency and interpretation accuracy in the face of complex conditions in clinical environments. In order to improve the interpretation accuracy of the automatic blood group interpretation system, the important role of deep learning in the blood group interpretation system was studied. Based on the AlexNet network model, this paper proposes an improved scheme because of its advantages in terms of speeding up the convergence training speed and enhancing the model's generalizability. However, it still needs improvement in terms of blood group interpretation accuracy. The improved AlexNet network model proposed in this paper added an attention mechanism to the network structure, optimized the loss function in the training algorithm, and adjusted the learning rate attenuation function. The experiments showed that compared with the accuracy of the AlexNet model, its training effect was remarkable, with an accuracy of 96.9%-an increase of 3%. Moreover, the improved network model paid more attention to fine-grained classification, minimized the loss rate, and improved the accuracy of system interpretation.