Design and development of healthcare data classification with Gannet Geese migration optimisation

A novel internet of things (IoT) with blockchain enabled healthcare medical data classification with deep learning-based optimisation algorithmic technique is developed. This research initially explored the IoT-based blockchain approach. Then, the input data obtained from the database undergo linear normalisation to transform it into a structured format. After that, the normalised data is given to the feature fusion phase to reduce the dimension of data features; here the feature fusion is performed based on deep neural network (DNN) and Matusita distance. The data augmentation is done by using the synthetic minority over-sampling technique (SMOTE). The augmented data are allowed for medical data classification utilising deep residual network (DRN) which is trained using Gannet Geese migration optimisation (GGMO). The GGMO-based DRN gives better efficiency with augmented accuracy of 92.2%, TPR of 90.2%, and TNR of 92.4%.