Classification of H1N1 and Seasonal Vaccines Using Deep Learning-Technique

Resumen

Vaccination plays a important aspect of public health in the control and management of various infectious diseases. Considering the complex and continual evolution of vaccination research, new computational techniques are developed to extend vaccine analysis and classification technique. Through a various evaluation of optimizers such as Adam, SGD, RMSprop, Nadam, and Adagrad, this work examines the categorization of H1N1 and seasonal influenza vaccines using deep learning, aimed at improving model performance.

The models underwent multiple training and validation procedures .The performance calculated using accuracy, precision, recall, and F1-score Advanced neural network architectures were employed to uncover complex structures and relationships within diverse vaccine datasets. The accuracy optained using adam Optimizer for H1N1 was 76.3% and for the seasonal Vaccine is 78.7% The final outcomed examines the optimizer selection significantly and the models in deep learning  vaccine classification was explained . Through the identification of best approaches, the performed model advances in  predictive modeling accuracy, supporting improved vaccination strategies and broader computational applications in healthcare.