Enhanced Immunity Disorder Classification Through Hybrid Model Integration

Abstract

This chapter proposes a comprehensive approach for classifying immunity disorders using various deep learning techniques, including Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), and Recurrent Neural Networks (RNN). The study focuses on preprocessing the dataset from Kaggle, titled “Food: Allergens and Allergies,” to enhance the classification accuracy. T-distributed Stochastic Neighbor Embedding (t-SNE) is applied for preprocessing, and Principal Component Analysis (PCA) is applied to reduce dimensionality. Subsequently, the study explores the combination of CNN with t-SNE and PCA to leverage deep learning and dimensionality reduction techniques. This approach addresses the allergy dataset's complexities by strategically combining CNN with t-SNE and PCA and provides a promising framework for more accurate and reliable immunity disorder classification. The suggested system's accuracy, precision, and recall are among the common evaluation measures used to assess its performance. With an accuracy of 90.50%, precision of 0.89, and recall of 0.88, respectively, the experimental findings show that combining CNN with t-SNE and PCA produces greater classification performance than separate models. The suggested technique offers a viable method for correctly and quickly classifying immune illnesses and advancing medical diagnostics and healthcare.