An Optimized Hybrid Model for Classifying Bacterial Genus using an Integrated CNN-RF Approach on 16S rDNA Sequences

OPTIMIZED CNN-RF MODEL FOR BACTERIAL GENUS CLASSIFICATION

Abstract

The classification of the bacterial genus based on 16S ribosomal DNA (rDNA) sequences is crucial in microbiology and medical research. In recent years, deep learning techniques such as Convolutional Neural Networks (CNNs) have shown promising results in this field. However, these models are limited by the need for large annotated datasets and can be prone to overfitting. On the other hand, Random Forest (RF) algorithms are well known for their accuracy and robustness, but lack the ability to capture complex patterns in sequences. In this study, we propose a hybrid CNN-RF model to address these limitations and improve the classification of the bacterial genus based on 16S rDNA sequences. Our model combines the strengths of both approaches by using CNNs to extract features from the sequences and RF to make the final classification decision. The proposed hybrid model was evaluated on a 16S rDNA sequence dataset and showed improved performance compared to both standalone CNN and RF models. Experimental results show that the proposed model outperforms the existing model in terms of accuracy. On the test set, the proposed model achieved an accuracy of 98.93% while the standalone CNN and RF with an accuracy of 91.95% and 68.78% respectively. This work demonstrates the effectiveness of the Integrated CNN-RF approach in bacterial genus classification and highlights its potential for future applications in microbial research.