Table 1.
The analysis of related literature in the context of predicting the microbe organisms.
Fig 1.
The architecture of the proposed approach for predicting microbe organisms.
It involves data collection, exploratory data analysis, model training and testing.
Table 2.
Description of dataset features.
Fig 2.
The bar chart-based frequency analysis of each microorganism target label showing the number of samples in each class.
Fig 3.
The correlation analysis of employed dataset features indicating the importance of features regarding the target class.
Fig 4.
The scatter plot showing the distribution of features regarding Solidity and Eccentricity along with the target class.
Fig 5.
The scatter showing the distribution of features regarding Extent and Orientation along with the target class.
Fig 6.
The architecture of the proposed HMC approach showing the voting process for the hybrid classifier.
Table 3.
The hyperparameters of employed learning techniques.
Table 4.
Performance analysis of employed machine and deep learning techniques with the proposed technique.
Fig 7.
Comparative analysis of employed machine learning and deep learning models in terms of accuracy and recall.
Fig 8.
Comparative analysis of employed machine learning and deep learning models in terms of prediction error rate.
Table 5.
Individual class-vise report of the proposed approach.
Table 6.
K-fold cross-validation results of employed models.
Table 7.
Performance analysis of the proposed approach with state-of-the-art studies.