Table 4 A comprehensive comparison between the proposed voting-based method and the other previously introduced approaches
From: A voting-based machine learning approach for classifying biological and clinical datasets
Method name | Description | Accuracy | References | |||
|---|---|---|---|---|---|---|
WDBC | CHD5 | CHD2 | SHD | |||
Cooperative coevolution and RF | Filtering samples and features using the genetic algorithm and offering a clinical decision support system using random forest | 97.1 | – | 93.4 | 96.8 | [41] |
ECSA | Extending crow search algorithm for feature selection and categorizing biological samples using the KNN algorithm | 95.76 | – | – | 82.96 | [42] |
DISON and ERT | Providing a clinical decision support system using an extremely randomized tree-based feature selection algorithm and creating a prediction model using Diverse Intensified Strawberry Optimized Neural network | – | – | 93.67 | 94.5 | [43] |
Adaboost SVM | Choosing informative features using three bioinspired optimization algorithm and Adaboost SVM | 98.73 | – | – | – | [44] |
AGFS | Merging the genetic algorithm and fuzzy logic concept for classifying clinical datasets | – | 76.67 | – | – | [45] |
SRLPSO-ELM | Proposing a self-adaptive machine learning technique based on the particle swarm optimization algorithm and extreme learning classifier | – | – | 91.33 | 89.96 | [46] |
SVM-GA | Generating a clinical data classification model based on combining the genetic algorithm and the SVM classifier | – | 72.55 | 90.57 | – | [47] |
ABCO with SVM | Employing the ant colony optimization algorithm for picking out features and evaluating them using the SVM classifier | – | – | 83.17 | 84.81 | [48] |
CFCSA | Designing a hybrid system combining crow search optimization algorithm, chaos theory, and fuzzy c-means algorithm | 98.6 | – | – | 88.0 | [49] |
CSA | Applying the crow search optimization algorithm for selecting features and creating a prediction model using the KNN algorithm | 90.28 | – | – | 78.84 | [50] |
RS-BPNN | Building a prediction model for classifying clinical datasets using the rough set theory and backpropagation neural network | 98.60 | – | – | 90.40 | [51] |
FELM | Extending the concept of fuzzy logic and extreme learning for training an artificial neural network | – | 73.77 | 93.55 | 94.44 | [52] |
ANNWCC | Training an artificial neural network using the world competitive contests algorithm | – | 71.5 | 94.5 | 96.5 | [25] |
CSO, KH, BFO, and super learner | Combining three optimization algorithms with the SVM classifier | 96.83 | – | 84.00 | 86.36 | [48] |
TRADER -SVM | Selecting features using the Trader algorithm and evaluating them using the SVM classifier | 100 | 64.96 | 88.85 | 89.45 | – |
Proposed voting-based model | Labeling a given data sample based on aggregating the prediction results of several models | 100 | 67.21 | 88.85 | 92.73 | – |