2.1.6. Random Forest (RF)

Random forest is a supervised machine learning algorithm that builds on the concept of tree classifiers. It generates a large number of classification trees and uses them to classify new feature vectors. Each tree in the forest classifies the input vector, and the tree's classification is counted as a "vote" for that class. The forest then chooses the classification with the highest number of votes across all the trees in the forest as the final prediction. RF is a highly effective algorithm for handling complex, high-dimensional datasets. It uses ensemble learning to reduce overfitting and improve the model's accuracy by combining the outputs of multiple decision trees [50].

## 2.1.7. Artificial Neural Network (ANN)

Artificial neural networks (ANNs) are computer programs designed to mimic the way the human brain processes information. They derive their inspiration from biological neural networks and adopt a similar structure of interconnected neurons to perform complex tasks. ANNs acquire knowledge through experience by identifying patterns and relationships in data instead of relying on explicit programming to accomplish the task.

An ANN typically consists of many processing elements (PE), also known as artificial neurons, which are connected by weights. These weights constitute the neural structure of the network and are organized into layers. The structure of an ANN is shown in Figure 1E. Through a process of training, the network learns to adjust the weights between the neurons to produce the desired output given a specific input. ANNs can be used for a variety of tasks, such as image and speech recognition, natural language processing, predictive analytics, and healthcare [51]. Figure 1 represents common supervised ML algorithms.

#### *2.2. Unsupervised Machine Learning*

Unsupervised learning is a subfield of machine learning where the data provided to the machine learning algorithm is unlabeled, and it is up to the algorithm to make sense of the data on its own. In unsupervised learning, the algorithm looks for patterns and structures in the data and tries to group similar data points together based on their similarities or differences. One of the key advantages of unsupervised learning is that it can reveal insights and relationships that may not be immediately apparent to human observers. By discovering patterns and similarities in the data, unsupervised learning can help uncover the hidden relationships that can be useful for making decisions or solving problems. For example, unsupervised machine learning can be used to identify customer

segments in a marketing dataset or to find anomalies or outliers in a dataset that may indicate fraudulent activity [41].

**Figure 1.** Schematic illustrations of supervised machine learning algorithms. (**A**) SVM model. Reprinted from [52]. (**B**) KNN model Reprinted from [53]. (**C**) DT model. Reprinted from [54]. (**D**) LR model Reprinted from [55]. (**E**) ANN model. Reprinted from [56].
