Description:
This project investigates the use of Machine Learning algorithms to classify tumors. The dataset used consists of 500 images of tumors, divided into two classes: benign and malignant.
Two Machine Learning algorithms were evaluated: Random Forest and Naive Bayes. The results show that Random Forest outperformed Naive Bayes, with an accuracy rate of 0.9736842105263158.
Requirements:
- Python 3.8 or higher
- Scikit-learn, matplotlib and pandas libraries
Conclusion:
The results of this project show that Machine Learning algorithms can be effective in classifying tumors. The Random Forest algorithm performed better than Naive Bayes, with an accuracy rate of 0.9736842105263158. However, it is important to note that the results should be interpreted with caution as the data set used was relatively small. Additionally, Machine Learning algorithms can be susceptible to bias, which must be considered when interpreting results. To further improve the performance of the algorithms, it is possible to use larger and more diverse data sets. Furthermore, it is important to investigate methods to reduce lifetimes in Machine Learning algorithms.
Author:
- [Kaíque Freire dos Santos]