You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
My Ph.D. thesis finished and defended at the Brno University of Technology (2018). The package contains all necessary files such as bibtex, template, texts, figures, and all other files according to http://latex.feec.vutbr.cz
One of the most dreadful disease is breast cancer and it has a potential cause for death in women. Every year, death rate increases drastically due to breast cancer. An effective way to classify data is through classification or data mining. This becomes very handy, especially in the medical field where diagnosis and analysis are done through th…
This prototype seeks to alleviate the complexities by identifying pain points in the diagnostic journey and providing a user-friendly platform for managing animal data. This project incorporates machine learning models to enhance diagnostic accuracy, focusing on fungal diseases.
Using a Gaussian Naive Bayes model to diagnose acute urinary inflammation and acute nephritises. Achieved a level of 90% and 95% diagnosing separately and nearly 100% with diagnosing together.
Exploring predictive K-Means Clustering, and Random Forest Classifiers in Breast Cancer diagnostics. I then work on "unboxing" the RFA to investigate feature contribution priorities - an important process in the pursuit of algorithm transparency, particularly in light of the ethical issues raised as industries shift towards complex neural algori…
Liver Disease prediction using binary classification such as SVM, ANN, or Random Forest. Generate missing data using the MICE algorithm. Use SMOTE to oversample minority class to reduce biases towards majority class. ROC analysis and k-fold Cross-validation Hypothesis tests were done. Data Source: UCI Machine Learning Repository