Investigating the Role of Feature Variation and Data Transformations of Different Types of Machine Learning Algorithms in Classifying Benign - Malignant Breast Cancer DOI

Anak Agung Ngurah Gunawana,

Putu Astri Novianti,

Anak Agung Ngurah Frady Cakra Negara

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Май 5, 2025

Abstract Objective: to explain how the role of data transformation and feature selection can be used improve performance machine learning in terms classifying breast tumors into benign or malignant categories based on available cancer datasets. Method: taken from Kaggle Wisconsin, there are 569 data, consisting 357 benign, 212 malignant. 70% is for training 30% testing. Data divided 3 types features (10 features, 30 optional features), each done (original, binary bipolar). By using 7 algorithms (logistic regression, decision tree, naïve bayes, random forest, SVM, ANN, KNN), values TP, FP, FN, TN, accuracy, sensitivity, specificity, precision calculated. Results: ANN method with bipolar has highest values. Conclusion: Proper learning, as well use learning.

Язык: Английский

Investigating the Role of Feature Variation and Data Transformations of Different Types of Machine Learning Algorithms in Classifying Benign - Malignant Breast Cancer DOI

Anak Agung Ngurah Gunawana,

Putu Astri Novianti,

Anak Agung Ngurah Frady Cakra Negara

и другие.

Research Square (Research Square), Год журнала: 2025, Номер unknown

Опубликована: Май 5, 2025

Abstract Objective: to explain how the role of data transformation and feature selection can be used improve performance machine learning in terms classifying breast tumors into benign or malignant categories based on available cancer datasets. Method: taken from Kaggle Wisconsin, there are 569 data, consisting 357 benign, 212 malignant. 70% is for training 30% testing. Data divided 3 types features (10 features, 30 optional features), each done (original, binary bipolar). By using 7 algorithms (logistic regression, decision tree, naïve bayes, random forest, SVM, ANN, KNN), values TP, FP, FN, TN, accuracy, sensitivity, specificity, precision calculated. Results: ANN method with bipolar has highest values. Conclusion: Proper learning, as well use learning.

Язык: Английский

Процитировано

0