Application Of The Support Vector Machine And Neural Network Model Based On Particle Swarm Optimization For Breast Cancer Prediction

Application Of The Support Vector Machine And Neural Network Model Based On Particle Swarm Optimization For Breast Cancer Prediction

• By Purwaningsih, Esty;
• Jurnal Nasional Terakreditasi
• 288
• 66-73

There are several studies in the medical field that classify data to diagnose and analyze decisions. To predict breast cancer, this study compares two methods, the

Support Vector Machine method and the Neural Network method based on Particle

Swarm Optimization (PSO) which is intended to determine the highest accuracy value

in the Coimbra dataset data. To implement the Support Vector Machine and Neural

Network method based on PSO, RapidMiner software is used. Then the application

results are compared using Confusion Matrix and ROC Curve. Based on the accuracy of the two models, it is known that the PSO-based Neural Network model has a higher

accuracy value of 84.55% than the results of the PSO-based Vector Support Machine

with an accuracy value of 80.08%. The calculation results, the accuracy of the AUC

performance obtained by the results of the study are, the two methods are PSO-based

Neural Network with AUC value of 0.885 and PSO-based Support Vector Machine with

a value of 0.819 included in the category of Good Classification. 

• Katakunci
• URL https://jurnal.polgan.ac.id/index.php/sinkron/article/view/10195/256
• Penerbit ,

REFERENSI