Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
September 10, 2025Journal Of Computer Networks Architecture and High Performance ComputingOpen Access

The implementation of the Random Forest Algorithm with Resampling and Without Resampling on the Hepatitis C Disease Dataset

View Full Paper
Ask AI
Bookmark
Share

Authors

IHI Gede HendrayanaUniversitas Teknologi IndonesiaNDNi Putu Dita Ariani Sukma DewiBadan Pengkajian dan Penerapan TeknologiJAJiyestha Aji Dharma AryasaInstitut Teknologi Indonesia

Discussion

Loading...

Member takes

Overview

Analysis evaluates random forest accuracy in hepatitis c classification, highlighting smote+enn effectiveness for class balance.

Key Points

  • Hepatitis C classification achieved high accuracy of 0.9837 but struggled with minority class detection.
  • SMOTE+ENN improved performance, achieving precision and recall of 1.00 for major hepatitis classes.
  • Baseline random forest without resampling showed limitations in minority class detection, especially recall rates.
  • Selecting appropriate resampling techniques is crucial for enhancing AI-based diagnostic tools for hepatitis C.

Cite This Study

Hendrayana et al. (2025) studied this question.

synapsesocial.com/papers/68c1b60d54b1d3bfb60eb1f7https://doi.org/10.47709/cnahpc.v7i3.6089
View Full Paper
Ask AI
Bookmark
Share