EVALUASI KINERJA SUPPORT VECTOR MACHINE (SVM) DALAM PREDIKSI KANKER PARU-PARU

Erovand, Briliant Hibatullah and Agarina, Melda (2025) EVALUASI KINERJA SUPPORT VECTOR MACHINE (SVM) DALAM PREDIKSI KANKER PARU-PARU. Skripsi thesis, Institut Informatika dan Bisnis Darmajaya.

[img] Text
COVER.pdf
Download (258kB)
[img] Text
HALAMAN PERNYATAAN.pdf
Download (275kB)
[img] Text
HALAMAN PERSETUJUAN.pdf
Download (115kB)
[img] Text
HALAMAN PENGESAHAN.pdf
Download (115kB)
[img] Text
RIWAYAT HIDUP.pdf
Download (179kB)
[img] Text
HALAMAN PERSEMBAHAN.pdf
Download (177kB)
[img] Text
MOTTO.pdf
Download (221kB)
[img] Text
INTISARI & ABSTRACT.pdf
Download (279kB)
[img] Text
PRAKATA.pdf
Download (245kB)
[img] Text
DAFTAR ISI.pdf
Download (294kB)
[img] Text
DAFTAR TABEL & GAMBAR.pdf
Download (165kB)
[img] Text
BAB 1.pdf
Download (279kB)
[img] Text
BAB 2.pdf
Download (373kB)
[img] Text
BAB 3.pdf
Download (416kB)
[img] Text
BAB 4.pdf
Download (1MB)
[img] Text
BAB 5.pdf
Download (264kB)
[img] Text
DAFTAR PUSAKA.pdf
Download (226kB)
[img] Text
LAMPIRAN.pdf
Download (136kB)

Abstract

PERFORMANCE EVALUATION OF SUPPORT VECTOR MACHINE (SVM) IN LUNG CANCER PREDICTION By BRILLIANT HIBATULLAH EROVAND E-mail : brillianthibatullahlpg@gmail.com This study aims to evaluate the performance of the Support Vector Machine (SVM) algorithm in predicting lung cancer using a public dataset from Kaggle consisting of 5,000 patient records with 18 feature attributes. The research method applies the CRISP-DM framework, which includes the stages of business understanding, data understanding, data preparation, modeling, evaluation, and deployment. In the data preparation stage, data transformation, normalization using the Min-Max Scaling method, and feature selection through Recursive Feature Elimination (RFE) were performed. The modeling process utilized two SVM kernel types, namely Linear and Radial Basis Function (RBF). Evaluation results indicate that the Linear kernel achieved an accuracy of 89%, while the RBF kernel reached 89.6%. After hyperparameter tuning using GridSearchCV and cross-validation, the SVM model with the RBF kernel achieved an improved accuracy of 91.7%, with precision, recall, and F1-score values exceeding 90% for both target classes. The findings demonstrate that the SVM algorithm, particularly with the optimized RBF kernel, provides superior classification performance compared to previous studies. The resulting model has the potential to serve as a foundation for developing medical decision support systems aimed at early detection of lung cancer efficient, and assist medical professionals in clinical decision-making. Keywords: Support Vector Machine, Prediction, Lung Cancer, Machine Learning, CRISP-DM

Item Type: Thesis (Skripsi)
Subjects: Ilmu Komputer
eSkripsi
Divisions: Skripsi/TA & PKPM/KP - Fakultas Ilmu Komputer > Sistem Informasi
Depositing User: Brilliant Erovand
Date Deposited: 02 Dec 2025 06:23
Last Modified: 02 Dec 2025 06:23
URI: http://repo.darmajaya.ac.id/id/eprint/23244

Actions (login required)

View Item View Item