Skripsi

ANALISIS PERBANDINGAN ALGORITMA MACHINE LEARNING UNTUK KLASIFIKASI TINGKAT KEPARAHAN KECELAKAAN LALU LINTAS

---

Traffic accidents are a serious public safety issue that requires data-driven analytical approaches. This study aims to classify traffic accident severity into three classes, namely fatal, serious, and slight, using machine learning algorithms. Four algorithms are evaluated: Random Forest, Light Gradient Boosting Machine (LightGBM), Support Vector Machine (SVM), and K-Nearest Neighbors (KNN). Model performance is evaluated using accuracy, precision, recall, and f1-score, with f1-score emphasized due to the imbalanced class distribution. The results indicate that LightGBM achieves the best performance, with an accuracy of 0.9874, precision of 0.9940, recall of 0.9683, and an f1-score of 0.9807. Confusion matrix analysis shows that most instances across all severity classes are correctly classified. Furthermore, model interpretability analysis using Shapley Additive Explanations (SHAP) reveals that number_of_casualties, casualty_severity, and enhanced_severity_collision are the most influential features. Overall, this study demonstrates that LightGBM is effective for multiclass traffic accident severity classification.

---

Availability

Detail Information

Series Title

-

Call Number

T1931602026

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026

Collation

xv, 73 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

388.312 07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

kecelakaan lalu lintas
Prodi Sistem Komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment