The Sriwijaya University Library

  • Home
  • Information
  • News
  • Help
  • Login
  • Librarian
  • Member Area
  • Select Language :
    Arabic Bengali Brazilian Portuguese English Espanol German Indonesian Japanese Malay Persian Russian Thai Turkish Urdu

Search by :

ALL Author Subject ISBN/ISSN Advanced Search

Last search:

{{tmpObj[k].text}}
Image of OPTIMALISASI IDENTIFIKASI POLA KECELAKAAN LALU LINTAS MELALUI UNSUPERVISED FEATURE SELECTION DAN SHAP
Bookmark Share

Skripsi

OPTIMALISASI IDENTIFIKASI POLA KECELAKAAN LALU LINTAS MELALUI UNSUPERVISED FEATURE SELECTION DAN SHAP

Almira, Ednagea - Personal Name;

The analysis of traffic accident patterns using unsupervised clustering algorithms on high-dimensional data is often hindered by the presence of uninformative variables (noise) and the limitations of conventional statistical methods in interpreting the meaning of the formed clusters. This research aims to optimize the identification and interpretation of accident patterns through the integration of the Unsupervised Feature Selection (UFS) and SHAP methods. The Sequential Filtering on Variance and Correlation approach was applied to reduce data dimensionality, followed by clustering with K-Means, and variable interpretation through a Random Forest surrogate model and SHAP values. The UFS process successfully filtered 98 encoded variables into the 15 most relevant features, utilizing the Société de l'assurance automobile du Québec (2016-2022) dataset comprising 886,795 incident records. This reduction was proven to optimize the clustering structure by minimizing distance distortion, validated by a consistent increase in internal evaluation metric scores compared to the use of raw data. The K-Means algorithm identified two highly contrasting risk patterns: low-speed urban intersection incidents involving multiple vehicles and high-speed single-vehicle incidents on rural roads. The application of SHAP analysis successfully dismantled the "black box" nature of the clustering algorithm by providing transparent explanations regarding the direction of variable influence, the magnitude of impact, and identifying the transition point on the speed limit that determines pattern classification. Overall, this integrated framework proved effective in addressing the problems of high dimensionality and shallow interpretation, thereby generating accident risk profile insights that are objective, structurally accurate, and comprehensively understandable.


Availability
#
Central Library (REFERENCES) T1984162026
T198416
Available but not for loan - Not for Loan
Detail Information
Series Title
-
Call Number
T1984162026
Publisher
Indralaya : Prodi Magister Ilmu Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2026
Collation
xiv, 73 hlm.:ilus.; 29 cm
Language
Indonesia
ISBN/ISSN
-
Classification
363.125 07
Content Type
Text
Media Type
-
Carrier Type
-
Edition
-
Subject(s)
kecelakaan lalu lintas
Prodi Magister Ilmu Komputer
Specific Detail Info
-
Statement of Responsibility
TUTI
Other version/related

No other version available

File Attachment
  • OPTIMALISASI IDENTIFIKASI POLA KECELAKAAN LALU LINTAS MELALUI UNSUPERVISED FEATURE SELECTION DAN SHAP
Comments

You must be logged in to post a comment

The Sriwijaya University Library
  • Information
  • Services
  • Librarian
  • Member Area

About Us

As a complete Library Management System, SLiMS (Senayan Library Management System) has many features that will help libraries and librarians to do their job easily and quickly. Follow this link to show some features provided by SLiMS.

Search

start it by typing one or more keywords for title, author or subject

Keep SLiMS Alive Want to Contribute?

© 2026 — Senayan Developer Community

Powered by SLiMS
Select the topic you are interested in
  • Computer Science, Information & General Works
  • Philosophy & Psychology
  • Religion
  • Social Sciences
  • Language
  • Pure Science
  • Applied Sciences
  • Art & Recreation
  • Literature
  • History & Geography
Icons made by Freepik from www.flaticon.com
Advanced Search
Where do you want to share?