ANALISIS PERILAKU PENGEMUDI BERDASARKAN DATA CAN BUS TERHADAP KONSUMSI BAHAN BAKAR BERBASIS ALGORITMA KLASIFIKASI

Hendri Ridwan Ramadhan, . (2026) ANALISIS PERILAKU PENGEMUDI BERDASARKAN DATA CAN BUS TERHADAP KONSUMSI BAHAN BAKAR BERBASIS ALGORITMA KLASIFIKASI. Skripsi thesis, Universitas Pembangunan Nasional Veteran Jakarta.

[img] Text
ABSTRAK.pdf
Download (211kB)
[img] Text
AWAL.pdf
Download (833kB)
[img] Text
BAB 1.pdf
Restricted to Repository UPNVJ Only
Download (268kB)
[img] Text
BAB 2.pdf
Restricted to Repository UPNVJ Only
Download (583kB)
[img] Text
BAB 3.pdf
Restricted to Repository UPNVJ Only
Download (625kB)
[img] Text
BAB 4.pdf
Restricted to Repository UPNVJ Only
Download (3MB)
[img] Text
BAB 5.pdf
Download (194kB)
[img] Text
DAFTAR PUSTAKA.pdf
Download (235kB)
[img] Text
RIWAYAT HIDUP.pdf
Restricted to Repository UPNVJ Only
Download (143kB)
[img] Text
LAMPIRAN.pdf
Download (569kB)
[img] Text
HASIL PLAGIARISME.pdf
Restricted to Repository staff only
Download (18MB)
[img] Text
ARTIKEL KI.pdf
Restricted to Repository staff only
Download (519kB)

Abstract

The development of vehicle data acquisition technologies such as the CAN Bus has become increasingly important for analyzing driver behavior and fuel efficiency, especially for taxi fleets like Bluebird that face high operational costs. This study utilizes CAN Bus data from a Toyota Hiace operating on the Jakarta–Bandung route, collected using Teltonika’s FMC130 and LVCAN200 devices. The data were analyzed using classification algorithms (Random Forest, Decision Tree, Naïve Bayes, SVM, and KNN) in Python via Google Colab and visualized through graphs and tables. The results show that aggressive driving behavior leads to 17.2% higher fuel consumption compared to conservative driving. Random Forest and Decision Tree achieved the highest accuracy of 98%, followed by KNN with 96%, and SVM with 80%. Meanwhile, Naïve Bayes demonstrated the lowest performance, with accuracy 76%. This model provides valuable insights for taxi companies to optimize driver behavior and reduce fuel costs.

Item Type: Thesis (Skripsi)
Subjects: T Technology > TK Electrical engineering. Electronics Nuclear engineering
Divisions: Fakultas Teknik > Program Studi Teknik Elektro (S1)
Depositing User: HENDRI RIDWAN RAMADHAN
Date Deposited: 03 Feb 2026 07:54
Last Modified: 03 Feb 2026 07:54
URI: http://repository.upnvj.ac.id/id/eprint/42495

Actions (login required)

View Item View Item