Prediksi Kepadatan Kendaraan Pada Tol Surabaya Mojokerto Berdasarkan Data History E-Toll Menggunakan Hidden Markov Model

Yunaningrum, Rania (2024) Prediksi Kepadatan Kendaraan Pada Tol Surabaya Mojokerto Berdasarkan Data History E-Toll Menggunakan Hidden Markov Model. Other thesis, Institut Tekonologi Sepuluh Nopember.

Text 5003201076-Undergraduate_Theses.pdf - Accepted Version Restricted to Repository staff only until 1 October 2026. Download (3MB) | Request a copy

Abstract

Jalan Tol Surabaya-Mojokerto memiliki peran yang sangat pent-ing dalam merubah lanskap perjalanan antara Surabaya Mojok-erto secara substansial. Keberadaan jalan tol ini membawa dampak positif yang terlihat melalui signifikansi pengurangan waktu tempuh, peningkatan efisiensi logistik, dan perbaikan mobilitas barang secara keseluruhan. Lebih dari sekadar mem-permudah pergerakan penduduk, jalan tol ini menjadi tulang punggung dalam mendukung distribusi dan transportasi barang, aspek krusial untuk pertumbuhan berbagai sektor ekonomi di wilayah tersebut. Kemacetan dan kerusakan jalan menjadi salah satu permasalahan yang sering terjadi pada suatu jalan dengan kesibukan tinggi. Penelitian ini difokuskan pada analisis proba-bilitas dan volume kendaraan di berbagai golongan yang me-lalui tol tersebut. Mengingat keterbatasan dalam melakukan observasi langsung, pendekatan Hidden Markov Model (HMM) dengan tapping e-Toll diaplikasikan untuk mengamati asal gerbang dan jenis kendaraan, membuka jendela wawasan men-dalam terhadap pola pergerakan di Jalan Tol Surabaya-Mojokerto. Kebaikan model diukur Mean Absolute Error (MAE) dari parameter input dengan setiap hasil estimasi paramter mas-ing-masing pendekatan. Pengukuran kebaikan model mem-peroleh estimasi parameter HMM menggunakan bayesian lebih mirip dengan parameter input sehingga model yang terbentuk lebih representatif jika digunakan untuk memprediksi kepadatan kendaraan.
=======================================================================================================================
The Surabaya-Mojokerto Toll Road plays a crucial role in substantially transforming the travel landscape between Surabaya and Mojokerto. The existence of this toll road has brought about positive impacts, evident through the significant reduction in travel time, in-creased logistical efficiency, and overall improvement in the mobility of goods. Beyond merely facilitating the movement of the population, this toll road serves as the backbone in supporting the distribution and transportation of goods a crucial aspect for the growth of various economic sectors in the region. Traffic congestion and road damage often pose challenges on a busy road. This research focuses on the analysis of the probability and volume of vehicles in various categories passing through the toll road. Considering the limitations in direct observation, the Hidden Markov Model (HMM) approach with e-Toll tapping is ap-plied to observe the gate of origin and vehicle types, providing a deep insight into the movement patterns on the Surabaya-Mojokerto Toll Road. The goodness of the model is measured using Mean Absolute Error (MAE) of input parameters and estimated parameters in every approaches. Measuring the goodness of the model obtains HMM parameter estimates using Bayesian that are more similar to the input parameters so that the model formed is more representative when used to predict vehicle density.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Algoritma Viterbi, Bayesian, Expectation Maximation, Hidden Markov Model, Kepadaran Kendaraan
Subjects:	H Social Sciences > HA Statistics > HA31.7 Estimation Q Science > QA Mathematics > QA274.2 Stochastic analysis Q Science > QA Mathematics > QA274.7 Markov processes--Mathematical models. Q Science > QA Mathematics > QA402.6 Transportation problems (Programming)
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Rania Yunaningrum
Date Deposited:	09 Aug 2024 03:36
Last Modified:	09 Aug 2024 03:36
URI:	http://repository.its.ac.id/id/eprint/113383

Actions (login required)

View Item