Dewi, Ratih Kusuma (2018) Pemodelan Pemilihan Moda Transportasi pada Komuter di Jabodetabek Menggunakan Bayesian Network dan Regresi Logistik Polytomous. Masters thesis, Institut Teknologi Sepuluh Nopember.
Preview |
Text
1316201703-Master_Thesis.PDF - Accepted Version Download (2MB) | Preview |
Abstract
Fenomena urban sprawl yang terjadi di DKI Jakarta menyebabkan pemekaran daerah disekitarnya. Urban sprawl merupakan proses perembetan kenampakan fisik kota ke arah luar yang disebabkan oleh pesatnya perkembangan ekonomi dan pertumbuhan penduduk. Kawasan “Bodetabek” berubah fungsi menjadi pemukiman yang padat penduduk bahkan menjadi kawasan industri. Oleh karena itu, sebagian penduduk Bodetabek maupun DKI Jakarta meninggalkan rumah untuk melakukan aktivitasnya di luar wilayah administrasi tempat tinggalnya dan kembali pada hari itu juga. Pelaku migrasi semacam ini biasanya disebut sebagai komuter. Pergerakan rutin para komuter Jabodetabek menjadi penyebab utama kemacetan lalu lintas. Peralihan moda transportasi komuter dari kendaraan pribadi ke angkutan umum merupakan solusi untuk mengurangi kemacetan. Meski demikian, belum semua komuter berminat menggunakan angkutan umum. Hasil dari Survei Komuter 2014 menunjukkan bahwa hanya 27 persen komuter Jabodetabek yang menggunakan kendaraan umum untuk pergi ke tempat tujuan. Bayesian Network (BN) dan regresi logistik digunakan dalam pemodelan pemilihan moda transportasi di Jabodetabek. Regresi logistik sudah banyak digunakan dalam pemodelan klasifikasi. Sementara BN merupakan model yang mampu menjelaskan struktur hubungan antara berbagai variabel random yang kompleks ke dalam bentuk diagram berdasarkan teori peluang bersyarat. Pada penelitian ini akan dibandingkan BN dan Regresi Logistik Polytomous dalam pemodelan pemilihan moda transportasi di Jabodetabek. Penggunaan Regresi Logistik Polytomous disebabkan karena jumlah kategori pada variabel respon lebih dari dua. Hasil penelitian menunjukkan bahwa pada data testing, metode Regresi Logistik Polytomous (enter) mempunyai Correct Classifiation Rate (CCR) dan Area Under The Curve (AUC) tertinggi, yang berarti metode tersebut memberikan akurasi yang tertinggi.
=========== The urban sprawl phenomenon that occurred in DKI Jakarta led to the expansion of the surrounding area. Urban sprawl is a process of physical exposure to the outer city physical appearance caused by the rapid economic development and population growth. The "Bodetabek" area has turned into a densely populated residence and even an industrial estate. Compromise made by citizens of Bodetabek and DKI Jakarta leave the house to carry out its activities outside the administrative area of his residence and back on that day. People who do this kind of migration are called commuters. The routine movement of Jabodetabek commuter is the main cause of traffic jam. The transition of commuter transport modes from private vehicles to public transport is a solution to reduce congestion. However, not all commuters are interested in using public transportation. The results from the 2014 Komuter Survey show that only 27 percent of Jabodetabek commuters use public transport to go to their destination. Bayesian Network (BN) and logistic regression are used in modeling of transportation choice in Jabodetabek. Logistic regression is widely used in classification modeling. While BN is a capable model of explaining the structure of relationships between complex random variables into diagrammatic forms based on conditional probability theory. In this research, BN will be compared with polytomous logistic regression in modeling of transportation choice in Jabodetabek. The use of polytomous logistic regression is due to the number of categories in the response variable more than two. The results showed that the highest value of Correct Classifiation Rate (CCR) and Area Under The Curve (AUC) is achieved by Polytomous Logistic Regression (enter) in testing data, it means this method produce the best accuracy.
| Item Type: | Thesis (Masters) |
|---|---|
| Additional Information: | RTSt 519.542 Dew p |
| Uncontrolled Keywords: | Bayesian Network; Regresi Logistik Polytomous; komuter; Jabodetabek; Bayesian Network; Polytomous Logistic Regression; commuter; Jabodetabek |
| Subjects: | H Social Sciences > HA Statistics H Social Sciences > HE Transportation and Communications > HE311.I4 Urban transportation Q Science > QA Mathematics > QA278.2 Regression Analysis. Logistic regression |
| Divisions: | Faculty of Mathematics, Computation, and Data Science > Statistics > 49101-(S2) Master Thesis |
| Depositing User: | Ratih Kusuma Dewi |
| Date Deposited: | 29 Jan 2018 04:56 |
| Last Modified: | 25 Apr 2024 08:42 |
| URI: | http://repository.its.ac.id/id/eprint/50890 |
Actions (login required)
 |
View Item |