Rekomendasi Rute Bus Kota Surabaya Berbasis Konsep 15-Minute City Menggunakan Genetic Algorithm

Zainal, Zharga Prayata (2026) Rekomendasi Rute Bus Kota Surabaya Berbasis Konsep 15-Minute City Menggunakan Genetic Algorithm. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5025221136-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Kota Surabaya sebagai pusat perekonomian dan bagian dari kawasan metropolitan di Indonesia mengalami peningkatan kebutuhan transportasi publik. Meskipun telah tersedia moda transportasi seperti Suroboyo Bus dan Trans Semanggi Suroboyo, rute yang ada masih belum optimal dalam menjangkau penduduk dan fasilitas secara merata. Penelitian ini bertujuan mengembangkan sistem rekomendasi rute bus Kota Surabaya berbasis konsep 15-minute city, yaitu konsep perencanaan kota di mana kebutuhan dasar masyarakat dapat diakses dalam waktu 15 menit dengan berjalan kaki atau bersepeda. Sistem dibangun melalui beberapa tahap. Pertama, klasifikasi kandidat halte menggunakan kombinasi lima model machine learning, yaitu Decision Tree, Random Forest, XGBoost, LightGBM, dan AdaBoost, melalui metode soft voting dengan skema leave-one-route-out dan recall sebagai metrik utama. Kedua, penilaian kelayakan setiap kandidat menggunakan Fuzzy Inference System. Ketiga, generasi populasi awal rute menggunakan K-Shortest Path dan random route. Keempat, optimasi rute menggunakan Genetic Algorithm dengan fitness function berbasis population coverage dan cakupan fasilitas dalam kerangka 15-minute city. Sistem diuji pada empat rute, yaitu SBR1, TMK2, SBR4, dan SBR5. Hasil pengujian menunjukkan bahwa keempat rute usulan memiliki fitness yang lebih tinggi dibanding rute eksisting, dengan peningkatan population coverage sebesar 4,44%–19,88% dan jumlah fasilitas sebesar 2,37% 25,04%, sementara panjang rute berkurang atau hanya bertambah 1%. Peningkatan fitness terbesar diperoleh pada rute SBR4 sebesar 32% dan SBR5 sebesar 27%.
=====================================================================================================================================
Surabaya City, as an economic center and part of a metropolitan region in Indonesia, is experiencing an increasing demand for public transportation. Although transportation modes such as Suroboyo Bus and Trans Semanggi Suroboyo are already available, the existing routes remain suboptimal in reaching the population and facilities evenly. This study aims to develop a bus route recommendation system for Surabaya City based on the 15-minute city concept, a city planning concept in which the basic needs of the community can be accessed within 15 minutes by walking or cycling. The system was built through several stages. First, the classification of candidate bus stops using a combination of five machine learning models, namely Decision Tree, Random Forest, XGBoost, LightGBM, and AdaBoost, through a soft voting method with a leave-one-route-out scheme and recall as the primary metric. Second, the feasibility assessment of each candidate using a Fuzzy Inference System. Third, the generation of an initial route population using K-Shortest Path and random routes. Fourth, route optimization using a Genetic Algorithm with a fitness function based on population coverage and facility coverage within the 15-minute city framework. The system was tested on four routes, namely SBR1, TMK2, SBR4, and SBR5. The test results show that all four proposed routes have higher fitness than the existing routes, with an increase in population coverage of 4,44%–19,88% and in the number of facilities of 2,37%–25,04%, while route length decreased or increased by only 1%. The largest fitness improvement was obtained on route SBR4 at 32% and route SBR5 at 27%.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	15-Minute City, Genetic Algorithm, Rekomendasi Rute Bus, Machine Learning, Fuzzy Inference System, Soft Voting, Coverage,15-Minute City, Genetic Algorithm, Bus Route Recommendation, Machine Learning, Fuzzy Inference System, Soft Voting, Coverage.
Subjects:	H Social Sciences > HT Communities. Classes. Races > HT166 City Planning--Environmental aspects Q Science > QA Mathematics > QA75 Electronic computers. Computer science. EDP
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Informatics Engineering > 55201-(S1) Undergraduate Thesis
Depositing User:	Zharga Prayata Zainal
Date Deposited:	28 Jul 2026 00:55
Last Modified:	28 Jul 2026 00:55
URI:	http://repository.its.ac.id/id/eprint/137962

Actions (login required)

View Item