Analisis Risiko Kecelakaan Lalu Lintas di Jalan Raya Kabupaten Nganjuk Menggunakan Spatio-temporal Point Process On A Linear Network

Ramadhan, Yuri Aditya Rahmad (2025) Analisis Risiko Kecelakaan Lalu Lintas di Jalan Raya Kabupaten Nganjuk Menggunakan Spatio-temporal Point Process On A Linear Network. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211006-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (6MB) | Request a copy

Abstract

Kecelakaan lalu lintas merupakan salah satu tantangan besar dalam pengelolaan transportasi di Indonesia, yang berdampak luas terhadap aspek sosial, ekonomi, dan keselamatan masyarakat. Jawa Timur pada tahun 2023 tercatat sebagai provinsi dengan jumlah kecelakaan lalu lintas tertinggi, dengan Kabupaten Nganjuk sebagai salah satu penyumbang utama. Oleh karena itu, penelitian ini bertujuan untuk menganalisis faktor-faktor yang memengaruhi risiko kecelakaan lalu lintas di Kabupaten Nganjuk berdasarkan aspek spasial dan temporal. Faktor spasial direpresentasikan oleh karakteristik geometrik jalan, sedangkan faktor temporal mencakup variabel cuaca dan iklim. Model yang digunakan adalah separable spatio-temporal intensity, yang dianalisis menggunakan pendekatan spatio-temporal point process on a linear network. separable spatio-temporal digunakan karena faktor risiko yang dianalisis tidak terjadi dependensi secara spasial maupun temporal. Estimasi spasial dilakukan dengan Poisson point process menggunakan skema Berman-Turner dan metode Iteratively Reweighted Least Squares (IRLS), sedangkan aspek temporal dianalisis menggunakan Generalized Linear Model Poisson log-linear dengan iterasi Newton-Raphson. Pemilihan estimasi didasarkan nilai pair correlation function yang mendekati 1 yang mengindikasikan kejadian mengikuti proses Poisson. Hasil menunjukkan bahwa jarak ke lampu lalu lintas, jumlah lajur, dan jenis jalan signifikan secara spasial, sedangkan curah hujan, durasi penyinaran matahari, dan kecepatan angin signifikan secara temporal pada model spatio-temporal intensity. Model spatio-temporal intensity merupakan model terbaik diperoleh melalui seleksi menggunakan backward elimination berdasarkan nilai Bayesian Information Criterion (BIC) terkecil. Hasil prediksi model menunjukkan bahwa risiko kecelakaan lalu lintas di Kabupaten Nganjuk cenderung tinggi pada ruas jalan arteri, terutama di jalur keluar-masuk bagian timur dan area pusat kabupaten. Intensitas kecelakaan tertinggi terjadi pada akhir-awal tahun (Januari–Februari, November) dan pertengahan tahun (Agustus–September).
==================================================================================================================================
Traffic accidents represent one of the major challenges in Indonesia’s transportation management, with wide-ranging impacts on social, economic, and public safety aspects. In 2023, East Java was recorded as the province with the highest number of traffic accidents, with Nganjuk Regency being one of the main contributors. Therefore, this study aims to analyze the factors influencing traffic accident risk in Nganjuk Regency from both spatial and temporal perspectives. Spatial factors are represented by road geometric characteristics, while temporal factors include weather and climate variables. The model used is the separable spatio-temporal intensity model, analyzed using the spatio-temporal point process on a linear network approach. The separable spatio-temporal model was chosen because the risk factors under analysis are assumed to be independent in both space and time. Spatial estimation was carried out using the Poisson point process with the Berman-Turner quadrature scheme and the Iteratively Reweighted Least Squares (IRLS) method, while the temporal aspect was analyzed using a Poisson log-linear Generalized Linear Model (GLM) with the Newton-Raphson iteration method. The estimation approach was selected based on the pair correlation function value approaching 1, indicating that the events follow a Poisson process. The results show that distance to traffic lights, number of lanes, and road type are significant spatial factors, while rainfall, sunshine duration, and wind speed are significant temporal factors in the spatio-temporal intensity model. The spatio-temporal intensity model was identified as the best model through backward elimination based on the smallest Bayesian Information Criterion (BIC) value. The model's prediction results indicate that the risk of traffic accidents in Nganjuk Regency tends to be higher along arterial roads, especially on routes connecting to the eastern boundary and central areas of the regency. The highest accident intensity occurs at the end and beginning of the year (January–February, November) and in the middle of the year (August–September).

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Cuaca dan Iklim, Geometrika Jalan, Kecelakaan Lalu Lintas, Pengelolaan Transportasi, Spatio-temporal Point Process on a Linear Network, Road Geometric, Spatio-temporal Point Process on a Linear Network, Traffic Accidents, Transportation Management, Weather and Climate
Subjects:	H Social Sciences > HA Statistics > HA30.6 Spatial analysis
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Yuri Aditya Rahmad Ramadhan
Date Deposited:	01 Aug 2025 03:16
Last Modified:	01 Aug 2025 03:16
URI:	http://repository.its.ac.id/id/eprint/125223

Actions (login required)

View Item