PENENTUAN DAERAH RAWAN KECELAKAAN DENGAN PENDEKATAN METODE JARINGAN SYARAF TIRUAN

Annur Ma'ruf

Abstract


Technology improvement gives positive impacts on increasing transportation mode. But it has a negative impact such as traffic jam and increasing number in traffic accident, so road safety issues must be a common concern. One of the efforts to prevent tha accident is to identify accident-prone areas as a warning system for user. Eleven road sections in Malang District and supported data from Satkorlantas Polres Malang District is used as scope of discussion in this study. In this study, the factors that caused accidents such as road characteristic, geometric and environment condition is used for identifcation the accident-prone area. Based on the data, database mapping was done and the pattern of potential accident-prone areas was determined. It can be used for analysis and decision. Mapping and testing process uses a neural network approach because the accuracy of this method has been already proven in various applications. The results approach on prone area identification indicates a precision with a variance of 0.15% in compare with accident-based data analysis through the validation process. This result shows that neural network approach can be used to identify the accident-prone areas as one of the solution in accident prevention and efforts in road safety improvement.


Keywords


Accident-prone area, Highway, Neural network, Safety

Full Text:

PDF

References


---, 2005, Audit Keselamatan Jalan, Pedoman Konstruksi dan Bangunan Pd T-17-2005 B. Jakarta: Departemen Pekerjaan Umum Republik Indonesia.

---, 2004, Penanganan Lokasi Rawan Kecelakaan Lalu Lintas Pedoman Konstruksi dan Bangunan, Pd T-09-2004-B. Jakarta: Departemen Permukiman dan Prasarana Wilayah Republik Indonesia.

Enggarsari, U., dan Sa'diyah, N. K., 2017, Kajian Terhadap Faktor-Faktor Penyebab Kecelakaan Lalu Lintas Dalam Upaya Perbaikan Pencegahan Kecelkaan Lalu Lintas. Perspektif Volume 22 No. 3, 228-237.

Hidayati, A., dan Hendrati, L. Y., 2016, Analisis Risiko Kecelakaan Lalu Lintas Berdasar Pengetahuan, Penggunaan Jalur dan Kecepatan Berkendara. Jurnal Berkala Epidermiologi Vol 4. No. 2, 275-287.

Keymanesh, M., Ziari, H., Roudini, S., dan Ahangar, A. N., 2017, Identification and Prioritization of "Black Spot" Without Using Accident Information. Modelling and Simulation In Engineering, 1-9.

Marsaid, Hidayat, M., dan Ahsan, 2013, Faktor Yang Berhubungan Dengan Kejadian Kecelakaan Lalu Lintas Pada Pengendara Sepeda Motor Di Wilayah Polres Kabupaten Malang. Jurnal Ilmu Keperawatan Volume 1, No. 2, 98-112.

Ma'ruf, A., Sulistio, H., dan Anwar, M. R., 2016, Kajian Audit Keselamatan Jalan Pada Sebelas Ruas Jalan Utama Di Wilayah Kabupaten Malang. Tesis, Universitas Brawijaya Malang.

Ma'ruf, A., Sulistio, H., dan Anwar, M. R., 2016, Kajian Audit Keselamatan Jalan Pada Sebelas Ruas Jalan Utama Di Wilayah Kabupaten Malang. Prokons Jurnal Teknik Sipil Vol. 10 No. 2, 69-78.

Mulyono, A. T., Kushari, B., dan Gunawan, H. E., 2009, Audit Keselamatan Infrastruktur Jalan (Studi Kasus Jalan Nasional KM 78-KM 79 Jalur Pantura Jawa, Kabupaten Batang). Jurnal Teknik Sipil-Jurnal Teoritis dan Terapan Bidang Rekayasa Sipil Vo.16 No. 3, 163-174.

Purnomo, M. H., 2006, Supervised Neural Network Dan Aplikasinya. Jakarta: Graha Ilmu.

Putri, C. E., 2014, Analisis Karakteristik Kecelakaan Dan Faktor Penyebab Kecelakaan Pada Lokasi Blackspot Di Kota Kayu Agung. Jurnal Teknik Sipil dan Lingkungan Vol. 2 No. 1, 154-161.

Suyanto, 2014, Artificial Intelligence Searching, Reasoning, Planning, Learning. Bandung: Informatika.

Widodo, P. P., dan Handayanto, R. T., 2012, Penerapan Soft Computing Dengan MATLAB. Bandung: Rekayasa Sains.




DOI: http://dx.doi.org/10.21776/ub.rekayasasipil.2019.013.01.10

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.