Garuda - Garba Rujukan Digital

KONSTRIBUSI MOBILITAS SISWA SMAN FAVORIT TERHADAP KINERJA RUAS JALAN DI KOTA BANDUNG Agus, Supratman; Maulana, Ifan; Akbardin, Juang
Jurnal Transportasi Vol 11, No 3 (2011)
Publisher : Jurnal Transportasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (519.742 KB)

The volume of traffic on the road sections leading to the center of the City of Bandung is influenced by the number of vehicles used by students of favorite school located in the center of Bandung. This study was carried out on the trips made by the students of the state favorite schools in Bandung and the impact of the trips on the performance of the road. The results indicate that if there were not any journey undertaken by students heading to favorite schools, the degree of saturation of road or the potential traffic congestion on the road could have been reduced.Keywords: favorite schools, traffic volume,road service level.

PENGEMBANGAN MODEL ANDREASSEN DAN ARTIFICIAL NEURAL NETWORKS MULTI VARIABEL UNTUK PREDIKSI FATALITAS LALULINTAS JALAN PADA WILAYAH PERKOTAAN DI JAWA BARAT Agus, Supratman
Jurnal Transportasi Vol 13, No 3 (2013)
Publisher : Jurnal Transportasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (411.654 KB)

Law Number 22 Year 2009 stated that fatality data must be completed with data from hospitals. However, the data reported by the Police of the Republic of Indonesia has not been in accordance to the law. In many countries researchers have been using population and motor vehicles numbers as variables to predict the number of fatalities. Those variables are not fit with Indonesian condition. The main purpose of this study was to develop better fatality prediction model in line with Indonesian condition. This was done by developing multivariable Andreassen and ANN models. The model was built by using population data taken from 8 cities in West Java Province. The main results from model validation test are: (1) three variables ANN with one hidden layer prediction model was the best prediction used for predicting the number of fatalities, (2) the number of fatalities was 122.8% larger than that reported by the Police, and (3) Andreassen prediction model was unfit to be used in Indonesia.

PREDIKSI JUMLAH FATALITAS DENGAN METODE ARTIFICIAL NEURAL NETWORK BERDASARKAN UNDANG-UNDANG LALULINTAS TAHUN 2009 DAN KARAKTERISTIK WILAYAH Agus, Supratman
Jurnal Transportasi Vol 15, No 1 (2015)
Publisher : Jurnal Transportasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (386.955 KB)

AbstractÂ Law No. 22 of 2009, on Road Traffic and Road Transport, stated that the fatality data should be complemented with data coming from the hospital. The fatality data reported by the police is the data from the place of traffic accident. Two variables, population and number of vehicles, have been used to predict the number of traffic accident fatalities in many countries. The purpose of this study was to develop a multivariable Artificial Neural Network model for the prediction of fatality in Indonesia. The predictive model was built with input population data of 2007-2010 from the 26 counties and cities in West Java. The study results showed that the ANN three variables with two hidden layer (ANN3-2HL) model is the best-fatality prediction models and prediction of the number of fatalities in West Java Province for 2010 is 3,872 people, which means greater than the number in the data of the Indonesian National Police. Model ANN3-2HL is expected to be used to predict the actual number of fatalities in road safety studies in Indonesia. Key words: traffic, road safety, accidents, fatalitiesÂ Â AbstrakÂ Undang-Undang Nomor 22 Tahun 2009, tentang Lalulintas dan Angkutan Jalan, menyatakan bahwa data fatalitas perlu dilengkapi dengan data yang berasal dari rumah sakit. Data fatalitas yang dilaporkan oleh Kepolisian berasal dari lokasi kejadian. Untuk memprediksi jumlah fatalitas kecelakaan lalulintas di banyak negara, digunakan dua variabel, yaitu jumlah penduduk dan jumlah kendaraan. Tujuan studi ini adalah mengembangkan model Artificial Neural Network multivariabel untuk prediksi fatalitas di Indonesia. Model prediksi dibangun dengan input data populasi tahun 2007-2010 dari 26 kabupaten-kota di Jawa Barat. Hasil studi menunjukkan bahwa model ANN tiga variabel dengan dua hidden layer (ANN3-2HL) merupakan model prediksi fatalitas terbaik dan jumlah prediksi fatalitas tahun 2010 di Provinsi Jawa Barat adalah 3.872 orang, yang berarti lebih banyak dari data Kepolisian Republik Indonesia. Model ANN3-2HL diharapkan dapat digunakan untuk meramalkan jumlah fatalitas aktual pada studi keselamatan jalan di Indonesia.Â Kata-kata kunci: lalulintas, keselamatan jalan, kecelakaan, fatalitas

PERBANDINGAN MODEL ANDREASSEN DAN MODEL ARTIFICIAL NEURAL NETWORK UNTUK PREDIKSI FATALITAS KORBAN KECELAKAAN LALULINTAS Agus, Supratman
Jurnal Transportasi Vol 12, No 1 (2012)
Publisher : Jurnal Transportasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (246.504 KB)

In ASEAN, Indonesia has largest area and population, longest road infrastructure, and largest number of motor vehicles, but road victimsâ fatality is low. This indicates under-reporting. Existing model of road victimsâ fatality is Andreassen models which use population numbers and motor vehicles numbers asvariables to prediction numbers of fatality. This study aimed to obtaining the best predictive model of road victimsâ fatality which suits Indonesiaâs conditions. Three models were compared are Andreassen model, Artificial Neural Network with two variables (ANN2) and four variables (ANN4), with driving license holderand road length as two additional variables. Model validation was performed on three cities in West Java with different categories population densities. The results reveal that ANN4 is the best fatality prediction model. In addition, predictions of road victim numbers in Indonesia are not only influenced by populationand vehicles number, but also by driving license holder numbers and road length.Keywords: fatality, model comparison, Andreassen model, Artificial Neural Network model

PREDIKSI JUMLAH FATALITAS DENGAN METODE ARTIFIAL NEURAL NETWORKBERDASARKAN UNDANG-UNDANG LALU LINTAS TAHUN 2009 DAN KARAKTERISTIK WILAYAH Agus, Supratman
Prosiding Forum Studi Transportasi Antar Perguruan Tinggi Vol 3 No 1 (2015): The 17th FSTPT of International Symposium
Publisher : FSTPT Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar

Ordinance Number 22 Year 2009 stated that fatality data must be completed with hospitals’ data. However, the data reported by Republic of Indonesia Police has not been in accordance to the law. In many countries, researchers have been using population and motor vehicles numbers as variables to predict fatality victims’ number. Those variables are not fit with Indonesian condition. The main purpose of the study was to develop better fatality prediction model in line with Indonesian condition. This was done by developing multivariable ANN models. The model was built by using population data taken from 26 cities/ in West Java Province. Main results from model validation test are: (1) three variables ANNwith two hidden layer prediction model was the best prediction used for to predict fatality numbers; (2) Fatality number was 90.93% bigger than that fatality data reported by Police RI, that was, 2026 people; ANN3-2HL prediction model was unfit to be used in Indonesia.

VARIABEL UNTUK PREDIKSI FATALITAS KECELAKAAN LALU LINTAS BERDASARKAN KARAKTERISTIK DEMOGRAFI WILAYAH DAN INFRASTRUKTUR JALAN DI INDONESIA Agus, Supratman
Jurnal Transportasi Vol 16, No 3 (2016)
Publisher : Jurnal Transportasi

AbstractÂ This study aims to determine variables which can be used to predict the number of actual fatalities in Indonesia. The method used is the linear correlation coefficient between variables, and correlation between each variable with traffic accident fatalities. The result shows that the variables of population, motorized vehicles, and accessibility are the selected variables with great and significant effects on actual fatality number prediction in Indonesia. Also, the variable of driver licensed ownership has no positive effect on driver behavior and the Andreassen Model (1985) is not suitable to be used for fatality prediction in Indonesia. It is recommended to develop a fatality prediction model in Indonesia with considering the 3 selected variables resulted from this study.Â Keywords: Andreassen Model, fatality, fatality prediction, traffic accident, variable analysis.Â Â Abstrak Â Penelitian ini dimaksudkan untuk mengetahui variabel yang dapat digunakan untuk memprediksi jumlah fatalitas aktual di Indonesia. Metode yang digunakan adalah koefisien korelasi linier antarvariabel serta korelasi masing-masing variabel terhadap fatalitas kecelakaan lalu lintas. Hasil studi ini menunjukkan bahwa variabel-variabel jumlah penduduk, kendaraan bermotor, dan aksesibilitas merupakan variabel-variabel terpilih yang memiliki pengaruh sangat kuat dan signifikan terhadap prediksi jumlah fatalitas aktual di Indonesia. Selain itu diketahui bahwa variabel kepemilikan Surat Izin Mengemudi tidak memiliki pengaruh positif terhadap perilaku pengemudi di jalan dan Model Andreassen (1985) tidak tepat untuk digunakan memprediksi fatalitas di Indonesia. Untuk itu disarankan untuk mengembangkan model prediksi fatalitas di Indonesia dengan mempertimbangkan 3 variabel terpilih hasil penelitian ini.Â Kata-kata kunci: Model Andreassen, fatalitas, prediksi fatalitas, kecelakaan lalu lintas, analisis variabel.

KONSTRIBUSI MOBILITAS SISWA SMAN FAVORIT TERHADAP KINERJA RUAS JALAN DI KOTA BANDUNG Agus, Supratman; Maulana, Ifan; Akbardin, Juang
Jurnal Transportasi Vol 11, No 3 (2011)
Publisher : Jurnal Transportasi

The volume of traffic on the road sections leading to the center of the City of Bandung is influenced by the number of vehicles used by students of favorite school located in the center of Bandung. This study was carried out on the trips made by the students of the state favorite schools in Bandung and the impact of the trips on the performance of the road. The results indicate that if there were not any journey undertaken by students heading to favorite schools, the degree of saturation of road or the potential traffic congestion on the road could have been reduced.Keywords: favorite schools, traffic volume,road service level.

PENGEMBANGAN MODEL ANDREASSEN DAN ARTIFICIAL NEURAL NETWORKS MULTI VARIABEL UNTUK PREDIKSI FATALITAS LALULINTAS JALAN PADA WILAYAH PERKOTAAN DI JAWA BARAT Agus, Supratman
Jurnal Transportasi Vol 13, No 3 (2013)
Publisher : Jurnal Transportasi

Law Number 22 Year 2009 stated that fatality data must be completed with data from hospitals. However, the data reported by the Police of the Republic of Indonesia has not been in accordance to the law. In many countries researchers have been using population and motor vehicles numbers as variables to predict the number of fatalities. Those variables are not fit with Indonesian condition. The main purpose of this study was to develop better fatality prediction model in line with Indonesian condition. This was done by developing multivariable Andreassen and ANN models. The model was built by using population data taken from 8 cities in West Java Province. The main results from model validation test are: (1) three variables ANN with one hidden layer prediction model was the best prediction used for predicting the number of fatalities, (2) the number of fatalities was 122.8% larger than that reported by the Police, and (3) Andreassen prediction model was unfit to be used in Indonesia.

PERBANDINGAN MODEL ANDREASSEN DAN MODEL ARTIFICIAL NEURAL NETWORK UNTUK PREDIKSI FATALITAS KORBAN KECELAKAAN LALULINTAS Agus, Supratman
Jurnal Transportasi Vol 12, No 1 (2012)
Publisher : Jurnal Transportasi

In ASEAN, Indonesia has largest area and population, longest road infrastructure, and largest number of motor vehicles, but road victimsâ fatality is low. This indicates under-reporting. Existing model of road victimsâ fatality is Andreassen models which use population numbers and motor vehicles numbers asvariables to prediction numbers of fatality. This study aimed to obtaining the best predictive model of road victimsâ fatality which suits Indonesiaâs conditions. Three models were compared are Andreassen model, Artificial Neural Network with two variables (ANN2) and four variables (ANN4), with driving license holderand road length as two additional variables. Model validation was performed on three cities in West Java with different categories population densities. The results reveal that ANN4 is the best fatality prediction model. In addition, predictions of road victim numbers in Indonesia are not only influenced by populationand vehicles number, but also by driving license holder numbers and road length.Keywords: fatality, model comparison, Andreassen model, Artificial Neural Network model

PREDIKSI JUMLAH FATALITAS DENGAN METODE ARTIFICIAL NEURAL NETWORK BERDASARKAN UNDANG-UNDANG LALULINTAS TAHUN 2009 DAN KARAKTERISTIK WILAYAH Agus, Supratman
Jurnal Transportasi Vol 15, No 1 (2015)
Publisher : Jurnal Transportasi

AbstractÂ Law No. 22 of 2009, on Road Traffic and Road Transport, stated that the fatality data should be complemented with data coming from the hospital. The fatality data reported by the police is the data from the place of traffic accident. Two variables, population and number of vehicles, have been used to predict the number of traffic accident fatalities in many countries. The purpose of this study was to develop a multivariable Artificial Neural Network model for the prediction of fatality in Indonesia. The predictive model was built with input population data of 2007-2010 from the 26 counties and cities in West Java. The study results showed that the ANN three variables with two hidden layer (ANN3-2HL) model is the best-fatality prediction models and prediction of the number of fatalities in West Java Province for 2010 is 3,872 people, which means greater than the number in the data of the Indonesian National Police. Model ANN3-2HL is expected to be used to predict the actual number of fatalities in road safety studies in Indonesia. Key words: traffic, road safety, accidents, fatalitiesÂ Â AbstrakÂ Undang-Undang Nomor 22 Tahun 2009, tentang Lalulintas dan Angkutan Jalan, menyatakan bahwa data fatalitas perlu dilengkapi dengan data yang berasal dari rumah sakit. Data fatalitas yang dilaporkan oleh Kepolisian berasal dari lokasi kejadian. Untuk memprediksi jumlah fatalitas kecelakaan lalulintas di banyak negara, digunakan dua variabel, yaitu jumlah penduduk dan jumlah kendaraan. Tujuan studi ini adalah mengembangkan model Artificial Neural Network multivariabel untuk prediksi fatalitas di Indonesia. Model prediksi dibangun dengan input data populasi tahun 2007-2010 dari 26 kabupaten-kota di Jawa Barat. Hasil studi menunjukkan bahwa model ANN tiga variabel dengan dua hidden layer (ANN3-2HL) merupakan model prediksi fatalitas terbaik dan jumlah prediksi fatalitas tahun 2010 di Provinsi Jawa Barat adalah 3.872 orang, yang berarti lebih banyak dari data Kepolisian Republik Indonesia. Model ANN3-2HL diharapkan dapat digunakan untuk meramalkan jumlah fatalitas aktual pada studi keselamatan jalan di Indonesia.Â Kata-kata kunci: lalulintas, keselamatan jalan, kecelakaan, fatalitas

Title

Found 11 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 11 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 11 Documents
Search