Claim Missing Document
Check
Articles

Found 5 Documents
Search

ANTI-VANDALISM SYSTEM FOR MONITORING SMART LEVEL CROSSING PROPERTY: A COMPREHENSIVE REVIEW Rosyidi, M.; Fiantika, Thiya; Irawati, Novi; Nugroho, Sinung
Majalah Ilmiah Pengkajian Industri Vol. 14 No. 3 (2020): Majalah Ilmiah Pengkajian Industri
Publisher : Deputi TIRBR-BPPT

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29122/mipi.v14i3.4089

Abstract

This research addresses the problem of vandalism incident related to the smart level crossing technology. Smart level crossing system is essential as a safety system inside the level area, because of that any failure related to the System will endanger the railway and road user. Another subsystem that protects smart level crossing property is critical. This research will show the plan for applying anti-vandalism technology and analysis another possibility of technology related to the System. Keywords: Vandalism, Smart, Level crossing, Subsystem, Railway.
CHARACTER RECOGNITION FOR INDONESIAN LICENSE PLATE BY USING IMAGE ENHANCEMENT AND CONVOLUTIONAL NEURAL NETWORK Bismantoko, Sahid; Rosyidi, M.; Chasanah, Umi; Suksmono, Adityo; Widodo, Tri
Majalah Ilmiah Pengkajian Industri Vol. 14 No. 2 (2020): Majalah Ilmiah Pengkajian Industri
Publisher : Deputi TIRBR-BPPT

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29122/mipi.v14i2.4198

Abstract

Many Intelligent Transport System technology have been applied in real world problems such as traffic monitoring, parking management, toll collection, law enforcement. ALPR system is one of the ITS technologies that is widely applied, however this ALPR system can not produce faultless recognition yet, especially for Indonesia license plate. In this research, image enhancement and Convolution Neural Network are proposed to the character recognition. The dataset used in this research are Indonesia license plate. The first step is train dataset to recognize character and evaluate the model with recall, precision, and f-1 score from test dataset. The model achieves accuracy and loss just over 0.99 and just below 0.01 on validation dataset respectively.Key Words : ALPR; ITS; Recall; Precision; F-1 Score; Accuracy; Loss.
A COMPARISON PRE-TRAINED MODELS FOR AUTOMATIC INDONESIAN LICENSE PLATE RECOGNITION Bismantoko, Sahid; Rosyidi, M.; Chasanah, Umi; Haryono, Asep; Widodo, Tri
Majalah Ilmiah Pengkajian Industri Vol. 15 No. 1 (2021): Majalah Ilmiah Pengkajian Industri
Publisher : Deputi TIRBR-BPPT

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

Abstract

Automatic License Plate Recognition is related to the Intelligent Transportation System (ITS) that supports the road's e-law enforcement system. In the case of the Indonesian license plate, with various colour rules for font and background, and sometimes vehicle owners modify their license plate font format, this is a challenge in the image processing approach. This research utilizes pre-trained of AlexNet, VGGNet, and ResNet to determine the optimum model of Indonesian character license plate recognition. Three pre-trained approaches in CNN-based detection for reducing time for a build if model from scratch. The experiment shows that using the pre-trained ResNet model gives a better result than another two approaches. The optimum results were obtained at epoch 50 with an accuracy of 99.9% and computation time of 26 minutes. This experiment results fulfil the goal of this research. Keywords : ALPR; ITS; CNN; AlexNet; VGGNet; ResNet
Theoretical Experiments on Road Profile Data Analysis using Filter Combinations Karmiadji, Djoko Wahyu; Rosyidi, M.; Widodo, Tri; Zaenal, Harris; Nurdam, Nofriyadi; Kadir, Andi M.; Hidayat, Sofwan; Bismantoko, Sahid; Pramana, Nurhadi; Winarno, Winarno
Automotive Experiences Vol 6 No 3 (2023)
Publisher : Automotive Laboratory of Universitas Muhammadiyah Magelang in collaboration with Association of Indonesian Vocational Educators (AIVE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/ae.9901

Abstract

Identification of road profiles is needed to provide the input of automotive simulation and endurance testing. The analysis with estimation methods is mostly done to identify road profiles. The main goal of analysis methods is to obtain the data of vertical displacements due to road profile measurement. The acceleration data is obtained from measuring road profile by using 4 sensors of accelerometer placed on each car wheel. The measuring data is converted to be vertical displacement data by using a "double integrator", however, it is not easy to get accurate results since the signal obtained carries a lot of noise and it is necessary to design the right filter reduce the noise. In this study, the signal filtering methods reducing the noise were used Fast Fourier Transform (FFT) and Kalman Filter (KF) combination. Experiments were carried out by combining Fast Fourier Transform and Kalman Filters using an input signal with unit (volt) in the time domain. In addition, this research focused on preparing the survey data that has been obtained by eliminating the noise to convert becoming the displacement input data for providing the loads of automotive simulation testing.
The Road Safety: Utilising Machine Learning Approach for Predicting Fatality in Toll Road Accidents Mutharuddin, Mutharuddin; Rosyidi, M.; Karmiadji, Djoko Wahyu; Fitri, Hastiya Annisa; Irawati, Novi; Waskito, Dwitya Harits; Mardiana, Tetty Sulastry; Subaryata, Subaryata; Nugroho, Sinung
Automotive Experiences Vol 7 No 2 (2024)
Publisher : Automotive Laboratory of Universitas Muhammadiyah Magelang in collaboration with Association of Indonesian Vocational Educators (AIVE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31603/ae.11082

Abstract

Road safety is one of the critical government transportation concerns, especially on the toll roads. With the increasing number of toll roads as part of infrastructure planning, road traffic accidents are significantly escalating. Developing a system that predicts accidents on toll roads will benefit to reduce the harm that is caused by traffic accidents. This study will propose a method for analysing toll road accidents in Indonesia using historical toll road accident data as a dataset to become a pattern to examine the frequency of accidents. This dataset consists of various parameters from three main factors that cause accidents: human, environmental, and road infrastructure factors. Machine learning technique will be mainly used to determine the most influencing factors by employing classifiers such as Logistic Regression (LR), Decision Tree (DT), Gaussian Naïve Bayes (GNB), and K-Nearest Neighbors (KNN) can construct the prediction model. Fourteen subfactors from the data were used to predict the future fatalities caused by accidents, which allowed the system to forecast the accident fatality. The results show accuracy performance on the test set with LR, DT, KNN, and GNB models, 85.3%, 79.4%, 87.1%, and 77.1%, respectively. The KNN Classifier model has the most minor error value of 0.6 compared to the other models. The study’s findings will help analyse the causal factors involved in toll road accidents and could be utilised by road authorities to employ risk control options to mitigate the ramifications.