Klasifikasi Jenis Kendaraan Pada Jalan Raya Menggunakan Metode Convolutional Neural Networks (CNN)
Abstract
Traffic congestion is a major problem that occurs in big cities in Indonesia. This can cause various negative impacts such as waste of fuel, waste of time, and air pollution. Therefore, the government divides the types of highways and only allows large cargo trucks to pass on arterial roads. So it is necessary to have a smart city to implement government policies in order to overcome the impacts caused by traffic congestion. Classification of the types of vehicles that pass on the highway needs to be done so that there are no vehicle violations outside the specifications that are allowed to enter certain highways. Classification of vehicle types using the Convolution Neural Network (CNN) method. The architecture used is in the form of an existing CNN architecture or an existing CNN architecture, namely googlenet and shufflenet. We fine tune Googlenet and Shufflenet to get maximum accuracy. The dataset used is data taken from several CCTV camera points in several cities in Indonesia in July 2021. The proposed method can classify vehicle types with an accuracy of 95.88% Googlenet and 96.48% Shufflenet. Thus, it is hoped that it can contribute to researchers to develop a better CNN so that it can be implemented for the benefit of road traffic in Indonesia in the future
Downloads
References
Fadlia, N., & Kosasih, R. (2019). Klasifikasi Jenis Kendaraan Menggunakan Metode Convolutional Neural Network (Cnn). Jurnal Ilmiah Teknologi Dan Rekayasa, 24(3), 207–215. https://doi.org/10.35760/tr.2019.v24i3.2397
Gando, G., Yamada, T., Sato, H., Oyama, S., & Kurihara, M. (2016). Fine-tuning deep convolutional neural networks for distinguishing illustrations from photographs. Expert Systems with Applications, 66, 295–301.
Hariani, P., Safina, L., & Syarifuddin, J. (2017). City Smart Transportation Sebagai Strategi Medan Menuju Smart City. Jurnal Pembangunan Perkotaan, 5(2), 50–58.
Nurhikmat, T. (2018). Implementasi Deep Learning Untuk Image Classification Menggunakan Algoritma Convolutional Neural Network (CNN) Pada Citra Wayang Golek.
Putra, I. (2016). Klasifikasi citra menggunakan convolutional neural network (CNN) pada caltech 101. Institut Teknologi Sepuluh Nopember.
Rahman, S, Ramli, M., Arnia, F., Muharar, R., & Sembiring, A. (2021). Performance analysis of mAlexnet by training option and activation function tuning on parking images. IOP Conference Series: Materials Science and Engineering, 1087(1), 012084. https://doi.org/10.1088/1757-899X/1087/1/012084
Rahman, Sayuti, Ramli, M., Arnia, F., Sembiring, A., & Muharar, R. (2020). Convolutional Neural Network Customization for Parking Occupancy Detection. 2020 International Conference on Electrical Engineering and Informatics (ICELTICs), 1–6.
Sabilla, I. A. (2020). Arsitektur Convolutional Neural Network (CNN) untuk Klasifikasi Jenis dan Kesegaran Buah pada Neraca Buah. Institut Teknologi Sepuluh Nopember.
Shukla, S., Balachandran, K., & Sumitha, V. S. (2016). A framework for smart transportation using Big Data. 2016 International Conference on ICT in Business Industry & Government (ICTBIG), 1–3.
Suyuti, R. (2012). Implementasi” Intelligent Transportation System (ITS)” untuk Mengatasi Kemacetan Lalu Lintas di DKI Jakarta. Konstruksia, 3(2).
Zhang, X., Zhou, X., Lin, M., & Sun, J. (2018). Shufflenet: An extremely efficient convolutional neural network for mobile devices. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 6848–6856.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Klasifikasi Jenis Kendaraan Pada Jalan Raya Menggunakan Metode Convolutional Neural Networks (CNN)
Pages: 292-301
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
