Baseline Evaluation of Backpropagation Artificial Neural Network for Visual Image-Based Vehicle Type Classification

Abstract

The increasing number of vehicles in urban areas requires technology-based solutions for efficient transportation management. This study proposes a vehicle classification model using Artificial Neural Networks (ANN) with the backpropagation algorithm, based on digital image data. The model is a feedforward neural network comprising an input layer, a hidden layer with 64 sigmoid-activated neurons, and an output layer with 7 softmax-activated neurons. The dataset, sourced from Roboflow Inc., consists of 16,185 images across eight vehicle classes: Hummer, Toyota Innova, Hyundai Creta, Suzuki Swift, Audi, Mahindra Scorpio, Rolls Royce, and Tata Safari. The data is split 80:20 for training and testing. Input features include vehicle dimensions, dominant RGB color, number of axles, and license plate detection. The model is trained using gradient descent and categorical crossentropy loss. Evaluation results show 85% validation accuracy at epoch 28 and 100% test accuracy. Precision, recall, and F1-score indicate strong performance, though minor errors occur in visually similar classes. These findings demonstrate that backpropagation-based ANN is effective for vehicle classification and can be applied in systems such as automatic parking and traffic monitoring

Keywords

Vehicle classification; artificial neural network; backpropagation; Roboflow dataset; intelligent transportation.

Full Text:

PDF Check Plagiarism PDF

References

Mukaroh and P. S. Sasongko, “Vehicle Plate Number Recognition System Using Backpropagation Artificial Neural Network,” J. Masy. Inform., vol. 11, no. 2, pp. 27–35, 2020, doi: 10.14710/jmasif.11.2.34870.

D. Kurniasari, P. S. Ramadhani, W. Wamiliana, and W. Warsono, “Application of the Artificial Neural Network Algorithm to Predict the Realization of the Duty Tax on the Name of Motor Vehicles in Lampung Province, Indonesia,” J. Artif. Intel. Data Min., vol. 7, no. 2, p. 392, 2024, doi: 10.24014/ijaidm.v7i2.29456.

J. Management, I. Jmti, B. Applications, S. M. Parking, P. L. Lintas, and DANS Security, “Motorcycle in digital image using accurate identification and classification in,” vol. 16, no. 1, pp. 84–90, 2025.

D. Andini, “Artificial Neural Network for Classification of Fever Diseases Using Backpropagation Algorithm,” Bull. Artif. Intell., vol. 2, no. 1, pp. 86–99, 2023, doi: 10.62866/buai.v2i1.80.

C. P. Harahap, “Classification of Fever Diseases Using Artificial Neural Networks Backpropagation Algorithm,” J. Informatics Data Sci., vol. 1, no. 2, pp. 1–6, 2023, doi: 10.24114/j-ids.v1i2.38680.

J. Purwono, S. Sugyaningsih, and E. Yuliati, “Artificial Neural Network Analysis,” Device, vol. 6, no. 7, pp. 117–121, 2019.

M. I. Nugraha and A. Armansyah, “Closing Vocational High School Expertise Competence with Student Interest Classification Approach Using Artificial Neural Network,” J. Technol. Sist. Inf. and Apl., vol. 6, no. 3, pp. 269–275, 2023, doi: 10.32493/jtsi.v6i3.30143.

R. Hidayat, R. Toyib, Y. Apridiansyah, and Y. Reswan, “Classification of herbal leaf images with their efficacy for treatment using artificial neural networks (backpropagation),” vol. 9, no. 4, pp. 5571–5577, 2025.

B. Ardi Isnanto, “田永杰, 唐志坚, 李世斌 (1.2.3),” Detikproperti, vol. 5, no. 4, pp. 119–121, 2023.

S. Informasi and S. Kaputama, “Artificial Neural Network (ANN) Predicts Rubella Disease Using Backpropagation Method,” no. 4, 2024.

D. Miftahul, J. Musdar, N. S. Eriyani, S. Azis, A. B. Kaswar, and S. Sasmita, “Implementation of backpropagation artificial neural network for carrot freshness level classification based on digital image processing with morphological operations,” vol. 9, no. 3, pp. 1518–1533, 2024.

E. Rami Ate, T. Trisno, and M. W. Malo, “Classification of Sumba Woven Fabrics Using Artificial Neural Networks,” J. Technol. Inf. Syst., vol. 3, no. 1, pp. 1–12, 2024, doi: 10.70129/jtis.v3i1.514.

A. Cervellieri, “A Feed-Forward Back-Propagation Neural Network Approach for Integration of Electric Vehicles into Vehicle-to-Grid (V2G) to Predict State of Charge for Lithium-Ion Batteries,” Energies, vol. 17, no. 23, 2024, doi: 10.3390/en17236107.

R. Asmidewi, Y. Muhyidin, and I. Engineering, “Application of Backpropagation Neural Network in Predicting Mandatory Test Vehicle Parks,” pp. 133–146, 2024.

S. Dalm, J. Offergeld, N. Ahmad, and M. van Gerven, “Efficient Deep Learning with Decorrelated Backpropagation,” 2024, [Online]. Available: http://arxiv.org/abs/2405.02385.

M. K. Ngwenyama and M. N. Gitau, “Application of back propagation neural network in complex diagnostics and forecasting loss of life of cellulose paper insulation in oil-immersed transformers,” Sci. Rep., vol. 14, no. 1, pp. 1–28, 2024, doi: 10.1038/s41598-024-56598-x.

P. Salgado and T. P. A. Perdicoúlis, “Multi-back-propagation Algorithm for Signal Neural Network Decomposition,” Neural Process. Lett., vol. 56, no. 2, pp. 1–27, 2024, doi: 10.1007/s11063-024-11518-y.

D. D. Anjani, C. Prakasiwi, and A. P. Windarto, “Analysis of the Application of Backpropagation Artificial Neural Network in Predicting Sales of Crystal Ice Products,” J. Informatics, Electr. Electron. Eng., vol. 3, no. 1, pp. 153–163, 2023, doi: 10.47065/jieee.v3i1.1610.

F. Tedy, P. Batarius, I. P. A. N. Samane, and A. A. J. Sinlae, “Artificial Neural Network-Based Prediction Model Back Propagation on Blood Demand and Blood Supply,” J. RESTI (Information Systems Engineering and Technology), vol. 7, no. 6, pp. 1403–1411, 2023, doi: 10.29207/resti.v7i6.5508.

V. M. M. Siregar, K. Sinaga, E. Sirait, A. S. Manalu, and M. Yunus, “Classification of Customer Satisfaction Through Machine Learning: An Artificial Neural Network Approach,” Internet Things Artif. Intel. J., vol. 3, no. 3, pp. 273–282, 2023, doi: 10.31763/iota.v3i3.643.

L. Y. Zhong and 林延中, “Mei kuang an quan yi qi ji zhuang bei xuan xing shou ce,” vol. 6, no. 3, pp. 187–193, 1989.

A. H. Sulasmoro, C. Supriyanto, and V. Suhartono, “Implementation of Bagging to Improve the Accuracy of Final Project Theme Classification Using Backpropagation Neural Network Algorithm,” Senit, pp. 10–17, 2016.

W. Guswanti, I. Afrianty, E. Budianita, and F. Syafria, “Comparison of Random and Nguyen-Widrow Weight Initialization in Backpropagation in Diabetes Disease Classification,” J. Informatika: J. Pengembangan IT, vol. 10, no. 2, pp. 323–332, 2025, doi: 10.30591/jpit.v9ix.xxx.

P. L. W. E. Putra, M. Naufal, and E. Y. Hidayat, “A Comparative Study of MobileNet Architecture Optimizer for Crowd Prediction,” J. Inform. J. Developer. IT, vol. 8, no. 3, pp. 241–247, 2023, doi: 10.30591/jpit.v8i3.5703.

H. Zhang, Y. Li, and L. Yan, “Prediction Model of Car Ownership Based on Back Propagation Neural Network Optimized by Particle Swarm Optimization,” Sustain., vol. 15, no. 4, pp. 1–14, 2023, doi: 10.3390/su15042908.

T. Sun, P. K. Wong, and X. Wang, “Back Propagation Neural Network-Based Fault Diagnosis and Fault Tolerant Control of Distributed Drive Electric Vehicles Based on Sliding Mode Control-Based Direct Yaw Moment Control,” Vehicles, vol. 6, no. 1, pp. 93–119, 2024, doi: 10.3390/vehicles6010004.

S. Song and Z. Miao, “Research on vehicle type classification based on spatial pyramid representation and BP neural network,” Lect. Notes Comput. Sci., vol. 9219, pp. 188–196, 2015, doi: 10.1007/978-3-319-21969-1_17.

B. Zhang and K. Zeng, “A Lightweight Method for Vehicle Classification Based on Improved Binarized Convolutional Neural Network,” Electron., vol. 11, no. 12, 2022, doi: 10.3390/electronics11121852.

H. Mayatopani, R. I. Borman, W. T. Atmojo, and Arisantoso, “Classification of Vehicle Types Using Backpropagation,” J. Ris. Inform., vol. 4, no. 1, 2021, [Online]. Available: https://ejournal.kresnamediapublisher.com/index.php/jri/article/view/139.

T. Fang, Z. Li, J. Zhang, D. Qi, and L. Zhang, “Open-Set Recognition of Wood Species Based on Deep Learning Feature Extraction Using Leaves,” J. Imaging, vol. 9, no. 8, 2023, doi: 10.3390/jimaging9080154.

L. V. Fausett, Fundamentals of Neural Networks, Prentice Hall, 1993. [Online]. Available: file:///C:/Users/USER/Downloads/Laurene V. Fausett - Fundamentals of Neural Networks (1993, Prentice Hall) - libgen.li-1.pdf.

http://dx.doi.org/10.28989/compiler.v14i2.3210

Article Metrics

Abstract view: 35 times
Download     : 9   times Download     : 2   times

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

Refbacks

• There are currently no refbacks.