FuelGuard: Fuel Consumption Anomaly Detection and Visual Verification in Logistics Using Isolation Forest, CBIR, and OCR

Sigit Auliana; Basuki Rakhim Setya Permana; Mochammad Darip; Sujan Chandra  Roy

doi:10.52436/1.jutif.2025.6.6.5276

Authors

Sigit Auliana Computer Science, Universitas Bina Bangsa, Indonesia
Basuki Rakhim Setya Permana Computer Science, Universitas Bina Bangsa, Indonesia
Mochammad Darip Computer Science, Universitas Bina Bangsa, Indonesia
Sujan Chandra Roy Institute of Information and Communication Technology (IICT), Chittagong University of Engineering and Technology, Bangladesh

DOI:

https://doi.org/10.52436/1.jutif.2025.6.6.5276

Keywords:

Anomaly Detection, CBIR, Isolation Forest, Machine Learning, OCR

Abstract

Manual fuel reporting in Indonesian logistics companies, such as PT Balaraja Distribusindoraya, often leads to inefficiency, fraud, and lack of anomaly supervision. This research aims to develop a web-based system that integrates machine learning and computer vision to monitor fuel consumption and detect anomalies in logistics fleets. The proposed system employs Isolation Forest for unsupervised anomaly detection based on fuel volume, travel distance, and fuel ratio, combined with a deep learning–based CBIR module using MobileNetV2 to validate fuel station images, and OCR to extract numerical data from receipts. Following the CRISP-DM methodology, the model was trained and deployed through a Flask-based API and evaluated using black-box and white-box testing. Experimental results show that Isolation Forest achieves the highest anomaly detection performance (F1-Score = 0.81, ROC-AUC = 0.99), CBIR validates official fuel stations with ≥95% similarity, and OCR reaches 97% accuracy in receipt recognition. The novelty of this study lies in its hybrid integration of anomaly detection and visual verification within a single scalable platform. This research contributes to Informatics by providing a framework for hybrid anomaly detection systems that enhance digitalization, transparency, and operational efficiency in the logistics sector.

Downloads

Download data is not yet available.

References

K. Tsolaki, T. Vafeiadis, A. Nizamis, D. Ioannidis, and D. Tzovaras, “Utilizing Machine Learning on Freight Transportation and Logistics Applications: A review,” ICT Express, pp. 284–295, June 2023, doi: 10.1016/j.icte.2022.02.001.

M. Su, Z. Su, S. Cao, K.-S. Park, and S.-H. Bae, “Fuel Consumption Prediction and Optimization Model for Pure Car/Truck Transport Ships,” J. Mar. Sci. Eng., vol. 11, no. 6, June 2023, doi: 10.3390/jmse11061231.

A. Barbado and Ó. Corcho, “Interpretable machine learning models for predicting and explaining vehicle fuel consumption anomalies,” Eng. Appl. Artif. Intell., vol. 115, p. 105222, Oct. 2022, doi: 10.1016/j.engappai.2022.105222.

B. B. Turan, E. Genç, İ. N. Akçığ, N. Göztepe, M. E. Mumcuoğlu, and M. Ünel, “Detecting high fuel consumption in HDVs with ensemble of anomaly detection models,” Aug. 2024, Accessed: July 29, 2025. [Online]. Available: http://dx.doi.org/10.1109/INDIN58382.2024.10774415

H. Xiang et al., “OptIForest: Optimal Isolation Forest for Anomaly Detection,” June 23, 2023, arXiv: arXiv:2306.12703. doi: 10.48550/arXiv.2306.12703.

A. Kumar, K. Hegde, K. Challa, and Y. H, “Anomaly Detection in Fleet Vehicle Data and Statistical Approach to Develop Engine System OBD Thresholds,” SAE Publ., p. 10, Dec. 2024, doi: https://doi.org/10.4271/2024-28-0195.

O. F. M. ElMahdy, M. E. Hassan, and S. M. Metwalli, “Machine learning anomaly detection of lost and unaccounted for gas in natural gas networks,” J. Eng. Appl. Sci., vol. 72, no. 1, p. 123, Aug. 2025, doi: 10.1186/s44147-025-00677-x.

M. Atemkeng et al., “Label Assisted Autoencoder for Anomaly Detection in Power Generation Plants,” Feb. 06, 2023, arXiv: arXiv:2302.02896. doi: 10.48550/arXiv.2302.02896.

A. Giannoulidis and A. Gounaris, “A context-aware unsupervised predictive maintenance solution for fleet management,” J. Intell. Inf. Syst., vol. 60, no. 2, pp. 521–547, Apr. 2023, doi: 10.1007/s10844-022-00744-2.

A. S. Muhammad, C. Wang, and L. Chen, “A Telemetric Framework for Assessing Vehicle Emissions Based on Driving Behavior Using Unsupervised Learning,” Vehicles, vol. 6, no. 4, pp. 2170–2194, Dec. 2024, doi: 10.3390/vehicles6040106.

T. Phiboonbanakit, V.-N. Huynh, T. Horanont, and T. Supnithi, “Unsupervised hybrid anomaly detection model for logistics fleet management systems,” IET Intell. Transp. Syst., vol. 13, no. 11, Nov. 2019, Accessed: Aug. 16, 2025. [Online]. Available: https://trid.trb.org/View/1697032

J. M. Z. H, J. Hossen, and A. B. A. Aziz, “Unsupervised Anomaly Detection for Energy Consumption in Time Series using Clustering Approach,” Emerg. Sci. J., vol. 5, no. 6, pp. 840–854, Dec. 2021, doi: 10.28991/esj-2021-01314.

N. Norouzkhani et al., “Developing and evaluating a gamified self-management application for inflammatory bowel disease using the ADDIE model and Sukr framework,” BMC Med. Inform. Decis. Mak., vol. 25, no. 1, p. 11, Jan. 2025, doi: 10.1186/s12911-024-02842-3.

G. M. Nguegnang, M. Atemkeng, T. Ansah-Narh, R. Rockefeller, G. M. Nguegnang, and M. A. Garuti, “Predicting Fuel Consumption in Power Generation Plants using Machine Learning and Neural Networks,” Feb. 11, 2022, arXiv: arXiv:2202.05591. doi: 10.48550/arXiv.2202.05591.

D. Zhao et al., “A Review of the Data-Driven Prediction Method of Vehicle Fuel Consumption,” Energies, vol. 16, no. 14, Art. no. 14, Jan. 2023, doi: 10.3390/en16145258.

A. Fan, Y. Wang, L. Yang, X. Tu, J. Yang, and Y. Shu, “Comprehensive evaluation of machine learning models for predicting ship energy consumption based on onboard sensor data,” Ocean Coast. Manag., vol. 248, p. 106946, Feb. 2024, doi: 10.1016/j.ocecoaman.2023.106946.

H. Xiang et al., “OptIForest: Optimal Isolation Forest for Anomaly Detection,” in Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, Macau, SAR China: International Joint Conferences on Artificial Intelligence Organization, Aug. 2023, pp. 2379–2387. doi: 10.24963/ijcai.2023/264.

L. Utkin, A. Ageev, A. Konstantinov, and V. Muliukha, “Improved Anomaly Detection by Using the Attention-Based Isolation Forest,” Algorithms, vol. 16, no. 1, p. 19, Jan. 2023, doi: 10.3390/a16010019.

W. Hurst, C. A. C. Montañez, and N. Shone, “Time-Pattern Profiling from Smart Meter Data to Detect Outliers in Energy Consumption,” IoT, vol. 1, no. 1, pp. 92–108, Sept. 2020, doi: 10.3390/iot1010006.

G. Airlangga, “Advanced Machine Learning Techniques For Seismic Anomaly Detection In Indonesia: A Comparative Study Of LOF, Isolation Forest, And One-Class SVM,” J. Lebesgue J. Ilm. Pendidik. Mat. Mat. Dan Stat., vol. 5, no. 1, pp. 49–61, Apr. 2024, doi: 10.46306/lb.v5i1.490.

A. S. Mohammad, T. G. Jarullah, M. T. S. Al-Kaltakchi, J. Alshehabi Al-Ani, and S. Dey, “IoT-MFaceNet: Internet-of-Things-Based Face Recognition Using MobileNetV2 and FaceNet Deep-Learning Implementations on a Raspberry Pi-400,” J. Low Power Electron. Appl., vol. 14, no. 3, p. 46, Sept. 2024, doi: 10.3390/jlpea14030046.

C. Li et al., “PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System,” June 14, 2022, arXiv: arXiv:2206.03001. doi: 10.48550/arXiv.2206.03001.

F. Moradi, M. Tarif, and M. Homaei, “Semi-Supervised Supply Chain Fraud Detection with Unsupervised Pre-Filtering,” Aug. 07, 2025, arXiv: arXiv:2508.06574. doi: 10.48550/arXiv.2508.06574.

H. Wang, L. S. Sua, and B. Alidaee, “Enhancing supply chain security with automated machine learning,” July 22, 2025, arXiv: arXiv:2406.13166. doi: 10.48550/arXiv.2406.13166.

K. Sivakoti, “Vehicle Detection and Classification for Toll collection using YOLOv11 and Ensemble OCR,” Dec. 13, 2024, arXiv: arXiv:2412.12191. doi: 10.48550/arXiv.2412.12191.

K. Thammarak, Y. Sirisathitkul, P. Kongkla, and S. Intakosum, “Automated Data Digitization System for Vehicle Registration Certificates Using Google Cloud Vision API,” Civ. Eng. J., vol. 8, no. 7, pp. 1447–1458, July 2022, doi: 10.28991/CEJ-2022-08-07-09.

D. Fleischhacker, W. Goederle, and R. Kern, “Improving OCR Quality in 19th Century Historical Documents Using a Combined Machine Learning Based Approach,” Jan. 15, 2024, arXiv: arXiv:2401.07787. doi: 10.48550/arXiv.2401.07787.