Anomaly Detection in Emerging Crimes with Deep Autoencoder Architecture

Document Type : Original Article

Author

Department of Electrical Engineering, Payame Noor University, Tehran, Iran.

Abstract

Crimes nowadays pose unique issues to security and legal institutions and requires smart approaches to different types of peculiar behavior within. This paper proposes a deep learning autoencodes framework to analyze and recognize unusual activities in the FBI’s crime dataset. Utilizing the autoencoder model’s architecture consisting of input, compression, and output layers, the Adam optimizer is used with a Mean Squared Error loss function for training, validating with twenty percent of the data. A reconstruction error is calculated and subsequently, a threshold of the 95th percentile of the average MSE is set to flag anomalies. Findings prove that the model outperforms all comparative methodologies, achieving 98% accuracy and a 97% precision F1 score. In addition, the model was shown to have an AUC on ROC curve of 98.2% which confirms the model’s ability to accurately classify normal and abnormal samples. This study illustrates the capability of multi-dimensional autoencoders to analyze and process complex crime data which can greatly aid security agencies in premeditative and reactive responses to crime. Further research will focus on attention-based hybrid models along with system for real-time responsive tracing of volatile hyperdynamics.

Keywords

References

  1. Rezaei, G., & dorostkar yaghouti, b. (2024). Artificial intelligence in crime prevention; advantages and challenges. Journal of Information and Communication Technology in Policing, 5(19), -. doi:10.22034/pitc.2024.1279899.1303.
  2. Ozkan-Okay, M., Akin, E., Aslan, Ö., Kosunalp, S., Iliev, T., Stoyanov, I., & Beloev, I. (2024). A Comprehensive Survey: Evaluating the Efficiency of Artificial Intelligence and Machine Learning Techniques on Cyber Security Solutions. IEEE Access, 12, 12229–12256. doi:10.1109/access.2024.3355547.
  3. Dorrani, Z. (2025). Optimization of Photonic Nanocrystals for Invisibility Using Artificial Intelligence. Journal of Advanced Materials in Engineering, 44(1), 55–70. doi:10.47176/jame.44.1.1088.
  4. SabbaghGol, H., Saadatfar, H., & Khazaiepoor, M. (2024). Predicting alzheimer's disease: A machine learning approach using advanced feature selection techniques. Journal of Modern Medical Information Sciences, 10(3), 307-324.
  5. Shirazi, H. , Shadan, F. , & Qorbani Fouladi, M. (2024). Damage Detection of Truss Bridges Using Artificial Neural Network Considering the Effect of Non-Structural Elements. Contributions of Science and Technology for Engineering, 1(1), 43-49. doi:10.22080/cste.2024.5013.
  6. Dorrani, Z., & Abadi, H. J. (2024). Neural Network Design for Energy Estimation in Surge Arresters. Majlesi Journal of Telecommunication Devices, 13(4), 229-237. doi:10.71822/mjtd.2024.1130109.
  7. Notghimoghadam, S. M., Farsi, H., & Mohamadzadeh, S. (2023). Object Detection by a Hybrid of Feature Pyramid and Deep Neural Networks. Journal of Electrical and Computer Engineering Innovations, 11(1), 173–182. doi:10.22061/jecei.2022.9012.567.
  8. Ahmed, W., & Yousaf, M. H. (2024). A Deep Autoencoder-Based Approach for Suspicious Action Recognition in Surveillance Videos. Arabian Journal for Science and Engineering, 49(3), 3517–3532. doi:10.1007/s13369-023-08038-7.
  9. Veena, K., Meena, K., Kuppusamy, R., Teekaraman, Y., Angadi, R. V., & Thelkar, A. R. (2022). Cybercrime: Identification and Prediction Using Machine Learning Techniques. Computational Intelligence and Neuroscience, 2022, 8237421. doi:10.1155/2022/8237421.
  10. Farsi, H., Notghi Moghadam, S. M., Barati, A., & Mohamadzadeh, S. (2026). Development of a Deep Learning Model Inspired by Transformer Networks for Multi-class Skin Lesion Classification. International Journal of Engineering, 39(1), 135–147. doi:10.5829/ije.2026.39.01a.11.
  11. Rohani, M., Farsi, H., & Mohamadzadeh, S. (2025). Advanced Multi-Task Learning with Lightweight Networks and Multi-Head Attention for Efficient Facial Attribute Estimation. International Journal of Engineering, 38(10), 2259–2272. doi:10.5829/ije.2025.38.10a.05.
  12. Rohani, M., Farsi, H., & Mohamadzadeh, S. (2023). Deep Multi-task Convolutional Neural Networks for Efficient Classification of Face Attributes. International Journal of Engineering, 36(11), 2102–2111. doi:10.5829/ije.2023.36.11b.14.
  13. Dorrani, Z. (2023). Road Detection with Deep Learning in Satellite Images. Majlesi Journal of Telecommunication Devices, 12(1), 43–47.
  14. Dorrani, Z., Farsi, H., & Mohammadzadeh, S. (2022). Edge Detection and Identification using Deep Learning to Identify Vehicles. Journal of Information Systems and Telecommunication, 10(39), 201–210. doi:10.52547/jist.16385.10.39.201.
  15. Dorrani, Z., Farsi, H., & Mohamadzadeh, S. (2022). Deep Learning in Vehicle Detection Using ResUNet-a Architecture. Jordan Journal of Electrical Engineering, 8(2), 165. doi:10.5455/jjee.204-1638861465.
  16. Dorrani, Z. (2024). Traffic Scene Analysis and Classification using Deep Learning. International Journal of Engineering, 37(3), 496–502. doi:5829/ije.2024.37.03c.06.
  17. Zhao, H., Min, S., Fang, J., & Bian, S. (2025). AI-driven music composition: Melody generation using Recurrent Neural Networks and Variational Autoencoders. Alexandria Engineering Journal, 120, 258–270. doi:10.1016/j.aej.2025.02.013.
  18. Zhao, X., Liu, P., Mahmoudi, S., Garg, S., Kaddoum, G., & Hassan, M. M. (2024). DDANF: Deep denoising autoencoder normalizing flow for unsupervised multivariate time series anomaly detection. Alexandria Engineering Journal, 108, 436–444. doi:10.1016/j.aej.2024.07.013.
  19. Kasimu, A., Zhou, W., Meng, Q., Wang, Y., Wang, Z., Zhang, Q., & Peng, Y. (2025). Performance evaluation of pretrained deep learning architectures for railway passenger ride quality classification. Alexandria Engineering Journal, 118, 194–207. doi:10.1016/j.aej.2025.01.007.
  20. Abbas, Z. K., & Al-Ani, A. A. (2022). Anomaly detection in surveillance videos based on H265 and deep learning. International Journal of Advanced Technology and Engineering Exploration, 9(92), 910–922. doi:10.19101/IJATEE.2021.875907.
  21. Hussain, A., Khan, S. U., Khan, N., Ullah, W., Alkhayyat, A., Alharbi, M., & Baik, S. W. (2024). Shots segmentation-based optimized dual-stream framework for robust human activity recognition in surveillance video. Alexandria Engineering Journal, 91, 632–647. doi:10.1016/j.aej.2023.11.017.
  22. Said Elsayed, M., Le-Khac, N.-A., Dev, S., & Jurcut, A. D. (2020). Network Anomaly Detection Using LSTM Based Autoencoder. Proceedings of the 16th ACM Symposium on QoS and Security for Wireless and Mobile Networks, 37–45. doi:10.1145/3416013.3426457.
  23. Elmetwally, A., Eldeeb, R., & Elmougy, S. (2025). Deep learning based anomaly detection in real-time video. Multimedia Tools and Applications, 84(11), 9555–9571. doi:10.1007/s11042-024-19116-9.
  24. Tutar, H., Güneş, A., Zontul, M., & Aslan, Z. (2024). A Hybrid Approach to Improve the Video Anomaly Detection Performance of Pixel- and Frame-Based Techniques Using Machine Learning Algorithms. Computation, 12(2), 19. doi:10.3390/computation12020019.
  25. Ganagavalli, K., & Santhi, V. (2024). YOLO-based anomaly activity detection system for human behavior analysis and crime mitigation. Signal, Image and Video Processing, 18(Suppl 1), 417–427. doi:10.1007/s11760-024-03164-7.
  26. Jebur, S. A., Alzubaidi, L., Saihood, A., Hussein, K. A., Hoomod, H. K., & Gu, Y. (2025). A Scalable and Generalised Deep Learning Framework for Anomaly Detection in Surveillance Videos. International Journal of Intelligent Systems, 2025(1). Portico. doi:10.1155/int/1947582.
  27. Natha, P., & Rajeswari, P. R. (2024). Skin Cancer Detection using Machine Learning Classification Models. International Journal of Intelligent Systems and Applications in Engineering, 12(6s), 139–145.
  28. Moazzami Gudarzi, A. , & Ozgoli, H. A. (2024). Optimal Selection and Efficient Utilization of Particle Swarm Optimization Methods for Designing Renewable Energy Microgrids. Contributions of Science and Technology for Engineering, 1(2), 20-30. doi:10.22080/cste.2024.27781.1002.
  29. Dorrani, Z., Farsi, H., & Mohamadzadeh, S. (2023). Shadow Removal in Vehicle Detection Using ResUNet-a. Iranian Journal of Energy and Environment, 14(1), 87–95. doi:10.5829/ijee.2023.14.01.11.
  30. Dorrani, Z. (2024). Deep Learning for Line Road Detection in Smart Cars. Majlesi Journal of Telecommunication Devices, 13(2). doi:10.30486/MJTD.2024.1107681
  31. Zakaria, N. J., Shapiai, M. I., Ghani, R. A., Yassin, M. N. M., Ibrahim, M. Z., & Wahid, N. (2023). Lane Detection in Autonomous Vehicles: A Systematic Review. IEEE Access, 11(1), 3729–3765. doi:10.1109/ACCESS.2023.3234442.
  32. Elharrouss, O., Hmamouche, Y., Idrissi, A. K., El Khamlichi, B., & El Fallah-Seghrouchni, A. (2023). Refined edge detection with cascaded and high-resolution convolutional network. Pattern Recognition, 138(1), 109361. doi:10.1016/j.patcog.2023.109361.
  33. Burgsteiner, H., Kandlhofer, M., & Steinbauer, G. (2016). IRobot: Teaching the Basics of Artificial Intelligence in High Schools. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). doi:10.1609/aaai.v30i1.9864.
  34. Mousavimehr S. M., & Kavianpour, M. R. (2025). Estimating Groundwater Levels in Tehran Province Using Ensemble Learning Algorithms, Contributions of Science and Technology for Engineering, 2(1), 51-63. doi:22080/cste.2025.29082.1036.
Contributions of Science and Technology for Engineering
Volume 2, Issue 3
July 2025
Pages 45-56

Files

History

  • Receive Date: 26 March 2025
  • Revise Date: 10 May 2025
  • Accept Date: 07 June 2025
  • First Publish Date: 07 June 2025
  • Publish Date: 01 July 2025

Share

How to cite

Statistics