SavedAdd your journal

Journals / Turkish Journal of Engineering / 2026 / Volume: 10 Issue: 4

DeepSwarm-DBSCAN: Deep Learning and Swarm Intelligence for Automated Density-Based Clustering

Asmaa Khazaal(University of Baghdad)0000-0003-0486-1142
Mohammad Ali Balafar(University of Tabriz)0000-0001-5898-0871
Ali Jameel Hashim(The Communication and Media Commission (CMC))
Pages
—
Publication Date
2026-10-16
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

DeepSwarm-DBSCAN offers a robust, scalable, and efficient clustering framework suitable for real-world high- dimensional data analysis across diverse application domains.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Density-Based Spatial Clustering of Applications with Noise is widely used for unsupervised clustering due to its ability to identify arbitrarily shaped clusters and handle noise.
📊
Key Findings & Data:The proposed DeepSwarm-DBSCAN framework integrates deep neural networks with an enhanced Particle Swarm Optimization (PSO) algorithm to automatically determine optimal DBSCAN hyper- parameters.
💡
Conclusion & Impact:DeepSwarm-DBSCAN offers a robust, scalable, and efficient clustering framework suitable for real-world high- dimensional data analysis across diverse application domains.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Dynamic Environment · Anomaly Detection · Deep Neural Network

Abstract

Density-Based Spatial Clustering of Applications with Noise is widely used for unsupervised clustering due to its ability to identify arbitrarily shaped clusters and handle noise. However, its effectiveness strongly depends on appropriate hyperparameter selection, which becomes challenging and computationally expensive for high-dimensional data. This study aims to address this limitation by proposing an automated and scalable optimization framework. The proposed DeepSwarm-DBSCAN framework integrates deep neural networks with an enhanced Particle Swarm Optimization (PSO) algorithm to automatically determine optimal DBSCAN hyper- parameters. Convolutional Neural Networks (CNN) and Autoencoders (AE) learn compact and meaningful feature representations, projecting high-dimensional data into lower-dimensional latent spaces. An adaptive PSO strategy then searches this reduced space to optimize clustering validity metrics efficiently. Experimental evaluations on MNIST and CIFAR-10 datasets demonstrate that DeepSwarm-DBSCAN outperforms conventional DBSCAN, achieving clustering accuracies of 92%, 91%, and 94%—with a silhouette coefficient of 0.7 on MNIST—indicating strong cluster coherence. Additionally, the proposed approach reduces hyperparameter optimization runtime by approximately 30% compared to traditional grid search methods. Conclusion: The results confirm that combining deep representation learning with swarm-based optimization provides an effective solution for DBSCAN hyperparameter tuning. DeepSwarm- DBSCAN offers a robust, scalable, and efficient clustering framework suitable for real- world high-dimensional data analysis across diverse application domains. The results confirm that combining deep representation learning with swarm-based optimization provides an effective solution for DBSCAN hyperparameter tuning. DeepSwarm-DBSCAN offers a robust, scalable, and efficient clustering framework suitable for real-world high- dimensional data analysis across diverse application domains.

🔖

Cite This Article

Khazaal, A., Balafar, M. A., Hashim, A. J. (2026). DeepSwarm-DBSCAN: Deep Learning and Swarm Intelligence for Automated Density-Based Clustering. Turkish Journal of Engineering, Volume: 10 Issue: 4. https://doi.org/10.31127/tuje.1888218

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (26)

  1. Harika, B., Yerram, T., Katukuri, M., & Mitukula, R. (2026). Smart wearable vision-assistance system for visually impaired using edge-based deep learning. Turkish Journal of Engineering.
  2. Zhang, R., Peng, H., Dou, Y., et al. (2022). Automating DBSCAN via deep reinforcement learning. In Proceedings of the ACM International Conference (pp. 2620–2630). https://doi.org/10.1145/3511808.3557245
  3. Manikandan, T., Yogarayan, S., Sayeed, M. S., et al. (2025). Fog-aware hierarchical autoencoder with latent-space gating and density-based clustering for privacy-preserving threat detection in IoT-enabled smart farming environments. Research Square. https://doi.org/10.21203/rs.3.rs-7449865/v1
  4. Prabu, K., & Sudhakar, P. (2024). A hybrid deep learning approach for enhanced network intrusion detection. Indonesian Journal of Electrical Engineering and Computer Science, 33(3), 1915–1923. https://doi.org/10.11591/ijeecs.v33.i3.pp1915-1923
  5. Yang, Y., Chen, Q., Li, H., et al. (2022). An efficient DBSCAN optimized by arithmetic optimization algorithm with opposition-based learning. The Journal of Supercomputing, 78, 19566–19604. https://doi.org/10.1007/s11227-022-04634-w
  6. Elahifar, B., & Hosseini, E. (2024). Automated real-time prediction of geological formation tops during drilling operations: An applied machine learning solution for the Norwegian continental shelf. Journal of Petroleum Exploration and Production Technology, 14, 1661–1703. https://doi.org/10.1007/s13202-024-01789-5
  7. Bekri, M. E. (2023). Dynamic inertia weight particle swarm optimization for anomaly detection: A case of precision irrigation. Journal of Internet Services and Information Security, 13(2), 157–176. https://doi.org/10.58346/jisis.2023.i2.010
  8. Poli, R., Langdon, W. B., & McPhee, N. (2021). Particle swarm optimization: A review of the state-of-the-art. Swarm and Evolutionary Computation, 55, 100737.
  9. Belek, A. E., & Katılmış, Z. (2026). A multi-stage machine learning pipeline for Alzheimer's disease classification using optimized ensemble models. Turkish Journal of Engineering.
  10. Özkurt, C., Canay, Ö., Üzelge, P., Dursun, A., & Soyaslan, M. (2026). Real-time bolt defect detection with artificial intelligence in industrial quality control applications: Comparative evaluation of YOLO architectures. Turkish Journal of Engineering.
  11. Ye, F. (2017). Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data. PLoS ONE, 12. https://doi.org/10.1371/journal.pone.0188746
  12. Wang, Z., & Ye, C. (2024). Deep clustering evaluation: How to validate internal clustering validation measures. arXiv. https://doi.org/10.48550/arXiv.2403.14830
  13. Ezenkwu, C. P., Starkey, A., & Aziz, A. A. (2025). Clusterswarm: Cluster-specific feature selection using binary particle swarm optimisation. Computing, 107. https://doi.org/10.1007/s00607-025-01534-8
  14. Djenouri, Y., Srivastava, G., & Lin, J. C. (2020). Fast and accurate convolution neural network for detecting manufacturing data. IEEE Transactions on Industrial Informatics, 17, 2947–2955. https://doi.org/10.1109/TII.2020.3001493
  15. Bengio, Y., Courville, A., & Vincent, P. (2013). Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(8), 1798–1828.
  16. LeCun, Y., Cortes, C., & Burges, C. J. C. (2019). The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist/
  17. Xie, J., Girshick, R., & Hjelm, R. D. (2016). Unsupervised deep embedding for clustering analysis. In Proceedings of the 33rd International Conference on Machine Learning (Vol. 48, pp. 478–487).
  18. Guo, X., Gao, L., Ding, J., et al. (2017). Improved deep embedded clustering with enhanced structure preserving. In Proceedings of the IEEE International Conference on Computer Vision (ICCV) (pp. 313–321).
  19. Li, J., Huang, J., Gao, X., et al. (2023). Unsupervised deep embedded clustering for high-dimensional visual features of fashion images. Applied Sciences, 13(5), 2828.
  20. Choi, M., & Lee, K. (2018). Hierarchical convolutional neural networks for image classification. Journal of the Korea Institute of Information and Communication Engineering, 22(1), 127–134.
  21. Hjelm, R. D., Fedorov, A., Lavoie-Marchildon, S., et al. (2018). Invariant information clustering for unsupervised image classification and segmentation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 335–345).
  22. Sun, H., Li, X., Ma, J., et al. (2021). SPICE: Semantic pseudo-labeling for image clustering. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 12461–12470).
  23. Huang, Z., Liang, Z., Zhou, S., et al. (2025). An improved density-based spatial clustering of applications with noise algorithm with an adaptive parameter based on the sparrow search algorithm. Algorithms, 18, 273. https://doi.org/10.3390/a18050273
  24. Leiber, C., Miklautz, L., Plant, C., et al. (2025). An introductory survey to autoencoder-based deep clustering: Sandboxes for combining clustering with deep learning. arXiv. https://doi.org/10.48550/arXiv.2504.02087
  25. Peng, H., Huang, X., Sun, S., Zhang, R., Wang, X., & Yu, P. S. (2026). Adaptive and robust DBSCAN with multi-agent reinforcement learning. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(4), 4860–4877. https://doi.org/10.1109/TPAMI.2025.3648017
  26. Ramesh, D., & Jaya, T. (2025). Scalable multi-clustering aggregation scheme in WSN using machine learning. Turkish Journal of Engineering, 9(1), 103–115. https://doi.org/10.31127/tuje.1488192