Fusion-Driven Spatio-Temporal Deep Learning for IoT Intrusion Detection: Integrating CNN, TCN, and CapsuleNet Features with LSTM
Corresponding author: B. Chempavathy
Abstract
The rapid growth of Internet of Things (IoT) devices has increased their susceptibility to various cyber-attacks, making efficient intrusion detection crucial. This study presents a hybrid deep learning model that integrates a Convolutional Neural Network (CNN), a Temporal Convolutional Network (TCN), a Capsule Network (CapsuleNet), and a Long Short-Term Memory (LSTM) to examine complex network behavior patterns for IoT security. This architecture uses CNN and TCN for spatial and temporal feature extraction, CapsuleNet to augment representational capacity, and LSTM to describe long-term dependencies. The model is trained and validated using the NSL-KDD dataset, which encompasses five classes: Normal, Remote to Local (R2L), User to Root (U2R), Denial of Service (DoS), and Probe. Data augmentation using SMOTE reduces class imbalance, while performance measures such as accuracy, recall, and F1 score provide a comprehensive evaluation of performance. The proposed hybrid model achieved a maximum accuracy of 98.71%, outperforming individual models that reached accuracies from 91.02% to 96.76%. This integration of approaches provides an effective and dependable solution for IoT intrusion detection, demonstrating its efficacy in protecting dynamic low-power IoT settings.
Keywords:
IoT security, intrusion detection system, feature fusion, spatio-temporal deep learning, intelligent threat detectionDownloads
References
M. Benmalek and A. Seddiki, "Particle swarm optimization-enhanced machine learning and deep learning techniques for Internet of Things intrusion detection," Data Science and Management, Feb. 2025. DOI: https://doi.org/10.1016/j.dsm.2025.02.005
S. Jamshidi, A. Nikanjam, K. W. Nafi, F. Khomh, and R. Rasta, "Application of deep reinforcement learning for intrusion detection in Internet of Things: A systematic review," Internet of Things, vol. 31, May 2025, Art. no. 101531. DOI: https://doi.org/10.1016/j.iot.2025.101531
A. K. Silivery, K. R. M. Rao, and R. Solleti, "Dual-path feature extraction based hybrid intrusion detection in IoT networks," Computers and Electrical Engineering, vol. 122, Mar. 2025, Art. no. 109949. DOI: https://doi.org/10.1016/j.compeleceng.2024.109949
T. Devapriya, V. Ganesan, and S. Velmurugan, "Efficient malicious node detection in wireless sensor networks using Rabin-Karp algorithm," International Journal of Advances in Signal and Image Sciences, vol. 10, no. 2, pp. 24–36, Dec. 2024. DOI: https://doi.org/10.29284/IJASIS.10.2.2024.24-36
M. A. Talukder, M. Khalid, and N. Sultana, "A hybrid machine learning model for intrusion detection in wireless sensor networks leveraging data balancing and dimensionality reduction," Scientific Reports, vol. 15, no. 1, Feb. 2025, Art. no. 4617. DOI: https://doi.org/10.1038/s41598-025-87028-1
H. Chen, Z. Wang, S. Yang, X. Luo, D. He, and S. Chan, "Intrusion detection using synaptic intelligent convolutional neural networks for dynamic Internet of Things environments," Alexandria Engineering Journal, vol. 111, pp. 78–91, Jan. 2025. DOI: https://doi.org/10.1016/j.aej.2024.10.014
R. Kumar and M. Swarnkar, "QuIDS: A Quantum Support Vector machine-based Intrusion Detection System for IoT networks," Journal of Network and Computer Applications, vol. 234, Feb. 2025, Art. no. 104072. DOI: https://doi.org/10.1016/j.jnca.2024.104072
S. P. Maniraj, C. S. Ranganathan, and S. Sekar, "Securing web applications with owasp zap for comprehensive security testing," International Journal of Advances in Signal and Image Sciences, vol. 10, no. 2, pp. 12–23, Dec. 2024. DOI: https://doi.org/10.29284/IJASIS.10.2.2024.12-23
H. Zeghida et al., "Enhancing IoT cyber attacks intrusion detection through GAN-based data augmentation and hybrid deep learning models for MQTT network protocol cyber attacks," Cluster Computing, vol. 28, no. 1, Nov. 2024, Art. no. 58. DOI: https://doi.org/10.1007/s10586-024-04752-5
R. K. Vanakamamidi, L. Ramalingam, N. Abirami, S. Priyanka, C. S. Kumar, and S. Murugan, "IoT Security Based on Machine Learning," in 2023 Second International Conference On Smart Technologies For Smart Nation (SmartTechCon), Aug. 2023, pp. 683–687. DOI: https://doi.org/10.1109/SmartTechCon57526.2023.10391727
A. Almotairi, S. Atawneh, O. A. Khashan, and N. M. Khafajah, "Enhancing intrusion detection in IoT networks using machine learning-based feature selection and ensemble models," Systems Science & Control Engineering, vol. 12, no. 1, Dec. 2024, Art. no. 2321381. DOI: https://doi.org/10.1080/21642583.2024.2321381
N. U. Bhanu, S. R. Mallick, S. R. Chappidi, and K. Sangeethalakshmi, "RF-SFAD: A Random Forest Model for Selective Forwarding Attack Detection In Mobile Wireless Sensor Networks," International Journal of Advances in Signal and Image Sciences, vol. 11, no. 1, pp. 104–116, Jun. 2025. DOI: https://doi.org/10.29284/IJASIS.11.1.2025.104-116
B. R. Kikissagbe and M. Adda, "Machine Learning-Based Intrusion Detection Methods in IoT Systems: A Comprehensive Review," Electronics, vol. 13, no. 18, Jan. 2024, Art. no. 3601. DOI: https://doi.org/10.3390/electronics13183601
M. Amru et al., "Network intrusion detection system by applying ensemble model for smart home," International Journal of Electrical and Computer Engineering (IJECE), vol. 14, no. 3, pp. 3485-3494, Jun. 2024. DOI: https://doi.org/10.11591/ijece.v14i3.pp3485-3494
A. H. A. Saq, A. Zainal, B. A. S. Al-Rimy, A. Alyami, and H. A. Abosaq, "Intrusion Detection in IoT using Gaussian Fuzzy Mutual Information-based Feature Selection," Engineering, Technology & Applied Science Research, vol. 14, no. 6, pp. 17564–17571, Dec. 2024. DOI: https://doi.org/10.48084/etasr.8268
S. Sekar et al., "Intrusion detection and prevention using Bayesian decision with fuzzy logic system," International Journal of Electrical and Computer Engineering (IJECE), vol. 15, no. 1, pp. 1200–1208, Feb. 2025. DOI: https://doi.org/10.11591/ijece.v15i1.pp1200-1208
A. A. A. Mohammed, "Improving Intrusion Detecction Systems by using Deep Learning Methods on Time Series Data," Engineering, Technology & Applied Science Research, vol. 15, no. 1, pp. 19267–19272, Feb. 2025. DOI: https://doi.org/10.48084/etasr.9417
K. Alemerien, S. Al-suhemat, and M. Almahadin, "Towards optimized machine-learning-driven intrusion detection for Internet of Things applications," International Journal of Information Technology, vol. 16, no. 8, pp. 4981–4994, Dec. 2024. DOI: https://doi.org/10.1007/s41870-024-01852-8
A. Alsajri and A. Steiti, "Intrusion Detection System Based on Machine Learning Algorithms: (SVM and Genetic Algorithm)," Babylonian Journal of Machine Learning, vol. 2024, pp. 15–29, Jan. 2024. DOI: https://doi.org/10.58496/BJML/2024/002
"NSL-KDD." Kaggle, [Online]. Available: https://www.kaggle.com/datasets/hassan06/nslkdd.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, Jun. 2002. DOI: https://doi.org/10.1613/jair.953
M. Jain and A. Srihari, "Comparison of Machine Learning Algorithm in Intrusion Detection Systems: A Review Using Binary Logistic Regression." Authorea, May 27, 2025. DOI: https://doi.org/10.22541/au.174837862.20090642/v1
Downloads
How to Cite
License
Copyright (c) 2025 B. Chempavathy, S. K. Mouleeswaran
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement 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 acknowledgement 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
