Amr H. Abdelhaliem; Bajeszeyadaljunaeidia; Islam S. Fathi; Mohammed Tawfik; Issa Alsmadi

Integrating Fractional Generalized Laguerre Moment with Deep Residual Learning for Real-Time Attack Classification

PDF (2235KB), PP.233-253

Views: 0 Downloads: 0

Author(s)

Amr H. Abdelhaliem ¹ Bajeszeyadaljunaeidia ² Islam S. Fathi ^2,* Mohammed Tawfik ³ Issa Alsmadi ⁴

1. Department of Cyber Security, Faculty of Science and Information Technology, Irbid National University, Irbid, Jordan.

2. Department of Computer Science, Faculty of Information Technology, Ajloun National University P.O.43, Ajloun-26810, JORDAN.

3. Department of Cyber Security, Faculty of Information Technology, Ajloun National University P.O.43, Ajloun-26810, JORDAN.

4. Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Ajloun National University, Ajloun, Jordan.

* Corresponding author.

DOI: https://doi.org/10.5815/ijwmt.2026.03.16

Received: 23 Mar. 2026 / Revised: 1 Apr. 2026 / Accepted: 11 May 2026 / Published: 8 Jun. 2026

Index Terms

Internet of Things Security, Fractional Generalized Laguerre Moment, Deep Residual Learning, Feature Extraction, Attack Classification

Abstract

IoT networks face persistent security challenges due to limited compute, heterogeneous hardware, and weak threat-detection coverage. Classical machine-learning methods struggle with high-dimensional traffic and novel attack patterns. This paper proposes a hybrid framework combining Fractional Generalized Laguerre (FrGL) moment-based feature extraction with a Residual Network augmented by Squeeze-and-Excitation attention (ResNet-SE). FrGL moments yield compact, noise-resistant descriptors via simple recurrence relations, while ResNet-SE mitigates degradation in deep networks through identity shortcuts and adaptively recalibrates channels to highlight attack-relevant features. On the Bot-IoT and Leopard Mobile IoT benchmarks the method reaches 99.78 % accuracy and 99.37 % F1, exceeding KNN (84.7 %), MLR (87.5 %) and a baseline CNN (99.3 %); cross-dataset tests on UNSW-NB15 and IoT-Bot give 96.34 % and 97.12 % accuracy. The framework additionally delivers per-sample inference latency on server- and edge-class hardware (3.9 ms on an NVIDIA V100 and 27.4 ms on a Raspberry Pi 4B with a Coral USB accelerator), an energy cost of 0.42 J per inference on the edge platform, a sensitivity analysis over learning rate, batch size, fractional order λ and reduction ratio r, and an adversarial-robustness evaluation under FGSM and PGD attacks, supporting real-time deployment on resource-constrained IoT gateways.

Cite This Paper

Amr H. Abdelhaliem, Bajeszeyadaljunaeidia, Islam S. Fathi, Mohammed Tawfik, Issa Alsmadi, Yong Fan, "Integrating Fractional Generalized Laguerre Moment with Deep Residual Learning for Real-Time Attack Classification", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.3, pp. 233-253, 2026. DOI:10.5815/ijwmt.2026.03.16

Reference

[1]A. Gaurav, V. Arya, K. T. Chui, and B. B. Gupta . AI-based model for securing cognitive IoT devices in advance communication systems, Int. J. Cogn. Comput. Eng., vol. 6, pp. 351–359, 2025.
[2]Hassan, Gaber, et al. .Efficient compression of fetal phonocardiography bio-medical signals for Internet of Healthcare Things. IEEE Access 11 (2023): 122991-123003.
[3]Al-madni, Ali Mansour, et al. .An Optimized Blockchain Model for Secure and Efficient Data Management in Internet of Things. 2024 IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS). IEEE, 2024.‏
[4]A. Gueriani, H. Kheddar, and Y. Himeur .Enhancing IoT security with CNN and LSTM-based intrusion detection systems," arXiv: 2405.18624, May 2024.
[5]D. V. Janardhana Rao et al. .A high performance hybrid LSTM CNN secure architecture for IoT environments using deep learning. Sci. Rep., vol. 15, art. 7750, 2025.
[6]Rebocho, Maria das Neves. A note on Laguerre-Hahn orthogonal polynomials: from 1984 to 2024. Numerical Algorithms (2025): 1-15.‏
[7]Sayyouri, Mhamed, et al. .A fast and accurate computation of 2D and 3D generalized Laguerre moments for images analysis. Multimedia Tools and Applications 80.5 (2021): 7887-7910
[8]Liaw, Constanze, and John Osborn. .Moment representations of the exceptional X1‐Laguerre orthogonal polynomials. Mathematische Nachrichten 290.11-12 (2017): 1716-1731.‏
[9]Benouini, Rachid, et al. . Fractional‐order generalized Laguerre moments and moment invariants for grey‐scale image analysis. IET Image Processing 15.2 (2021): 523-541.‏
[10]Kim, Taekyun, et al. .A note on degenerate generalized Laguerre polynomials and Lah numbers. Advances in Difference Equations 2021.1 (2021): 421.‏
[11]Aldakheel, Eman Abdullah, et al. Efficient Analysis of Large-Size Bio-Signals Based on Orthogonal Generalized Laguerre Moments of Fractional Orders and Schwarz–Rutishauser Algorithm. Fractal and Fractional 7.11 (2023): 826.‏
[12]Hassan, Gaber, Khalid M. Hosny, and Islam S. Fathi. .Optimized bio-signal reconstruction and watermarking via enhanced fractional orthogonal moments. Scientific Reports 15.1 (2025): 30337.
[13]H. Shu, H. Zhang, C. Beijing, P. Haigron, and L. M. Luo. Fast computation of Tchebichef moments for binary and grayscale images. IEEE Trans. Image Process., vol. 19, no. 12, pp. 3171–3180, Dec. 2010.
[14]R. Mukundan. A new class of rotational invariants using discrete orthogonal moments. in Proc. 6th IASTED Int. Conf. Signal Image Process., 2004, pp. 80–84.
[15]B. Xiao, J. Ma, and X. Wang. Image analysis by Bessel-Fourier moments. Pattern Recognit., vol. 43, no. 8, pp. 2620–2629, Aug. 2010.
[16]H. Zhang, H. Shu, G. N. Han, G. Coatrieux, L. Luo, and J. L. Coatrieux. Blurred image recognition by Legendre moment invariants. IEEE Trans. Image Process., vol. 19, no. 3, pp. 596–611, Mar. 2010.
[17]H. Z. Shu, L. M. Luo, W. X. Yu, and Y. Fu. A novel algorithm for computing translation and scale invariants of Tchebichef moments. Pattern Recognit., vol. 40, no. 7, pp. 2030–2040, July 2007.
[18]K. He, X. Zhang, S. Ren, and J. Sun. Deep residual learning for image recognition. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2016, pp. 770–778.
[19]A. G. Roy, N. Navab, and C. Wachinger. Recalibrating fully convolutional networks with spatial and channel 'squeeze & excitation' blocks. IEEE Trans. Med. Imaging, vol. 38, no. 2, pp. 540–549, Feb. 2019.
[20]M. Woo, J. Park, J. Lee, and I. S. Kweon. CBAM: Convolutional Block Attention Module . In Proc. Eur. Conf. Comput. Vis. (ECCV), 2018, pp. 3–19.
[21]S. Xie, R. Girshick, P. Dollár, Z. Tu, and K. He. Aggregated residual transformations for deep neural networks. in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2017, pp. 5987–5995.
[22]M. Abd Elaziz, L. Abualigah, and I. Attiya, . Advanced optimization technique for scheduling IoT tasks in cloud-fog computing environments. Future Generation Computer Systems, vol. 124, pp. 142-154, 2021.
[23]R. Ghafari and N. Mansouri. An efficient task scheduling in fog computing using improved artificial hummingbird algorithm. Journal of Computational Science, vol. 74, pp. 102152, 2023.
[24]H. K. Apat and B. Sahoo,. JaGW: A hybrid meta-heuristic algorithm for IoT workflow placement in fog computing environment. Simulation Modelling Practice and Theory, vol. 144, p. 103163, 2025.
[25]H. K. Apat and B. Sahoo. LESP: A fault-aware internet of things service placement in fog computing. Sustainable Computing: Informatics and Systems, vol. 46, pp. 101097, 2025.
[26]M. L. Hernandez-Jaimes, A. Martinez-Cruz, K. A. Ramírez-Gutiérrez, and C. Feregrino-Uribe. Artificial intelligence for IoMT security: A review of intrusion detection systems, attacks, datasets and Cloud-Fog-Edge architectures. Internet of Things, vol. 23, p. 100887, 2023.
[27]S. R. Alotaibi et al. Explainable artificial intelligence in web phishing classification on secure IoT with cloud-based cyber-physical systems. Alexandria Engineering Journal, vol. 110, pp. 490-505, 2025.
[28]T. Al-Shurbaji et al. BoT-EnsIDS: Approach for detecting IoT Botnet attacks leveraging bio-inspired based ensemble feature selection and hybrid deep learning model. Alexandria Engineering Journal, vol. 129, pp. 744-767, 2025.
[29]Ankalaki, Shilpa, et al. Cyber-attack prediction: From traditional machine learning to generative artificial intelligence. Ieee Access 13: 44662-44706, 2025.
[30]M. J. C. S. Reis, AI-driven anomaly detection for securing IoT devices in 5G-enabled smart cities. Electronics, vol. 14, no. 12, art. 2492, 2025.
[31]A. Karim, M. Zeroual, Y. Baddi, H. Toumi, and F. Bensalah. Using Artificial Intelligence and SDN for Dynamic Scalable Control of Security Rules: An IoT Security Solution. Procedia Computer Science, vol. 251, pp. 814-817, 2024.
[32]I. S. Fathi and M. Tawfik. Enhancing IoT systems with bio-inspired intelligence in fog computing environments. Stat., Optim. Inf. Comput., vol. 13, pp. 1918-1934, May 2025.
[33]Islam S. Fathi, Ardah, Hanin, G. Hassan, Mohammed Aly,. Protecting IOT Networks Through AI-Based Solutions and Fractional Tchebichef Moments. Fractal Fract, 2025.
[34]Y. Wu, Y. Huo, X. Fan, Q. Gao, J. Mao, and T. Jing. Secure transmission for uplink MIMO-OFDM IoT systems: time-domain artificial noise and deep reinforcement learning against intelligent eavesdroppers. Digital Communications and Networks, 2025.
[35]J. M. Núñez V., J. M. Corchado, D. M. Giraldo, S. Rodríguez-González, and F. De la Prieta,. Recommendation system using bio-inspired algorithms for urban orchards. Internet of Things, vol. 26, art. 101173, 2024.
[36]K. S. Alshudukhi, M. Humayun, and G. N. Alwakid, . Integrating edge intelligence with blockchain-driven secured IoT healthcare optimization model. Comput. Mater. Contin., vol. 83, no. 2, pp. 1973–1986, 2025.
[37]M. Alshammeri, M. Humayun, K. Haseeb, and G. N. Alwakid, . AI-driven sentiment-enhanced secure IoT communication model using resilience behavior analysis. Comput. Mater. Contin., vol. 84, no. 1, pp. 433–446, 2025.
[38]M. N. Alatawi, .EdgeGuard-IoT: 6G-enabled edge intelligence for secure federated learning and adaptive anomaly detection in Industry 5.0. Comput. Mater. Contin., vol. 85, no. 1, pp. 695–727, 2025.
[39]Aly, Mohammed, Abdullatif Ghallab, and Islam S. Fathi. Enhancing facial expression recognition system in online learning context using efficient deep learning model.IEEE Access 11 (2023): 121419-121433.
[40]‏Miao, Lizhi, et al. .SNUNet3+: A full-scale connected Siamese network and a dataset for cultivated land change detection in high-resolution remote-sensing images. IEEE Transactions on Geoscience and Remote Sensing 62 (2023): 1-18.‏
[41]Agrawal, Neelam, and Himanshu Govil. A deep residual convolutional neural network for mineral classification. Advances in Space Research 71.8 (2023): 3186-3202.
[42]‏Peterson, Jared M., Joffrey L. Leevy, and Taghi M. Khoshgoftaar. A review and analysis of the bot-iot dataset. 2021 IEEE International Conference on Service-Oriented System Engineering (SOSE). IEEE, 2021.‏
[43]Alsaedi, Abdullah, et al. .TON_IoT telemetry dataset: A new generation dataset of IoT and IIoT for data-driven intrusion detection systems. Ieee Access 8 (2020): 165130-165150.‏

International Journal of Wireless and Microwave Technologies (IJWMT)