Smart City Gnosys
Smart city article details
| Title | Hybridization Of Deep Learning Models With Crested Porcupine Optimizer Algorithm-Based Cybersecurity Detection On Industrial Iot For Smart City Environments |
|---|---|
| ID_Doc | 29841 |
| Authors | Alzakari S.A.; Aljebreen M.; Asiri M.M.; MANSOURI W.; Alahmari S.; Alqahtani M.; Sorour S.; Bedewi W. |
| Year | 2025 |
| Published | Alexandria Engineering Journal, 127 |
| DOI | http://dx.doi.org/10.1016/j.aej.2025.05.024 |
| Abstract | Smart cities have attracted extensive coverage from multidisciplinary studies, and many artificial intelligence (AI) solutions have been designed. Conversely, cybersecurity has constantly been a crucial issue and is becoming gradually dangerous in smart cities. The attack defence models are inappropriate for perceiving multistep assaults as the recognition rules are restricted, and efficacy is partial due to many false security alarms. Therefore, an innovative solution is immediately required to progress cybersecurity defence ability. Machine learning (ML) methods are commonly employed to recognize numerous attacks because they could help network administrators grab analogous initials to avert intrusion. This study presents Cybersecurity using a Crested Porcupine Optimizer Algorithm with Hybrid Deep Learning Models (CCPOA-HDLM). The foremost intention of this study is to improve cybersecurity detection and classification in smart city environments. To accomplish that, the CCPOA-HDLM method comprises distinct processes such as min-max normalization, improved Salp swarm algorithm (ISSA)-based feature selection, Multi-Channel Convolutional Neural Network - Recurrent Neural Network (MCNN-RNN)-based cybersecurity detection, and crested porcupine optimizer (CPO)-based parameter selection process. Primarily, data normalization utilizing min-max normalization is implemented. Next, the CCPOA-HDLM method utilizes ISSA based feature selection method to select optimum features. The CCPOA-HDLM technique employs a hybrid of the MCNN-RNN model for the cybersecurity detection and classification process. Moreover, the hyperparameter range of the hybrid of DL techniques occurs using the CPO technique. The experimental validation of the CCPOA-HDLM approach is performed on the UNSW-NB15 dataset, and the outcome portrayed a superior accuracy value of 99.04 % over other recent approaches under various measures. © 2025 The Authors |
| Author Keywords | Crested porcupine optimizer; Cybersecurity; Hybrid deep learning; Improved salp swarm algorithm; Smart city |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
29797  | 0.889 | Gupta S.K.; Tripathi M.; Grover J. | Hybrid Optimization And Deep Learning Based Intrusion Detection System | Computers and Electrical Engineering, 100 (2022) |
| 57853 | 0.882 | Al-Taleb N.; Saqib N.A. | Towards A Hybrid Machine Learning Model For Intelligent Cyber Threat Identification In Smart City Environments | Applied Sciences (Switzerland), 12, 4 (2022) |
| 35068 | 0.878 | Alghanmi N.A. | Leveraging Digital Twins With Hybrid Deep Learning Model For Robust Intrusion Detection System In Smart City Environment | Fusion: Practice and Applications, 19, 1 (2025) |
| 4601 | 0.876 | Kumar P.J.; Neduncheliyan S. | A Shark Inspired Ensemble Deep Learning Stacks For Ensuring The Security In Internet Of Things (Iot)-Based Smart City Infrastructure | International Journal of Computational Intelligence Systems, 17, 1 (2024) |
| 7444 | 0.876 | Jaganraja V.; Srinivasan R. | An Agile Solution For Enhancing Cybersecurity Attack Detection Using Deep Learning Privacy-Preservation In Iot-Smart City | Wireless Networks, 31, 3 (2025) |
| 7763 | 0.875 | Stanly Jayaprakash J.; Kodati S.; Kanchana A.; Al-Farouni M.; Ramachandra A.C. | An Effective Cyber Security Threat Detection In Smart Cities Using Dueling Deep Q Networks | 4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024 (2024) |
| 13293 | 0.875 | Khan J.; Elfakharany R.; Saleem H.; Pathan M.; Shahzad E.; Dhou S.; Aloul F. | Can Machine Learning Enhance Intrusion Detection To Safeguard Smart City Networks From Multi-Step Cyberattacks? | Smart Cities, 8, 1 (2025) |
| 7014 | 0.874 | Reis M.J.C.S. | Ai-Driven Anomaly Detection For Securing Iot Devices In 5G-Enabled Smart Cities | Electronics (Switzerland), 14, 12 (2025) |
| 30748 | 0.871 | Devi E. M R.; Almakayeel N.; Lydia E.L. | Improved Sand Cat Swarm Optimization With Deep Learning Based Enhanced Malicious Activity Recognition For Cybersecurity | Alexandria Engineering Journal, 98 (2024) |
| 2187 | 0.871 | Gill K.S.; Dhillon A. | A Hybrid Machine Learning Framework For Intrusion Detection System In Smart Cities | Evolving Systems, 15, 6 (2024) |