Water Moth Search Algorithm-based Deep Training for Intrusion Detection in IoT
| Autor: | P R Sudha, Nagamani H. Shahapure, P.M. Rekha, M Punitha |
|---|---|
| Rok vydání: | 2021 |
| Předmět: |
Computer Networks and Communications
Computer science Feature selection Intrusion detection system computer.software_genre Field (computer science) Task (computing) Recurrent neural network Search algorithm Classifier (linguistics) Sensitivity (control systems) Data mining computer Software Information Systems |
| Zdroj: | Journal of Web Engineering. |
| ISSN: | 1544-5976 1540-9589 |
| Popis: | The economic growth and information technology leads to the development of Internet of Things (IoT) industry and has become the emerging field of research. Several intrusion detection techniques are introduced but the detection of intrusion and malicious activities poses a challenging task. This paper devises a novel method, namely the Water Moth Search algorithm (WMSA) algorithm, for training Deep Recurrent Neural Network (Deep RNN) to detect malicious network activities. The WMSA algorithm is newly devised by combining Water Wave optimization (WWO) and the Moth Search Optimization (MSO). The pre-processing is employed for the removal of redundant data. Then, the feature selection is devised using the Wrapper approach, then using the selected features; the Deep RNN classifier effectively detects the intrusion using the selected features. The proposed WMSA-based Deep RNN showed improved results with maximal accuracy, specificity, and sensitivity of 0.96, 0.973 and 0.960. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|