Radial Basis Kernel Regressive Feature Extraction and Robert Ensembled Brown Boost Classifier for Attack Detection in Cloud Environment
Cloud computing shares the resource in information technology field. The existing technique is failed to provide better results for identifying unknown attacks with higher accuracy and lesser time consumption. In order to address these problems, Radial Basis Kernel Regressive Feature Extracted Brown...
Gespeichert in:
Veröffentlicht in: | Webology 2021-12, Vol.18 (2), p.41-59 |
---|---|
1. Verfasser: | |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Cloud computing shares the resource in information technology field. The existing technique is failed to provide better results for identifying unknown attacks with higher accuracy and lesser time consumption. In order to address these problems, Radial Basis Kernel Regressive Feature Extracted Brown Boost Classification (RBKRFEBBC) method is introduced for performing the attack detection in cloud computing. The main objective of RBKRFEBBC method is to improve the attack detection performance with higher accuracy and minimal time consumption. Dichotomous radial basis kernelized regressive function is used in RBKRFEBBC method to extract the relevant features through determining the correlation between the output and one or more input variables (i.e., features of patient transaction data). After extracting relevant features, GRNBBC algorithm is used in RBKRFEBBC method to improve the secured data communication performance through classifying the patient data transaction as attack presence or attack absence. By this way, attack detection is carried out in accurate manner. Experimental evaluation is carried out by NSL-KDD dataset using different metrics like attack detection accuracy, attack detection time and error rate. The evaluation result shows RBKRFEBBC method improves the accuracy and minimizes the time consumption as well as error rate than existing works. |
---|---|
ISSN: | 1735-188X 1735-188X |
DOI: | 10.14704/WEB/V18I2/WEB18306 |