MLBFN optimized with Archimedes optimization Algorithm for SRCE

The Internet of Things (IoT) and its devices have become an integral part of the people’s daily lives recently. The growing demand for intelligent applications indicates that the IoT improves regular automation and intelligent sensing, whichimproves quality of life. Datapresent in a variety of forms...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Expert systems with applications Jg. 255; S. 124529
Hauptverfasser:	Kumar Kannaiah, Sathish, Sonaimuthu, Sridevi, Rama Krishnan Alangudi Balaji, Navaneetha, Seshadri Aravinth, Sinnappampatty
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier Ltd 01.12.2024
Schlagworte:	Archimedes Optimization Algorithm Hexadecimal Local Adaptive Binary Pattern Multi-Lead-Branch Fusion Network Resource Constrained Environments Structural interval gradient filtering Resource Constrained Environments Multi-Lead-Branch Fusion Network Structural interval gradient filtering Archimedes Optimization Algorithm Hexadecimal Local Adaptive Binary Pattern
ISSN:	0957-4174
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	The Internet of Things (IoT) and its devices have become an integral part of the people’s daily lives recently. The growing demand for intelligent applications indicates that the IoT improves regular automation and intelligent sensing, whichimproves quality of life. Datapresent in a variety of forms and formatsis the fundamental element of the IoT ecosystem. Then, the gathered information is utilized to generate context awareness and arrive at significant conclusions.Numerousobstacles related to object security are used tomaintain on-going services withmany benefitsusing IoT. In this manuscript, Multi-Lead-Branch Fusion Network optimized using Archimedes Optimization Algorithm for Securing Resource Constrained Environments (MLBF-ArOA-SRCE)is proposed. Initially, the data are acquired from the N-BaIoT dataset. The input data are pre-processed using Structural Interval Gradient Filtering (SIGF) which requires using the common organising techniques to put the data in an accessible format, like removing extra spaces and entries without values. Then,the pre-processed data are fed intoHexadecimal Local Adaptive Binary Pattern (HLABP) for extracting features. Then, the extracted features are provided to the Multi-Lead-Branch Fusion Network (MLBFN) which classifies the benign and malicious attack. TheMLBFN does not express any adoption of optimization strategies for scaling the ideal parameters for Securing Resource Constrained Environments. Hence, Archimedes Optimization Algorithm (ArOA) is utilized to improve the MLBFN weight parameters. The performance of the proposed techniqueis examined using performance metrics like precision, recall, f-measure, specificity, and accuracy. The proposed MLBF-ArOA-SRCE method provides 38%, 14%, 29.93% higher recall; 26.87%, 25.41%, 17.92 %higher accuracy; 30.88%, 13.29%, 25.71% higher specificity compared with existing approaches like RER-EML, FOG-PDM, ALSN-SSP respectively.
ISSN:	0957-4174
DOI:	10.1016/j.eswa.2024.124529