Nature-inspired adaptive decision support system for secured clustering in cyber networks

The Internet of Things (IoT) technology has proved that Wireless Sensor Networks (WSN) is important for all IoT application areas. WSN combined with other advanced technologies like Artificial Intelligence (AI) brings automation via the sensing, transmitting, and monitoring steps. However, the cyber...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Multimedia tools and applications Ročník 83; číslo 1; s. 3153 - 3187
Hlavní autoři: Qureshi, Shahana Gajala, Shandilya, Shishir Kumar
Médium: Journal Article
Jazyk:angličtina
Vydáno: New York Springer US 01.01.2024
Springer Nature B.V
Témata:
1203: Applications of Advanced Artificial Intelligence in Multimedia and Information Security
Algorithms
Artificial intelligence
Clustering
Communication
Computer Communication Networks
Computer Science
Cybersecurity
Data Structures and Information Theory
Data transmission
Decision making
Decision support systems
Denial of service attacks
Energy consumption
Evolutionary algorithms
Evolutionary computation
Genetic algorithms
Internet of Things
Multimedia Information Systems
Nodes
Optimization
Sensors
Special Purpose and Application-Based Systems
Trustworthiness
Wireless sensor networks
Adaptive defense
Nature-inspired cyber security
Nature-inspired decision support system
Optimization
Secure clustering
ISSN:1380-7501, 1573-7721
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:The Internet of Things (IoT) technology has proved that Wireless Sensor Networks (WSN) is important for all IoT application areas. WSN combined with other advanced technologies like Artificial Intelligence (AI) brings automation via the sensing, transmitting, and monitoring steps. However, the cyber threats such as Malware, Distributed Denial of Service Attack (DDoS), and Man in the Middle (MitM), etc. limits the potential of such networks. Several security methods were introduced in last decade to protect the WSN from various cyber threats; however, due to resource-constrained sensor nodes, designing the energy-efficient security algorithm for WSN is a widely studied research problem. In the proposed work, a novel Nature-inspired Decision Support System for Secure Clustering (NIDSC) is proposed to overcome the security issues with minimum resource consumptions and computational overhead. In NIDSC, a hybrid trust model is designed to evaluate each sensor node before selecting Cluster Head (CH) by measuring various sensor node parameters, to achieve a reliable decision support system which classifies each node as either legitimate or attacker. Later, the proposed decision support system along with clustering optimization is formulated for CH selection using a natural evolution-based hybrid trust model. Due to its fast convergence over other optimization algorithms, the nature-inspired Differential Evolution (DE) algorithm is used to perform Decision Support System (DSS) for optimal and secure WSN clustering. The proposed method is a lightweight trust-based decision-making method for Quality of Service (QoS) clustering to establish secure data transmission in intra-cluster and/or inter-cluster communication. The simulation is carried out to analyze and compare the performance of the proposed method with the existing works such as Low Energy Adaptive Clustering Hierarchy(LEACH), Trust Management System (TMS), and Energy-efficient Trusted Moth Flame Optimization and Genetic Algorithm based clustering algorithm(eeTMFO/GA). The comparisons were mainly focused on throughput, Packet Delivery Ratio (PDR), delay, communication overhead, and energy consumption to validate the performance of the proposed method. The experimental results found that the proposed method has got improved throughput value (~3 kbps), improved PDR (~4%), minimum delay (~0.01 seconds), less communication overhead (~0.75 ms, and less energy consumption (~0.003 joules) as compared to the existing methods on various testcase scenarios.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1380-7501
1573-7721
DOI:10.1007/s11042-022-13336-7