Article Preview
Top1. Introduction
WSNs include a small-sized self-governing wireless sensor device, which is generally placed in aggressive and vulnerable environments to monitor and collect data (Subba, et al., 2018; Deng & Liu, 2007). Despite widespread adaptation, WSNs are given to multiple restrictions associated with processing abilities, thin wireless bandwidths, random sensor node deployment, limited storage spaces, and limited battery power (Wazid & Das, 2016; Akyildiz, et al., 2002). Moreover, sensor nodes are typically less expensive and tamper-prone tools (Otoum, et al., 2019; Borkar, et al., 2019). Thus, the attacks can take control of them during physical modifications and can easily develop fake data during compromised nodes for deceiving WSN and turns out to be unproductive (Wang, et al., 2006; Salmon, et al., 2013; Qu, et al., 2018). The entire elements mentioned above can create intrusion detection and network security as a crucial part of WSNs (Qu, et al., 2018; Otoum, et al., 2018).
Table 1. Abbreviations | Descriptions |
ABC | Artificial Bee Colony |
ASCH-IDS | Adaptive Supervised and Clustered Hybrid IDS |
CH | Cluster Head |
CSO | Chicken Swarm Optimization |
DHOA | Deer Hunting Optimization Algorithm |
DoS | Denial of Service |
FDR | False Discovery Rate |
FNR | False Negative Rate |
FPR | False Positive Rate |
GWO | Grey Wolf Optimization |
IDS | Intrusion Detection System |
KBIDS | Knowledge-Based Intrusion Detection Strategy |
KDE | Kernel Density Estimation |
KL | Kullback-Leibler |
MCC | Matthew’s Correlation Coefficient |
MSCA | Mean Shift Clustering Algorithm |
NN | Neural Network |
NPV | Negative Predictive Value |
O-DHOA | Opposition-based Deer Hunting Optimization Algorithm |
PDF | Probability Density Function |
PDR | Packet Delivery Ratio |
PSO | Particle Swarm Optimization |
RBC-IDS | Restricted Boltzmann Machine-based Clustered IDS |
SVM | Support Vector Machine |
WOA | Whale Optimization Algorithm |
WSN | Wireless Sensor Networks |