244
ISSN 1060-992X, Optical Memory and Neural Networks, 2020, Vol. 29, No. 3, pp. 244–256. © Allerton Press, Inc., 2020.
Supervised Machine Learning Classification Algorithmic
Approach for Finding Anomaly Type of Intrusion
Detection in Wireless Sensor Network
Ashwini B. Abhale
a,
* and S. S. Manivannan
b
a
D.Y. Patil College of Engineering and Technology, Akurdi, India
b
Vellore Institute of Technology, Vellore, Tamil Nadu, India
*e-mail: ashwiniabhale@gmail.com
Received November 21, 2019; revised March 11, 2020; accepted May 25, 2020
Abstract—From the last decade, the use of internet and its growth is continuously increasing. Simi-
larly, numbers of services are coming out along with the internet and it is being used for providing facil-
ities to human beings. Wireless sensor have been used for various application such as fire safety, mili-
tary application, petroleum industry, security system, monitoring and environmental condition and
many more. WSN node exposes itself to various security related attacks due to low battery power sup-
ply, low bandwidth support, data transmission over multi hop node, dependency on intermediate or
other nodes, distributed in nature and self-organization. The WSN attacks observe in all layers of OSI
model. Wireless sensor nodes has various issues because of that, it experiences number problem related
to its functionalities and some malfunction due to attacks. It is require to build defence and network
monitoring system for identifying attacks and prevent them. Intrusion detection system (IDS) plays an
important role to detect threads inside the system and generate the alert related to the attack. In this
work, supervised classification models for intrusion detection are built using such as Random Forest
classifier, Support Vector Machine, Decision Tree Classifier, LGBM Classifier, Extra Tree Classifier,
Gradient Boosting Classifier, Ada Boost Classifier, K Nearest Neighbour Classifier, MLP Classifier,
Gaussian Naive Bayes Classifier and Logistic Regression Classifier. The NSLKDD, i.e. Modified
version of the KDD99 Data Set on which we checks these algorithms. Experimental results how the
highest accuracy relative to other classification systems in the support vector machine.
Keywords: machine learning algorithm, classification, wireless sensor network, intrusion detection
system, accuracy, performance matrix
DOI: 10.3103/S1060992X20030029
1. INTRODUCTION
Wireless Sensor Network (WSNs) is formed by the combination of Sinks and Sensor Nodes. The sen-
sor node is main unit in WSNs and sensor network has the ability to self-organize. Self-Organization
formed by sensor node is completely distributed and decentralized in nature. Wireless Sensor Network
(WSNs) is formed by the combination of Sinks and Sensor Nodes. The sensor node is main unit in WSNs
and sensor network has the ability to self-organize. Self-Organization formed by sensor node is completely
distributed and decentralized in nature. The Wireless Sensor network is formed using centralized or dis-
tributed techniques [1]. The communication is made between the nodes via intermediate multi-hop
nodes. The responsibility of sensor node is to gather information from other nodes or sense the data from
the nearby environment and forwarded to the sink node. Due to the nature of WSNs, it is used in many
applications where wired network is not worked such as military application, petroleum industry, security
system, monitoring and environmental condition [2].
Most of the time, node is damaged due to change in environment condition or physical damage. Intru-
sion Detection is also one of the best solutions used for preventing the wireless sensor network attacks.
IDS are used for detecting intrusion only, it means that, it can detect the attack but not prevent it. Intru-
sion Detection system detects the attacks, it informs to the system admin/system controller by raising an
alarm or signal. The system admin / system controller takes specific action against attacks detected by IDS
system. IDS system can be a detection system based on signature categories and a detection system based
on anomalies. Signature-based detection system detects the attack within the system in which the signa-