Features Extraction on IoT Intrusion Detection System Using Principal Components Analysis (PCA)

Published on Oct 1, 2020
· DOI :10.23919/EECSI50503.2020.9251292
Estimated H-index: 3
(Sriwijaya University),
Benni Purnama3
Estimated H-index: 3
(Sriwijaya University)
+ 5 AuthorsRahmat Budiarto13
Estimated H-index: 13
(Al Baha University)
Feature extraction solves the problem of finding the most efficient and comprehensive set of features. A Principle Component Analysis (PCA) feature extraction algorithm is applied to optimize the effectiveness of feature extraction to build an effective intrusion detection method. This paper uses the Principal Components Analysis (PCA) for features extraction on intrusion detection system with the aim to improve the accuracy and precision of the detection. The impact of features extraction to attack detection was examined. Experiments on a network traffic dataset created from an Internet of Thing (IoT) testbed network topology were conducted and the results show that the accuracy of the detection reaches 100 percent.
#1Deris StiawanH-Index: 9
#2Mohammad Yazid Bin Idris (UTM: Universiti Teknologi Malaysia)H-Index: 4
Last. Rahmat Budiarto (Al Baha University)H-Index: 13
view all 6 authors...
Internet of Things (IoT) devices may transfer data to the gateway/application server through File Transfer Protocol (FTP) transaction. Unfortunately, in terms of security, the FTP server at a gateway or data sink very often is improperly set up. At the same time, password matching/theft holding is among the popular attacks as the intruders attack the IoT network. Thus, this paper attempts to provide an insight of this type of attack with the main aim of coming up with attack patterns that may he...
18 CitationsSource
Oct 1, 2018 in ICEE (International Conference on Electrical Engineering)
#1SharipuddinH-Index: 3
#2KurniabudiH-Index: 3
Last. Rahmat Budiarto (Al Baha University)H-Index: 13
view all 9 authors...
This study presents the testing of several devices (sensors) in obtaining sensor performance, there are several experiments and evaluations of the results obtained in the topology. Each sensor must be able to provide some results in the form of accuracy, reliability, range, and resolution. The accuracy and reliability have very important role in producing accurate data. With several explanations and analysis, it is expected to produce a reference for advanced development and policies making in t...
1 CitationsSource
Oct 1, 2018 in ICEE (International Conference on Electrical Engineering)
#1KurniabudiH-Index: 3
#2Benni PurnamaH-Index: 3
Last. Rahmat Budiarto (Al Baha University)H-Index: 13
view all 6 authors...
A robust increasing on smart sensors in Internet of Thing (IoT) results huge and heterogenous data and becomes a challenge in data prepocessing and analysis for anomaly detection. The lack of IoT publicly available dataset is one issue in anomaly detection research. To resolve that problem, a testbed topology is proposed in this research. In addition, a high-dimensionality data analysis faces a computational complexity. The purpose of this study is to presents a global framework for anomaly dete...
3 CitationsSource
Oct 1, 2018 in ICEE (International Conference on Electrical Engineering)
#2Siti NurmainiH-Index: 10
Last. Firdaus JasmirH-Index: 1
view all 5 authors...
Intrusion Detection System (IDS) can detect attacks by analysing the patterns of data traffic in the network. With a large amount of data that is processed in the IDS, then need to do a feature extraction to reduce the computational cost of processing raw data in IDS. Feature extraction will transform features to the lower dimension to accelerate the learning process and improve the accuracy. This research on automatic feature extraction using simple autoencoder and SVM to classify attacks on ID...
12 CitationsSource
Classification features are crucial for an intrusion detection system (IDS), and the detection performance of IDS will change dramatically when providing different input features. Moreover, the large number of network traffic and their high-dimensional features will result in a very lengthy classification process. Recently, there is an increasing interest in the application of deep learning approaches for classification and learn feature representations. So, in this paper, we propose using the s...
43 CitationsSource
#1Nawel YalaH-Index: 4
#2Belkacem FerganiH-Index: 8
Last. Anthony Fleury (university of lille)H-Index: 21
view all 3 authors...
An activity recognition system on streaming data must analyze the drift in the sensing values and, at any significant change detected, decide if there is a change in the activity performed by the person. The performances of such system depend on both the feature extraction (FE) and the classification stages in the context of streaming data. In the context of streaming and high imbalanced data, this paper proposes and evaluates three FE methods in conjunction with five classification techniques. ...
29 CitationsSource
#1Y-h. Taguchi (Chu-Dai: Chuo University)H-Index: 21
Principal Components Analysis Based Unsupervised Feature Extraction Applied to Gene Expression Analysis of Blood from Dengue Haemorrhagic Fever Patients
24 CitationsSource
#1Abdulla Amin Aburomman (UKM: National University of Malaysia)H-Index: 5
#2Mamun Bin Ibne Reaz (UKM: National University of Malaysia)H-Index: 23
Feature extraction addresses the problem of finding the most compact and informative set of features. To maximize the effectiveness of each single feature extraction algorithm and to develop an efficient intrusion detection system, an ensemble of Linear Discriminant Analysis (LDA) and Principle Component Analysis (PCA) feature extraction algorithms is implemented. This ensemble PCA-LDA method has led to good results and showed a greater proportion of precision in comparison to a single feature e...
20 CitationsSource
#1Yasir Hamid (PEC: Pondicherry Engineering College)H-Index: 6
#2M. Sugumaran (PEC: Pondicherry Engineering College)H-Index: 7
Last. Ludovic JournauxH-Index: 9
view all 3 authors...
With varied and widespread attacks on information systems, intrusion detection systems (IDS) have become an indispensable part of security policy for protecting data. IDS monitor event logs and network traffic to uncover suspicious connections that deviate from the regular profile and identify them as threats or attacks. Like most of the cases the dataset used for intrusion detection i.e., KDD99 suffers two problems: imbalanced class distribution and curse of dimensionality. In this work SMOTE h...
9 CitationsSource
#1Y-h. Taguchi (Chu-Dai: Chuo University)H-Index: 21
Background The recently proposed principal component analysis (PCA) based unsupervised feature extraction (FE) has successfully been applied to various bioinformatics problems ranging from biomarker identification to the screening of disease causing genes using gene expression/epigenetic profiles. However, the conditions required for its successful use and the mechanisms involved in how it outperforms other supervised methods is unknown, because PCA based unsupervised FE has only been applied to...
26 CitationsSource
Cited By1
The prosperity of mobile networks and social networks brings revolutionary conveniences to our daily lives. However, due to the complexity and fragility of the network environment, network attacks are becoming more and more serious. Characterization of network traffic is commonly used to model and detect network anomalies and finally to raise the cybersecurity awareness capability of network administrators. As a tool to characterize system running status, entropy-based time-series complexity mea...