PSO-Driven Feature Selection and Hybrid Ensemble for Network Anomaly Detection

Louk, Maya Hilda Lestari; Tama, Bayu Adhi

doi:10.3390/bdcc6040137

Cited by 7 publications

(3 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preprocessing is the initial stage of the proposed system, which intends to transform the raw dataset in an easy and efficient format. Therefore, it is a significant process which the main objective of obtaining a dataset that can be considered credible and helpful for machine learning techniques prediction models [13]. Here, this stage is performed by using normalization method.…”

Section: Preprocessing Of the Datasetmentioning

confidence: 99%

Anomaly Detection in Human Disease: A Hybrid Approach Using GWO-SVM for Gene Selection

Mohammed,

Nazeeh,

Alisawi

et al. 2023

RIA

View full text Add to dashboard Cite

The goal is to facilitate early disease detection. A Grey Wolf Optimizer (GWO) was implemented in the proposed method, a meta-heuristic algorithm known for its efficiency in reducing computational time for high-dimensional data. This optimization technique simplifies the problem by breaking it into manageable subsets. Following this, a filter approach, such as analysis of variance (ANOVA), was used to select informative genes from the reduced data. A Support Vector Machine (SVM) was also used as a classifier to select genes that efficiently categorize anomalous cases, serving as a fitness function-this combined approach, referred to as GWO-SVM, and aimed to reduce computational time while improving accuracy. The experimental results demonstrated that the proposed method achieved an accuracy rate of 96.46% in predicting disease detection, representing a significant improvement compared to previous methods. These findings underscore the potential of the GWO-SVM approach in advancing anomaly detection in human diseases.

show abstract

Section: Preprocessing Of the Datasetmentioning

confidence: 99%

Anomaly Detection in Human Disease: A Hybrid Approach Using GWO-SVM for Gene Selection

Mohammed,

Nazeeh,

Alisawi

et al. 2023

RIA

View full text Add to dashboard Cite

show abstract

“…However, the proposed work does not outperform for all datasets in term of specificity, and false positive. The work in [5] proposed an anomaly detection system based on ensemble learning. The optimal FS from the network traffic is performed using the PSO algorithm.…”

Section: Literature Surveymentioning

confidence: 99%

Feature selection using bio-inspired optimization for IoT intrusion detection and prevention system

Singh,

Ujjwal

2023

IJITS JOURNAL

View full text Add to dashboard Cite

Nowadays smart Internet of Things (IoT) devices are used briskly, and these devices communicate with each other via wireless medium. However, this increase in IoT devices has resulted in a rise of security issues associated with the IoT system. Therefore, an intrusion detection and prevention system (IDPS) is used to locate and report any malicious activity. The IDPS's feature selection (FS) task is necessary to improve the data quality and decrease the data used for classifying intrusive traffic. Therefore, this paper proposes a novel FS method that hybridizes improved salp swarm algorithm and harris hawk optimization algorithm. The XGBoost classifier is used for classifying reduced network traffic. Proposed system demonstrates high accuracy and low computation time, surpassing other related approaches used for the IDPS feature selection task.

show abstract

“…A particle swarm optimization (PSO)-driven selection approach to identify the optimum feature subsets and hybrid ensemble can help to enhance anomaly-based intrusion detection systems [8]. Research [9] undertaken into deep learning to detect and protect against botnet threats in relation to flying ad hoc networks (FANETs) utilizes the hybrid shark and bear smell optimization algorithm (HSBSOA).…”

mentioning

confidence: 99%