Condition Elements Extraction based on PCA Attribute Reduction and Xgboost

Luzhe Cao, Jinxuan Cao, Haoran Yin, Yongcheng Duan, Xueyan Wu

Abstract

In order to solve the problems of high data redundancy, unsatisfactory classification effect and low precision rate of situation elements extraction in large-scale network, a algorithm that extraction of situation elements based on PCA attribute reduction and Xgboost is proposed. Firstly, PCA is used to reduce the attributes of the data set, and then Xgboost classifier is constructed to classify and train the data after dimension reduction. In order to verify the effectiveness of the proposed algorithm, NSL-KDD data set was used to test the proposed algorithm. Through experiments, this algorithm is compared with SVM and other five algorithms. The experimental results show that the precision rate of the algorithm is greatly improved and the extraction of situation elements is effectively improved.

Download


Paper Citation


in Harvard Style

Cao L., Cao J., Yin H., Duan Y. and Wu X. (2020). Condition Elements Extraction based on PCA Attribute Reduction and Xgboost.In Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS, ISBN 978-989-758-426-8, pages 243-248. DOI: 10.5220/0009370002430248


in Bibtex Style

@conference{iotbds20,
author={Luzhe Cao and Jinxuan Cao and Haoran Yin and Yongcheng Duan and Xueyan Wu},
title={Condition Elements Extraction based on PCA Attribute Reduction and Xgboost},
booktitle={Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS,},
year={2020},
pages={243-248},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009370002430248},
isbn={978-989-758-426-8},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 5th International Conference on Internet of Things, Big Data and Security - Volume 1: IoTBDS,
TI - Condition Elements Extraction based on PCA Attribute Reduction and Xgboost
SN - 978-989-758-426-8
AU - Cao L.
AU - Cao J.
AU - Yin H.
AU - Duan Y.
AU - Wu X.
PY - 2020
SP - 243
EP - 248
DO - 10.5220/0009370002430248