摘要
随着数据复杂度的激增,传统的异常检测方法不再适用,而深度学习可通过多层神经网络处理复杂数据并进行异常检测。通过对国内外研究成果的广泛调研,首先,介绍了异常检测及其分类,并将基于深度学习的异常检测模型分为基于生成模型、基于重构模型和基于单分类模型3类。其次,梳理了不同类别下深度异常检测模型的构造原理和发展脉络,并分析了不同模型的适用范围和优缺点;介绍了异常检测常用的数据集和评估指标,并对比分析了不同模型的性能。最后,总结了深度异常检测面临的挑战,并对未来的研究方向进行了展望。
With the proliferation of data complexity,traditional methods for anomaly detection are no longer applicable,while deep learning can process complex data and perform anomaly detection by multi-layer neural network.Through extensive research on domestic and international research results,firstly,anomaly detection and the types of detection methods are introduced.And deep learning based anomaly detection models are classified into three categories of generative-based model,reconstruction-based model and single classification-based model.Secondly,the construction principles and development context of deep anomaly detection models under different categories are sorted out,and the applicability,advantages and disadvantages of various models are analyzed.Then,the commonly used datasets and evaluation indicators for anomaly detection are introduced,and the performance of different models are compared and analyzed.Finally,the challenges faced by deep anomaly detection are summarized and the future research directions are prospected.
作者
周茂袁
伍小双
ZHOU Maoyuan;WU Xiaoshuang(College of Science,CAUC,Tianjin 300300,China)
出处
《中国民航大学学报》
CAS
2023年第4期1-7,36,共8页
Journal of Civil Aviation University of China
基金
国家社会科学基金项目(19BTJ033)。
关键词
深度学习
异常检测
机器学习
自动编码器
神经网络
deep learning
anomaly detection
machine learning
autoencoder
neural network
