A Hybrid Deep Learning-Based Unsupervised Anomaly Detection in High Dimensional Data

自编码 计算机科学 维数之咒 异常检测 人工智能 人工神经网络 深度学习 机器学习 功能(生物学) 模式识别(心理学) 随机梯度下降算法 数据挖掘 进化生物学 生物
作者
Amgad Muneer,Shakirah Mohd Taib,Suliman Mohamed Fati,Abdullateef Oluwagbemiga Balogun,Izzatdin Abdul Aziz
出处
期刊:Computers, materials & continua 卷期号:70 (3): 5363-5381 被引量:12
标识
DOI:10.32604/cmc.2022.021113
摘要

Anomaly detection in high dimensional data is a critical research issue with serious implication in the real-world problems. Many issues in this field still unsolved, so several modern anomaly detection methods struggle to maintain adequate accuracy due to the highly descriptive nature of big data. Such a phenomenon is referred to as the “curse of dimensionality” that affects traditional techniques in terms of both accuracy and performance. Thus, this research proposed a hybrid model based on Deep Autoencoder Neural Network (DANN) with five layers to reduce the difference between the input and output. The proposed model was applied to a real-world gas turbine (GT) dataset that contains 87620 columns and 56 rows. During the experiment, two issues have been investigated and solved to enhance the results. The first is the dataset class imbalance, which solved using SMOTE technique. The second issue is the poor performance, which can be solved using one of the optimization algorithms. Several optimization algorithms have been investigated and tested, including stochastic gradient descent (SGD), RMSprop, Adam and Adamax. However, Adamax optimization algorithm showed the best results when employed to train the DANN model. The experimental results show that our proposed model can detect the anomalies by efficiently reducing the high dimensionality of dataset with accuracy of 99.40%, F1-score of 0.9649, Area Under the Curve (AUC) rate of 0.9649, and a minimal loss function during the hybrid model training.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
1秒前
1秒前
NexusExplorer应助MCS采纳,获得10
1秒前
医无止境完成签到,获得积分10
1秒前
2秒前
姜一笑完成签到,获得积分20
2秒前
2秒前
2秒前
李爱国应助微辣不加香菜采纳,获得10
3秒前
3秒前
3秒前
3秒前
4秒前
Akim应助红木白花采纳,获得10
4秒前
4秒前
4秒前
鹿冶完成签到 ,获得积分10
5秒前
包佳梁发布了新的文献求助10
5秒前
ZZ完成签到,获得积分10
5秒前
5秒前
kyan发布了新的文献求助10
6秒前
sha完成签到,获得积分10
6秒前
6秒前
6秒前
7秒前
勤恳觅珍发布了新的文献求助10
7秒前
36456657发布了新的文献求助10
7秒前
7秒前
顾矜应助漂亮的振家采纳,获得10
8秒前
XX完成签到,获得积分10
8秒前
山猫完成签到,获得积分10
9秒前
开心人达发布了新的文献求助10
9秒前
10秒前
Cecily发布了新的文献求助10
10秒前
10秒前
Lirui2333完成签到 ,获得积分10
11秒前
pcr163应助cxt采纳,获得50
11秒前
执着冬亦关注了科研通微信公众号
12秒前
彭于晏应助o30采纳,获得10
12秒前
SYLH应助David_xx采纳,获得10
12秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
Cognitive Neuroscience: The Biology of the Mind 1000
Technical Brochure TB 814: LPIT applications in HV gas insulated switchgear 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Picture Books with Same-sex Parented Families: Unintentional Censorship 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3969383
求助须知:如何正确求助?哪些是违规求助? 3514211
关于积分的说明 11172730
捐赠科研通 3249476
什么是DOI,文献DOI怎么找? 1794909
邀请新用户注册赠送积分活动 875441
科研通“疑难数据库(出版商)”最低求助积分说明 804827