LUAD: A lightweight unsupervised anomaly detection scheme for multivariate time series data

异常检测 计算机科学 预言 数据挖掘 多元统计 自编码 异常(物理) 人工智能 时间序列 编码器 方案(数学) 机器学习 模式识别(心理学) 深度学习 数学分析 物理 操作系统 数学 凝聚态物理
作者
Jin Fan,Zhentao Liu,Huifeng Wu,Jia Wu,Zhipeng Si,Hao Peng,Tom H. Luan
出处
期刊:Neurocomputing [Elsevier BV]
卷期号:557: 126644-126644 被引量:11
标识
DOI:10.1016/j.neucom.2023.126644
摘要

Anomaly detection of multivariate time series data has drawn extensive research attention recently, as it can be widely applied into various different domains, such as Prognostics Health Management, community behaviour monitoring, financial Anti-fraud and so on. Anomalies typically refer to unexpected observations or sequences within the captured data. The prevailing solutions of current anomaly detection methods are not only highly related to the individual use, but also rely on the domain-specific prior knowledge. Existing methods of anomaly detection by detecting aberrations encounter fundamental engineering challenges in terms of steam data online nature and the lack of expert knowledge for the training data set. Also, to meet the practical requirements, the anomaly detection model is often required to be used in edge architectures where the computing resources are limited, which leads to the demand for developing light-weight anomaly detection methods. To address these challenges, we propose a lightweight, unsupervised anomaly detection scheme, called LUAD. LUAD is consists of a detection model and a diagnosis model. The detection model learns the normal patterns of input data via an encoder–decoder scheme that combines Temporal Convolutional Network (TCN) and Variational Auto-Encoder (VAE) to deconstruct and reconstruct multivariate time series data. The diagnosis model improves LUAD's overall detection accuracy and provides a reasonable explanation for an anomaly. Experiments on three very different public datasets indicate that LUAD is both highly generalizable and more accurate than the two current state-of-the-arts. Overall, the LUAD model outperforms the baselines both in effectiveness (0.71%∼1.45% higher) and efficiency (31X smaller in model size, 1.9X faster in training time).
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
田様应助幽默平安采纳,获得10
1秒前
可爱的函函应助刘小小123采纳,获得10
2秒前
瓣落的碎梦完成签到,获得积分0
4秒前
善学以致用应助momo采纳,获得10
5秒前
孝顺的觅风完成签到 ,获得积分10
5秒前
7秒前
刘小小123发布了新的文献求助10
10秒前
健壮的面包完成签到,获得积分10
10秒前
13秒前
孙燕应助科研界的恩希玛采纳,获得20
16秒前
17秒前
迷茫的一代完成签到,获得积分10
19秒前
量子星尘发布了新的文献求助10
19秒前
xingxingwang完成签到,获得积分10
20秒前
春来发布了新的文献求助30
21秒前
22秒前
22秒前
刘小小123完成签到,获得积分20
22秒前
xzy完成签到 ,获得积分10
23秒前
搜集达人应助无情向梦采纳,获得10
25秒前
阿伟1999发布了新的文献求助50
27秒前
momo发布了新的文献求助10
28秒前
li完成签到,获得积分10
29秒前
如此发布了新的文献求助10
31秒前
32秒前
赵静1234567890完成签到,获得积分10
32秒前
xxxllllll发布了新的文献求助10
36秒前
科研通AI2S应助科研通管家采纳,获得10
36秒前
Owen应助科研通管家采纳,获得10
36秒前
乐乐应助科研通管家采纳,获得10
36秒前
科研通AI5应助科研通管家采纳,获得10
36秒前
YamDaamCaa应助科研通管家采纳,获得50
36秒前
科研通AI5应助科研通管家采纳,获得10
36秒前
科目三应助科研通管家采纳,获得10
37秒前
爆米花应助科研通管家采纳,获得10
37秒前
稳重淇完成签到 ,获得积分10
37秒前
37秒前
38秒前
39秒前
daaarrr完成签到,获得积分10
42秒前
高分求助中
A new approach to the extrapolation of accelerated life test data 1000
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
‘Unruly’ Children: Historical Fieldnotes and Learning Morality in a Taiwan Village (New Departures in Anthropology) 400
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
基于可调谐半导体激光吸收光谱技术泄漏气体检测系统的研究 350
Robot-supported joining of reinforcement textiles with one-sided sewing heads 320
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 3989334
求助须知:如何正确求助?哪些是违规求助? 3531428
关于积分的说明 11253936
捐赠科研通 3270119
什么是DOI,文献DOI怎么找? 1804887
邀请新用户注册赠送积分活动 882087
科研通“疑难数据库(出版商)”最低求助积分说明 809173