Filters








20 Hits in 1.7 sec

A Review on Anomaly Detection in Time Series

2021 International Journal of Advanced Trends in Computer Science and Engineering  
In this article we will first define what an anomaly in time series is, and then describe quickly some of the methods suggested in the past two or three years for detection of anomaly in time series  ...  Among others, it is very simple to obtain time series data from a variety of various science and finance applications and an anomaly detection technique for time series is becoming a very prominent research  ...  Deep Learning Approach for Unsupervised Outlier Detection in Time Series In standard anomaly detection techniques, current points and seasonal fluctuations normally found in streaming data cannot be observed  ... 
doi:10.30534/ijatcse/2021/571032021 fatcat:5alfes5srzakzdvfgxtdniyn3q

FuseAD: Unsupervised Anomaly Detection in Streaming Sensors Data by Fusing Statistical and Deep Learning Models

Mohsin Munir, Shoaib Ahmed Siddiqui, Muhammad Ali Chattha, Andreas Dengel, Sheraz Ahmed
2019 Sensors  
In this paper, we present a novel anomaly detection technique, FuseAD, which takes advantage of both statistical and deep-learning-based approaches by fusing them together in a residual fashion.  ...  For some types of data and use-cases, statistical anomaly detection techniques work better, whereas for others, deep learning-based techniques are preferred.  ...  and deep learning models for anomaly detection.  ... 
doi:10.3390/s19112451 fatcat:pefz2ibc5zb67c2biexmyfustu

Unsupervised Anomaly Detection in Multivariate Spatio-Temporal Data using Deep Learning: Early Detection of COVID-19 Outbreak in Italy

Yildiz Karadayi, Mehmet N. Aydin, A. Selcuk Ogrenci
2020 IEEE Access  
In this paper, a hybrid deep learning framework is proposed to solve the unsupervised anomaly detection problem in multivariate spatio-temporal data.  ...  Unsupervised anomaly detection for spatio-temporal data has extensive use in a wide variety of applications such as earth science, traffic monitoring, fraud and disease outbreak detection.  ...  [66] present DeepAnT, a deep learning based unsupervised anomaly detection approach for time series data.  ... 
doi:10.1109/access.2020.3022366 pmid:34931155 pmcid:PMC8668158 fatcat:m23b5ijr25ahfko2ktxqhx2fsa

Unsupervised Anomaly Detection in Stream Data with Online Evolving Spiking Neural Networks [article]

Piotr S. Maciąg, Robert Bembenik Institute of Computer Science, Warsaw University of Technology, Warsaw, Poland, TECNALIA Parque Tecnológico de Bizkaia, Derio, Spain, University of the Basque Country UPV/EHU, Bilbao, Spain)
2019 arXiv   pre-print
In this work, we propose a novel OeSNN-UAD (Online evolving Spiking Neural Networks for Unsupervised Anomaly Detection) approach for online anomaly detection in univariate time series data.  ...  The proposed OeSNN-UAD approach was experimentally compared to the state-of-the-art unsupervised methods and algorithms for anomaly detection in stream data.  ...  Abstract-In this work, we propose a novel OeSNN-UAD (Online evolving Spiking Neural Networks for Unsupervised Anomaly Detection) approach for online anomaly detection in univariate time series data.  ... 
arXiv:1912.08785v1 fatcat:guh5dcypdbdn5fi2idtfsfvqza

KPI-TSAD: A Time-Series Anomaly Detector for KPI Monitoring in Cloud Applications

Juan Qiu, Qingfeng Du, Chongshu Qian
2019 Symmetry  
To address this limitation, we propose a novel anomaly detector (called KPI-TSAD) for time-series KPIs based on supervised deep-learning models with convolution and long short-term memory (LSTM) neural  ...  Therefore, anomaly detection presents a challenge for all types of temporal data, particularly when non-stationary time series have special adaptability requirements or when the nature of potential anomalies  ...  We give thanks to the public datasets provided by the Yahoo and AIOps Challenges; those datasets provided strong support for our experiments.  ... 
doi:10.3390/sym11111350 fatcat:svpgcv3ljzhvflj4m5b6p6k5gq

Unsupervised Anomaly Detection Approach for Time-Series in Multi-Domains Using Deep Reconstruction Error

Tsatsral Amarbayasgalan, Van Huy Pham, Nipon Theera-Umpon, Keun Ho Ryu
2020 Symmetry  
By focusing on these problems, we propose a novel deep learning-based unsupervised anomaly detection approach (RE-ADTS) for time-series data, which can be applicable to batch and real-time anomaly detections  ...  Automatic anomaly detection for time-series is critical in a variety of real-world domains such as fraud detection, fault diagnosis, and patient monitoring.  ...  Mohsin et al. presented a deep learning-based DeepAnT method for unsupervised anomaly detection in time-series [20] .  ... 
doi:10.3390/sym12081251 fatcat:bm5cjz7775f5tnmjjfphvdldca

Change Point Enhanced Anomaly Detection for IoT Time Series Data

Elena-Simona Apostol, Ciprian-Octavian Truică, Florin Pop, Christian Esposito
2021 Water  
We employ both traditional and deep learning unsupervised algorithms, in total, five anomaly detection and five change point detection algorithms.  ...  In this paper, we propose a rule-based decision system that enhances anomaly detection in multivariate time series using change point detection.  ...  Another unsupervised non-Deep Learning approach is PBAD (pattern-based anomaly detection) [27] .  ... 
doi:10.3390/w13121633 fatcat:mji72vblmjcwrpl3vtse7pbhny

Anomaly Detection in Univariate Time-series: A Survey on the State-of-the-Art [article]

Mohammad Braei, Sebastian Wagner
2020 arXiv   pre-print
Anomaly detection for time-series data has been an important research field for a long time. Seminal work on anomaly detection methods has been focussing on statistical approaches.  ...  In recent years an increasing number of machine learning algorithms have been developed to detect anomalies on time-series.  ...  Deep Learning Anomaly detection approaches on time series Munir et al.  ... 
arXiv:2004.00433v1 fatcat:6ang6kfgsrd7jpck5ec4u6shoa

Recurrent Autoencoder Ensembles for Brake Operating Unit Anomaly Detection on Metro Vehicles

Jaeyong Kang, Chul-Su Kim, Jeong Won Kang, Jeonghwan Gwak
2022 Computers Materials & Continua  
This is the first proposal to employ an ensemble deep learning technique to detect BOU abnormalities in metro train braking systems.  ...  The anomaly detection of the brake operating unit (BOU) in the brake systems on metro vehicle is critical for the safety and reliability of the trains.  ...  The authors in [30] introduced a model called DeepAnT for time-series anomaly detection in an unsupervised manner.  ... 
doi:10.32604/cmc.2022.023641 fatcat:arwxb6onvbehtil4plhu4h4r2e

Anomaly Detection of the Brake Operating Unit on Metro Vehicles Using a One-Class LSTM Autoencoder

Jaeyong Kang, Chul-Su Kim, Jeong Won Kang, Jeonghwan Gwak
2021 Applied Sciences  
Hence, in this work, we propose a method for detecting anomalies of BOU on metro vehicles using a one-class long short-term memory (LSTM) autoencoder.  ...  However, current periodic maintenance and inspection cannot detect anomalies at an early stage. In addition, constructing a stable and accurate anomaly detection system is a very challenging task.  ...  In recent years, various unsupervised approaches for anomaly detection have been proposed and categorized into traditional machine learning and deep learning approaches.  ... 
doi:10.3390/app11199290 fatcat:p3jhfa7vpjek3ma2xoldjjmxd4

Deep Anomaly Detection for Time-series Data in Industrial IoT: A Communication-Efficient On-device Federated Learning Approach [article]

Yi Liu, Sahil Garg, Jiangtian Nie, Yang Zhang, Zehui Xiong, Jiawen Kang, M. Shamim Hossain
2020 arXiv   pre-print
With this focus, this paper proposes a new communication-efficient on-device federated learning (FL)-based deep anomaly detection framework for sensing time-series data in IIoT.  ...  Furthermore, this model retains the advantages of LSTM unit in predicting time series data.  ...  Munir et al. in [15] proposed a novel DAD approach, called DeepAnT, to achieve anomaly detection by utilizing deep Convolutional Neural Network (CNN) to predict anomaly value.  ... 
arXiv:2007.09712v1 fatcat:tkfhoj4rmrhnjmgp5zyn33xlai

Warping Resilient Scalable Anomaly Detection in Time Series [article]

Abilasha S, Sahely Bhadra, Deepak P, Anish Mathew
2021 arXiv   pre-print
In this paper, we propose a novel unsupervised time series anomaly detection method, WaRTEm-AD, that operates in two stages.  ...  for time series data.  ...  The work is supported by project titled "Robust Multiview Learning for Extreme Events Detection and Prediction in Time Series Data", IITPKD/2021/013/CSE/SAB funded by ICSR  ... 
arXiv:1906.05205v2 fatcat:yse2nf5d45akzdytutkd63lf5i

A simple method for unsupervised anomaly detection: An application to Web time series data

Keisuke Yoshihara, Kei Takahashi, Lianmeng Jiao
2022 PLoS ONE  
We propose a simple anomaly detection method that is applicable to unlabeled time series data and is sufficiently tractable, even for non-technical entities, by using the density ratio estimation based  ...  The result implies that it is essential in time series anomaly detection to incorporate the specific information on time series data into the model.  ...  Acknowledgments We are grateful to Flat inc. for sharing the data set with us. We also thank the participants at the International Conference on Operations Research 2019 for their helpful comments.  ... 
doi:10.1371/journal.pone.0262463 pmid:35015791 pmcid:PMC8752013 fatcat:bekblaruy5bmdo6x2vasnipesm

Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT [article]

Zekai Chen, Dingshuo Chen, Xiao Zhang, Zixuan Yuan, Xiuzhen Cheng
2021 arXiv   pre-print
This paper presented GTA, a new framework for multivariate time series anomaly detection that involves automatically learning a graph structure, graph convolution, and modeling temporal dependency using  ...  Furthermore, detecting anomalies in multivariate time series is difficult due to their temporal dependency and stochasticity.  ...  DeepAnt [31] was an unsupervised approach using convolutional neural network (CNN) to forecast future time series values and adopted Euclidean distance to measure the discrepancy for anomaly detection  ... 
arXiv:2104.03466v2 fatcat:kbiv3vvfmrbfhdzstdxdyz5xva

Anomaly Detection at Scale: The Case for Deep Distributional Time Series Models [article]

Fadhel Ayed, Lorenzo Stella, Tim Januschowski, Jan Gasthaus
2020 arXiv   pre-print
This paper introduces a new methodology for detecting anomalies in time series data, with a primary application to monitoring the health of (micro-) services and cloud resources.  ...  Our method is amenable to streaming anomaly detection and scales to monitoring for anomalies on millions of time series.  ...  Model The backbone of our anomaly detection technique is a deep probabilistic distributional time series model, i.e. a probabilistic model for time series x 1:T = x 1 , x 2 , . . . , x T , where each element  ... 
arXiv:2007.15541v1 fatcat:bx2tzzq5zrb3ro6pctbg6g6rty
« Previous Showing results 1 — 15 out of 20 results