An anomaly detection approach based on the combination of LSTM autoencoder and isolation forest for multivariate time series data

Due to the exponential growth of the Internet of Things networks and the massive amount of time series data collected from these networks, it is essential to apply efficient methods for Big Data analysis in order to extract meaningful information and statistics. Anomaly detection is an important part of time series analysis, improving the quality of further analysis, such as prediction and forecasting. Thus, detecting sudden change points with normal behavior and using them to discriminate between abnormal behavior, i.e., outliers, is a crucial step used to minimize the false positive rate and to build accurate machine learning models for prediction and forecasting. In this paper, we propose a rule-based decision system that enhances anomaly detection in multivariate time series using change point detection. Our architecture uses a pipeline that automatically manages to detect real anomalies and remove the false positives introduced by change points. We employ both traditional and deep learning unsupervised algorithms, in total, five anomaly detection and five change point detection algorithms. Additionally, we propose a new confidence metric based on the support for a time series point to be an anomaly and the support for the same point to be a change point. In our experiments, we use a large real-world dataset containing multivariate time series about water consumption collected from smart meters. As an evaluation metric, we use Mean Absolute Error (MAE). The low MAE values show that the algorithms accurately determine anomalies and change points. The experimental results strengthen our assumption that anomaly detection can be improved by determining and removing change points as well as validates the correctness of our proposed rules in real-world scenarios. Furthermore, the proposed rule-based decision support systems enable users to make informed decisions regarding the status of the water distribution network and perform effectively predictive and proactive maintenance.

Download Full-text

Clustering-based anomaly detection in multivariate time series data

Applied Soft Computing ◽

10.1016/j.asoc.2020.106919 ◽

2021 ◽

Vol 100 ◽

pp. 106919

Author(s):

Jinbo Li ◽

Hesam Izakian ◽

Witold Pedrycz ◽

Iqbal Jamal

Keyword(s):

Time Series ◽

Anomaly Detection ◽

Time Series Data ◽

Multivariate Time Series ◽

Series Data

Download Full-text

Anomaly Detection by STL Decomposition and Extended Isolation Forest on Environmental Univariate Time Series

10.5194/egusphere-egu2020-18471 ◽

2020 ◽

Author(s):

İsmail Sezen ◽

Alper Unal ◽

Ali Deniz

Keyword(s):

Time Series ◽

Seasonal Variation ◽

Anomaly Detection ◽

Time Series Data ◽

Complex Structure ◽

Series Data ◽

High Concentration ◽

Univariate Time Series ◽

Concentration Levels ◽

Isolation Forest

Atmospheric pollution is one of the primary problems and high concentration levels are critical for human health and environment. This requires to study causes of unusual high concentration levels which do not conform to the expected behavior of the pollutant but it is not always easy to decide which levels are unusual, especially, when data is big and has complex structure. A visual inspection is subjective in most cases and a proper anomaly detection method should be used. Anomaly detection has been widely used in diverse research areas, but most of them have been developed for certain application domains. It also might not be always a good idea to identify anomalies by using data from near measurement sites because of spatio-temporal complexity of the pollutant. That&#8217;s why, it&#8217;s required to use a method which estimates anomalies from univariate time series data.This work suggests a framework based on STL decomposition and extended isolation forest (EIF), which is a machine learning algorithm, to identify anomalies for univariate time series which has trend, multi-seasonality and seasonal variation. Main advantage of EIF method is that it defines anomalies by a score value.In this study, a multi-seasonal STL decomposition has been applied on a univariate PM10 time series to remove trend and seasonal parts but STL is not resourceful to remove seasonal variation from the data. The remainder part still has 24 hours and yearly variation. To remove the variation, hourly and annual inter-quartile ranges (IQR) are calculated and data is standardized by dividing each value to corresponding IQR value. This process ensures removing seasonality in variation and the resulting data is processed by EIF to decide which values are anomaly by an objective criterion.

Download Full-text

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33011409 ◽

2019 ◽

Vol 33 ◽

pp. 1409-1416 ◽

Cited By ~ 27

Author(s):

Chuxu Zhang ◽

Dongjin Song ◽

Yuncong Chen ◽

Xinyang Feng ◽

Cristian Lumezanu ◽

...

Keyword(s):

Time Series ◽

Anomaly Detection ◽

Power Plants ◽

Time Series Data ◽

Multivariate Time Series ◽

Series Data ◽

Feature Maps ◽

Multi Scale ◽

Unsupervised Anomaly Detection ◽

Detection And Diagnosis

Nowadays, multivariate time series data are increasingly collected in various real world systems, e.g., power plants, wearable devices, etc. Anomaly detection and diagnosis in multivariate time series refer to identifying abnormal status in certain time steps and pinpointing the root causes. Building such a system, however, is challenging since it not only requires to capture the temporal dependency in each time series, but also need encode the inter-correlations between different pairs of time series. In addition, the system should be robust to noise and provide operators with different levels of anomaly scores based upon the severity of different incidents. Despite the fact that a number of unsupervised anomaly detection algorithms have been developed, few of them can jointly address these challenges. In this paper, we propose a Multi-Scale Convolutional Recurrent Encoder-Decoder (MSCRED), to perform anomaly detection and diagnosis in multivariate time series data. Specifically, MSCRED first constructs multi-scale (resolution) signature matrices to characterize multiple levels of the system statuses in different time steps. Subsequently, given the signature matrices, a convolutional encoder is employed to encode the inter-sensor (time series) correlations and an attention based Convolutional Long-Short Term Memory (ConvLSTM) network is developed to capture the temporal patterns. Finally, based upon the feature maps which encode the inter-sensor correlations and temporal information, a convolutional decoder is used to reconstruct the input signature matrices and the residual signature matrices are further utilized to detect and diagnose anomalies. Extensive empirical studies based on a synthetic dataset and a real power plant dataset demonstrate that MSCRED can outperform state-ofthe-art baseline methods.

Download Full-text

GAN-Based Anomaly Detection and Localization of Multivariate Time Series Data for Power Plant

2020 IEEE International Conference on Big Data and Smart Computing (BigComp) ◽

10.1109/bigcomp48618.2020.00-97 ◽

2020 ◽

Cited By ~ 1

Author(s):

Yeji Choi ◽

Hyunki Lim ◽

Heeseung Choi ◽

Ig-Jae Kim

Keyword(s):

Time Series ◽

Power Plant ◽

Anomaly Detection ◽

Time Series Data ◽

Multivariate Time Series ◽

Series Data ◽

Detection And Localization

Download Full-text

Detecting Interesting and Anomalous Patterns In Multivariate Time-Series Data in an Offshore Platform Using Unsupervised Learning

10.4043/31297-ms ◽

2021 ◽

Author(s):

Ilan Sousa Figueirêdo ◽

Tássio Farias Carvalho ◽

Wenisten José Dantas Silva ◽

Lílian Lefol Nani Guarieiro ◽

Erick Giovani Sperandio Nascimento

Keyword(s):

Machine Learning ◽

Time Series ◽

Anomaly Detection ◽

Unsupervised Learning ◽

Time Series Data ◽

Multivariate Time Series ◽

Learning Algorithms ◽

Machine Learning Algorithms ◽

Series Data ◽

Unsupervised Machine Learning

Abstract Detection of anomalous events in practical operation of oil and gas (O&G) wells and lines can help to avoid production losses, environmental disasters, and human fatalities, besides decreasing maintenance costs. Supervised machine learning algorithms have been successful to detect, diagnose, and forecast anomalous events in O&G industry. Nevertheless, these algorithms need a large quantity of annotated dataset and labelling data in real world scenarios is typically unfeasible because of exhaustive work of experts. Therefore, as unsupervised machine learning does not require an annotated dataset, this paper intends to perform a comparative evaluation performance of unsupervised learning algorithms to support experts for anomaly detection and pattern recognition in multivariate time-series data. So, the goal is to allow experts to analyze a small set of patterns and label them, instead of analyzing large datasets. This paper used the public 3W database of three offshore naturally flowing wells. The experiment used real data of production of O&G from underground reservoirs with the following anomalous events: (i) spurious closure of Downhole Safety Valve (DHSV) and (ii) quick restriction in Production Choke (PCK). Six unsupervised machine learning algorithms were assessed: Cluster-based Algorithm for Anomaly Detection in Time Series Using Mahalanobis Distance (C-AMDATS), Luminol Bitmap, SAX-REPEAT, k-NN, Bootstrap, and Robust Random Cut Forest (RRCF). The comparison evaluation of unsupervised learning algorithms was performed using a set of metrics: accuracy (ACC), precision (PR), recall (REC), specificity (SP), F1-Score (F1), Area Under the Receiver Operating Characteristic Curve (AUC-ROC), and Area Under the Precision-Recall Curve (AUC-PRC). The experiments only used the data labels for assessment purposes. The results revealed that unsupervised learning successfully detected the patterns of interest in multivariate data without prior annotation, with emphasis on the C-AMDATS algorithm. Thus, unsupervised learning can leverage supervised models through the support given to data annotation.

Download Full-text