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

Symmetry ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 1251 ◽  
Author(s):  
Tsatsral Amarbayasgalan ◽  
Van Huy Pham ◽  
Nipon Theera-Umpon ◽  
Keun Ho Ryu
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Real Time ◽  
Reconstruction Error ◽  
Ar Model ◽  
Detection Methods ◽  
Series Data ◽  
Detection Approach ◽  
Unsupervised Anomaly Detection ◽  
Anomaly Detector

Automatic anomaly detection for time-series is critical in a variety of real-world domains such as fraud detection, fault diagnosis, and patient monitoring. Current anomaly detection methods detect the remarkably low proportion of the actual abnormalities correctly. Furthermore, most of the datasets do not provide data labels, and require unsupervised approaches. 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. RE-ADTS consists of two modules including the time-series reconstructor and anomaly detector. The time-series reconstructor module uses the autoregressive (AR) model to find an optimal window width and prepares the subsequences for further analysis according to the width. Then, it uses a deep autoencoder (AE) model to learn the data distribution, which is then used to reconstruct a time-series close to the normal. For anomalies, their reconstruction error (RE) was higher than that of the normal data. As a result of this module, RE and compressed representation of the subsequences were estimated. Later, the anomaly detector module defines the corresponding time-series as normal or an anomaly using a RE based anomaly threshold. For batch anomaly detection, the combination of the density-based clustering technique and anomaly threshold is employed. In the case of real-time anomaly detection, only the anomaly threshold is used without the clustering process. We conducted two types of experiments on a total of 52 publicly available time-series benchmark datasets for the batch and real-time anomaly detections. Experimental results show that the proposed RE-ADTS outperformed the state-of-the-art publicly available anomaly detection methods in most cases.

Variance error of multi-classification based anomaly detection for time series data

2020 ◽  
pp. 1-16
Author(s):  
Baoquan Wang ◽  
Tonghai Jiang ◽  
Xi Zhou ◽  
Bo Ma ◽  
Fan Zhao ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Short Term Memory ◽  
Computational Cost ◽  
Reconstruction Error ◽  
Detection Methods ◽  
Series Data ◽  
Data Set

For abnormal detection of time series data, the supervised anomaly detection methods require labeled data. While the range of outlier factors used by the existing semi-supervised methods varies with data, model and time, the threshold for determining abnormality is difficult to obtain, in addition, the computational cost of the way to calculate outlier factors from other data points in the data set is also very large. These make such methods difficult to practically apply. This paper proposes a framework named LSTM-VE which uses clustering combined with visualization method to roughly label normal data, and then uses the normal data to train long short-term memory (LSTM) neural network for semi-supervised anomaly detection. The variance error (VE) of the normal data category classification probability sequence is used as outlier factor. The framework enables anomaly detection based on deep learning to be practically applied and using VE avoids the shortcomings of existing outlier factors and gains a better performance. In addition, the framework is easy to expand because the LSTM neural network can be replaced with other classification models. Experiments on the labeled and real unlabeled data sets prove that the framework is better than replicator neural networks with reconstruction error (RNN-RS) and has good scalability as well as practicability.

scholarly journals BeatGAN: Anomalous Rhythm Detection using Adversarially Generated Time Series

2019 ◽  
Author(s):  
Bin Zhou ◽  
Shenghua Liu ◽  
Bryan Hooi ◽  
Xueqi Cheng ◽  
Jing Ye
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Large Scale ◽  
Data Augmentation ◽  
Time Series Data ◽  
Detection Algorithm ◽  
Reconstruction Error ◽  
Series Data ◽  
Lower Accuracy ◽  
Unsupervised Anomaly Detection

Given a large-scale rhythmic time series containing mostly normal data segments (or `beats'), can we learn how to detect anomalous beats in an effective yet efficient way? For example, how can we detect anomalous beats from electrocardiogram (ECG) readings? Existing approaches either require excessively high amounts of labeled and balanced data for classification, or rely on less regularized reconstructions, resulting in lower accuracy in anomaly detection. Therefore, we propose BeatGAN, an unsupervised anomaly detection algorithm for time series data. BeatGAN outputs explainable results to pinpoint the anomalous time ticks of an input beat, by comparing them to adversarially generated beats. Its robustness is guaranteed by its regularization of reconstruction error using an adversarial generation approach, as well as data augmentation using time series warping. Experiments show that BeatGAN accurately and efficiently detects anomalous beats in ECG time series, and routes doctors' attention to anomalous time ticks, achieving accuracy of nearly 0.95 AUC, and very fast inference (2.6 ms per beat). In addition, we show that BeatGAN accurately detects unusual motions from multivariate motion-capture time series data, illustrating its generality.

scholarly journals Anomaly Detection and Classification of Physiological Signals in IoT- Based Healthcare Framework

2021 ◽  
Author(s):  
Menaa Nawaz ◽  
Jameel Ahmed
Keyword(s):  
Time Series ◽  
Feature Extraction ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Real Time ◽  
Signal Analysis ◽  
Physiological Signals ◽  
Series Data ◽  
Time Signal ◽  
Biomedical Sensors

Abstract Physiological signals retrieve information from sensors implanted or attached to the human body. These signals are vital data sources that can assist in predicting the disease well before time; thus, proper treatment can be made possible. With the addition of the Internet of Things in healthcare, real-time data collection and preprocessing for signal analysis has reduced the burden of in-person appointments and decision making on healthcare. Recently, deep learning-based algorithms have been implemented by researchers for the recognition, realization and prediction of diseases by extracting and analyzing important features. In this research, real-time 1-D time series data of on-body noninvasive biomedical sensors were acquired, preprocessed and analysed for anomaly detection. Feature engineered parameters of large and diverse datasets have been used to train the data to make the anomaly detection system more reliable. For comprehensive real-time monitoring, the implemented system uses wavelet time scattering features for classification and a deep learning-based autoencoder for anomaly detection of time series signals to assist the clinical diagnosis of cardiovascular and muscular activity. In this research, an implementation of an IoT-based AI-edge healthcare framework using biomedical sensors was presented. This paper also aims to analyse cloud data acquired through biomedical sensors using signal analysis techniques for anomaly detection, and time series classification has been performed for disease prognosis in real time by implementing 24 AI-based techniques to find the most accurate technique for real-time raw signals. The deep learning-based LSTM method based on wavelet time scattering feature extraction has shown a classification test accuracy of 100%. Using wavelet time scattering feature extraction achieved 95% signal reduction to increase the real-time processing speed. In real-time signal anomaly detection, 98% accuracy is achieved using LSTM autoencoders. The average mean absolute error loss of 0.0072 for normal signals and 0.078 is achieved for anomalous signals.

scholarly journals Deep Quantile Regression for Unsupervised Anomaly Detection in Time-Series

2021 ◽  
Vol 2 (6) ◽  
Author(s):  
Ahmad Idris Tambuwal ◽  
Daniel Neagu
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Quantile Regression ◽  
Gaussian Distribution ◽  
Time Series Data ◽  
Prediction Interval ◽  
Data Interpretation ◽  
Research Literature ◽  
Detection Methods ◽  
Series Data

AbstractTime-series anomaly detection receives increasing research interest given the growing number of data-rich application domains. Recent additions to anomaly detection methods in research literature include deep neural networks (DNNs: e.g., RNN, CNN, and Autoencoder). The nature and performance of these algorithms in sequence analysis enable them to learn hierarchical discriminative features and time-series temporal nature. However, their performance is affected by usually assuming a Gaussian distribution on the prediction error, which is either ranked, or threshold to label data instances as anomalous or not. An exact parametric distribution is often not directly relevant in many applications though. This will potentially produce faulty decisions from false anomaly predictions due to high variations in data interpretation. The expectations are to produce outputs characterized by a level of confidence. Thus, implementations need the Prediction Interval (PI) that quantify the level of uncertainty associated with the DNN point forecasts, which helps in making better-informed decision and mitigates against false anomaly alerts. An effort has been made in reducing false anomaly alerts through the use of quantile regression for identification of anomalies, but it is limited to the use of quantile interval to identify uncertainties in the data. In this paper, an improve time-series anomaly detection method called deep quantile regression anomaly detection (DQR-AD) is proposed. The proposed method go further to used quantile interval (QI) as anomaly score and compare it with threshold to identify anomalous points in time-series data. The tests run of the proposed method on publicly available anomaly benchmark datasets demonstrate its effective performance over other methods that assumed Gaussian distribution on the prediction or reconstruction cost for detection of anomalies. This shows that our method is potentially less sensitive to data distribution than existing approaches.

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

2019 ◽  
Vol 33 ◽  
pp. 1409-1416 ◽  
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.

Sign in / Sign up

Export Citation Format

Share Document