scholarly journals Time Series Data Augmentation for Deep Learning: A Survey

2021 ◽  
Author(s):  
Qingsong Wen ◽  
Liang Sun ◽  
Fan Yang ◽  
Xiaomin Song ◽  
Jingkun Gao ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Data Augmentation ◽  
Time Series Data ◽  
Training Data ◽  
Superior Performance ◽  
Series Data ◽  
Future Directions

Deep learning performs remarkably well on many time series analysis tasks recently. The superior performance of deep neural networks relies heavily on a large number of training data to avoid overfitting. However, the labeled data of many real-world time series applications may be limited such as classification in medical time series and anomaly detection in AIOps. As an effective way to enhance the size and quality of the training data, data augmentation is crucial to the successful application of deep learning models on time series data. In this paper, we systematically review different data augmentation methods for time series. We propose a taxonomy for the reviewed methods, and then provide a structured review for these methods by highlighting their strengths and limitations. We also empirically compare different data augmentation methods for different tasks including time series classification, anomaly detection, and forecasting. Finally, we discuss and highlight five future directions to provide useful research guidance.

scholarly journals Deep Learning for Anomaly Detection in Time-Series Data: Review, Analysis, and Guidelines

IEEE Access ◽  
2021 ◽  
Vol 9 ◽  
pp. 120043-120065
Author(s):  
Kukjin Choi ◽  
Jihun Yi ◽  
Changhwa Park ◽  
Sungroh Yoon
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Series Data ◽  
Review Analysis

scholarly journals A deep learning approach for anomaly detection with industrial time series data: a refrigerators manufacturing case study

2019 ◽  
Vol 38 ◽  
pp. 233-240 ◽  
Author(s):  
Mattia Carletti ◽  
Chiara Masiero ◽  
Alessandro Beghi ◽  
Gian Antonio Susto
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Series Data ◽  
Learning Approach

scholarly journals CORN: An Alternative Way to Utilize Time-Series Data of SAR Images in Newly Built Construction Detection

2020 ◽  
Vol 12 (6) ◽  
pp. 990
Author(s):  
Raveerat Jaturapitpornchai ◽  
Poompat Rattanasuwan ◽  
Masashi Matsuoka ◽  
Ryosuke Nakamura
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Data ◽  
Source Code ◽  
Training Data ◽  
Series Data ◽  
Learning Networks ◽  
Chronological Order ◽  
Alos Palsar ◽  
Sar Images

The limitations in obtaining sufficient datasets for training deep learning networks is preventing many applications from achieving accurate results, especially when detecting new constructions using time-series satellite imagery, since this requires at least two images of the same scene and it must contain new constructions in it. To tackle this problem, we introduce Chronological Order Reverse Network (CORN)—an architecture for detecting newly built constructions in time-series SAR images that does not require a large quantity of training data. The network uses two U-net adaptations to learn the changes between images from both Time 1–Time 2 and Time 2–Time 1 formats, which allows it to learn double the amount of changes in different perspectives. We trained the network with 2028 pairs of 256 × 256 pixel SAR images from ALOS-PALSAR, totaling 4056 pairs for the network to learn from, since it learns from both Time 1–Time 2 and Time 2–Time 1. As a result, the network can detect new constructions more accurately, especially at the building boundary, compared to the original U-net trained by the same amount of training data. The experiment also shows that the model trained with CORN can be used with images from Sentinel-1. The source code is available at https://github.com/Raveerat-titech/CORN.

scholarly journals A Novel Deep Learning Approach for Anomaly Detection of Time Series Data

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Zhiwei Ji ◽  
Jiaheng Gong ◽  
Jiarui Feng
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Short Term Memory ◽  
Training Data ◽  
Series Data ◽  
Real Time System ◽  
Statistical Strategy ◽  
Anomaly Classification ◽  
Real World Datasets

Anomalies in time series, also called “discord,” are the abnormal subsequences. The occurrence of anomalies in time series may indicate that some faults or disease will occur soon. Therefore, development of novel computational approaches for anomaly detection (discord search) in time series is of great significance for state monitoring and early warning of real-time system. Previous studies show that many algorithms were successfully developed and were used for anomaly classification, e.g., health monitoring, traffic detection, and intrusion detection. However, the anomaly detection of time series was not well studied. In this paper, we proposed a long short-term memory- (LSTM-) based anomaly detection method (LSTMAD) for discord search from univariate time series data. LSTMAD learns the structural features from normal (nonanomalous) training data and then performs anomaly detection via a statistical strategy based on the prediction error for observed data. In our experimental evaluation using public ECG datasets and real-world datasets, LSTMAD detects anomalies more accurately than other existing approaches in comparison.

scholarly journals Evaluation metrics for anomaly detection algorithms in time-series

2019 ◽  
Vol 11 (2) ◽  
pp. 113-130 ◽  
Author(s):  
György Kovács ◽  
Gheorghe Sebestyen ◽  
Anca Hangan
Keyword(s):  
Time Series ◽  
Anomaly Detection ◽  
Time Series Data ◽  
Confusion Matrix ◽  
Series Data ◽  
Time Data ◽  
Temporal Dimension ◽  
Detection Techniques ◽  
Detection Algorithms

Abstract Time-series are ordered sequences of discrete-time data. Due to their temporal dimension, anomaly detection techniques used in time-series have to take into consideration time correlations and other time-related particularities. Generally, in order to evaluate the quality of an anomaly detection technique, the confusion matrix and its derived metrics such as precision and recall are used. These metrics, however, do not take this temporal dimension into consideration. In this paper, we propose three metrics that can be used to evaluate the quality of a classification, while accounting for the temporal dimension found in time-series data.

scholarly journals Membrane System-Based Improved Neural Networks for Time-Series Anomaly Detection

Processes ◽  
2020 ◽  
Vol 8 (9) ◽  
pp. 1168
Author(s):  
Wenxiang Guo ◽  
Xiyu Liu ◽  
Laisheng Xiang
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Anomaly Detection ◽  
Domain Knowledge ◽  
Time Series Data ◽  
Short Term Memory ◽  
Membrane System ◽  
Superior Performance ◽  
Series Data ◽  
Training Time

Anomaly detection in time series has attracted much attention recently and is quite a challenging task. In this paper, a novel deep-learning approach (AL-CNN) that classifies the time series as normal or abnormal with less domain knowledge is proposed. The proposed algorithm combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) to effectively model the spatial and temporal information contained in time-series data, the techniques of Squeeze-and-Excitation are applied to implement the feature recalibration. However, the difficulty of selecting multiple parameters and the long training time of a single model make AL-CNN less effective. To alleviate these challenges, a hybrid dynamic membrane system (HM-AL-CNN) is designed which is a new distributed and parallel computing model. We have performed a detailed evaluation of this proposed approach on three well-known benchmarks including the Yahoo S5 datasets. Experiments show that the proposed method possessed a robust and superior performance than the state-of-the-art methods and improved the average on three used indicators significantly.

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.

Sign in / Sign up

Export Citation Format

Share Document