Time Series Data Augmentation for Deep Learning: A Survey

Wen, Quan; Sun, Liang; Yang, Fan; Song, Xiaomin; Gao, Jingkun; Wang, Xue; Xu, Huan

doi:10.24963/ijcai.2021/631

Cited by 359 publications

(142 citation statements)

References 26 publications

Supporting

Mentioning

141

Contrasting

Order By: Relevance

“…Data augmentation is an efficient tool for increasing the size and enhancing the quality of the training data. It mainly aims to generate more data covering unseen input spaces (Wen et al, 2020). Data augmentation can make the model more robust by enlarging the size and adding noise or causing transformation.…”

Section: Data Augmentationmentioning

confidence: 99%

Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020

et al. 2022

View full text Add to dashboard Cite

Cardiovascular diseases (CVDs) are one of the most fatal disease groups worldwide. Electrocardiogram (ECG) is a widely used tool for automatically detecting cardiac abnormalities, thereby helping to control and manage CVDs. To encourage more multidisciplinary researches, PhysioNet/Computing in Cardiology Challenge 2020 (Challenge 2020) provided a public platform involving multi-center databases and automatic evaluations for ECG classification tasks. As a result, 41 teams successfully submitted their solutions and were qualified for rankings. Although Challenge 2020 was a success, there has been no in-depth methodological meta-analysis of these solutions, making it difficult for researchers to benefit from the solutions and results. In this study, we aim to systematically review the 41 solutions in terms of data processing, feature engineering, model architecture, and training strategy. For each perspective, we visualize and statistically analyze the effectiveness of the common techniques, and discuss the methodological advantages and disadvantages. Finally, we summarize five practical lessons based on the aforementioned analysis: (1) Data augmentation should be employed and adapted to specific scenarios; (2) Combining different features can improve performance; (3) A hybrid design of different types of deep neural networks (DNNs) is better than using a single type; (4) The use of end-to-end architectures should depend on the task being solved; (5) Multiple models are better than one. We expect that our meta-analysis will help accelerate the research related to ECG classification based on machine-learning models.

show abstract

Section: Data Augmentationmentioning

confidence: 99%

Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020

et al. 2022

View full text Add to dashboard Cite

show abstract

“…It should be noted that this type of augmentation is only applicable to raw EEG data. Time Warping (TimeW): TimeW is an augmentation technique that randomly modifies the temporal position of a signal [31]. It simulates the variation of the temporal location of an event in a time window.…”

Section: ) Authentication By Classificationmentioning

confidence: 99%

Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms

et al. 2021

View full text Add to dashboard Cite

Electroencephalography (EEG) based biometric systems are gaining attention for their anti-spoofing capability but lack accuracy due to signal variability at different psychological and physiological conditions. On the other hand, keystroke dynamics-based systems achieve very high accuracy but have low anti-spoofing capability. To address these issues, a novel multimodal biometric system combining EEG and keystroke dynamics is proposed in this paper. A dataset was created by acquiring both keystroke dynamics and EEG signals simultaneously from 10 users. Each user participated in 500 trials at 10 different sessions (days) to replicate real-life signal variability. A machine learning classification pipeline is developed using multi-domain feature extraction (time, frequency, time-frequency), feature selection (Gini impurity), classifier design, and score level fusion. Different classifiers were trained, validated, and tested for two different classification experimentspersonalized and generalized. For identification and authentication, 99.9% and 99.6% accuracies are achieved, respectively for Random Forest classifier using 5 fold cross-validation. These results outperform the individual modalities with a significant margin (~5%). We also developed a binary template matching-based algorithm, which gives 6X faster system with 93.64% accuracy. The proposed method can be considered secure and reliable for any kind of biometric identification and authentication.

show abstract

“…If the train set contains information (e.g., same data points) from the test set, then it is likely that the model will present overfitting. Furthermore, to accurately train and test classification models, it is ideal that all classes have similar sizes, especially during the testing stages [62]. Having balanced classes allows us to easily compare classification metrics such as the confusion matrix, precision, recall, and f1-score.…”

Section: Training Validation and Test Setsmentioning

confidence: 99%

Big Machinery Data Preprocessing Methodology for Data-Driven Models in Prognostics and Health Management

Cofre-Martel

Droguett

Modarres

2021

Sensors

View full text Add to dashboard Cite

Sensor monitoring networks and advances in big data analytics have guided the reliability engineering landscape to a new era of big machinery data. Low-cost sensors, along with the evolution of the internet of things and industry 4.0, have resulted in rich databases that can be analyzed through prognostics and health management (PHM) frameworks. Several data-driven models (DDMs) have been proposed and applied for diagnostics and prognostics purposes in complex systems. However, many of these models are developed using simulated or experimental data sets, and there is still a knowledge gap for applications in real operating systems. Furthermore, little attention has been given to the required data preprocessing steps compared to the training processes of these DDMs. Up to date, research works do not follow a formal and consistent data preprocessing guideline for PHM applications. This paper presents a comprehensive step-by-step pipeline for the preprocessing of monitoring data from complex systems aimed for DDMs. The importance of expert knowledge is discussed in the context of data selection and label generation. Two case studies are presented for validation, with the end goal of creating clean data sets with healthy and unhealthy labels that are then used to train machinery health state classifiers.

show abstract

Time Series Data Augmentation for Deep Learning: A Survey

Cited by 359 publications

References 26 publications

Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020

Practical Lessons on 12-Lead ECG Classification: Meta-Analysis of Methods From PhysioNet/Computing in Cardiology Challenge 2020

Multimodal EEG and Keystroke Dynamics Based Biometric System Using Machine Learning Algorithms

Big Machinery Data Preprocessing Methodology for Data-Driven Models in Prognostics and Health Management

Contact Info

Product

Resources

About