English
Related papers

Related papers: Time Series Data Augmentation as an Imbalanced Lea…

200 papers

Most forecasting methods use recent past observations (lags) to model the future values of univariate time series. Selecting an adequate number of lags is important for training accurate forecasting models. Several approaches and heuristics…

Machine Learning · Statistics 2024-05-21 José Leites , Vitor Cerqueira , Carlos Soares

Time-series data augmentation mitigates the issue of insufficient training data for deep learning models. Yet, existing augmentation methods are mainly designed for classification, where class labels can be preserved even if augmentation…

Machine Learning · Computer Science 2023-03-28 Xiyuan Zhang , Ranak Roy Chowdhury , Jingbo Shang , Rajesh Gupta , Dezhi Hong

Forecasting future outcomes from recent time series data is not easy, especially when the future data are different from the past (i.e. time series are under temporal drifts). Existing approaches show limited performances under data drifts,…

Machine Learning · Computer Science 2022-11-23 Jaehoon Lee , Chan Kim , Gyumin Lee , Haksoo Lim , Jeongwhan Choi , Kookjin Lee , Dongeun Lee , Sanghyun Hong , Noseong Park

Data augmentation is commonly used to encode invariances in learning methods. However, this process is often performed in an inefficient manner, as artificial examples are created by applying a number of transformations to all points in the…

Machine Learning · Computer Science 2019-03-04 Michael Kuchnik , Virginia Smith

Time series are all around in real-world applications. However, unexpected accidents for example broken sensors or missing of the signals will cause missing values in time series, making the data hard to be utilized. It then does harm to…

Machine Learning · Computer Science 2020-11-24 Chenguang Fang , Chen Wang

Synthetic time series are often used in practical applications to augment the historical time series dataset for better performance of machine learning algorithms, amplify the occurrence of rare events, and also create counterfactual…

Machine Learning · Computer Science 2023-09-18 Andrea Coletta , Sriram Gopalakrishan , Daniel Borrajo , Svitlana Vyetrenko

Handling imbalance in class distribution when building a classifier over tabular data has been a problem of long-standing interest. One popular approach is augmenting the training dataset with synthetically generated data. While classical…

Machine Learning · Computer Science 2025-02-20 Annie D'souza , Swetha M , Sunita Sarawagi

In recent years, neural networks achieved much success in various applications. The main challenge in training deep neural networks is the lack of sufficient data to improve the model's generalization and avoid overfitting. One of the…

Machine Learning · Computer Science 2021-08-24 Mohammad Akyash , Hoda Mohammadzade , Hamid Behroozi

In recent times, deep artificial neural networks have achieved many successes in pattern recognition. Part of this success can be attributed to the reliance on big data to increase generalization. However, in the field of time series…

Machine Learning · Computer Science 2021-09-15 Brian Kenji Iwana , Seiichi Uchida

Data augmentation is a crucial tool in time series forecasting, especially for deep learning architectures that require a large training sample size to generalize effectively. However, extensive datasets are not always available in…

Machine Learning · Computer Science 2026-01-28 Luis Amorim , Moises Santos , Paulo J. Azevedo , Carlos Soares , Vitor Cerqueira

Self-supervised contrastive learning has become a key technique in deep learning, particularly in time series analysis, due to its ability to learn meaningful representations without explicit supervision. Augmentation is a critical…

Machine Learning · Computer Science 2024-07-15 Ziyu Liu , Azadeh Alavi , Minyi Li , Xiang Zhang

Time Series Classification (TSC) has drawn a lot of attention in literature because of its broad range of applications for different domains, such as medical data mining, weather forecasting. Although TSC algorithms are designed for…

Machine Learning · Computer Science 2021-10-12 Syed Rawshon Jamil

Irregularly-sampled time series occur in many domains including healthcare. They can be challenging to model because they do not naturally yield a fixed-dimensional representation as required by many standard machine learning models. In…

Machine Learning · Computer Science 2020-08-19 Steven Cheng-Xian Li , Benjamin M. Marlin

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Machine Learning · Computer Science 2020-11-24 Joel Jang , Yoonjeon Kim , Kyoungho Choi , Sungho Suh

For over two decades, detecting rare events has been a challenging task among researchers in the data mining and machine learning domain. Real-life problems inspire researchers to navigate and further improve data processing and algorithmic…

Machine Learning · Computer Science 2025-09-09 Elaheh Jafarigol , Theodore Trafalis , Neshat Mohammadi

In forecasting multiple time series, accounting for the individual features of each sequence can be challenging. To address this, modern deep learning methods for time series analysis combine a shared (global) model with local layers,…

Machine Learning · Computer Science 2025-02-14 Luca Butera , Giovanni De Felice , Andrea Cini , Cesare Alippi

Irregularly sampled time series are increasingly prevalent, particularly in medical domains. While various specialized methods have been developed to handle these irregularities, effectively modeling their complex dynamics and pronounced…

Machine Learning · Computer Science 2023-11-01 Zekun Li , Shiyang Li , Xifeng Yan

For several years till date, the major issues in terms of solving for classification problems are the issues of Imbalanced data. Because majority of the machine learning algorithms by default assumes all data are balanced, the algorithms do…

Machine Learning · Statistics 2020-10-12 Richmond Addo Danquah

Deep Learning methods have significantly advanced various data-driven tasks such as regression, classification, and forecasting. However, much of this progress has been predicated on the strong but often unrealistic assumption that training…

Machine Learning · Computer Science 2023-10-12 Josias Moukpe

Data augmentation is a crucial technique for improving model generalization and robustness, particularly in deep learning models where training data is limited. Although many augmentation methods have been developed for time series…

Machine Learning · Computer Science 2026-04-13 Jafar Bakhshaliyev , Johannes Burchert , Niels Landwehr , Lars Schmidt-Thieme