Results 1 to 10 of about 655,816 (301)
Time-series representation learning via Time-Frequency Fusion Contrasting [PDF]
Frontiers in Artificial IntelligenceTime series is a typical data type in numerous domains; however, labeling large amounts of time series data can be costly and time-consuming. Learning effective representation from unlabeled time series data is a challenging task.
Wenbo Zhao, Ling Fan
doaj +2 more sources
Time-Series Representation Feature Refinement with a Learnable Masking Augmentation Framework in Contrastive Learning [PDF]
SensorsIn this study, we propose a novel framework for time-series representation learning that integrates a learnable masking-augmentation strategy into a contrastive learning framework.
Junyeop Lee +3 more
doaj +2 more sources
A unified time series classification framework via adaptive Gaussian image representation [PDF]
Scientific ReportsReal-world time series classification (TSC) is frequently hindered by significant data heterogeneity, characterized by complex multivariate dependencies and variable sequence lengths.
Xinyue Ren +3 more
doaj +2 more sources
IEEE Access, 2017 Data representation and similarity measurement are two basic aspects of similarity detection in time series data mining. In this paper, we present two novel approaches to perform similarity detection efficiently and effectively.
Miaomiao Zhang, Dechang Pi
doaj +3 more sources
Temporal Multi-Features Representation Learning-Based Clustering for Time-Series Data
IEEE AccessTime-series clustering remains a challenge in data mining. Although novel deep-learning-based representation learning integrated with deep clustering methods have considerably enhanced the performance of time-series clustering, efficiently capturing the ...
Jaehoon Lee, Dohee Kim, Sunghyun Sim
doaj +3 more sources
Stock Embeddings: Representation Learning for Financial Time Series
Engineering Proceedings, 2023 Identifying meaningful and actionable relationships between the price movements of financial assets is a challenging but important problem for many financial tasks, from portfolio optimization to sector classification.
Rian Dolphin, Barry Smyth, Ruihai Dong
doaj +1 more source
Distance- and Momentum-Based Symbolic Aggregate Approximation for Highly Imbalanced Classification
Sensors, 2022 Time-series representation is the most important task in time-series analysis. One of the most widely employed time-series representation method is symbolic aggregate approximation (SAX), which converts the results from piecewise aggregate approximation ...
Dong-Hyuk Yang, Yong-Shin Kang
doaj +1 more source
Time series classification through visual pattern recognition
Journal of King Saud University: Computer and Information Sciences, 2022 In this paper, a new approach to time series classification is proposed. It transforms the scalar time series into a two-dimensional space of amplitude (time series values) and a change of amplitude (increment).
Agnieszka Jastrzebska
doaj +1 more source
Generalized relational tensors for chaotic time series [PDF]
PeerJ Computer Science, 2023 The article deals with a generalized relational tensor, a novel discrete structure to store information about a time series, and algorithms (1) to fill the structure, (2) to generate a time series from the structure, and (3) to predict a time series. The
Vasilii A. Gromov +2 more
doaj +2 more sources
Learning Disentangled Representations for Time Series
CoRR, 2021 Time-series representation learning is a fundamental task for time-series analysis. While significant progress has been made to achieve accurate representations for downstream applications, the learned representations often lack interpretability and do not expose semantic meanings.
Yuening Li +6 more
openaire +2 more sources