Transfer learning for time series classification using synthetic data generation

• URL: http://arxiv.org/abs/2207.07897v1
• Date: Sat, 16 Jul 2022 10:35:14 GMT
• Title: Transfer learning for time series classification using synthetic data generation
• Abstract summary: We propose an innovative Transfer learning for Time series classification method. Instead of using an existing dataset from the UCR archive as the source dataset, we generated a 15,000,000 univariate time series dataset. We also used our own 55 regression tasks as the source tasks, which produced better results than selecting classification tasks from the UCR archive.
• Score: 15.73311395567215
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this paper, we propose an innovative Transfer learning for Time series classification method. Instead of using an existing dataset from the UCR archive as the source dataset, we generated a 15,000,000 synthetic univariate time series dataset that was created using our unique synthetic time series generator algorithm which can generate data with diverse patterns and angles and different sequence lengths. Furthermore, instead of using classification tasks provided by the UCR archive as the source task as previous studies did,we used our own 55 regression tasks as the source tasks, which produced better results than selecting classification tasks from the UCR archive

Related papers

• SMart: A Multi-source Multi-phase Time Series Representation Transfer Framework [8.331063987724717]
  We propose a new TSRL framework, namely multi-source multi-phase time series representation transfer (SMart)<n> Experimental results show that SMart outperforms several state-of-the-art models for time series representation learning, classification and regression.
  arXiv  Detail & Related papers  (2026-09-02T07:12:39Z)
• Adapt-$\infty$: Scalable Lifelong Multimodal Instruction Tuning via Dynamic Data Selection [89.42023974249122]
  Adapt-$infty$ is a new multi-way and adaptive data selection approach for Lifelong Instruction Tuning. We construct pseudo-skill clusters by grouping gradient-based sample vectors. We select the best-performing data selector for each skill cluster from a pool of selector experts.
  arXiv  Detail & Related papers  (2024-10-14T15:48:09Z)
• Model Selection with a Shapelet-based Distance Measure for Multi-source Transfer Learning in Time Series Classification [6.875312133832079]
  We propose a novel method of selecting and using multiple datasets for transfer learning for time series classification. Our method combines multiple datasets as one source dataset for pre-training neural networks. We demonstrate that it is possible to increase the performance of temporal convolutional neural networks (CNN) on time series datasets.
  arXiv  Detail & Related papers  (2024-09-30T06:57:30Z)
• CRAFT Your Dataset: Task-Specific Synthetic Dataset Generation Through Corpus Retrieval and Augmentation [51.2289822267563]
  We propose Corpus Retrieval and Augmentation for Fine-Tuning (CRAFT), a method for generating synthetic datasets. We use large-scale public web-crawled corpora and similarity-based document retrieval to find other relevant human-written documents. We demonstrate that CRAFT can efficiently generate large-scale task-specific training datasets for four diverse tasks.
  arXiv  Detail & Related papers  (2024-09-03T17:54:40Z)
• Chronos: Learning the Language of Time Series [79.38691251254173]
  Chronos is a framework for pretrained probabilistic time series models. We show that Chronos models can leverage time series data from diverse domains to improve zero-shot accuracy on unseen forecasting tasks.
  arXiv  Detail & Related papers  (2024-03-12T16:53:54Z)
• Temporal Treasure Hunt: Content-based Time Series Retrieval System for Discovering Insights [34.1973242428317]
  Time series data is ubiquitous across various domains such as finance, healthcare, and manufacturing. The ability to perform Content-based Time Series Retrieval (CTSR) is crucial for identifying unknown time series examples. We introduce a CTSR benchmark dataset that comprises time series data from a variety of domains.
  arXiv  Detail & Related papers  (2023-11-05T04:12:13Z)
• RED CoMETS: An ensemble classifier for symbolically represented multivariate time series [1.0878040851638]
  This paper introduces a novel ensemble classifier called RED CoMETS. Red CoMETS builds upon the success of Co-eye, an ensemble classifier specifically designed for symbolically represented univariate time series. It achieves the highest reported accuracy in the literature for the 'HandMovementDirection' dataset.
  arXiv  Detail & Related papers  (2023-07-25T17:36:34Z)
• TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series [61.436361263605114]
  Time series data are often scarce or highly sensitive, which precludes the sharing of data between researchers and industrial organizations. We introduce Time Series Generative Modeling (TSGM), an open-source framework for the generative modeling of synthetic time series.
  arXiv  Detail & Related papers  (2023-05-19T10:11:21Z)
• HyperTime: Implicit Neural Representation for Time Series [131.57172578210256]
  Implicit neural representations (INRs) have recently emerged as a powerful tool that provides an accurate and resolution-independent encoding of data. In this paper, we analyze the representation of time series using INRs, comparing different activation functions in terms of reconstruction accuracy and training convergence speed. We propose a hypernetwork architecture that leverages INRs to learn a compressed latent representation of an entire time series dataset.
  arXiv  Detail & Related papers  (2022-08-11T14:05:51Z)
• TTS-GAN: A Transformer-based Time-Series Generative Adversarial Network [4.989480853499916]
  Time-series data is one of the most common types of data used in medical machine learning applications. We introduce TTS-GAN, a transformer-based GAN which can successfully generate realistic synthetic time-series data sequences. We use visualizations and dimensionality reduction techniques to demonstrate the similarity of real and generated time-series data.
  arXiv  Detail & Related papers  (2022-02-06T03:05:47Z)
• Towards Generating Real-World Time Series Data [52.51620668470388]
  We propose a novel generative framework for time series data generation - RTSGAN. RTSGAN learns an encoder-decoder module which provides a mapping between a time series instance and a fixed-dimension latent vector. To generate time series with missing values, we further equip RTSGAN with an observation embedding layer and a decide-and-generate decoder.
  arXiv  Detail & Related papers  (2021-11-16T11:31:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.