SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2007.15951 · 2020

An Empirical Survey of Data Augmentation for Time Series Classification with Neural Networks

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 19 functions out of this paper's own repositories and ran 14 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
uchidalab/time_series_augmentation canonical 14 of 19
FunctionStatusWhere it lives
border_selection Ran uchidalab/time_series_augmentation/utils/prototype_selection.py
code served (permissive licence) · get_code("0f0f7c721707eed3")
center_selection Ran uchidalab/time_series_augmentation/utils/prototype_selection.py
code served (permissive licence) · get_code("dbf36d6824e2a63d")
cnn_lenet Ran uchidalab/time_series_augmentation/utils/models.py
code served (permissive licence) · get_code("fe95b56755997e58")
compute_CD Ran uchidalab/time_series_augmentation/utils/nemenyi.py
code served (permissive licence) · get_code("87f38bda64fde768")
get_datasets Ran uchidalab/time_series_augmentation/utils/input_data.py
code served (permissive licence) · get_code("e381033c0b9d40ec")
jitter Ran uchidalab/time_series_augmentation/utils/augmentation.py
code served (permissive licence) · get_code("7e91f7d6b90183d5")
load_data_from_file Ran uchidalab/time_series_augmentation/utils/input_data.py
code served (permissive licence) · get_code("7cf31f6b78c606a2")
mlp4 Ran uchidalab/time_series_augmentation/utils/models.py
code served (permissive licence) · get_code("0297da83a1396658")
nb_classes Ran uchidalab/time_series_augmentation/utils/datasets.py
code served (permissive licence) · get_code("3213e921153b8366")
nb_dims Ran uchidalab/time_series_augmentation/utils/datasets.py
code served (permissive licence) · get_code("343f559e28587141")
random_selection Ran uchidalab/time_series_augmentation/utils/prototype_selection.py
code served (permissive licence) · get_code("43dc9c195316089e")
rotation Ran uchidalab/time_series_augmentation/utils/augmentation.py
code served (permissive licence) · get_code("ec568a4fd5c0ca0c")
scaling Ran uchidalab/time_series_augmentation/utils/augmentation.py
code served (permissive licence) · get_code("570f35b7d04be7f7")
shape_dtw Ran uchidalab/time_series_augmentation/utils/dtw.py
code served (permissive licence) · get_code("4967a8f159950811")
class_offset Not yet run uchidalab/time_series_augmentation/utils/datasets.py
code served (permissive licence) · get_code("03a4fd381f7f635d")
dtw Not yet run uchidalab/time_series_augmentation/utils/dtw.py
code served (permissive licence) · get_code("66037d9834a6eeb5")
get_model Not yet run uchidalab/time_series_augmentation/utils/models.py
code served (permissive licence) · get_code("4c6299e6a59d9118")
graph_ranks Not yet run uchidalab/time_series_augmentation/utils/nemenyi.py
code served (permissive licence) · get_code("bb052203a1f1e8df")
read_data_sets Not yet run uchidalab/time_series_augmentation/utils/input_data.py
code served (permissive licence) · get_code("0dfcb65b2964f827")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

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 recognition, many datasets are often very small. One method of addressing this problem is through the use of data augmentation. In this paper, we survey data augmentation techniques for time series and their application to time series classification with neural networks. We propose a taxonomy and outline the four families in time series data augmentation, including transformation-based methods, pattern mixing, generative models, and decomposition methods. Furthermore, we empirically evaluate 12 time series data augmentation methods on 128 time series classification datasets with six different types of neural networks. Through the results, we are able to analyze the characteristics, advantages and disadvantages, and recommendations of each data augmentation method. This survey aims to help in the selection of time series data augmentation for neural network applications.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2007.15951")
get_code_for_paper("2007.15951")
have("2007.15951")

Connect an agent — have() is free.