A Bag-of-Features Framework to Classify Time Series

By Mustafa Gokce Baydogan, George C. Runger, Eugene Tuv. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013

363 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/e1e5d83a955d073d86bb13e620f7f00dd0955ae9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Rohit J. Kate
2. Anthony J. Bagnall
3. Jason Lines
4. Tim Oates
5. Zhiguang Wang
6. Weizhong Yan
7. Anastasios Tefas
8. Aaron Bostrom

In Signal Processing

1. Rohit J. Kate
2. Anthony J. Bagnall
3. Jason Lines
4. Aaron Bostrom
5. Tim Oates
6. Zhiguang Wang
7. James Large
8. Jon Hills

Citations in the corpus

• Time series classification with ensembles of elastic distance measures (2015, methodology): “Baydogan et al. (2013) describe a bag-of-features approach that combines interval and frequency features.”
• Time-series classification using neural Bag-of-Features (2017, methodology): “However, it was established that it can be used for a wide range of tasks, such as video [11], and time-series representation [7]–[9].”
• The great time series classification bake off: a review and experimental evaluation of recent algorithmic advances (2016, background): “2 Time series bag of features (TSBF) (Baydogan et al. 2013)”
• Multi-Scale Convolutional Neural Networks for Time Series Classification (2016, methodology): “We also select 11 existing methods with state-of-the-art results published within the recent three years, including: DTW with a warping window constraint set through cross validation (DTW CV) [23], Fast Shapelet (FS) [24] , SAX with vector space model (SV) [29], Bag-of-SFA-Symbols (BOSS) [26], Shotg”
• Using dynamic time warping distances as features for improved time series classification (2016, background): “In some papers the experimental setting is not clear, for example, Baydogan et al. (2013) took average of ten different error rates of their method and it is not clear which of the settings is best.”
• Time-Series Classification with COTE: The Collective of Transformation-Based Ensembles (2015, background): “The establishment of the UCR repository for TSC problems [1] has engendered growth in the number of algorithms proposed for TSC (for example, see [2], [3], [4], [5], [6], [7], [8], [9]).”
• LSTM Fully Convolutional Networks for Time Series Classification (2017, background): “Bag-of-Words (BoW) [2], Bag-of-features (TSBF) [3], Bag-of-SFA-Symbols (BOSS) [4], BOSSVS [5], Word ExtrAction for time Series cLassification (WEASEL) [6], have obtained promising results in the field.”
• Time series classification from scratch with deep neural networks: A strong baseline (2016, background): “We select seven existing best methods 2 that claim the state-of-the-art results and published within recent three years: time series based on a bag-offeatures (TSBF), Elastic Ensemble (PROP), 1-NN Bag-Of-SFA-Symbols (BOSS) in Vector Space (BOSSVS), the Shapelet Ensemble (SE1) model, flat-COTE (COTE) ”