FastDTW: Toward Accurate Dynamic Time Warping in Linear Time and Space

By Stan Salvador, Philip Ka-Fai Chan. 2004

620 citations recorded by the source corpus.

How researchers see this paper

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

1. Zhuolin Jiang
2. Jacob O. Wobbrock
3. Zhe L. Lin
4. Yang Li
5. Anupam Agrawal
6. Larry S. Davis
7. John Wilkes
8. Xiaohui Gu

Citations in the corpus

• TSViz: Demystification of Deep Learning Models for Time-Series Analysis (2018, methodology): “Since we are operating with 1D signals (each filter outputs a 1D activation vector), therefore, in order to compute the similarities between the filters, we leveraged a technique which is very common in time-series analysis community for alignment called as Dynamic Time Warping (DTW) [26].”
• struc2vec: Learning Node Representations from Structural Identity (2017, methodology): “We adopt Dynamic Time Warping (DTW) to measure the distance between two ordered degree sequences, a technique that can cope beŠer with sequences of di‚erent sizes and loosely compares sequence paŠerns [18, 20].”
• Voice Recognition Algorithms using Mel Frequency Cepstral Coefficient (MFCC) and Dynamic Time Warping (DTW) Techniques (2010, methodology): “DTW algorithm is based on Dynamic Programming techniques as describes in [11].”
• Gestures without libraries, toolkits or training: a $1 recognizer for user interface prototypes (2007, methodology): “As noted, there are procedures to accelerate DTW [24], but these make it a more complicated algorithm, which runs counter to our motivation for this work.”
• PRESS: PRedictive Elastic ReSource Scaling for cloud systems (2010, methodology): “Since S and S′ are similar but time-shifted, PRESS applies the dynamic time warping (DTW) algorithm [5] to determine the alignment.”
• Vision based hand gesture recognition for human computer interaction: a survey (2012, methodology): “Examples are applying constraints to DTW (Eamonn and Pazzani 2001), approximation of the algorithm (Stan and Philip 2004) and lower bounding techniques (Keogh and Ratanamahatana 2005).”
• Recognizing actions by shape-motion prototype trees (2009, methodology): “Motivated by them, we use the FastDTW algorithm [22] to automatically identify optimal matching segments and compute alignment-based distances between two sequences.”
• A review on time series data mining (2011, unknown): “A FastDTW is proposed by Salvador and Chan (2004).”