@Article{s21175801,
AUTHOR = {Li, Kenan and Deng, Huiyu and Morrison, John and Habre, Rima and Franklin, Meredith and Chiang, Yao-Yi and Sward, Katherine and Gilliland, Frank D. and Ambite, José Luis and Eckel, Sandrah P.},
TITLE = {W-TSS: A Wavelet-Based Algorithm for Discovering Time Series Shapelets},
JOURNAL = {Sensors},
VOLUME = {21},
YEAR = {2021},
NUMBER = {17},
ARTICLE-NUMBER = {5801},
URL = {https://www.mdpi.com/1424-8220/21/17/5801},
PubMedID = {34502692},
ISSN = {1424-8220},
ABSTRACT = {Many approaches to time series classification rely on machine learning methods. However, there is growing interest in going beyond black box prediction models to understand discriminatory features of the time series and their associations with outcomes. One promising method is time-series shapelets (TSS), which identifies maximally discriminative subsequences of time series. For example, in environmental health applications TSS could be used to identify short-term patterns in exposure time series (shapelets) associated with adverse health outcomes. Identification of candidate shapelets in TSS is computationally intensive. The original TSS algorithm used exhaustive search. Subsequent algorithms introduced efficiencies by trimming/aggregating the set of candidates or training candidates from initialized values, but these approaches have limitations. In this paper, we introduce Wavelet-TSS (W-TSS) a novel intelligent method for identifying candidate shapelets in TSS using wavelet transformation discovery. We tested W-TSS on two datasets: (1) a synthetic example used in previous TSS studies and (2) a panel study relating exposures from residential air pollution sensors to symptoms in participants with asthma. Compared to previous TSS algorithms, W-TSS was more computationally efficient, more accurate, and was able to discover more discriminative shapelets. W-TSS does not require pre-specification of shapelet length.},
DOI = {10.3390/s21175801}
}

{"_id":"xGiNWKg3qXCtGqw7n","bibbaseid":"li-deng-morrison-habre-franklin-chiang-sward-gilliland-etal-wtssawaveletbasedalgorithmfordiscoveringtimeseriesshapelets-2021","author_short":["Li, K.","Deng, H.","Morrison, J.","Habre, R.","Franklin, M.","Chiang, Y.","Sward, K.","Gilliland, F. D.","Ambite, J. L.","Eckel, S. P."],"bibdata":{"bibtype":"article","type":"article","author":[{"propositions":[],"lastnames":["Li"],"firstnames":["Kenan"],"suffixes":[]},{"propositions":[],"lastnames":["Deng"],"firstnames":["Huiyu"],"suffixes":[]},{"propositions":[],"lastnames":["Morrison"],"firstnames":["John"],"suffixes":[]},{"propositions":[],"lastnames":["Habre"],"firstnames":["Rima"],"suffixes":[]},{"propositions":[],"lastnames":["Franklin"],"firstnames":["Meredith"],"suffixes":[]},{"propositions":[],"lastnames":["Chiang"],"firstnames":["Yao-Yi"],"suffixes":[]},{"propositions":[],"lastnames":["Sward"],"firstnames":["Katherine"],"suffixes":[]},{"propositions":[],"lastnames":["Gilliland"],"firstnames":["Frank","D."],"suffixes":[]},{"propositions":[],"lastnames":["Ambite"],"firstnames":["José","Luis"],"suffixes":[]},{"propositions":[],"lastnames":["Eckel"],"firstnames":["Sandrah","P."],"suffixes":[]}],"title":"W-TSS: A Wavelet-Based Algorithm for Discovering Time Series Shapelets","journal":"Sensors","volume":"21","year":"2021","number":"17","article-number":"5801","url":"https://www.mdpi.com/1424-8220/21/17/5801","pubmedid":"34502692","issn":"1424-8220","abstract":"Many approaches to time series classification rely on machine learning methods. However, there is growing interest in going beyond black box prediction models to understand discriminatory features of the time series and their associations with outcomes. One promising method is time-series shapelets (TSS), which identifies maximally discriminative subsequences of time series. For example, in environmental health applications TSS could be used to identify short-term patterns in exposure time series (shapelets) associated with adverse health outcomes. Identification of candidate shapelets in TSS is computationally intensive. The original TSS algorithm used exhaustive search. Subsequent algorithms introduced efficiencies by trimming/aggregating the set of candidates or training candidates from initialized values, but these approaches have limitations. In this paper, we introduce Wavelet-TSS (W-TSS) a novel intelligent method for identifying candidate shapelets in TSS using wavelet transformation discovery. We tested W-TSS on two datasets: (1) a synthetic example used in previous TSS studies and (2) a panel study relating exposures from residential air pollution sensors to symptoms in participants with asthma. Compared to previous TSS algorithms, W-TSS was more computationally efficient, more accurate, and was able to discover more discriminative shapelets. W-TSS does not require pre-specification of shapelet length.","doi":"10.3390/s21175801","bibtex":"@Article{s21175801,\nAUTHOR = {Li, Kenan and Deng, Huiyu and Morrison, John and Habre, Rima and Franklin, Meredith and Chiang, Yao-Yi and Sward, Katherine and Gilliland, Frank D. and Ambite, José Luis and Eckel, Sandrah P.},\nTITLE = {W-TSS: A Wavelet-Based Algorithm for Discovering Time Series Shapelets},\nJOURNAL = {Sensors},\nVOLUME = {21},\nYEAR = {2021},\nNUMBER = {17},\nARTICLE-NUMBER = {5801},\nURL = {https://www.mdpi.com/1424-8220/21/17/5801},\nPubMedID = {34502692},\nISSN = {1424-8220},\nABSTRACT = {Many approaches to time series classification rely on machine learning methods. However, there is growing interest in going beyond black box prediction models to understand discriminatory features of the time series and their associations with outcomes. One promising method is time-series shapelets (TSS), which identifies maximally discriminative subsequences of time series. For example, in environmental health applications TSS could be used to identify short-term patterns in exposure time series (shapelets) associated with adverse health outcomes. Identification of candidate shapelets in TSS is computationally intensive. The original TSS algorithm used exhaustive search. Subsequent algorithms introduced efficiencies by trimming/aggregating the set of candidates or training candidates from initialized values, but these approaches have limitations. In this paper, we introduce Wavelet-TSS (W-TSS) a novel intelligent method for identifying candidate shapelets in TSS using wavelet transformation discovery. We tested W-TSS on two datasets: (1) a synthetic example used in previous TSS studies and (2) a panel study relating exposures from residential air pollution sensors to symptoms in participants with asthma. Compared to previous TSS algorithms, W-TSS was more computationally efficient, more accurate, and was able to discover more discriminative shapelets. W-TSS does not require pre-specification of shapelet length.},\nDOI = {10.3390/s21175801}\n}\n\n\n\n","author_short":["Li, K.","Deng, H.","Morrison, J.","Habre, R.","Franklin, M.","Chiang, Y.","Sward, K.","Gilliland, F. D.","Ambite, J. L.","Eckel, S. P."],"key":"s21175801","id":"s21175801","bibbaseid":"li-deng-morrison-habre-franklin-chiang-sward-gilliland-etal-wtssawaveletbasedalgorithmfordiscoveringtimeseriesshapelets-2021","role":"author","urls":{"Paper":"https://www.mdpi.com/1424-8220/21/17/5801"},"metadata":{"authorlinks":{}},"downloads":1},"bibtype":"article","biburl":"http://knowledge-computing.github.io/publications.bib","dataSources":["8u7qceCaxL8Gt5PoF","HAFwXuLZf7sqJvp2S","3sPtWLmmdPRfH69LS","Lsm8pmGSv2KvYKbGa","M3cm7WzF5gdELQkoy"],"keywords":[],"search_terms":["tss","wavelet","based","algorithm","discovering","time","series","shapelets","li","deng","morrison","habre","franklin","chiang","sward","gilliland","ambite","eckel"],"title":"W-TSS: A Wavelet-Based Algorithm for Discovering Time Series Shapelets","year":2021,"downloads":1}