{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T15:04:23Z","timestamp":1777734263331,"version":"3.51.4"},"reference-count":32,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,10,31]],"date-time":"2022-10-31T00:00:00Z","timestamp":1667174400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NIH","award":["1R01HD083431-01A1"],"award-info":[{"award-number":["1R01HD083431-01A1"]}]},{"name":"NSF","award":["IIS2008202"],"award-info":[{"award-number":["IIS2008202"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Comput. Healthcare"],"published-print":{"date-parts":[[2022,10,31]]},"abstract":"<jats:p>SummerTime seeks to summarize global time-series signals and provides a fixed-length, robust representation of the variable-length time series. Many machine learning methods depend on data instances with a fixed number of features. As a result, those methods cannot be directly applied to variable-length time series data. Existing methods such as sliding windows can lose minority local information. Summarization conducted by the SummerTime method will be a fixed-length feature vector which can be used in place of the time series dataset for use with classical machine learning methods. We use Gaussian Mixture models (GMM) over small same-length disjoint windows in the time series to group local data into clusters. The time series\u2019 rate of membership for each cluster will be a feature in the summarization. By making use of variational methods, GMM converges to a more robust mixture, meaning the clusters are more resistant to noise and overfitting. Further, the model is naturally capable of converging to an appropriate cluster count. We validate our method on a challenging real-world dataset, an imbalanced physical activity dataset with a variable-length time series structure. We compare our results to state-of-the-art studies and show high-quality improvement by classifying with only the summarization.<\/jats:p>","DOI":"10.1145\/3532628","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T13:20:59Z","timestamp":1663161659000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["SummerTime: Variable-length Time Series Summarization with Application to Physical Activity Analysis"],"prefix":"10.1145","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0478-4223","authenticated-orcid":false,"given":"Kevin","family":"Amaral","sequence":"first","affiliation":[{"name":"University of Massachusetts Boston, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2840-6745","authenticated-orcid":false,"given":"Zihan","family":"Li","sequence":"additional","affiliation":[{"name":"University of Massachusetts Boston, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3383-551X","authenticated-orcid":false,"given":"Wei","family":"Ding","sequence":"additional","affiliation":[{"name":"University of Massachusetts Boston, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1297-9538","authenticated-orcid":false,"given":"Scott","family":"Crouter","sequence":"additional","affiliation":[{"name":"University of Tennessee-Knoxville, Knoxville, TN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3789-7686","authenticated-orcid":false,"given":"Ping","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Massachusetts Boston, Boston, MA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,12,7]]},"reference":[{"issue":"6","key":"e_1_3_1_2_2","doi-asserted-by":"crossref","first-page":"716","DOI":"10.1152\/japplphysiol.01189.2013","article-title":"Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: Laboratory-based calibrations are not enough","volume":"118","author":"Bastian Thomas","year":"2015","unstructured":"Thomas Bastian, Aur\u00e9lia Maire, Julien Dugas, Abbas Ataya, Cl\u00e9ment Villars, Florence Gris, Emilie Perrin, Yanis Caritu, Maeva Doron, St\u00e9phane Blanc, Pierre Jallon, and Chantal Simon. 2015. Automatic identification of physical activity types and sedentary behaviors from triaxial accelerometer: Laboratory-based calibrations are not enough. Journal of Applied Physiology 118, 6 (2015), 716\u2013722.","journal-title":"Journal of Applied Physiology"},{"issue":"2","key":"e_1_3_1_3_2","doi-asserted-by":"crossref","first-page":"476","DOI":"10.1007\/s10618-015-0425-y","article-title":"Time series representation and similarity based on local autopatterns","volume":"30","author":"Gokce Baydogan Mustafa","year":"2016","unstructured":"Mustafa Gokce Baydogan and George Runger. 2016. Time series representation and similarity based on local autopatterns. Data Mining and Knowledge Discovery 30, 2 (2016), 476\u2013509.","journal-title":"Data Mining and Knowledge Discovery"},{"key":"e_1_3_1_4_2","article-title":"Mixture models and em","author":"Bishop Christopher M.","year":"2006","unstructured":"Christopher M. Bishop. 2006. Mixture models and em. In Pattern Recognition and Machine Learning, Chapter 9. Springer, 2006.","journal-title":"Pattern Recognition and Machine Learning, Chapter 9"},{"key":"e_1_3_1_5_2","volume-title":"Pattern Recognition and Machine Learning, Chapter 5","author":"Bishop Christopher M.","year":"2006","unstructured":"Christopher M. Bishop. 2006. Neural networks. In Pattern Recognition and Machine Learning, Chapter 5. Springer, 2006."},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSRE.2018.2813138"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1152\/japplphysiol.00818.2005"},{"key":"e_1_3_1_8_2","unstructured":"Journal of Applied Physiology"},{"key":"e_1_3_1_9_2","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1145\/3097983.3098060","article-title":"Toeplitz inverse covariance-based clustering of multivariate time series data","author":"Hallac David","year":"2017","unstructured":"David Hallac, Sagar Vare, Stephen Boyd, and Jure Leskovec. 2017. Toeplitz inverse covariance-based clustering of multivariate time series data. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201917). ACM, New York, 215\u2013223.","journal-title":"Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD\u201917)"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10618-013-0322-1"},{"key":"e_1_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.04.014"},{"key":"e_1_3_1_12_2","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1109\/ACCESS.2017.2749323","article-title":"R&P: An low-cost device-free activity recognition for E-health","volume":"6","author":"Li Liyao","year":"2017","unstructured":"Liyao Li, Rui Bai, Binbin Xie, Yao Peng, Anwen Wang, Wei Wang, Bo Jiang, Jian Liang, and Xiaojiang Chen. 2017. R&P: An low-cost device-free activity recognition for E-health. IEEE Access 6 (2017), 81\u201390.","journal-title":"IEEE Access"},{"key":"e_1_3_1_13_2","unstructured":"The MathWorks Inc. Natick Massachusetts 2018 version R2018a"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2014.2300480"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2006.872273"},{"key":"e_1_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2945911"},{"key":"e_1_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1002\/cpe.5909"},{"key":"e_1_3_1_18_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22253"},{"key":"e_1_3_1_19_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22252"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3049734"},{"key":"e_1_3_1_21_2","doi-asserted-by":"publisher","DOI":"10.1002\/cae.22179"},{"key":"e_1_3_1_22_2","first-page":"1","article-title":"Sentiment analysis in Turkish based on weighted word embeddings","author":"Onan Aytu\u011f","year":"2020","unstructured":"Aytu\u011f Onan. 2020. Sentiment analysis in Turkish based on weighted word embeddings. In 2020 28th Signal Processing and Communications Applications Conference (SIU). IEEE, 1\u20134.","journal-title":"2020 28th Signal Processing and Communications Applications Conference (SIU)"},{"key":"e_1_3_1_23_2","first-page":"293","article-title":"Topic-enriched word embeddings for sarcasm identification","author":"Onan Aytu\u011f","year":"2019","unstructured":"Aytu\u011f Onan. 2019. Topic-enriched word embeddings for sarcasm identification. In Computer Science On-Line Conference 2019. Springer, Cham, 293\u2013304.","journal-title":"Computer Science On-Line Conference 2019"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.06.005"},{"key":"e_1_3_1_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2016.03.045"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1177\/0165551516638784"},{"key":"e_1_3_1_27_2","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1109\/ICDM.2014.27","article-title":"Dynamic time warping averaging of time series allows faster and more accurate classification","author":"Petitjean Francois","year":"2014","unstructured":"Francois Petitjean, Germain Forestier, Geoffrey I. Webb, Ann E. Nicholson, Yanping Chen, and Eamonn Keogh. 2014. Dynamic time warping averaging of time series allows faster and more accurate classification. In 2014 IEEE International Conference on Data Mining (ICDM). IEEE (2014), 470\u2013479.","journal-title":"2014 IEEE International Conference on Data Mining (ICDM)"},{"key":"e_1_3_1_28_2","doi-asserted-by":"crossref","DOI":"10.1152\/japplphysiol.00465.2009","article-title":"An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer","author":"Staudenmayer John","year":"2009","unstructured":"John Staudenmayer, David Pober, Scott Crouter, David Bassett, and Patty Freedson. 2009. An artificial neural network to estimate physical activity energy expenditure and identify physical activity type from an accelerometer. Journal of Applied Physiology (2009).","journal-title":"Journal of Applied Physiology"},{"key":"e_1_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.06.023"},{"issue":"9","key":"e_1_3_1_30_2","doi-asserted-by":"crossref","first-page":"1801","DOI":"10.1249\/MSS.0b013e318258ac11","article-title":"Artificial neural networks to predict activity type and energy expenditure in youth","volume":"44","author":"Trost Stewart G.","year":"2012","unstructured":"Stewart G. Trost, Weng-Keen Wong, Karen A. Pfeiffer, and Yonglei Zheng. 2012. Artificial neural networks to predict activity type and energy expenditure in youth. Medicine and Science in Sports and Exercise 44, 9 (2012), 1801.","journal-title":"Medicine and Science in Sports and Exercise"},{"key":"e_1_3_1_31_2","first-page":"947","article-title":"Time series shapelets: A new primitive for data mining","author":"Ye Lexiang","year":"2009","unstructured":"Lexiang Ye and Eamonn Keogh. 2009. Time series shapelets: A new primitive for data mining. In 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 947\u2013956.","journal-title":"15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"e_1_3_1_32_2","first-page":"1","article-title":"Motionword: An activity recognition algorithm based on intelligent terminal and cloud","author":"Yao Zhenjie","year":"2017","unstructured":"Zhenjie Yao, Zhipeng Zhang, Junyan Wang, and Li-Qun Xu. 2017. Motionword: An activity recognition algorithm based on intelligent terminal and cloud. In 2017 20th International Conference on Information Fusion (Fusion). IEEE, 1\u20135.","journal-title":"2017 20th International Conference on Information Fusion (Fusion)"},{"key":"e_1_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.smhl.2017.12.003"}],"container-title":["ACM Transactions on Computing for Healthcare"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532628","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3532628","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3532628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T17:51:04Z","timestamp":1750182664000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3532628"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,31]]},"references-count":32,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,10,31]]}},"alternative-id":["10.1145\/3532628"],"URL":"https:\/\/doi.org\/10.1145\/3532628","relation":{},"ISSN":["2691-1957","2637-8051"],"issn-type":[{"value":"2691-1957","type":"print"},{"value":"2637-8051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,10,31]]},"assertion":[{"value":"2021-03-23","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-17","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-07","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}