Can somebody suggest a popular method for clustering multivariate discrete-time time-series data ? My dataset is about water quality parameters taken in 6 stations by seasons in 5 years .
The work by Rob Hyndman could be helpful in this regard (you will find some videos about that on youtube as well):
Wang, X., Smith, K., & Hyndman, R. (2006). Characteristic-based clustering for time series data. Data Mining and Knowledge Discovery, 13(3), 335-364. doi:10.1007/s10618-005-0039-x
Hyndman, R. J., Wang, E., & Laptev, N. (2015). Large-scale unusual time series detection. Paper presented at the 2015 IEEE international conference on data mining workshop (ICDMW).
Kang, Y., Hyndman, R. J., & Li, F. (2020). GRATIS: GeneRAting TIme Series with diverse and controllable characteristics. Statistical Analysis and Data Mining: The ASA Data Science Journal.
Talagala, T. S., Hyndman, R. J., & Athanasopoulos, G. (2018). Meta-learning how to forecast time series. Monash Econometrics and Business Statistics Working Papers, 6, 18.
This is an expensive book - the cheapest I can find is over $150:
Time Series Clustering and Classification by Maharaj - AbeBooks
A book with a similar title is also expensive:
Time Series Clustering and Classification by Caiado - AbeBooks
Others may comment on the usefulness of the second book.
Unless you have a rich relative you'll have to use Inter-Library Loan through your institution. In my day, that was the only option if the library didn't have a copy - no Abebooks.com then...
Hong Luan Luan Dear sir, you may find this link of some value in ref to Alan F Rawle suggestion: Time Series Clustering and Classification | Elizabeth Ann Maharaj (Author); Pierpaolo D`Urso (Author); Jorge Caiado (Author) | download (b-ok.cc) Best wishes, David Booth
Resat Kasap thanks sir, the article is indeed what I need to check for my research. However, it is too math-intensive, making it exotic to laymen. Perhaps I should start learning maths again ...