SMiLer is a SeMiLazy time series prediction system for sensors. The overall framework of SMiLer comprising of two main steps: search step and prediction step. More details about it can be found in the paper:
Jingbo Zhou, Anthony K. H. Tung; "SMiLer: A Semi-Lazy Time Series Prediction System for Sensors"; Proc. of 2015 ACM Int. Conf. on Management of Data (SIGMOD 2015)
You can see a running example in the folder "src/demo". The demo also give a brief introudction about the API and parameters.
####Dependencies The current code depends on the following external libraries:
Armadillo (http://arma.sourceforge.net/), is a high quality C++ linear algebra library.
OpenBLAS (optional, http://www.openblas.net/), is an optimized BLAS library. OpenBLAS is not mandatory, but it helps Armadillo achieve better performance. (You also can use BLAS, ATLAS and LAPACK together to replace the OpenBLAS.)
Note: The project is created by Nsight IDE.
Note: Open issues if you have any question relating to this project.