DTL4STL is a tool for Temporal Logic Inference.
Given a set of signals, which contains both positive and negative examples, it induces a Decision Tree that is mapped to an STL formula. The tree and the corresponding formula can be used for data classification or other purposes.
Questions and bug reports can be sent to < gbombara AT bu DOT edu >
Version 2.9 – download
NOTE – a refactored and extended version of this tool is underdeveloped. Please, check back soon.
To install the package, just run DTL4STL_Init.m script first.
Information about the dataset format is contained in CaseStudies/Dataset_Info.txt
Execution scripts for the Case Studies are contained in the Scripts/ folder.
This software has been developed and tested with MATLAB R2015b on Windows 10.
However, it SHOULD work on any recent version of MATLAB/OS.
This software requires the MATLAB optimization toolbox.
Other third-party libraries are included in the ThirdParty/ directory.
Acknowledge this work
To cite this work please use:
Giuseppe Bombara, Cristian Vasile, Francisco Penedo, Hirotoshi Yasuoka,
Calin Belta, A Decision Tree Approach to Data Classification using
Signal Temporal Logic, Hybrid Systems: Computation and Control (HSCC),
Vienna, Austria, 2016