Mining Shape Expressions From Positive Examples

Bartocci, Ezio; Deshmukh, Jyotirmoy; Gigler, Felix; Mateis, Cristinel; Ničković, Dejan; Qin, Xin

doi:10.1109/tcad.2020.3012240

Cited by 11 publications

(2 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ShapeIt is implemented in Python 3 with the use of external Python and Java libraries. Segmentation module implements the piecewise-linear approximation algorithm with quadratic complexity from [3] that given a time series and a mean square error (MSE) threshold computes the minimal sequence of segments such that for each segment of data, its linear regression MSE is below the threshold. The input of this module is a set of time-series and the output is a set of line segment sequences, where each line segment is characterized by slope, relative offset and duration parameters.…”

Section: Shapeit Architecture Methods and Implementationmentioning

confidence: 99%

“…Given a set of time-series and a maximum error threshold, ShapeIt implements the specification mining procedure [3] consisting of three steps: (1) segmentation of time-series into an optimal piecewise-linear approximation, (2) abstraction and clustering of linear segments into a finite set of symbols, where each symbol represent a set of similar lines, and (3) learning of linear shape expressions from the sequences of symbols generated in the previous step.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mining Shape Expressions with ShapeIt

Bartocci¹,

Deshmukh²,

Mateis³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

We present ShapeIt, a tool for mining specifications of cyberphysical systems (CPS) from their real-valued behaviors. The learned specifications are in the form of linear shape expressions, a declarative formal specification language suitable to express behavioral properties over real-valued signals. A linear shape expression is a regular expression composed of parameterized lines as atomic symbols with symbolic constraints on the line parameters. We present here the architecture of our tool along with the different steps of the specification mining algorithm. We also describe the usage of the tool demonstrating its applicability on several case studies from different application domains.

show abstract

Section: Shapeit Architecture Methods and Implementationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%