Neural State Classification for Hybrid Systems

07/26/2018
by   Dung Phan, et al.
0

We introduce the State Classification Problem (SCP) for hybrid systems, and present Neural State Classification (NSC) as an efficient solution technique. SCP generalizes the model checking problem as it entails classifying each state s of a hybrid automaton as either positive or negative, depending on whether or not s satisfies a given time-bounded reachability specification. This is an interesting problem in its own right, which NSC solves using machine-learning techniques, Deep Neural Networks in particular. State classifiers produced by NSC tend to be very efficient (run in constant time and space), but may be subject to classification errors. To quantify and mitigate such errors, our approach comprises: i) techniques for certifying, with statistical guarantees, that an NSC classifier meets given accuracy levels; ii) tuning techniques, including a novel technique based on adversarial sampling, that can virtually eliminate false negatives (positive states classified as negative), thereby making the classifier more conservative. We have applied NSC to six nonlinear hybrid system benchmarks, achieving an accuracy of 99.25 99.98 0.0015 to 0 after tuning the classifier. We believe that this level of accuracy is acceptable in many practical applications, and that these results demonstrate the promise of the NSC approach.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/09/2019

Generalized Property-Directed Reachability for Hybrid Systems

Generalized property-directed reachability (GPDR) belongs to the family ...
05/30/2018

Approximate LTL model checking

Linear Temporal Logic (LTL) model checking has been applied to many fiel...
02/23/2019

Experimental Study on CTL model checking using Machine Learning

The existing core methods, which are employed by the popular CTL model c...
12/04/2020

A novel multi-classifier information fusion based on Dempster-Shafer theory: application to vibration-based fault detection

Achieving a high prediction rate is a crucial task in fault detection. A...
09/17/2019

Fiber Nonlinearity Mitigation via the Parzen Window Classifier for Dispersion Managed and Unmanaged Links

Machine learning techniques have recently received significant attention...
02/06/2019

Equal Opportunity in Online Classification with Partial Feedback

We study an online classification problem with partial feedback in which...
02/15/2021

Model-bounded monitoring of hybrid systems

Monitoring of hybrid systems attracts both scientific and practical atte...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.