A framework for mining hybrid automata from input/output traces

Medhat, Ramy; Ramesh, Srivatsa; Bonakdarpour, Borzoo; Fischmeister, Sebastian

doi:10.1109/emsoft.2015.7318273

Cited by 31 publications

(25 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, an automata-based model mining method was proposed in [10]. While some objectives remain similar with our proposition, the mining method presented in their work does not focus on the energy consumption of embedded systems.…”

Section: Related Workmentioning

confidence: 89%

Automatic Inference of Energy Models for Peripheral Components in Embedded Systems

Cherifi

Vantroys

Boé³

et al. 2017

2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)

View full text Add to dashboard Cite

Surrounding autonomous embedded devices are in a constant expansion. The advent and the rise of Internet of Things (IoT) enable these objects to take a giant step forward, especially regarding their large scale deployment in real-world applications of the everyday life. A significant part of these objects are battery-powered and energy-dependent. Thus, energy is a critical resource which greatly complicates the development of the embedded software. By decomposing the energy consumption of a battery-powered IoT device, we can see that peripheral components are the major contributors among the overall consumption. Indeed, these components are exploited and repeatedly used by the object to interact and communicate with its surrounding environment during all the application lifetime. Acquire the expertise to handle accurately, during the development stage, the behaviour of every on-board peripheral component is a big challenge to improve the development of IoT embedded applications.To guide the developer in this task, we propose an automated inference procedure of energy models for peripheral components. An accurate automata-based model of the energy consumption can be generated, with only little efforts from the developer, based on real runtime measurements, providing precise energy figures. The proposed process is focused on a lightweight code generation step and simple analyses of the energy output traces, allowing a quick regeneration of the models in the case of a peripheral component modification. We show the potentials of the proposed procedure by real experiments on real peripherals. The obtained results are satisfactory, and we believe that our proposition is able to enhance the embedded development in an energy-constrained environment.

show abstract

Section: Related Workmentioning

confidence: 89%

Automatic Inference of Energy Models for Peripheral Components in Embedded Systems

Cherifi

Vantroys

Boé³

et al. 2017

2017 IEEE 5th International Conference on Future Internet of Things and Cloud (FiCloud)

View full text Add to dashboard Cite

show abstract

“…A seminal work in the first category is Angluin's work on learning DFAs with membership and equivalence queries [7]. This work has been subsequently extended to other types of machines, such as Mealy machines [43], symbolic / extended Mealy machines [28,11], I/O automata [2], register automata [26,1], or hybrid automata [36]. These works are not directly applicable to the problem studied in this paper, as we explicitly forbid both membership and equivalence queries.…”

Section: Related Workmentioning

confidence: 99%

“…Initially, the set of red states only contains the initial state q , and the set of blue states contains the one-letter successors of q (lines 13,14). Unmarked states will eventually become blue (lines 38,43), and then either merged with red ones (lines 27,36) or become red states themselves (line 42).…”

Section: Algorithms To Solve the Lmomio Problemmentioning

confidence: 99%

Learning Moore machines from input–output traces

Giantamidis

Tripakis

Basagiannis

2019

Int J Softw Tools Technol Transfer

View full text Add to dashboard Cite

The problem of learning automata from example traces (but no equivalence or membership queries) is fundamental in automata learning theory and practice. In this paper we study this problem for finite state machines with inputs and outputs, and in particular for Moore machines. We develop three algorithms for solving this problem: (1) the PTAP algorithm, which transforms a set of input-output traces into an incomplete Moore machine and then completes the machine with self-loops; (2) the PRPNI algorithm, which uses the well-known RPNI algorithm for automata learning to learn a product of automata encoding a Moore machine; and (3) the MooreMI algorithm, which directly learns a Moore machine using PTAP extended with state merging. We prove that MooreMI has the fundamental identification in the limit property. We also compare the algorithms experimentally in terms of the size of the learned machine and several notions of accuracy, introduced in this paper. Finally, we compare with OSTIA, an algorithm that learns a more general class of transducers, and find that OSTIA generally does not learn a Moore machine, even when fed with a characteristic sample. arXiv:1605.07805v2 [cs.FL] 2 Sep 2016research on grammatical inference [15] which has studied similar, but not exactly the same problems, such as learning deterministic finite automata (DFA), which are special cases of Moore machines with a binary output, or subsequential transducers, which are more general than Moore machines.Our contributions are the following:1. We define formally the LMoMIO problem (learning Moore machines from input-output traces). Apart from the correctness criterion of consistency (that the learned machine be consistent with the given traces) we also introduce several performance criteria including size and accuracy of the learned machine, and computational complexity of the learning algorithm. 2. We adapt the notion of characteristic sample, which is known for DFA [15], to the case of Moore machines.Intuitively, a characteristic sample of a machine M is a set of traces which contains enough information to "reconstruct" M . The characteristic sample requirement (CSR) states that, when given as input a characteristic sample, the learning algorithm must produce a machine equivalent to the one that produced the sample. CSR is important, as it ensures identification in the limit: this is a key concept in automata learning theory which ensures that the learning algorithm will eventually learn the right machine when provided with a sufficiently large set of examples [18]. 3. We develop three algorithms to solve the LMoMIO problem, and analyze them in terms of computational complexity and other properties. We show that although all three algorithms guarantee consistency, only the most advanced among them, called MooreMI, satisfies the characteristic sample requirement. We also show that MooreMI achieves identification in the limit. 4. We report on a prototype implementation of all three algorithms and experimental results. The experiments show that Moor...

show abstract

“…However, their model neither contains state variables (i.e., the model is purely input-driven, comparable to the SARX model) nor invariants, and the number of modes needs to be fixed in advance. Medhat et al describe an abstract framework, based on heuristics, to learn linear hybrid automata from input/output traces [15]. They first employ Angluin's algorithm for learning a finite-state machine [3], which serves as the discrete structure of the hybrid automaton, before they decorate the automaton with continuous dynamics.…”

Section: Introductionmentioning

confidence: 99%

Membership-Based Synthesis of Linear Hybrid Automata

Soto

Henzinger

Schilling

et al. 2019

Computer Aided Verification

View full text Add to dashboard Cite

We present two algorithmic approaches for synthesizing linear hybrid automata from experimental data. Unlike previous approaches, our algorithms work without a template and generate an automaton with nondeterministic guards and invariants, and with an arbitrary number and topology of modes. They thus construct a succinct model from the data and provide formal guarantees. In particular, (1) the generated automaton can reproduce the data up to a specified tolerance and (2) the automaton is tight, given the first guarantee. Our first approach encodes the synthesis problem as a logical formula in the theory of linear arithmetic, which can then be solved by an smt solver. This approach minimizes the number of modes in the resulting model but is only feasible for limited data sets. To address scalability, we propose a second approach that does not enforce to find a minimal model. The algorithm constructs an initial automaton and then iteratively extends the automaton based on processing new data. Therefore the algorithm is well-suited for online and synthesis-in-the-loop applications. The core of the algorithm is a membership query that checks whether, within the specified tolerance, a given data set can result from the execution of a given automaton. We solve this membership problem for linear hybrid automata by repeated reachability computations. We demonstrate the effectiveness of the algorithm on synthetic data sets and on cardiac-cell measurements.

show abstract

A framework for mining hybrid automata from input/output traces

Cited by 31 publications

References 35 publications

Automatic Inference of Energy Models for Peripheral Components in Embedded Systems

Automatic Inference of Energy Models for Peripheral Components in Embedded Systems

Learning Moore machines from input–output traces

Membership-Based Synthesis of Linear Hybrid Automata

Contact Info

Product

Resources

About