Extending Identifiability Results from Continuous to Discrete-Space Systems
Fuente:
arXiv
Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911936201883648 |
|---|---|
| author | Sarathchandra, Anuththara Aghaeeyan, Azadeh Ramazi, Pouria |
| author_facet | Sarathchandra, Anuththara Aghaeeyan, Azadeh Ramazi, Pouria |
| contents | Researchers develop models to explain the unknowns.
These models typically involve parameters that capture tangible quantities, the estimation of which is desired.
Parameter identifiability investigates the recoverability of the unknown parameters given the error-free outputs, inputs, and the developed equations of the model.
Different notions of and methods to test identifiability exist for dynamical systems defined in the continuous space.
Yet little attention was paid to the identifiability of discrete space systems, where variables and parameters are defined in a discrete space.
We develop the identifiability framework for discrete space systems and highlight that this is not an immediate extension of the continuous space framework.
Unlike the continuous case, local identifiability concepts are sensitive to how a ``neighborhood'' is defined.
Moreover, results on algebraic identifiability that proved useful in the continuous space are less so in their discrete form as the notion of differentiability disappears. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_05736 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Extending Identifiability Results from Continuous to Discrete-Space Systems Sarathchandra, Anuththara Aghaeeyan, Azadeh Ramazi, Pouria Optimization and Control Researchers develop models to explain the unknowns. These models typically involve parameters that capture tangible quantities, the estimation of which is desired. Parameter identifiability investigates the recoverability of the unknown parameters given the error-free outputs, inputs, and the developed equations of the model. Different notions of and methods to test identifiability exist for dynamical systems defined in the continuous space. Yet little attention was paid to the identifiability of discrete space systems, where variables and parameters are defined in a discrete space. We develop the identifiability framework for discrete space systems and highlight that this is not an immediate extension of the continuous space framework. Unlike the continuous case, local identifiability concepts are sensitive to how a ``neighborhood'' is defined. Moreover, results on algebraic identifiability that proved useful in the continuous space are less so in their discrete form as the notion of differentiability disappears. |
| title | Extending Identifiability Results from Continuous to Discrete-Space Systems |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2403.05736 |