| dc.contributor | Finke, Jorge | |
| dc.contributor | Tobón, Luis Eduardo | |
| dc.creator | Contreras Franco, David | |
| dc.date | 2024-06-14T20:45:12Z | |
| dc.date | 2024-06-14T20:45:12Z | |
| dc.date | 2022 | |
| dc.date.accessioned | 2026-10-15T17:13:11Z | |
| dc.date.available | 2026-10-15T17:13:11Z | |
| dc.identifier | https://vitela.javerianacali.edu.co/handle/11522/2623 | |
| dc.identifier.uri | https://hdl.handle.net/20.500.12032/190374 | |
| dc.description | Este trabajo compara los métodos Sparse Identification of Nonlinear Dynamics (SINDy) y Nonlinear AutoRegressive Moving Average with eXogenous input (NARMAX) en la tarea de identificación de dinámicas. La comparación consideró sistemas de ecuaciones diferenciales ordinarias (ODE), como los sistemas caóticos, funciones de transferencia no lineales con entrada aleatoria y la evolución del grado de un nodo del modelo Barabási-Albert (BA), con la extensión de la capacidad para identificar diferentes ecuaciones entre dos nodos con diferentes valores de fitness en un modelo de Bianconi-Barabási. Las métricas de comparación seleccionadas se centran en la representación del modelo, la dispersión, el error de estimación y el tiempo. La comparación indica que SINDy encuentra modelos más dispersos, mientras que NARMAX encuentra modelos que minimizan el error de estimación. | |
| dc.description | This work compares the Sparse Identification of Nonlinear Dynamics (SINDy) and Nonlinear AutoRegressive Moving Average with eXogenous input (NARMAX) methods in the task of dynamics identification. The comparison considered Ordinary Differential Equation (ODE) systems, such as chaotic systems, nonlinear transfer functions with random input, and node degree evolution of the Barabási–Albert (BA) model, with the extension of their capability to identify different equations between two nodes with different fitness values in a Bianconi-Barabási model. The comparison metrics selected focus on model representation, sparsity, estimation error, and time. The comparison shows an initial indication that SINDy finds sparser models, while NARMAX finds models with minimised estimation error. | |
| dc.format | 58 p. | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.format | application/pdf | |
| dc.language | eng | |
| dc.publisher | Pontificia Univerisdad Javeriana Cali | |
| dc.rights | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.rights | https://creativecommons.org/licenses/by-nc-nd/4.0/ | |
| dc.rights | http://purl.org/coar/access_right/c_abf2 | |
| dc.subject | Barabási–Albert Model | |
| dc.subject | System Identification | |
| dc.subject | Data-driven methods | |
| dc.subject | Sparsity | |
| dc.title | Data-driven system identification of the Barabási–Albert Model | |
| dc.type | http://purl.org/coar/resource_type/c_7a1f | |
| dc.type | Tesis/Trabajo de grado - Monografía - Pregrado | |
| dc.type | https://purl.org/redcol/resource_type/TP | |
