| Título: | Optimal Support Vector Regression Algorithms for Multifunctional Sensor Signal Reconstruction |
| Autores: |
Liu, Xin; Haerbin Institute of Technology Liu, Dan; Haerbin Institute of Technology Zhang, Yan; Haerbin Institute of Technology Wang, Qisong; Haerbin Institute of Technology Zhang, Shen; Haerbin Institute of Technology Wang, Hua; Haerbin Institute of Technology |
| Fecha: | 2014-04-01 |
| Publicador: | TELKOMNIKA: Indonesian journal of electrical engineering |
| Fuente: |
 |
| Tipo: |
info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion |
| Tema: |
Instrument Science and Technology v-SVR; PSO; hyperparameters; multifunctional sensor; signal reconstruction |
| Descripción: | The empirical risk minimization methods were often used to estimate the multifunctional sensor regression function in signal reconstruction. The small size of sample data would lead to the problem of poor generalization capability and overfitting. Support vector machine (SVM) is a novel machine learning method based on structural risk minimization, and it can improve generalization capability and restrain overfitting. In this paper, an optimal ν Support Vector Regression (ν-SVR) algorithms have been proposed for multifunctional sensor reconstruction, which combined ν-SVR with particle swarm optimization (PSO), achieving accurate estimation of both the hyperparameters and reconstruction function. The results of emulation and theory analysis indicate that the proposed algorithm is more accurate and reliable for signal reconstruction. |
| Idioma: | No aplica |