The aim of this work is the analysis of an intracranial pressure (ICP) signal, measured by means of an optical fiber catheter. We want to propose an alternative method to valuate the pressure inside the skull, without any knowledge of compliance curve, that can be valuated directly only by means of invasive and dangerous methods. First, we propose a classic Fourier processing in order to filter the ICP signal by its spectral components due at cardiac and respiratory activity. Then we perform the same analysis by wavelet transform, in order to implement a multiresolution analysis. The wavelet tool can perform also a very reliable data compression. We can demonstrate the advantages in using a neuro-fuzzy network on wavelet coefficients in order to obtain an optimal prediction of ICP signal. Various network structures are presented, in order to obtain several trade-off between computational time and prediction mean square error. Such analysis was performed by changing the fuzzy rule numbers, modifying the cluster size of the data. A real-time implementation was also proposed in order to allows the clinical applications.
Intracranial pressure signal processing by adaptive fuzzy network / Azzerboni, B; Carpentieri, Mario; Ipsale, M; La Foresta, F; Morabito, Fc. - 2859:(2003), pp. 179-186. (Intervento presentato al convegno XIV Workshop Italiano su Reti Neurali, WIRN 2003 tenutosi a Vietri Sul Mare, Italy nel June 4-7, 2003) [10.1007/978-3-540-45216-4_20].
Intracranial pressure signal processing by adaptive fuzzy network
CARPENTIERI, Mario;
2003-01-01
Abstract
The aim of this work is the analysis of an intracranial pressure (ICP) signal, measured by means of an optical fiber catheter. We want to propose an alternative method to valuate the pressure inside the skull, without any knowledge of compliance curve, that can be valuated directly only by means of invasive and dangerous methods. First, we propose a classic Fourier processing in order to filter the ICP signal by its spectral components due at cardiac and respiratory activity. Then we perform the same analysis by wavelet transform, in order to implement a multiresolution analysis. The wavelet tool can perform also a very reliable data compression. We can demonstrate the advantages in using a neuro-fuzzy network on wavelet coefficients in order to obtain an optimal prediction of ICP signal. Various network structures are presented, in order to obtain several trade-off between computational time and prediction mean square error. Such analysis was performed by changing the fuzzy rule numbers, modifying the cluster size of the data. A real-time implementation was also proposed in order to allows the clinical applications.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
