Dipartimento d'Ingegneria

Electrical Engineering - Elettrotecnica

The field studies the theoretical and experimental aspects and the development of related applications of the two complementary strands of EMF and electrical and electronic circuits in civil, industrial and information engineering. In the first field problems of electromagnetic field, electromagnetic compatibility, and magnetofluidodinamics, of modeling and diagnostics of electric and magnetic materials of interest are studied. In the second line we study circuits, both analog and digital, and the related models: linear, nonlinear and time-varying lumped and distributed signal and power, mono and multi-dimensional. The two complementary approaches are applied to the analysis, synthesis, numerical modeling and automatic design of the equipment, devices and electrical systems, engineering of plasmas, thermonuclear fusion, particle accelerators, electrothermics, electromagnetic compatibility, the quality, safety and environmental impact in electrical applications, the circuits for signal processing, neural networks and adaptive circuits, power electronics and conversion of electrical energy.

Laboratorio di Elettrotecnica

Scritto da Lunedì, 16 Febbraio 2015 18:47
Presso la sede del Diparitmento di Ingegneria di Perugia è presente il Laboratorio di Elettrotecnica le cui caratteristiche ed attività sono descritte nel seguente sito web




LIBRO

In Research ,
Scritto da Venerdì, 21 Marzo 2014 08:59

Circuiti Elettrici  Seconda edizione

Renzo Perfetti

Zanichelli, 2013


La seconda edizione di Circuiti elettrici mantiene la collaudata impostazione basata su una graduale esposizione della teoria, con particolare attenzione alle tecniche di risoluzione dei problemi, descritte in forma algoritmica e illustrate attraverso numerosi esempi svolti. Alcuni argomenti sono presentati secondo un nuovo ordine, più funzionale alle esigenze didattiche. Molti esempi sono stati aggiornati.


Sito web del libro:

http://www.zanichelli.it/ricerca/prodotti/9788808178886/renzo-perfetti/circuiti-elettrici/

ARTICOLO

In Research ,
Scritto da Venerdì, 21 Marzo 2014 08:52

Recurrent neural network for approximate nonnegative matrix factorization

Giovanni Costantini, Renzo Perfetti, Massimiliano Todisco

 

 

A recurrent neural network solving the approximate nonnegative matrix factorization (NMF) problem is presented in this paper. The proposed network is based on the Lagrangian approach, and exploits a partial dual method in order to limit the number of dual variables. Sparsity constraints on basis or activation matrices are included by adding a weighted sum of constraint functions to the least squares reconstruction error. However, the corresponding Lagrange multipliers are computed by the network dynamics itself, avoiding empirical tuning or a validation process. It is proved that local solutions of the NMF optimization problem correspond to as many stable steady-state points of the network dynamics. The validity of the proposed approach is verified through several simulation examples concerning both synthetic and real-world datasets for feature extraction and clustering applications.

To be published in Neurocomputing (2014)

ARTICOLO

In Research ,
Scritto da Giovedì, 20 Marzo 2014 09:42
Retinal Blood Vessel Segmentation using Line Operators and Support Vector Classification
     
Elisa Ricci            Renzo Perfetti

IEEE Transactions on Medical Imaging vol. 26, N. 10, 2007


Abstract. In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. A line detector, previously used in mammography, is applied to the green channel of the retinal image. It is based on the evaluation of the average grey level along lines of fixed length passing through the target pixel at different orientations. Two segmentation methods are considered. The first uses the basic line detector whose response is thresholded to obtain unsupervised pixel classification. As a further development we employ two orthogonal line detectors along with the grey level of the target pixel to construct a feature vector for supervised classification using a support vector machine (SVM). The effectiveness of both methods is demonstrated through receiver operating characteristic (ROC) analysis on two publicly available databases of color fundus images.

Pagina 1 di 2

NOTA:

Questo sito utilizza i cookies, anche di terze parti, per le statistiche e per agevolare la navigazione nelle pagine del sito. Maggiori informazioni disponibili nell’informativa sulla privacy. Per saperne di piu'

Approvo