Filippo Sorbello | Università degli Studi di Palermo (original) (raw)

Uploads

Papers by Filippo Sorbello

Research paper thumbnail of Fingerprint Image Enhancement Using Directional Morphological Filter

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Trends in Artificial Intelligence

Lecture Notes in Computer Science, 1991

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time image processing on an embedded simd architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Hourly Forecasting of SO2 Pollutant Concentration Using an Elman Neural Network

Lecture Notes in Computer Science, 2006

In this paper the first results produced by an Elman neural network for hourly SO2 ground concent... more In this paper the first results produced by an Elman neural network for hourly SO2 ground concentration forecasting are presented. Time series has been recorded between 1998 and 2001 and are referred to a monitoring station of SO2in the industrial site of Priolo, Syracuse, Italy. Data has been kindly provided by CIPA (Consorzio Industriale per la Protezione dell’Ambiente, Siracusa, Italia).

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Monreale: a new genetic algorithm for the solution of the channel routing problem

Bookmarks Related papers MentionsView impact

Research paper thumbnail of CliffoSor: A Parallel Embedded Architecture for Geometric Algebra and Computer Graphics

Geometric object representation and their transformations are the two key aspects in computer gra... more Geometric object representation and their transformations are the two key aspects in computer graphics applications. Traditionally, compute-intensive matrix calculations are involved to model and render 3D scenery. Geometric algebra (a.k.a. Clifford algebra) is gaining growing attention for its natural way to model geometric facts coupled with its being a powerful analytical tool for symbolic calculations. In this paper, the architecture of CliffoSor (Clifford Processor) is introduced. ClifforSor is an embedded parallel coprocessing core that offers direct hardware support to Clifford algebra operators. A prototype implementation on an FPGA board is detailed. Initial test results show more than 4× speedup for Clifford products against the analogous operations in GAIGEN, a standard geometric algebra library generator for general purpose processors.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A genetic algorithm for the routing of VLSI circuits

Page 1. A GENETIC ALGORITHM FOR THE ROUTING OF VLSI CIRCUITS M. Geraci, P. Orlando, F. Sorbello*,... more Page 1. A GENETIC ALGORITHM FOR THE ROUTING OF VLSI CIRCUITS M. Geraci, P. Orlando, F. Sorbello*, G. Vassallo ... This problem was solved by Weaver with the same routing area but with the help of the user, we find the solution automatically and use fewer vias. ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Handwritten Character Recognition Using a MLP

CRC Press eBooks, Dec 17, 2020

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Application of eanets to feature recognition of articulation manner in knowledge-based automatic speech recognition

Lecture Notes in Computer Science, 2006

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time implementation of full-search vector quantization on a low memory SIMD architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time vector quantization-based image compression on the SIMPil low memory SIMD architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the 2nd Congress of the Italian Association for Artificial Intelligence on Trends in Artificial Intelligence

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the XIIth International Conference on AI*IA 2011: Artificial Intelligence Around Man and Beyond - Volume 6934

Bookmarks Related papers MentionsView impact

Research paper thumbnail of An Embedded Real-Time Automatic Lane-Keeping System

Springer eBooks, Sep 11, 2007

Advanced Driver Assistance Systems (ADAS) are safety systems capable of identifying an unavoidabl... more Advanced Driver Assistance Systems (ADAS) are safety systems capable of identifying an unavoidable dangerous scenario and reacting coherently. An automatic lane-keeping system is designed to prevent dangerous events when the driver left inadvertently his/her own lane. In this paper a real-time automatic lane-keeping system is proposed. The main features of the system are the lane markers location process as well as the generation of the vehicle’s steering angle. The system has been prototyped using the Celoxica RC203 board, equipped with a Xilinx Virtex II FPGA, for real-time processing of real motorway scenes coming from a CCD camera on a moving vehicle. The required processing time is 25,521 ms per frame, so that the system could process 39 frames/sec. Vehicle’s steering angle is computed with good approximation.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A Mlp-Based Digit And Uppercase Characters Recognition System

Perspectives in neural computing, 1997

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the 12th international conference on Artificial intelligence around man and beyond

Bookmarks Related papers MentionsView impact

Research paper thumbnail of An Heuristic Approach for the Training Dataset Selection in Fingerprint Classification Tasks

Springer eBooks, 2015

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Fast Convergence of Neural Networks by Application of a New Min-Max Algorithm

Abstract The paper presents a new application of the min-max method, an original algorithm previo... more Abstract The paper presents a new application of the min-max method, an original algorithm previously successfully applied in other areas and based on a combination of the quasi-Newton and steepest descent methods in order to find the weights minimising the error function of a feed forward neural networks. Preliminary results, obtained by applying the proposed method to a simple 2-2-1 architecture on small Boolean learning problems, are very promising.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A simple algorithm for frequency domain design

Alta Frequenza, Jun 1, 1976

An algorithm based on a modification of the Newton-Raphson and steepest descent methods and using... more An algorithm based on a modification of the Newton-Raphson and steepest descent methods and using a variable frequency procedure for frequency domain design is described. The structure of the algorithm (a flow chart of the variable frequency procedure is provided) is very simple and can thus be used in subprograms for optimal network design. The algorithm is applied to the optimization of the reflection coefficients of two and three step transformers.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Fingerprint Image Enhancement Using Directional Morphological Filter

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Trends in Artificial Intelligence

Lecture Notes in Computer Science, 1991

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time image processing on an embedded simd architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Hourly Forecasting of SO2 Pollutant Concentration Using an Elman Neural Network

Lecture Notes in Computer Science, 2006

In this paper the first results produced by an Elman neural network for hourly SO2 ground concent... more In this paper the first results produced by an Elman neural network for hourly SO2 ground concentration forecasting are presented. Time series has been recorded between 1998 and 2001 and are referred to a monitoring station of SO2in the industrial site of Priolo, Syracuse, Italy. Data has been kindly provided by CIPA (Consorzio Industriale per la Protezione dell’Ambiente, Siracusa, Italia).

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Monreale: a new genetic algorithm for the solution of the channel routing problem

Bookmarks Related papers MentionsView impact

Research paper thumbnail of CliffoSor: A Parallel Embedded Architecture for Geometric Algebra and Computer Graphics

Geometric object representation and their transformations are the two key aspects in computer gra... more Geometric object representation and their transformations are the two key aspects in computer graphics applications. Traditionally, compute-intensive matrix calculations are involved to model and render 3D scenery. Geometric algebra (a.k.a. Clifford algebra) is gaining growing attention for its natural way to model geometric facts coupled with its being a powerful analytical tool for symbolic calculations. In this paper, the architecture of CliffoSor (Clifford Processor) is introduced. ClifforSor is an embedded parallel coprocessing core that offers direct hardware support to Clifford algebra operators. A prototype implementation on an FPGA board is detailed. Initial test results show more than 4× speedup for Clifford products against the analogous operations in GAIGEN, a standard geometric algebra library generator for general purpose processors.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A genetic algorithm for the routing of VLSI circuits

Page 1. A GENETIC ALGORITHM FOR THE ROUTING OF VLSI CIRCUITS M. Geraci, P. Orlando, F. Sorbello*,... more Page 1. A GENETIC ALGORITHM FOR THE ROUTING OF VLSI CIRCUITS M. Geraci, P. Orlando, F. Sorbello*, G. Vassallo ... This problem was solved by Weaver with the same routing area but with the help of the user, we find the solution automatically and use fewer vias. ...

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Handwritten Character Recognition Using a MLP

CRC Press eBooks, Dec 17, 2020

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Experimental studies on continuous speech recognition using neural architectures with “adaptive” hidden activation functions

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Application of eanets to feature recognition of articulation manner in knowledge-based automatic speech recognition

Lecture Notes in Computer Science, 2006

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time implementation of full-search vector quantization on a low memory SIMD architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Real-time vector quantization-based image compression on the SIMPil low memory SIMD architecture

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the 2nd Congress of the Italian Association for Artificial Intelligence on Trends in Artificial Intelligence

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the XIIth International Conference on AI*IA 2011: Artificial Intelligence Around Man and Beyond - Volume 6934

Bookmarks Related papers MentionsView impact

Research paper thumbnail of An Embedded Real-Time Automatic Lane-Keeping System

Springer eBooks, Sep 11, 2007

Advanced Driver Assistance Systems (ADAS) are safety systems capable of identifying an unavoidabl... more Advanced Driver Assistance Systems (ADAS) are safety systems capable of identifying an unavoidable dangerous scenario and reacting coherently. An automatic lane-keeping system is designed to prevent dangerous events when the driver left inadvertently his/her own lane. In this paper a real-time automatic lane-keeping system is proposed. The main features of the system are the lane markers location process as well as the generation of the vehicle’s steering angle. The system has been prototyped using the Celoxica RC203 board, equipped with a Xilinx Virtex II FPGA, for real-time processing of real motorway scenes coming from a CCD camera on a moving vehicle. The required processing time is 25,521 ms per frame, so that the system could process 39 frames/sec. Vehicle’s steering angle is computed with good approximation.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A Mlp-Based Digit And Uppercase Characters Recognition System

Perspectives in neural computing, 1997

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Proceedings of the 12th international conference on Artificial intelligence around man and beyond

Bookmarks Related papers MentionsView impact

Research paper thumbnail of An Heuristic Approach for the Training Dataset Selection in Fingerprint Classification Tasks

Springer eBooks, 2015

Bookmarks Related papers MentionsView impact

Research paper thumbnail of Fast Convergence of Neural Networks by Application of a New Min-Max Algorithm

Abstract The paper presents a new application of the min-max method, an original algorithm previo... more Abstract The paper presents a new application of the min-max method, an original algorithm previously successfully applied in other areas and based on a combination of the quasi-Newton and steepest descent methods in order to find the weights minimising the error function of a feed forward neural networks. Preliminary results, obtained by applying the proposed method to a simple 2-2-1 architecture on small Boolean learning problems, are very promising.

Bookmarks Related papers MentionsView impact

Research paper thumbnail of A simple algorithm for frequency domain design

Alta Frequenza, Jun 1, 1976

An algorithm based on a modification of the Newton-Raphson and steepest descent methods and using... more An algorithm based on a modification of the Newton-Raphson and steepest descent methods and using a variable frequency procedure for frequency domain design is described. The structure of the algorithm (a flow chart of the variable frequency procedure is provided) is very simple and can thus be used in subprograms for optimal network design. The algorithm is applied to the optimization of the reflection coefficients of two and three step transformers.

Bookmarks Related papers MentionsView impact