Maide Bucolo

An object oriented segmentation on analog CNN chip

This paper introduces a real-time object oriented segmentation algorithm, designed and implemented on a new type of mixed analog/digital chip based on the cellular neural/nonlinear network (CNN) paradigm. The fully parallel architecture of the CNN processes all the pixels of an image at the same time, so the time spent for the image segmentation is independent of the number of objects in the image. This implementation of the segmentation algorithm is shown to well satisfy the real-time requirements both as a stand-alone processing procedure, and as a module inside the MPEG-4 video coding standard. Finally, the general purpose characteristics of the CNN universal chip allow to use the algorithm introduced as an efficient pre-processing procedure for many interesting image/video stand-alone applications.

Small-world networks of fuzzy chaotic oscillators

Abstract Small-world topology has been used to build lattices of nonlinear fuzzy systems. Chaotic units, ruled by linguistic description and with specified Lyapunov exponent, have been realized and connected using linear diffusion coefficient. The dynamic features of the networks versus the number of systems connected have been investigated to underline phenomena like spatiotemporal chaos and complete regularization. The synchronization characteristics in case of sparse long-term connections and the performances comparison with regular and random network configurations are shown.

Image processing for medical diagnosis using CNN

Abstract Medical diagnosis is one of the most important area in which image processing procedures are usefully applied. Image processing is an important phase in order to improve the accuracy both for diagnosis procedure and for surgical operation. One of these fields is tumor/cancer detection by using Microarray analysis. The research studies in the Cancer Genetics Branch are mainly involved in a range of experiments including the identification of inherited mutations predisposing family members to malignant melanoma, prostate and breast cancer. In bio-medical field the real-time processing is very important, but often image processing is a quite time-consuming phase. Therefore techniques able to speed up the elaboration play an important rule. From this point of view, in this work a novel approach to image processing has been developed. The new idea is to use the Cellular Neural Networks to investigate on diagnostic images, like: Magnetic Resonance Imaging, Computed Tomography, and fluorescent cDNA microarray images.

Complex dynamics through fuzzy chains

This paper gives a new contribution to characterize a class of complex systems build as arrays of coupled fuzzy logic based chaotic oscillators and investigates their dynamical features. Different spatio-temporal dynamics have been reproduced using interconnected fuzzy chaotic cells in order to study the effects, due to the variation of some parameters and network topologies, in the collective behavior and to highlight the synchronization capability of the complex fuzzy systems under consideration. The synchronization characteristics have been focused by defining a behavioral index.

An Improved Instrument for Real-Time Measurement of Blood Flow Velocity in Microvessels

A new approach for the measurement of red blood cell velocity at the level of microcirculation has been developed and characterized. The new real-time and automated measurement system is based on the dual-slit methodology, and blood flow information is extracted from images and transduced into two analog photometric signals and then processed using a hybrid analog-digital system that performs the cross correlation of the signals in real time. The characterization of the system consists of a calibration with a known velocity target, yielding to the hyperbolic calibration curve velocity versus delay and the determination of the velocity detectable range from 0.3 to 120 mm/s. A theoretical study of the measurement uncertainty and parametric studies were carried out to test the system robustness to changes of parameters and to determine the optimal configuration that is applicable to various experimental conditions. The system was further tested in in vivo experiments in the rat cremaster preparation in different types of vessels and flow velocities to verify the consistency of the results, as compared with those from conventional measuring systems. In addition, the dynamic behavior of the system and its response to changes in the measured velocity were studied through a continuous velocity record that was obtained during an experimental procedure.

THE CNN PARADIGM: SHAPES AND COMPLEXITY

The paper stresses the universal role that Cellular Nonlinear Networks (CNNs) are assuming today. It is shown that the dynamical behavior of 3D CNN-based models allows us to approach new emerging problems, to open new research frontiers as the generation of new geometrical forms and to establish some links between art, neuroscience and dynamical systems.

A cellular nonlinear network: real-time technology for the analysis of microfluidic phenomena in blood vessels

A new approach to the observation and analysis of dynamic structural and functional parameters in the microcirculation is described. The new non-invasive optical system is based on cellular nonlinear networks (CNNs), highly integrated analogue processor arrays whose processing elements, the cells, interact directly within a finite local neighbourhood. CNNs, thanks to their parallel processing feature and spatially distributed structure, are widely used to solve high-speed image processing and recognition problems and in the description and modelling of biological dynamics through the solution of time continuous partial differential equations (PDEs). They are therefore considered extremely suitable for spatial-temporal dynamic characterization of fluidic phenomena at micrometric to nanometric scales, such as blood flow in microvessels and its interaction with the cells of the vessel wall. A CNN universal machine (CNN-UM) structure was used to implement, via simulation and hardware (ACE16k), the algorithms to determine the functional capillarity density (FCD) and red blood cell velocity (RBCV) in capillaries obtained by intravital microscopy during in vivo experiments on hamsters. The system exploits the moving particles to distinguish the functional capillaries from the stationary background. This information is used to reconstruct a map and to calculate the velocity of the moving objects.

Bio-Microfluidics Real-Time Monitoring Using CNN Technology

A new non-invasive real-time system for the monitoring and control of microfluidodynamic phenomena involving transport of particles and two phase fluids is proposed. The general purpose design of such system is suitable for in vitro and in vivo experimental setup and, therefore, for microfluidic applications in the biomedical field, such as lab-on-chip and for research studies in the field of microcirculation. The system consists of an ad hoc optical setup for image magnification providing images suitable for acquisition and processing. The main feature of the optical system is the accessibility of the information at any point of the optical path. It was designed and developed using discrete opto-mechanic components mounted on a breadboard. The optical sensing, acquisition, and processing were all performed using an integrated vision system based on cellular nonlinear networks (CNNs) analogic (analog plus logic) technology called focal plane processor (FPP, Eye-RIS, Anafocus) that was inserted in the optical path. Ad hoc algorithms were implemented for the real-time analysis and extraction of fluidodynamic parameters in micro-channels. They were firstly tested on sequences of images recorded during in vivo microcirculation experiments on hamsters and then applied on images acquired and processed in real-time during in vitro experiments on two-phase fluid flow in a continuous microfluidic device (serpentine mixer, ThinXXS).

Network self-organization through “small-worlds” topologies

Abstract “Small-worlds” lattices have been investigated in order to underline self-organizing properties versus structure features of neural networks. The Hindmarsh–Rose model of biological neuron, showing a chaotic behavior, has been chosen as fundamental unit. Introducing small amount of long-term connections in high clustered structures, the complete regularization has been reached with a decreased minimum number of connections.

Microfluidic circuits and systems

The possibilities envisioned by the characterization of microfluidic systems cover a wide range of both scientific demands and industrial requirements, from life sciences to fine chemistry, from food quality to other microbiology applications. In these fields, the development of analytical methods and technological solutions oriented to the creation of a firm and structured link between models and experimentation on microfluidic systems, opens up the way for the study and characterization of microfluidic devices and phenomena from a point of view related to system and control theory.