C. Grava

Vision based algorithm for path planning of a mobile robot by using cellular neural networks

The paper presents a new vision based algorithm for mobile robots path planning in an environment with obstacles. Cellular neural networks (CNNs) processing techniques are used here for real time motion planning to reach a fixed target. The CNN methods have been considered a solution for image processing in autonomous mobile robots guidance. The choice of CNNs for the visual processing is based on the possibility of their hardware implementation in large networks on a single VLSI chip (cellular neural networks -universal machine, CNN-UM (Roska and Chua, 1993 and Kim et al., 2002))

Medical image enhancement by using cellular neural networks

The paper presents a medical image enhancement method taking the noise reduction and the contrast enhancement into consideration, as well as the possibility of implementation on an existing cellular neural network universal chip (CNN-UC), in a single step, by using only linear templates of 3times3 dimensions. Due to complete parallel processing, computing-time reduction is achieved

Applications of the Iterated Conditional Modes Algorithm for Motion Estimation in Medical Image Sequences

This paper presents a deterministic algorithm for motion estimation in medical image sequences. We are describing the iterated conditional modes (ICM) algorithm adapted to solve the motion estimation problem in medical image sequences. The proposed algorithm ensures a trade-off between precision and computational time that is a good efficiency when compared to the stochastic algorithms. The results are compared in terms of precision and of computational time with those of other basic algorithms such as the basic block-matching algorithm or the Horn & Schunck algorithm. The results are illustrated on CT (computer tomography) and MRI (magnetically resonance imaging) medical image sequences.

CNN Processing Techniques for Multi-robot Coordination

The paper presents some vision-based algorithms for multi-robot coordination. Cellular Neural Networks (CNNs) processing techniques are used here for real time motion planning of the robots. The CNN methods are considered an advantageous solution for image processing in autonomous mobile robots guidance.

A CNN Implementation of the Horn & Schunck Motion Estimation Method

In this paper the parallel implementation of the Horn and Schunck motion estimation method in image sequences is presented, by using cellular neural networks (CNN). One of the drawbacks of the classical motion estimation algorithms is the computational time. The goal of the CNN implementation of the Horn & Schunck method is to increase the efficiency of the well-known classical implementation of this method, which is one of the most used algorithms among the motion estimation techniques. The aim is to obtain a smaller computation time and to include such an algorithm in motion compensation algorithms implemented using CNN, in order to obtain homogeneous algorithms for real-time applications in artificial vision or medical imaging

ReX: Representative extrapolating relational databases

Abstract Generating synthetic data is useful in multiple application areas (e.g., database testing, software testing). Nevertheless, existing synthetic data generators are either limited to generating data that only respect the database schema constraints, or they are not accurate in terms of representativeness, unless a complex set of inputs are given from the user (such as the data characteristics of the desired generated data). In this paper, we present an extension of a prior representative extrapolation technique, namely ReX [20], limited to natural scaling rates. The objective is to produce in an automated and efficient way a representative extrapolated database, given an original database O and a rational scaling rate, s ∈ Q . In the extended version, the ReX system can handle rational scaling rates by combining existing efficient sampling and extrapolation techniques. Furthermore, we propose a novel sampling technique, RVFDS for handling positive rational values for the desired size of the generated database. We evaluate ReX in comparison with a realistic scaling method, namely UpSizeR [43], on both real and synthetic databases. We show that our solution statistically and significantly outperforms the compared method for rational scaling rates in terms of representativeness.

Bond-graph modeling of the equivalent circuit of an on-chip spiral inductor

The aim of this paper is the bond-graph modeling and simulation of the equivalent electrical circuit of an on-chip spiral inductor with two ports and the validation of the proposed model comparing it with experimental results obtained by direct measuring. The bond-graphs allow a unitary analysis, modeling or design of any complex system containing any electric, magnetic, pneumatic and hydraulic or any other components independent of their physical nature. The experimental/simulation results are similar with the experimental results and prove that the bond-graph modeling allow to analyze and design an on-chip spiral inductor in an unitary environment taking into account even the mutual inductance and other physical phenomena. The bond-graph modeling and designing method could be applied in the case of microwave circuits, taking into account that the analysis could be made in a wide range of frequencies.

Bond-graph modeling of the equivalent RL and RC scheme of the circuits composing an electrical transmission line

This paper aims to achieve the bond-graph model and the analysis of two equivalent electrical schemes that represents parts of the equivalent electrical schemes used for analyzing an electrical cable that contains 10 cells per meter. This analysis is performed with the aim to obtain results as close to reality as possible due to the influences of electrical cables used to interconnect different electrical systems and complex systems. The future work will aim to achieve the bond-graph model of an isolated cable with four conductors containing 10 cells per meter and its analysis using the 20SIM simulation software.

Bond-graph modeling of the equivalent scheme of an electrical transmission line

The aim of this work is to achieve a bond-graph modeling and analysis of the equivalent electrical scheme of a 1 meter long cable, with four conductors, that contains 10 cells per meter and to analyze it using the 20SIM simulation software. This analysis have been made with the purpose of obtaining results as close as possible to reality due to the influences of the connecting electrical cables at the interconnection of electrical systems and complex systems. Another future work will analyze the influence of the cables in the complex systems.

PDE-based medical images denoising using Cellular Neural Networks

This paper presents the medical image denoising by using Cellular Neural Networks (CNN), based on the variational model of Chan and Esedoglu [1]. There are also comparatively analyzed the proposed method and other CNN methods that uses variational computation, our proposed method offering the best efficiency in terms of image denoising and edge preservation.