This paper presents a new image segmentation approach based on distributed agents. In this approach, the segmentation is performed trough a simulation of the hybrid architecture of P2P networks by introducing the concept of “super agent”. Each super agent corresponds to an area of the image. The segmentation process within that zone is done by ordinary agents supervised by the super agent. Segm...

Scientific computations for diffusion equations and ANNs (Artificial Neural Networks) are data intensive tasks accompanied by heavy memory access; on the other hand, their computational complexities are relatively low. Thus, this type of tasks naturally maps onto SIMD (Single Instruction Multiple Data stream) parallel processing with distributed memory. This paper proposes a high performance ac...

BACKGROUND Recent brain imaging findings suggest that there are widely distributed abnormalities affecting the brain connectivity in individuals with autism spectrum disorder (ASD). Using graph theoretical analysis, it is possible to investigate both global and local properties of brain's wiring diagram, i.e., the connectome. METHODS We acquired diffusion-weighted magnetic resonance imaging d...

Considering the characteristics and location information of nodes in sensor networks, a modified directed transfer model of sensor networks and a new distributed data aggregation model based on “area” are proposed. On the basis of these new models, a novel mixed entropy data compression algorithm based on interval wavelet transforming is proposed for sensor network, according to the characteris...

In this paper, under the assumption that the activation functions only satisfy global Lipschitz conditions, a novel LMI-based sufficient condition for global asymptotic stability of equilibrium point of a class of BAM neural networks with reaction–diffusion terms and distributed delays is obtained by using degree theory, LMI method, inequalities technique and constructing Lyapunov functionals. ...

Constructing a new Lyapunov functional and employing inequality technique, the existence, uniqueness, and global exponential stability of the periodic oscillatory solution are investigated for a class of fuzzy bidirectional associative memory BAM neural networks with distributed delays and diffusion. We obtained some sufficient conditions ensuring the existence, uniqueness, and global exponenti...

This paper explores temporal and spatial dynamics of a population of Genetic Regulatory Networks (GRN). In order to so, a GRN model is spatially distributed to solve a multi-cellular Artificial Embryogeny problem, and Evolutionary Computation is used to optimize the developmental sequences. An in-depth analysis is provided and show that such a population of GRN display strong spatial synchroniz...

The CotsBots are inexpensive and modular mobile robots built entirely from commercial off-the-shelf components. These robots provide a convenient platform on which to investigate algorithms, cooperation, and distributed sensing in large (> 50) robot networks. Each robot is small (13cm x 6.5cm base) and costs under $200. Each is equipped with on-board processing, radio communication, and a base ...