With the continuing growth of the World Wide Web (WWW) services over the Internet, the demands for rapid image transmission over a network link of limited bandwidth and economical image storage of a large image database are increasing rapidly. In this paper, a classified binary-tree-structured Self-Organizing Feature Map neural network is proposed to design image vector codebooks for quantizing images. Simulations show that the algorithm not only produces codebooks with lower distortion than the well-known CVQ algorithm but also can minimize the edge degradation. Because the adjacent codewords in the proposed algorithm are updated concurrently, the codewords in the obtained codebooks tend to be ordered according to their mutual similarity which means more compression can be achieved with this algorithm. It should also be noticed that the obtained codebook is particularly well suited for progressive image transmission because it always forms a binary tree in the input space.

In this paper, a new family of interconnection networks which we call the Incrementally Extensible Twisted Cube (IETQ) is proposed. The topology of this network is a novel generalization of the twisted cube. It inherits all the merits but without the limitations owned by a twisted cube. First, this proposed IETQ is incrementally extensible and can be adapted for use in any number of nodes; therefore, this network is particularly well suited for the design of a distributed communication network with an arbitrary number of nodes. Second, the vertex connectivity of IETQ is n. Measured by this vertex connectivity, we demonstrate that this network is optimally fault-tolerant . And it is almost regular, because the difference between the maximum and minimum degree of any node in an IETQ is at most one. A shortestpath routing algorithm for IETQ is proposed to generate path for any given pair of vertices in the network. Third, comparing with most of the other competitors, the diameter of this IETQ network is only half in size. This low diameter helps to reduce the internode communication delay. Moreover, IETQ also possesses the property of a pancyclic network. This attractive property would enable us to map rings of any length into the proposed network.

Noise cancelation and system identification have been studied for many years, and adaptive filters have proved to be a good means for solving such problems. Some neural networks can be treated as nonlinear adaptive filters, and are thus expected to be more powerful than traditional adaptive filters when dealing with nonlinear system problems. In this paper, two new heterogeneous recurrent neural network (HRNN) architectures will be proposed to identify some nonlinear systems and to extract a fetal electrocardiogram (ECG), which is corrupted by a much larger noise signal, Mother's ECG. The main difference between a heterogeneous recurrent neural network (HRNN) and a recurrent neural network (RNN) is that a complete neural network is used for the feedback path along with an error back-propagation (BP) neural network as the feedforward one. Different feedback neural networks can be used to provide different feedback capabilities. In this paper, a BP neural network is used as the feedback network in the architecture we proposed. And a self-organizing feature mapping (SOFM) network is used next as an alternative feedback network to form another heterogeneous recurrent neural network (HRNN). The heterogeneous recurrent neural networks (HRNN) successfully solve these two problems and prove their superiority to traditional adaptive filters and BP neural networks.