No abstract

No abstract

Consistent performance, energy efficiency, and reliable transfer of data are critical factors for real-time monitoring of a patient's data, especially in a hospital environment. In this paper, a routing protocol is proposed by considering the QoS requirements of the Body Area Network (BAN) data packets. A mechanism for handling delay-sensitive packets is provided by this protocol. Moreover, linear programming based modeling along with graphical analysis is also done. Extensive simulations using the OMNeT++ based simulator Castalia 3.2 illustrate that the proposed algorithm provides better performance than other QoS-aware routing protocols in terms of higher successful transmission rates (throughputs), lower overall network traffic, no packets dropped due to MAC buffer overflow, and fewer numbers of packet time outs in both the mobile and static patient scenarios. The scalability of the protocol is demonstrated by simulating a 24-bed real hospital environment with 49 nodes. It is shown that, even in the larger real hospital scenario requiring the transmission of delay-sensitive data packets with stringent delay requirements, QPRD outperforms comparable protocols.

No abstract

This paper deals with a discrete-time recurrent neural network (DTRNN) with a block-diagonal feedback weight matrix, called the block-diagonal recurrent neural network (BDRNN), that allows a simplified approach to online training and to address network and training stability issues. The structure of the BDRNN is exploited to modify the conventional backpropagation through time (BPTT) algorithm. to reduce its storage requirement by a numerically stable method of recomputing the network state variables. The network and training stability is addressed by exploiting the BDRNN structure to directly monitor and maintain stability during weight updates by developing a functional measure of system stability that augments the cost function being minimized. Simulation results are presented to demonstrate the performance of the BDRNN architecture, its training algorithm, and the stabilization method.