• Journal of KIISE:Information Networking
• /
• 제29권4호
• /
• pp.386-396
• /
• 2002

This paper presents a neural network-based near-optimal routing algorithm. It employs a modified Hopfield Neural Network (MHNN) as a means to solve the shortest path problem. It uses every piece of information that is available at the peripheral neurons in addition to the highly correlated information that is available at the local neuron. Consequently, every neuron converges speedily and optimally to a stable state. The convergence is faster than what is usually found in algorithms that employ conventional Hopfield neural networks. Computer simulations support the indicated claims. The results are relatively independent of network topology for almost all source-destination pairs, which nay be useful for implementing the routing algorithms appropriate to multi -hop packet radio networks with time-varying network topology.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1991년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 22-24 Oct. 1991
• /
• pp.147-151
• /
• 1991

In this paper a time-optimal path planning scheme for the multiple robot manipulators will be proposed by using hopfield neural network. The time-optimal path planning, which can allow multiple robot system to perform the demanded tasks with a minimum execution time and collision avoidance, may be of consequence to improve the productivity. But most of the methods proposed till now suffers from a significant computational burden and thus limits the on-line application. One way to avoid such a difficulty is to rearrange the problem as MTSP(Multiple Travelling Salesmen Problem) and then apply the Hopfield network technique, which can allow the parallel computation, to the minimum time problem. This paper proposes an approach for solving the time-optimal path planning of the multiple robots by using Hopfield neural network. The effectiveness of the proposed method is demonstrated by computer simulation.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• 제41권1호
• /
• pp.1-8
• /
• 1992

Hopfield neural network has been applied to the problem of economic load dispatch(ELD) of electric power. The optimum values of neuron potentials are represented in terms of large numbers. The differential synchronous transition mode is used in this simulation. Through case studies, we have shown the possibility of the application of neural network to ELD. In case of including the transmission losses, the proposed method has an advantage that the problem can be solved simply with one neural network, without calculating incremental fuel costs and incremental losses required by traditional method.

• Journal of Institute of Control, Robotics and Systems
• /
• 제8권2호
• /
• pp.120-125
• /
• 2002

An optimization approach is used to partition the field of view. A cost function is defined to represent the constraints on the solution, which is then mapped onto a two-dimensional Hopfield neural network for minimization. Each neuron in the network represents a possible match between a field of view and one or multiple objects. Partition is achieved by initializing each neuron that represents a possible match and then allowing the network to settle down into a stable state. The network uses the initial inputs and the compatibility measures between a field of view and one or multiple objects to find a stable state.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 1990년도 하계학술대회 논문집
• /
• pp.485-491
• /
• 1990

We propose a minimum-time path planning soheme for the robot manipulator using Hopfield neural network. The minimum-time path planning, which can allow the robot system to perform the demanded tasks with a minimum execution time, may be of consequence to improve the productivity. But most of the methods proposed till now suffers from a significant computational burden and thus limits the on-line application. One way to avoid such a difficulty is to apply the neural network technique, which can allow the parallel computation, to the minimum-time problem. This paper propose an approach for solving the minimum-time path planning by using Hopfield neural network. The effectiveness of the proposed method is demonstrarted using the PUMA 560 manipulator.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제28권6A호
• /
• pp.379-385
• /
• 2003

In this paper, we propose a time constant control method for sieving local minimum problem of the multiuser detector using Hopfield neural network for synchronous multi-rate code division multiple access(CDMA) system in selective fading environments and its performance is compared with that of the parallel interference cancellation(PIC). We also assume that short scrambling codes of 256 chip length are used an uplink, suggest a simple correlation estimation algorithm and circuit complexity reduction method by using cyclostationarity property of short scrambling code.It is verified that multiuser detector using Hopfield neural network more efficiently cancels multiple access interference(MAI) and obtain better bit error rate and near-far resistant than conventional detector.

• Journal of the Korean Institute of Telematics and Electronics
• /
• 제26권10호
• /
• pp.1591-1597
• /
• 1989

Through the matematical alaysis of EX-NOR logic relation between the input vector and the memory matrix, we propose a new method for optical implementation of the bipolar Hopfield neural network model based on the optical vector-matrix multiplier.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제27권3B호
• /
• pp.188-195
• /
• 2002

In this paper, we consider efficient multiuser receiver structures using Hopfield neural network algorithm focused to construct a synchronous multi-rate code division multiple access (CDMA) system. Although the optimum receiver for multiuser detection can be realized attaining the best BER performance, it is too complex for practical implementation. Therefore, we propose near-optimal receivers of relatively low computationally complex multiuser detection structures for realizing multi-rate CDMA system and their performances are compared with conventional matched filter and other prominent multi-rate multiuser detectors, Computer simulations show that the Hopfield neural network based multiuser receiver achieves substantially better BER performance in Rayleigh fading environments.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• 제49권11호
• /
• pp.617-624
• /
• 2000

The negative weight can be ofter seen in Hopfield neural network, which is difficult to implement negative conductance in circuits. Usually, the inverted output of amplifier is used to avoid negative resistors for expressing the negative weights in hardware implementation. However, there is some difference between using negative resistor and the inverted output of amplifier for representing the negative weight. This difference is discussed in this paper.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• 제40권2호
• /
• pp.234-237
• /
• 1991

A new neural network model, based on the Hopfield crossbar associative network, is presented and shown to be an effective tool for the NP-Complete problems. This model is applied to a class of layer assignment problems for VLSI routing. The results indicate that this modified Hopfield model, improves stability and accuracy.