• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.1095-1098
• /
• 1993

This paper presents linear programming neural networks for job-shop scheduling. The starting times of tasks and constraints are formulated as the linear programming problem. A modified Hopfield neural network is proposed for solving job-shop scheduling.

• Investigative Magnetic Resonance Imaging
• /
• v.6 no.2
• /
• pp.137-146
• /
• 2002

Purpose : This paper introduces an improved classification approach which adopts a deterministic relaxation method and an agglomerative clustering technique for the classification of MRI using neural network. The proposed approach can solve the problems of convergency to local optima and computational burden caused by a large number of input patterns when a neural network is used for image classification. Materials and methods : Application of Hopfield neural network has been solving various optimization problems. However, major problem of mapping an image classification problem into a neural network is that network is opt to converge to local optima and its convergency toward the global solution with a standard stochastic relaxation spends much time. Therefore, to avoid local solutions and to achieve fast convergency toward a global optimization, we adopt MFA to a Hopfield network during the classification. MFA replaces the stochastic nature of simulated annealing method with a set of deterministic update rules that act on the average value of the variable. By minimizing averages, it is possible to converge to an equilibrium state considerably faster than standard simulated annealing method. Moreover, the proposed agglomerative clustering algorithm which determines the underlying clusters of the image provides initial input values of Hopfield neural network. Results : The proposed approach which uses agglomerative clustering and deterministic relaxation approach resolves the problem of local optimization and achieves fast convergency toward a global optimization when a neural network is used for MRI classification. Conclusion : In this paper, we introduce a new paradigm to classify MRI using clustering analysis and deterministic relaxation for neural network to improve the classification results.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.17-27
• /
• 2005

In this study, it proposes the neural network system for character recognition and restoration. Proposes system composed by recognition part and restoration part. In the recognition part. it proposes model of effective pattern recognition to improve ART Neural Network's performance by restricting the unnecessary top-down frame generation and transition. Also the location feature extraction algorithm which applies with Hangeul's structural feature can apply the recognition. In the restoration part, it composes model of inputted image's restoration by Hopfield neural network. We make part experiments to check system's performance, respectively. As a result of experiment, we see improve of recognition rate and possibility of restoration.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.323-328
• /
• 2006

Proteins in a cell appear as spots in a two dimensional gel image which is used in protein analysis. The spots from the same protein are in near position when comparing two gel images. Finding out the different proteins between a normal tissue and a cancer one is important information in drug development. Automatic matching of gel images is difficult because they are made from biological experimental processes. This matching problem is known to be NP-hard. Neural networks are usually used to solve such NP-hard problems. Hopfield neural network is selected since it is appropriate to solve the gel matching. An energy function with location and distance parameters is defined. The two spots which make the energy function minimum are matching spots and they came from the same protein. The energy function is designed to reflect the topology of spots by examining not only the given spot but also neighborhood spots.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.254-257
• /
• 1993

This paper presents a new method to implement Hebbian learning method on artificial neural network. In hebbian learning algorithm, complexity in terms of multiplications is high. To save the chip area, we consider a new learning circuit. By calculating similarity, or correlation between $X_i$ and $O_i$, large portion of circuits commonly used in conventional neural networks is not necessary for this new hebbian learning circuit named COR. The output signals of COR is applied to weight storage capacitors for direct control the voltages of the capacitors. The weighted sum, ${\Sigma}W_{ij}O_j$, is realized by multipliers, whose output currents are summed up in one line which goes to learning circuit or output circuit. The drain current of the multiplier can produce positive or negative synaptic weights. The pass transistor selects eight learning mode or recall mode. The layout of an learnable six-neuron fully connected Hopfield neural network is designed, and is simulated using PSPICE. The network memorizes, and retrieves the patterns correctly under the existence of minor noises.

• Proceedings of the KIEE Conference
• /
• 1995.11a
• /
• pp.569-571
• /
• 1995

This paper compares the simulated annealing and the Hopfield neural network method for an optimal routing in a multistage interconnection network(MIN). The MIN provides a multiple number of paths for ATM cells to avoid cell conflict. Exhaustive search always finds the optimal path, but with heavy computation. Although greedy method sets up a path quickly, the path found need not be optimal. The simulated annealing can find an sub optimal path in time comparable with the greedy method.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.2
• /
• pp.183-191
• /
• 1991

This paper develops a pole-zero assignment self-tuning regulator utilizing the method of a neural network in the plant parameter estimation. An approach to parameter estimation of the plant with a Hopfield neural network model is proposed, and the control characteristics of the plant are evaluated by means of a simulation for a second-order linear time invariant plant. The results obtained with those of Exponentially Weighted Recursive Least Squares(EWRLS) method are also shown.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.5
• /
• pp.59-68
• /
• 1998

This paper proposes a neural network algorithm for a channel assignment in cellular mobile communications. The proposed algorithm is developed base on hopfield neural network in order to minimize the number of channel without a confliction between cells. To compare the performance of the proposed algorithm, we used seven benchmark problems selected from kunz's and funabiki's papers. Experimental results show that the convergence times are reduced form 27% to 66% compared with Kunz's and funabiki's algorithm and vonvergence rates are improved to 100%.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.25 no.4B
• /
• pp.683-691
• /
• 2000

In this paper, we proposed the cell multiplexer using Hopfield neural network and the bandwidth predictor using the backpropagation neural network in order to make an accurate call setup decision. The cell multiplexer controls heterogeneous traffic and the bandwidth predictor estimates minimum bandwidth which satisfies traffic's QoS and maximizes throughput in network. Also, a novel connection admission controller decides on connection setup using the predicted bandwidth from bandwidth predictor and available bandwidth in networks. And then, we proposed a fuzzy traffic policer, when traffic sources violate the contract, takes an appropriate action and aim proved traffic shaper, which controls burstness which is one of key characteristics in multimedia traffic. We simulated the proposed controller. Simulation results show that the proposed controller outperforms existing controller.

• Proceedings of the KIEE Conference
• /
• 1989.11a
• /
• pp.397-400
• /
• 1989

This study is to design a method of parameter estimation for a second order linear time invarient system of self-tuning controller utilizing the neural network theory proposed by Hopfield. The result is compared with the other methods which are commonly used in controller theories.