• 제어로봇시스템학회:학술대회논문집
• /
• 1999.10a
• /
• pp.214-217
• /
• 1999

In this paper, genetic algorithm (GA) is implemented to search for the optimal structures (i.e. the kind of neural networks, the number of inputs and hidden neurons) of neural networks which are used approximating a given nonlinear function. Two kinds of neural networks, i.e. the multilayer feedforward [1] and time delay neural networks (TDNN) [2] are involved in this paper. The synapse weights of each neural network in each generation are obtained by associated training algorithms. The simulation results of nonlinear function approximation are given out and some improvements in the future are outlined.

• Proceedings of the Optical Society of Korea Conference
• /
• 1989.02a
• /
• pp.103-106
• /
• 1989

A method of adaptive formation of the synthetic discriminant function(SDF) both in image plane and spatial frequency plane by using the Widrow-Hoff learning rule is proposed. The proposed method uses minimum number of interconnections between neurons so it can reduce the time for learning the neural net. Also complex valued interconnection weights are introduced for the purposes of handling the phase objects or Fourier transformed spatial frequency objects which usually have complex values for the representation of not only amplitude but also phase information. Also methods of optical implementation for the complex valued interconnection weights are discussed.

• Proceedings of the Korean Information Science Society Conference
• /
• 1998.10a
• /
• pp.691-693
• /
• 1998

A parallel processing systolic array reduces execution time of the Back-propagation ANN. But, systolic array must be designed whenever the number of neurons in the ANN differ. To use the systolic array which is aready designed ad a fixed size VLSI chip, partition of the problem size systolic array must be performed. This paper presents a design method of the fixed size systolic array for the Back-propagation algorthm using LSGP and LPGS partion method

• The Korean Journal of Physiology and Pharmacology
• /
• v.2 no.2
• /
• pp.185-192
• /
• 1998

A role of endogenous somatostatin in pancreatic exocrine secretion induced by intrapancreatic cholinergic activation was studied in the isolated rat pancreas perfused with modified Krebs-Henseleit solution. Intrapancreatic neurons were activated by electrical field stimulation (EFS: 15 V, 2 msec and 8 Hz). Pancreatic exocrine secretion, including volume flow and amylase output, and release of somatostatin from the pancreas were respectively determined. Somatostatin cells in the islet were stained with an immunoperoxidase method. EFS significantly increased pancreatic volume flow and amylase output, which were reduced by atropine by 59% and 78%, respectively. Intraarterial infusion of either pertussis toxin or a somatostatin antagonist resulted in a further increase in the EFS-evoked pancreatic secretion. EFS also further elevated exocrine secretion in the pancreas treated with cysteamine, which was completely restored by intraarterial infusion of somatostatin. EFS significantly increased not only the number of immunoreactive somatostatin cells in the islet but also the concentration of immunoreactive somatostatin in portal effluent. It is concluded from the above results that intrapancreatic cholinergic activation elevates pancreatic exocrine secretion as well as release of endogenous somatostatin. Endogenous somatostatin exerts an inhibitory influence on exocrine secretion induced by intrapancreatic cholinergic activation via the islet-acinar portal system in the isolated pancreas of the rat.

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.8
• /
• pp.551-560
• /
• 2004

In this paper, we propose a new architecture of Self-Organizing Fuzzy Polynomial Neural Networks (SOFPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology involving mechanisms of genetic optimization, especially genetic algorithms (GAs). The proposed SOFPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional SOFPNNs. The design procedure applied in the construction of each layer of a SOFPNN deals with its structural optimization involving the selection of preferred nodes (or FPNs) with specific local characteristics (such as the number of input variables, the order of the polynomial of the consequent part of fuzzy rules, and a collection of the specific subset of input variables) and addresses specific aspects of parametric optimization. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. To evaluate the performance of the genetically optimized SOFPNN, the model is experimented with using two time series data(gas furnace and chaotic time series), A comparative analysis reveals that the proposed SOFPNN exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literatures.

• Korean Journal of Veterinary Research
• /
• v.39 no.3
• /
• pp.538-544
• /
• 1999

To elucidate the involvement of interleukin-$1{\beta}$ converting enzyme (ICE) in the course of experimental autoimmune encephalomyelitis (EAE), we induced EAE by immunizing rats with an emulsion of rat spinal cord homogenate with complete Freund's adjuvant supplemented with Mycobacterium tuberculosis (H37Ra, 5mg/ml) and then examined the expression of ICE in the spinal cord of rats with EAE. In normal rat spinal cords, ICE is constitutively, but weakly, expressed in ependymal cells, neurons, and some neuroglial cells. In EAE, many inflammatory cells are positive for ICE, and the majority of ICE+ cells were identified as ED1+ macrophages. During this stage of EAE, the number of ICE+ cells in brain cells, including neurons and astrocytes, increased and these cells also had increased ICE immunoreactivity. These findings suggest that the upregulation of ICE in both brain cells and invading hematogenous cells is stimulated by a secretory product from inflammatory cells, and that this enzyme is involved in the pathogenesis of EAE via the production of IL-1 beta.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.52-58
• /
• 2005

We have developed a Group Method of Data Handling (GMDH) type algorithm for designing multi-layered neural networks. The algorithm is general enough that it will accept any number of inputs and any sized training set. Each neuron of the resulting network is a function of two of the inputs to the layer. The equation for each of the neurons is a quadratic polynomial. Several forms of the equation are tested for each neuron to make sure that only the best equation of two inputs is kept. All possible combinations of two inputs to each layer are also tested. By carefully testing each resulting neuron, we have developed an algorithm to keep only the best neurons at each level. The algorithm's goal is to create as accurate a network as possible while minimizing the size of the network. Software was developed to train and simulate networks using our algorithm. Several applications were modeled using our software, and the result was that our algorithm succeeded in developing small, accurate, multi-layer networks.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.599-602
• /
• 2003

A new technique is presented to construct predictive models of plasma etch processes. This was accomplished by combining a backpropagation neural network (BPNN) and a random generator (RC). The RG played a critical role to control neuron gradients in the hidden layer, The predictive model constructed in this way is referred to as a randomized BPNN (RG-BPNN). The proposed scheme was evaluated with a set of experimental plasma etch process data. The etch process was characterized by a 2$^3$ full factorial experiment. The etch responses modeled are 4, including aluminum (Al) etch rate, profile angle, Al selectivity, and do bias. Additional test data were prepared to evaluate model appropriateness. The performance of RC-BPNN was evaluated as a function of the number of hidden neurons and the range of gradient. for given range and hidden neurons, 100 sets of random neuron gradients were generated and among them one best set was selected for evaluation. Compared to the conventional BPNN, the proposed RC-BPNN demonstrated about 50％ improvements in all comparisons. This illustrates that the RG-BPNN of multi-valued gradients is an effective way to considerably improve the predictive ability of current BPNN of single-valued gradient.

• The Korean Journal of Physiology and Pharmacology
• /
• v.4 no.1
• /
• pp.73-79
• /
• 2000

This study investigated whether propofol, an intravenous, non-barbiturate anesthetic, could reduce brain damage following global forebrain ischemia. Transient global ischemia was induced in gerbils by occlusion of bilateral carotid arteries for 3 min. Propofol (50 mg/kg) was administered intraperitoneally 30 min before, immediately after, and at 1 h, 2 h, 6 h after occlusion. Thereafter, propofol was administered twice daily for three days. Treated animals were processed in parallel with ischemic animals receiving 10% intralipid as a vehicle or with sham-operated controls. In histologic findings, counts of viable neurons were made in the pyramidal cell layer of the hippocampal CA1 area 4 days after ischemia. The number of viable neurons in the pyramidal cell layer of CA1 area was similar in animals treated with a vehicle or a subanesthetic dose of propofol. In terminal deoxynucleotidyl transferase (TdT)-mediated dUTP nick end-labeling (TUNEL) assay, semiquantitative analysis of dark-brown neuronal cells was made in the hippocampal CA1 area. There was no significant difference in the degree of TUNEL staining in the hippocampal CA1 area between vehicle-treated and propofol-treated animals. These results show that subanesthetic dose of propofol does not reduce delayed neuronal cell death following transient global ischemia in Mongolian gerbils.

• Journal of Ocean Engineering and Technology
• /
• v.34 no.3
• /
• pp.167-179
• /
• 2020

Recently, the increasing importance of artificial intelligence (AI) technology has led to its increased use in various fields in the shipbuilding and marine industries. For example, typical scenarios for AI include production management, analyses of ships on a voyage, and motion prediction. Therefore, this study was conducted to predict a response amplitude operator (RAO) through AI technology. It used a neural network based on one of the types of AI methods. The data used in the neural network consisted of the properties of the vessel and RAO values, based on simulating the in-house code. The learning model consisted of an input layer, hidden layer, and output layer. The input layer comprised eight neurons, the hidden layer comprised the variables, and the output layer comprised 20 neurons. The RAO predicted with the neural network and an RAO created with the in-house code were compared. The accuracy was assessed and reviewed based on the root mean square error (RMSE), standard deviation (SD), random number change, correlation coefficient, and scatter plot. Finally, the optimal model was selected, and the conclusion was drawn. The ultimate goals of this study were to reduce the difficulty in the modeling work required to obtain the RAO, to reduce the difficulty in using commercial tools, and to enable an assessment of the stability of medium/small vessels in waves.