• The KIPS Transactions:PartB
• /
• v.13B no.6 s.109
• /
• pp.615-624
• /
• 2006

The objective of this paper is to implement parallel multi-layer ANN(Artificial Neural Network) simulator based on the mobile agent system which is executed in parallel in the virtual parallel distributed computing environment. The Multi-Layer Neural Network is classified by training session, training data layer, node, md weight in the parallelization-level. In this study, We have developed and evaluated the simulator with which it is feasible to parallel the ANN in the training session and training data parallelization because these have relatively few network traffic. In this results, we have verified that the performance of parallelization is high about 3.3 times in the training session and training data. The great significance of this paper is that the performance of ANN's execution on virtual parallel computer is similar to that of ANN's execution on existing super-computer. Therefore, we think that the virtual parallel computer can be considerably helpful in developing the neural network because it decreases the training time which needs extra-time.

• Proceedings of the Korean Society for Agricultural Machinery Conference
• /
• 1996.06c
• /
• pp.1073-1080
• /
• 1996

The impact of the input and output probability distributions on the performance of neural networks to forecast two year peak stream flow (cubic meters per second) is examined for two major river basins of the US. The neural network input consisted of drainage area(square kilometers ) and elevation (meters). When data are normally distributed , the neural networks predict much better than when the data are non-normal and have larger tails in their distributions.

• Journal of applied mathematics & informatics
• /
• v.29 no.1_2
• /
• pp.103-117
• /
• 2011

By using an important lemma, some analysis techniques and Lyapunov functional method, we establish the sufficient conditions of the existence of equilibrium solution of a class of BAM neural network with impulses and distributed delays. Finally, applications and an example are given to illustrate the effectiveness of the main results.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.23 no.11 s.170
• /
• pp.1929-1939
• /
• 1999

This paper presents a neural network approach, which was named PRONET, to 3D object recognition and pose calculation. 3D objects are represented using a set of centroidal profile patterns that describe the boundary of the 2D views taken from evenly distributed view points. PRONET consists of the training stage and the execution stage. In the training stage, a three-layer feed-forward neural network is trained with the centroidal profile patterns using an error back-propagation method. In the execution stage, by matching a centroidal profile pattern of the given image with the best fitting centroidal profile pattern using the neural network, the identity and approximate orientation of the real object, such as a workpiece in arbitrary pose, are obtained. In the matching procedure, line-to-line correspondence between image features and 3D CAD features are also obtained. An iterative model posing method then calculates the more exact pose of the object based on initial orientation and correspondence.

• Tribology and Lubricants
• /
• v.30 no.6
• /
• pp.356-363
• /
• 2014

Marine diesel engines operate in environments in which damage easily occurs from corrosion. Recently, damage to cylinder liners has increased from corrosion wear caused by increased engine power. This damage can cause serious problems in the economy. Thus, many researchers have treated and studied damaged cylinder liners. However, a method is necessary for real-time monitoring of damage to cylinder liners during operation of the engine, before serious damage can occur. This study carries out reciprocating friction and wear tests on a cast iron specimen under various corrosion atmospheres and verifies the variations of friction coefficient and friction surface. Additionally, the friction coefficient and friction status are predicted by using a neural network that learns the vibration and frequency spectrum data from an acceleration sensor. According to our conclusions, amplitude is distributed highly at high frequencies, and values of standard deviation and kurtosis are high when damage to the friction surface is serious. The accuracy rate of the friction coefficient predicted by the neural network is over 80% of the real measured value without NaCl, and application of the neural network is very effective for diagnosing the friction condition and damage to the cylinder liner.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.993-996
• /
• 1993

This paper addresses the structure and its associated learning algorithms of a feedforward multi-layered connectionist network, which has distributed learning abilities, for realizing the basic elements and functions of a traditional fuzzy logic controller. The proposed neural-network-based fuzzy logic control system (NN-FLCS) can be contrasted with the traditional fuzzy logic control system in their network structure and learning ability. An on-line supervised structure/parameter learning algorithm dynamic learning algorithm can find proper fuzzy logic rules, membership functions, and the size of output fuzzy partitions simultaneously. Next, a Reinforcement Neural-Network-Based Fuzzy Logic Control System (RNN-FLCS) is proposed which consists of two closely integrated Neural-Network-Based Fuzzy Logic Controllers (NN-FLCS) for solving various reinforcement learning problems in fuzzy logic systems. One NN-FLC functions as a fuzzy predictor and the other as a fuzzy controller. As ociated with the proposed RNN-FLCS is the reinforcement structure/parameter learning algorithm which dynamically determines the proper network size, connections, and parameters of the RNN-FLCS through an external reinforcement signal. Furthermore, learning can proceed even in the period without any external reinforcement feedback.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.56-66
• /
• 2023

The goal of deep learning is to extract complex features from multidimensional data use the features to create models that connect input and output. Deep learning is a process of learning nonlinear features and functions from complex data, and the user data that is employed to train deep learning models has become the focus of privacy concerns. Companies that collect user's sensitive personal information, such as users' images and voices, own this data for indefinite period of times. Users cannot delete their personal information, and they cannot limit the purposes for which the data is used. The study has designed a deep learning method that employs privacy protection technology that uses distributed collaborative learning so that multiple participants can use neural network models collaboratively without sharing the input datasets. To prevent direct leaks of personal information, participants are not shown the training datasets during the model training process, unlike traditional deep learning so that the personal information in the data can be protected. The study used a method that can selectively share subsets via an optimization algorithm that is based on modified distributed stochastic gradient descent, and the result showed that it was possible to learn with improved learning accuracy while protecting personal information.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.243-248
• /
• 1996

In this paper, a general neural-network-based connectionist model, called Fuzzy Neural Network(FNN), is proposed for the realization of a fuzzy logic control system. The proposed FNN is a feedforward multi-layered network which integrates the basic elements and functions of a traditional fuzzy logic controller into a connectionist structure which has distributed learning abilities. Such FNN can be constructed from training examples by learning rule, and the connectionist structure can be trained to develop fuzzy logic rules and find optimal input/output membership functions. Computer simulation examples will be presented to illustrate the performance and applicability of the proposed FNN, and their associated learning algorithms.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.354-358
• /
• 2001

This paper presents a fuzzy neural network model which solves the underutilization problem. This fuzzy neural network has both stability and flexibility because it uses the control structure similar to AHT(Adaptive Resonance Theory)-l neural network. And this fuzzy nenral network does not need to initialize weights and is less sensitive to noise than ART-l neural network is. The learning rule of this fuzzy neural network is the modified and fuzzified version of Kohonen learning rule and is based on the fuzzification of leaky competitive leaming and the fuzzification of conditional probability. The similarity measure of vigilance test, which is performed after selecting a winner among output neurons, is the relative distance. This relative distance considers Euclidean distance and the relative location between a datum and the prototypes of clusters. To compare the performance of the proposed fuzzy neural network with that of Kohonen Self-Organizing Feature Map the IRIS data and Gaussian-distributed data are used.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.267-270
• /
• 1997

As an approach to develope a control system with robustness in changing control environment conditions, this paper will propose a robot manipulator control system using multilayer neural network and immune algorithm. The proposed immune algorithm which has the characteristics of immune system such as distributed and anomaly detection, probabilistic detection, learning and memory, consists of the innate immune algorithm and the adaptive immune algorithm. We will demonstrate the effectiveness of the proposed control system with simulations of a 2-link robot manipulator.