• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.585-590
• /
• 1998

The purpose of this paper is to develop a neurofuzzy modeling & inference system which can determine principle dimensions and hull factors in an initial ship design. Neurofuzzy modeling & inference for a hull form design (NeFHull) applies the given input-output data to the fuzzy theory. NeFHull also deals the fuzzificated values with neural networks. NeFHull redefines normalized input-output data as membership functions and executes the fuzzficated information with backporpagation-neural -networks. A hybrid learning algorithms utilized in the training of neural networks and examining the usefulness of suggested method through mathematical and mechanical examples.

• Proceedings of the KIEE Conference
• /
• 2005.07d
• /
• pp.2933-2935
• /
• 2005

The IRPO(Intensive Randomized Policy Optimizer) algorithm is a recently developed tool in the area of reinforcement leaming. And it has been shown to be very successful in several application problems. To compare with a general RL method, IRPO has some difference in that policy utilizes the entire history of agent -environment interaction. The policy is derived from the history directly, not through any kind of a model of the environment. In this paper, we consider a robot-control problem utilizing a IRPO algorithm. We also developed a MATLAH-based animation program, by which the effectiveness of the training algorithms were observed.

• The Journal of Information Systems
• /
• v.3
• /
• pp.147-169
• /
• 1994

This paper present s a pattern generation scheme from financial charts. The patterns constitute knowledge which consists of patterns as the conditional part and the impact of the pattern as the conclusion part. The patterns in charts are represented in a syntactic approach. If the pattern elements and the impact of patterns are defined, the patterns are synthesized from simple to the more highly credible by evaluating each intermediate pattern from the instances. The overall process is divided into primitive discovery by Genetic Algorithms and pattern synthesis from the discovered primitives by the Syntactic Pattern-based Inductive Learning (SYNPLE) algorithm which we have developed. We have applied the scheme to a chart : the trend lines of stock price in daily base. The scheme can generate very credible patterns from training data sets.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.217-220
• /
• 2005

The RPO algorithm is a recently developed tool in the area of reinforcement Loaming, And it has been shown In be very successful in several application problems. In this paper, we consider a robot-control problem utilizing a modified RPO algorithm in which its critic network is adapted via RLS(Recursive Least Square) algorithm. We also developed a MATLAB-based animation program, by which the effectiveness of the training algorithms were observed.

• Proceedings of the Korea Society for Simulation Conference
• /
• 1994.10a
• /
• pp.12-12
• /
• 1994

Simulation output knowledge analysis is one of problem-solving and/or knowledge adquistion process by investgating the system behavior under study through simulation . This paper describes an approach to simulation outputknowldege analysis using fuzzy neural network model. A fuzzy neral network model is designed with fuzzy setsand membership functions for variables of simulation model. The relationship between input parameters and output performances of simulation model is captured as system behavior knowlege in a fuzzy neural networkmodel by training examples form simulation exepreiments. Backpropagation learning algorithms is used to encode the knowledge. The knowledge is utilized to solve problem through simulation such as system performance prodiction and goal-directed analysis. For explicit knowledge acquisition, production rules are extracted from the implicit neural network knowledge. These rules may assit in explaining the simulation results and providing knowledge base for an expert system. This approach thus enablesboth symbolic and numeric reasoning to solve problem througth simulation . We applied this approach to the design problem of broadband communication network.

• Journal of Sensor Science and Technology
• /
• v.30 no.5
• /
• pp.286-289
• /
• 2021

Image classification is one of the fundamental applications of computer vision. It enables a system to identify an object in an image. Recently, image classification applications have broadened their scope from computer applications to edge devices. The convolutional neural network (CNN) is the main class of deep learning neural networks that are widely used in computer tasks, and it delivers high accuracy. However, CNN algorithms use a large number of parameters and incur high computational costs, which hinder their implementation in edge hardware devices. To address this issue, this paper proposes a lightweight image classifier that provides good accuracy while using fewer parameters. The proposed image classifier diverts the input into three paths and utilizes different scales of receptive fields to extract more feature maps while using fewer parameters at the time of training. This results in the development of a model of small size. This model is tested on the CIFAR-10 dataset and achieves an accuracy of 90% using .26M parameters. This is better than the state-of-the-art models, and it can be implemented on edge devices.

• Nuclear Engineering and Technology
• /
• v.55 no.10
• /
• pp.3716-3724
• /
• 2023

Loose parts monitoring and detecting alarm type in real Nuclear Power Plant have challenges such as background noise, insufficient alarm data, and difficulty of distinction between alarm data that occur during start and stop. Although many signal processing methods and alarm determination algorithms have been developed, it is not easy to determine valid alarm and extract the meaning data from alarm signal including background noise. To address these issues, this paper proposes a denoising autoencoder-based majority vote classification. Training and test data are prepared by acquiring alarm data from real NPP and simulation facility for data augmentation, and noisy data is reproduced by adding Gaussian noise. Using DAEs with 3, 5, 7, and 9 layers, features are extracted for each model and classified into neural networks. Finally, the results obtained from each DAE are classified by majority voting. Also, through comparison with other methods, the accuracy and the false alarm rate are compared, and the excellence of the proposed method is confirmed.

• Geomechanics and Engineering
• /
• v.37 no.5
• /
• pp.467-474
• /
• 2024

Monitoring and managing the condition of underground utilities is crucial for ground stability. This study aims to determine whether images obtained using ground penetrating radar (GPR) accurately reflect the characteristics of buried pipelines through image analysis. The investigation focuses on pipelines made from different materials, namely concrete and steel, with concrete pipes tested under various diameters to assess detectability under differing conditions. A total of 400 images are acquired at locations with pipelines, and for comparison, an additional 100 data points are collected from areas without pipelines. The study employs GPR at frequencies of 200 MHz and 600 MHz, and image analysis is performed using machine learning-based convolutional neural network (CNN) techniques. The analysis results demonstrate high classification reliability based on the training data, especially in distinguishing between pipes of the same material but of different diameters. The findings suggest that the integration of GPR and CNN algorithms can offer satisfactory performance in exploring the ground's interior characteristics.

• Journal of Internet Computing and Services
• /
• v.17 no.2
• /
• pp.49-57
• /
• 2016

Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving prediction accuracy. Bagging is one of the most popular ensemble learning techniques. Bagging has been known to be successful in increasing the accuracy of prediction of the individual classifiers. Bagging draws bootstrap samples from the training sample, applies the classifier to each bootstrap sample, and then combines the predictions of these classifiers to get the final classification result. Bootstrap samples are simple random samples selected from the original training data, so not all bootstrap samples are equally informative, due to the randomness. In this study, we proposed a new method for improving the performance of the standard bagging ensemble by optimizing bootstrap samples. A genetic algorithm is used to optimize bootstrap samples of the ensemble for improving prediction accuracy of the ensemble model. The proposed model is applied to a bankruptcy prediction problem using a real dataset from Korean companies. The experimental results showed the effectiveness of the proposed model.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.341-348
• /
• 2020

The ability to extract useful information from an image, such as the human eye, is an interface technology essential for AI computer implementation. The building recognition technology has a lower recognition rate than other image recognition technologies due to the various building shapes, the ambient noise images according to the season, and the distortion by angle and distance. The computer vision based building recognition algorithms presented so far has limitations in discernment and expandability due to manual definition of building characteristics. This paper introduces the deep learning CNN (Convolutional Neural Network) model, and proposes new method to improve the recognition rate even by changes of building images caused by season, illumination, angle and perspective. This paper introduces the partial images that characterize the building, such as windows or wall images, and executes the training with whole building images. Experimental results show that the building recognition rate is improved by about 14% compared to the general CNN model.