• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.35C no.7
• /
• pp.101-108
• /
• 1998

In this paper, after we got to realized FDNN (fuzzy decision neural network) applied the quantization triangularity fuzzy function to DBNN(decision based neural network) of a hierarchical structure for image process, we could esign hardware of the realized FDNN. Also it is normalized the standard image and the input image as the same size. We are applied DWW algorithm which selected the closest value with finding similarity of an interval image by this distance to FDNN. So we could calulated in terms of distance to weight of pixel which composed two image and eliminated the nise of image, minimized the lost of information, obtained the optimal information. It is designed hardware of high speed weighted FDNN using COMPASS tool. Aslo, the total circuit is realized as gates of 61,000 and could show to superiority of FDNN using the simulation.

• Journal of Information Processing Systems
• /
• v.19 no.2
• /
• pp.203-210
• /
• 2023

The addition of traditional elements can enhance the uniqueness of visual communication design. This paper briefly introduced visual communication and applications of traditional elements in visual communication design and applied paper cuts, a handmade graphic element, to the logo design of Dezhou University's 50th anniversary. The convolutional neural network (CNN) algorithm and the analytic hierarchy process method were applied to evaluation analysis and compared with the support vector machine (SVM) algorithm. The results of the CNN algorithm on the test set verified its effectiveness. The evaluation results of the CNN algorithm were similar to the manual evaluation results, further proving the effectiveness and high efficiency of the CNN algorithm. The hierarchical analysis and the analysis of the assessment results of the CNN algorithm found that the two logo designs made full use of paper cuts.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.878-882
• /
• 2004

In this paper, we propose a hierarchical hybrid neural network for detecting faults of induction motor. Implementing the classifier based on the input and output data, we apply appropriate transform and classification method at each step. In the proposed method, after obtaining the current of state of motor for each period, we transform it by Principle Component Analysis(PCA) to reduce its dimension. Before the training process, we use the conditional Fuzzy C-means(FCM) for obtaining the initial parameters of neural network for more effective learning procedure. From the various simulations, we find that the proposed method shows better performance to detect and diagnosis of induction motor and compare than other methods.

• Journal of the Korean Statistical Society
• /
• v.31 no.1
• /
• pp.63-75
• /
• 2002

Most attempts at Bayesian analysis of neural networks involve hierarchical modeling. We believe that similar results can be obtained with simpler models that require less computational effort, as long as appropriate restrictions are placed on parameters in order to ensure propriety of posterior distributions. In particular, we adopt a model first introduced by Lee (1999) that utilizes an improper prior for all parameters. Straightforward Gibbs sampling is possible, with the exception of the bias parameters, which are embedded in nonlinear sigmoidal functions. In addition to the problems posed by nonlinearity, direct sampling from the posterior distributions of the bias parameters is compounded due to the duplication of hidden nodes, which is a source of multimodality. In this regard, we focus on sampling from the marginal posterior distribution of the bias parameters with Markov chain Monte Carlo methods that combine traditional Metropolis sampling with a slice sampler described by Neal (1997, 2001). The methods are illustrated with data examples that are largely confined to the analysis of nonparametric regression models.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.6
• /
• pp.175-181
• /
• 2022

The condition of infrastructure deteriorates as the service life increases. Since most infrastructure in South Korea were intensively built during the period of economic growth, the proportion of outdated infrastructure is rapidly increasing now. Aging of such infrastructure can lead to safety accidents and even human casualties. To prevent these issues in advance, periodic and accurate inspection is essential. For this reason, the need for research to detect various types of damage using computer vision and deep learning is increasingly required in the field of remotely controlled or autonomous inspection. To this end, this study proposed a neural network structure that can detect concrete damage by classifying it into three types. In particular, the proposed neural network can detect them more accurately through a hierarchical learning technique. This neural network was trained with 2,026 damage images and tested with 508 damage images. As a result, we completed an algorithm with average mean intersection over union of 67.04% and F1 score of 52.65%. It is expected that the proposed damage detection algorithm could apply to accurate facility condition diagnosis in the near future.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.556-578
• /
• 2020

There are many different researches about how to analyze issues based on real-time news streams. But, there are few researches which analyze issues hierarchically from news articles and even a previous research of hierarchical issue analysis make clustering speed slower as the increment of news articles. In this paper, we propose a hierarchical and incremental clustering for semi real-time issue analysis on news articles. We trained siamese neural network based weighted cosine similarity model, applied this model to k-means algorithm which is used to make word clusters and converted news articles to document vectors by using these word clusters. Finally, we initialized an issue cluster tree from document vectors, updated this tree whenever news articles happen, and analyzed issues in semi real-time. Through the experiment and evaluation, we showed that up to about 0.26 performance has been improved in terms of NMI. Also, in terms of speed of incremental clustering, we also showed about 10 times faster than before.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.785-804
• /
• 2017

Due to various factors such as postures, facial expressions and illuminations, face recognition by videos often suffer from poor recognition accuracy and generalization ability, since the within-class scatter might even be higher than the between-class one. Herein we address this problem by proposing a hierarchical cascaded classifier for video face recognition, which is a multi-layer algorithm and accounts for the misclassified samples plus their similar samples. Specifically, it can be decomposed into single classifier construction and multi-layer classifier design stages. In single classifier construction stage, classifier is created by clustering and the number of classes is computed by analyzing distance tree. In multi-layer classifier design stage, the next layer is created for the misclassified samples and similar ones, then cascaded to a hierarchical classifier. The experiments on the database collected by ourselves show that the recognition accuracy of the proposed classifier outperforms the compared recognition algorithms, such as neural network and sparse representation.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2002.06a
• /
• pp.367-371
• /
• 2002

I construct a chaotically driven contraction system having some analogy with the information transfer mechanism in the brain system especially from CA1 cell to CA3 cell known from the empirical result. And I consider the properties of the response system on a state space according to the external input into the drive neuron by observing the fractal hierarchical structure. Then I induce the relation between the information about state transition of the chaotic time series and the spatial information on a fractal attractor to confirm the possibility of encoding of time series data to spatial information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.4
• /
• pp.1246-1262
• /
• 2021

Recent studies have demonstrated the strong ability of deep convolutional neural networks (CNNs) to significantly boost the performance in single image super-resolution (SISR). The key concern is how to efficiently recover and utilize diverse information frequencies across multiple network layers, which is crucial to satisfying super-resolution image reconstructions. Hence, previous work made great efforts to potently incorporate hierarchical frequencies through various sophisticated architectures. Nevertheless, economical SISR also requires a capable structure design to balance between restoration accuracy and computational complexity, which is still a challenge for existing techniques. In this paper, we tackle this problem by proposing a competent architecture called Enhanced U-Net Network (EUN), which can yield ready-to-use features in miscellaneous frequencies and combine them comprehensively. In particular, the proposed building block for EUN is enhanced from U-Net, which can extract abundant information via multiple skip concatenations. The network configuration allows the pipeline to propagate information from lower layers to higher ones. Meanwhile, the block itself is committed to growing quite deep in layers, which empowers different types of information to spring from a single block. Furthermore, due to its strong advantage in distilling effective information, promising results are guaranteed with comparatively fewer filters. Comprehensive experiments manifest our model can achieve favorable performance over that of state-of-the-art methods, especially in terms of computational efficiency.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.5
• /
• pp.57-64
• /
• 2004

We proposed the eye gaze tracking system under natural head movements, which consists of one narrow-view field CCD camera, two mirrors which of reflective angles are controlled and active infra-red illumination. The mirrors' angles were computed by geometric and linear algebra calculations to put the pupil images on the optical axis of the camera. Our system allowed the subjects head to move 90cm horizontally and 60cm vertically, and the spatial resolutions were about 6$^{\circ}$ and 7$^{\circ}$, respectively. The frame rate for estimating gaze points was 10～15 frames/sec. As gaze mapping function, we used the hierarchical generalized regression neural networks (H-GRNN) based on the two-pass GRNN. The gaze accuracy showed 94% by H-GRNN improved 9% more than 85% of GRNN even though the head or face was a little rotated. Our system does not have a high spatial gaze resolution, but it allows natural head movements, robust and accurate gaze tracking. In addition there is no need to re-calibrate the system when subjects are changed.